linux/tools/perf/builtin-sched.c

1780 lines
44 KiB
C
Raw Normal View History

#include "builtin.h"
#include "perf.h"
#include "util/util.h"
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 20:57:40 +01:00
#include "util/evlist.h"
#include "util/cache.h"
#include "util/evsel.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
#include "util/debug.h"
#include <sys/prctl.h>
#include <sys/resource.h>
#include <semaphore.h>
#include <pthread.h>
#include <math.h>
#define PR_SET_NAME 15 /* Set process name */
#define MAX_CPUS 4096
#define COMM_LEN 20
#define SYM_LEN 129
#define MAX_PID 65536
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct sched_atom;
struct task_desc {
unsigned long nr;
unsigned long pid;
char comm[COMM_LEN];
unsigned long nr_events;
unsigned long curr_event;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct sched_atom **atoms;
pthread_t thread;
sem_t sleep_sem;
sem_t ready_for_work;
sem_t work_done_sem;
u64 cpu_usage;
};
enum sched_event_type {
SCHED_EVENT_RUN,
SCHED_EVENT_SLEEP,
SCHED_EVENT_WAKEUP,
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
SCHED_EVENT_MIGRATION,
};
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct sched_atom {
enum sched_event_type type;
int specific_wait;
u64 timestamp;
u64 duration;
unsigned long nr;
sem_t *wait_sem;
struct task_desc *wakee;
};
#define TASK_STATE_TO_CHAR_STR "RSDTtZX"
enum thread_state {
THREAD_SLEEPING = 0,
THREAD_WAIT_CPU,
THREAD_SCHED_IN,
THREAD_IGNORE
};
struct work_atom {
struct list_head list;
enum thread_state state;
perf tools: Fix processing of randomly serialized sched traces Currently it's possible to meet such too high latency results with 'perf sched latency'. ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- xfce4-panel | 0.222 ms | 2 | avg: 4718.345 ms | max: 9436.493 ms | scsi_eh_3 | 3.962 ms | 36 | avg: 55.957 ms | max: 1977.829 ms | The origin is on traces that are sometimes badly serialized across cpus. For example the raw traces that raised such results for xfce4-panel: (1) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (2) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (3) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] The traces are processed in the order they arrive. Then in (2), xfce4-panel sleeps, it is first waken up in (3) and eventually scheduled in (5). The latency reported is then 1504 - 1495 = 9 secs, as reported by perf sched. But this is wrong, we are confident in the fact the traces are nicely serialized while we should actually more trust the timestamps. If we reorder by timestamps we get: (1) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (2) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (3) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] Now the trace make more sense, xfce4-panel is sleeping. Then it is woken up in (1), scheduled in (2) It goes to sleep in (3), woken up in (4) and scheduled in (5). Now, latency captured between (1) and (2) is of 39 us. And between (4) and (5) it is 2.1 ms. Such pattern of bad serializing is the origin of the high latencies reported by perf sched. Basically, we need to check whether wake up time is higher than schedule out time. If it's not the case, we need to tag the current work atom as invalid. Beside that, we may need to work later on a better ordering of the traces given by the kernel. After this patch: xfce4-session | 0.221 ms | 1 | avg: 0.538 ms | max: 0.538 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 03:01:12 +02:00
u64 sched_out_time;
u64 wake_up_time;
u64 sched_in_time;
u64 runtime;
};
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms {
struct list_head work_list;
struct thread *thread;
struct rb_node node;
u64 max_lat;
u64 max_lat_at;
u64 total_lat;
u64 nb_atoms;
u64 total_runtime;
};
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_sched;
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct trace_sched_handler {
int (*switch_event)(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine);
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
int (*runtime_event)(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine);
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
int (*wakeup_event)(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine);
/* PERF_RECORD_FORK event, not sched_process_fork tracepoint */
int (*fork_event)(struct perf_sched *sched, union perf_event *event,
struct machine *machine);
int (*migrate_task_event)(struct perf_sched *sched,
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine);
};
struct perf_sched {
struct perf_tool tool;
const char *sort_order;
unsigned long nr_tasks;
struct task_desc *pid_to_task[MAX_PID];
struct task_desc **tasks;
const struct trace_sched_handler *tp_handler;
pthread_mutex_t start_work_mutex;
pthread_mutex_t work_done_wait_mutex;
int profile_cpu;
/*
* Track the current task - that way we can know whether there's any
* weird events, such as a task being switched away that is not current.
*/
int max_cpu;
u32 curr_pid[MAX_CPUS];
struct thread *curr_thread[MAX_CPUS];
char next_shortname1;
char next_shortname2;
unsigned int replay_repeat;
unsigned long nr_run_events;
unsigned long nr_sleep_events;
unsigned long nr_wakeup_events;
unsigned long nr_sleep_corrections;
unsigned long nr_run_events_optimized;
unsigned long targetless_wakeups;
unsigned long multitarget_wakeups;
unsigned long nr_runs;
unsigned long nr_timestamps;
unsigned long nr_unordered_timestamps;
unsigned long nr_state_machine_bugs;
unsigned long nr_context_switch_bugs;
unsigned long nr_events;
unsigned long nr_lost_chunks;
unsigned long nr_lost_events;
u64 run_measurement_overhead;
u64 sleep_measurement_overhead;
u64 start_time;
u64 cpu_usage;
u64 runavg_cpu_usage;
u64 parent_cpu_usage;
u64 runavg_parent_cpu_usage;
u64 sum_runtime;
u64 sum_fluct;
u64 run_avg;
u64 all_runtime;
u64 all_count;
u64 cpu_last_switched[MAX_CPUS];
struct rb_root atom_root, sorted_atom_root;
struct list_head sort_list, cmp_pid;
};
static u64 get_nsecs(void)
{
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
static void burn_nsecs(struct perf_sched *sched, u64 nsecs)
{
u64 T0 = get_nsecs(), T1;
do {
T1 = get_nsecs();
} while (T1 + sched->run_measurement_overhead < T0 + nsecs);
}
static void sleep_nsecs(u64 nsecs)
{
struct timespec ts;
ts.tv_nsec = nsecs % 999999999;
ts.tv_sec = nsecs / 999999999;
nanosleep(&ts, NULL);
}
static void calibrate_run_measurement_overhead(struct perf_sched *sched)
{
u64 T0, T1, delta, min_delta = 1000000000ULL;
int i;
for (i = 0; i < 10; i++) {
T0 = get_nsecs();
burn_nsecs(sched, 0);
T1 = get_nsecs();
delta = T1-T0;
min_delta = min(min_delta, delta);
}
sched->run_measurement_overhead = min_delta;
printf("run measurement overhead: %" PRIu64 " nsecs\n", min_delta);
}
static void calibrate_sleep_measurement_overhead(struct perf_sched *sched)
{
u64 T0, T1, delta, min_delta = 1000000000ULL;
int i;
for (i = 0; i < 10; i++) {
T0 = get_nsecs();
sleep_nsecs(10000);
T1 = get_nsecs();
delta = T1-T0;
min_delta = min(min_delta, delta);
}
min_delta -= 10000;
sched->sleep_measurement_overhead = min_delta;
printf("sleep measurement overhead: %" PRIu64 " nsecs\n", min_delta);
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static struct sched_atom *
get_new_event(struct task_desc *task, u64 timestamp)
{
struct sched_atom *event = zalloc(sizeof(*event));
unsigned long idx = task->nr_events;
size_t size;
event->timestamp = timestamp;
event->nr = idx;
task->nr_events++;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
size = sizeof(struct sched_atom *) * task->nr_events;
task->atoms = realloc(task->atoms, size);
BUG_ON(!task->atoms);
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
task->atoms[idx] = event;
return event;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static struct sched_atom *last_event(struct task_desc *task)
{
if (!task->nr_events)
return NULL;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
return task->atoms[task->nr_events - 1];
}
static void add_sched_event_run(struct perf_sched *sched, struct task_desc *task,
u64 timestamp, u64 duration)
{
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct sched_atom *event, *curr_event = last_event(task);
/*
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
* optimize an existing RUN event by merging this one
* to it:
*/
if (curr_event && curr_event->type == SCHED_EVENT_RUN) {
sched->nr_run_events_optimized++;
curr_event->duration += duration;
return;
}
event = get_new_event(task, timestamp);
event->type = SCHED_EVENT_RUN;
event->duration = duration;
sched->nr_run_events++;
}
static void add_sched_event_wakeup(struct perf_sched *sched, struct task_desc *task,
u64 timestamp, struct task_desc *wakee)
{
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct sched_atom *event, *wakee_event;
event = get_new_event(task, timestamp);
event->type = SCHED_EVENT_WAKEUP;
event->wakee = wakee;
wakee_event = last_event(wakee);
if (!wakee_event || wakee_event->type != SCHED_EVENT_SLEEP) {
sched->targetless_wakeups++;
return;
}
if (wakee_event->wait_sem) {
sched->multitarget_wakeups++;
return;
}
wakee_event->wait_sem = zalloc(sizeof(*wakee_event->wait_sem));
sem_init(wakee_event->wait_sem, 0, 0);
wakee_event->specific_wait = 1;
event->wait_sem = wakee_event->wait_sem;
sched->nr_wakeup_events++;
}
static void add_sched_event_sleep(struct perf_sched *sched, struct task_desc *task,
u64 timestamp, u64 task_state __maybe_unused)
{
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct sched_atom *event = get_new_event(task, timestamp);
event->type = SCHED_EVENT_SLEEP;
sched->nr_sleep_events++;
}
static struct task_desc *register_pid(struct perf_sched *sched,
unsigned long pid, const char *comm)
{
struct task_desc *task;
BUG_ON(pid >= MAX_PID);
task = sched->pid_to_task[pid];
if (task)
return task;
task = zalloc(sizeof(*task));
task->pid = pid;
task->nr = sched->nr_tasks;
strcpy(task->comm, comm);
/*
* every task starts in sleeping state - this gets ignored
* if there's no wakeup pointing to this sleep state:
*/
add_sched_event_sleep(sched, task, 0, 0);
sched->pid_to_task[pid] = task;
sched->nr_tasks++;
sched->tasks = realloc(sched->tasks, sched->nr_tasks * sizeof(struct task_task *));
BUG_ON(!sched->tasks);
sched->tasks[task->nr] = task;
if (verbose)
printf("registered task #%ld, PID %ld (%s)\n", sched->nr_tasks, pid, comm);
return task;
}
static void print_task_traces(struct perf_sched *sched)
{
struct task_desc *task;
unsigned long i;
for (i = 0; i < sched->nr_tasks; i++) {
task = sched->tasks[i];
printf("task %6ld (%20s:%10ld), nr_events: %ld\n",
task->nr, task->comm, task->pid, task->nr_events);
}
}
static void add_cross_task_wakeups(struct perf_sched *sched)
{
struct task_desc *task1, *task2;
unsigned long i, j;
for (i = 0; i < sched->nr_tasks; i++) {
task1 = sched->tasks[i];
j = i + 1;
if (j == sched->nr_tasks)
j = 0;
task2 = sched->tasks[j];
add_sched_event_wakeup(sched, task1, 0, task2);
}
}
static void perf_sched__process_event(struct perf_sched *sched,
struct sched_atom *atom)
{
int ret = 0;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
switch (atom->type) {
case SCHED_EVENT_RUN:
burn_nsecs(sched, atom->duration);
break;
case SCHED_EVENT_SLEEP:
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (atom->wait_sem)
ret = sem_wait(atom->wait_sem);
BUG_ON(ret);
break;
case SCHED_EVENT_WAKEUP:
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (atom->wait_sem)
ret = sem_post(atom->wait_sem);
BUG_ON(ret);
break;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
case SCHED_EVENT_MIGRATION:
break;
default:
BUG_ON(1);
}
}
static u64 get_cpu_usage_nsec_parent(void)
{
struct rusage ru;
u64 sum;
int err;
err = getrusage(RUSAGE_SELF, &ru);
BUG_ON(err);
sum = ru.ru_utime.tv_sec*1e9 + ru.ru_utime.tv_usec*1e3;
sum += ru.ru_stime.tv_sec*1e9 + ru.ru_stime.tv_usec*1e3;
return sum;
}
static int self_open_counters(void)
{
struct perf_event_attr attr;
int fd;
memset(&attr, 0, sizeof(attr));
attr.type = PERF_TYPE_SOFTWARE;
attr.config = PERF_COUNT_SW_TASK_CLOCK;
fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
if (fd < 0)
pr_err("Error: sys_perf_event_open() syscall returned "
"with %d (%s)\n", fd, strerror(errno));
return fd;
}
static u64 get_cpu_usage_nsec_self(int fd)
{
u64 runtime;
int ret;
ret = read(fd, &runtime, sizeof(runtime));
BUG_ON(ret != sizeof(runtime));
return runtime;
}
struct sched_thread_parms {
struct task_desc *task;
struct perf_sched *sched;
};
static void *thread_func(void *ctx)
{
struct sched_thread_parms *parms = ctx;
struct task_desc *this_task = parms->task;
struct perf_sched *sched = parms->sched;
u64 cpu_usage_0, cpu_usage_1;
unsigned long i, ret;
char comm2[22];
int fd;
zfree(&parms);
sprintf(comm2, ":%s", this_task->comm);
prctl(PR_SET_NAME, comm2);
fd = self_open_counters();
if (fd < 0)
return NULL;
again:
ret = sem_post(&this_task->ready_for_work);
BUG_ON(ret);
ret = pthread_mutex_lock(&sched->start_work_mutex);
BUG_ON(ret);
ret = pthread_mutex_unlock(&sched->start_work_mutex);
BUG_ON(ret);
cpu_usage_0 = get_cpu_usage_nsec_self(fd);
for (i = 0; i < this_task->nr_events; i++) {
this_task->curr_event = i;
perf_sched__process_event(sched, this_task->atoms[i]);
}
cpu_usage_1 = get_cpu_usage_nsec_self(fd);
this_task->cpu_usage = cpu_usage_1 - cpu_usage_0;
ret = sem_post(&this_task->work_done_sem);
BUG_ON(ret);
ret = pthread_mutex_lock(&sched->work_done_wait_mutex);
BUG_ON(ret);
ret = pthread_mutex_unlock(&sched->work_done_wait_mutex);
BUG_ON(ret);
goto again;
}
static void create_tasks(struct perf_sched *sched)
{
struct task_desc *task;
pthread_attr_t attr;
unsigned long i;
int err;
err = pthread_attr_init(&attr);
BUG_ON(err);
err = pthread_attr_setstacksize(&attr,
(size_t) max(16 * 1024, PTHREAD_STACK_MIN));
BUG_ON(err);
err = pthread_mutex_lock(&sched->start_work_mutex);
BUG_ON(err);
err = pthread_mutex_lock(&sched->work_done_wait_mutex);
BUG_ON(err);
for (i = 0; i < sched->nr_tasks; i++) {
struct sched_thread_parms *parms = malloc(sizeof(*parms));
BUG_ON(parms == NULL);
parms->task = task = sched->tasks[i];
parms->sched = sched;
sem_init(&task->sleep_sem, 0, 0);
sem_init(&task->ready_for_work, 0, 0);
sem_init(&task->work_done_sem, 0, 0);
task->curr_event = 0;
err = pthread_create(&task->thread, &attr, thread_func, parms);
BUG_ON(err);
}
}
static void wait_for_tasks(struct perf_sched *sched)
{
u64 cpu_usage_0, cpu_usage_1;
struct task_desc *task;
unsigned long i, ret;
sched->start_time = get_nsecs();
sched->cpu_usage = 0;
pthread_mutex_unlock(&sched->work_done_wait_mutex);
for (i = 0; i < sched->nr_tasks; i++) {
task = sched->tasks[i];
ret = sem_wait(&task->ready_for_work);
BUG_ON(ret);
sem_init(&task->ready_for_work, 0, 0);
}
ret = pthread_mutex_lock(&sched->work_done_wait_mutex);
BUG_ON(ret);
cpu_usage_0 = get_cpu_usage_nsec_parent();
pthread_mutex_unlock(&sched->start_work_mutex);
for (i = 0; i < sched->nr_tasks; i++) {
task = sched->tasks[i];
ret = sem_wait(&task->work_done_sem);
BUG_ON(ret);
sem_init(&task->work_done_sem, 0, 0);
sched->cpu_usage += task->cpu_usage;
task->cpu_usage = 0;
}
cpu_usage_1 = get_cpu_usage_nsec_parent();
if (!sched->runavg_cpu_usage)
sched->runavg_cpu_usage = sched->cpu_usage;
sched->runavg_cpu_usage = (sched->runavg_cpu_usage * 9 + sched->cpu_usage) / 10;
sched->parent_cpu_usage = cpu_usage_1 - cpu_usage_0;
if (!sched->runavg_parent_cpu_usage)
sched->runavg_parent_cpu_usage = sched->parent_cpu_usage;
sched->runavg_parent_cpu_usage = (sched->runavg_parent_cpu_usage * 9 +
sched->parent_cpu_usage)/10;
ret = pthread_mutex_lock(&sched->start_work_mutex);
BUG_ON(ret);
for (i = 0; i < sched->nr_tasks; i++) {
task = sched->tasks[i];
sem_init(&task->sleep_sem, 0, 0);
task->curr_event = 0;
}
}
static void run_one_test(struct perf_sched *sched)
{
u64 T0, T1, delta, avg_delta, fluct;
T0 = get_nsecs();
wait_for_tasks(sched);
T1 = get_nsecs();
delta = T1 - T0;
sched->sum_runtime += delta;
sched->nr_runs++;
avg_delta = sched->sum_runtime / sched->nr_runs;
if (delta < avg_delta)
fluct = avg_delta - delta;
else
fluct = delta - avg_delta;
sched->sum_fluct += fluct;
if (!sched->run_avg)
sched->run_avg = delta;
sched->run_avg = (sched->run_avg * 9 + delta) / 10;
printf("#%-3ld: %0.3f, ", sched->nr_runs, (double)delta / 1000000.0);
printf("ravg: %0.2f, ", (double)sched->run_avg / 1e6);
printf("cpu: %0.2f / %0.2f",
(double)sched->cpu_usage / 1e6, (double)sched->runavg_cpu_usage / 1e6);
#if 0
/*
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
* rusage statistics done by the parent, these are less
* accurate than the sched->sum_exec_runtime based statistics:
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
*/
printf(" [%0.2f / %0.2f]",
(double)sched->parent_cpu_usage/1e6,
(double)sched->runavg_parent_cpu_usage/1e6);
#endif
printf("\n");
if (sched->nr_sleep_corrections)
printf(" (%ld sleep corrections)\n", sched->nr_sleep_corrections);
sched->nr_sleep_corrections = 0;
}
static void test_calibrations(struct perf_sched *sched)
{
u64 T0, T1;
T0 = get_nsecs();
burn_nsecs(sched, 1e6);
T1 = get_nsecs();
printf("the run test took %" PRIu64 " nsecs\n", T1 - T0);
T0 = get_nsecs();
sleep_nsecs(1e6);
T1 = get_nsecs();
printf("the sleep test took %" PRIu64 " nsecs\n", T1 - T0);
}
static int
replay_wakeup_event(struct perf_sched *sched,
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel, struct perf_sample *sample,
struct machine *machine __maybe_unused)
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const char *comm = perf_evsel__strval(evsel, sample, "comm");
const u32 pid = perf_evsel__intval(evsel, sample, "pid");
struct task_desc *waker, *wakee;
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
if (verbose) {
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
printf("sched_wakeup event %p\n", evsel);
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
printf(" ... pid %d woke up %s/%d\n", sample->tid, comm, pid);
}
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
waker = register_pid(sched, sample->tid, "<unknown>");
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
wakee = register_pid(sched, pid, comm);
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
add_sched_event_wakeup(sched, waker, sample->time, wakee);
return 0;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static int replay_switch_event(struct perf_sched *sched,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine __maybe_unused)
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const char *prev_comm = perf_evsel__strval(evsel, sample, "prev_comm"),
*next_comm = perf_evsel__strval(evsel, sample, "next_comm");
const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
next_pid = perf_evsel__intval(evsel, sample, "next_pid");
const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
struct task_desc *prev, __maybe_unused *next;
u64 timestamp0, timestamp = sample->time;
int cpu = sample->cpu;
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
s64 delta;
if (verbose)
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
printf("sched_switch event %p\n", evsel);
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
if (cpu >= MAX_CPUS || cpu < 0)
return 0;
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
timestamp0 = sched->cpu_last_switched[cpu];
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
if (timestamp0)
delta = timestamp - timestamp0;
else
delta = 0;
if (delta < 0) {
pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
return -1;
}
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
pr_debug(" ... switch from %s/%d to %s/%d [ran %" PRIu64 " nsecs]\n",
prev_comm, prev_pid, next_comm, next_pid, delta);
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
prev = register_pid(sched, prev_pid, prev_comm);
next = register_pid(sched, next_pid, next_comm);
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
sched->cpu_last_switched[cpu] = timestamp;
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
add_sched_event_run(sched, prev, timestamp, delta);
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
add_sched_event_sleep(sched, prev, timestamp, prev_state);
return 0;
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
}
static int replay_fork_event(struct perf_sched *sched,
union perf_event *event,
struct machine *machine)
{
struct thread *child, *parent;
child = machine__findnew_thread(machine, event->fork.pid,
event->fork.tid);
parent = machine__findnew_thread(machine, event->fork.ppid,
event->fork.ptid);
if (child == NULL || parent == NULL) {
pr_debug("thread does not exist on fork event: child %p, parent %p\n",
child, parent);
return 0;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (verbose) {
printf("fork event\n");
printf("... parent: %s/%d\n", thread__comm_str(parent), parent->tid);
printf("... child: %s/%d\n", thread__comm_str(child), child->tid);
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
register_pid(sched, parent->tid, thread__comm_str(parent));
register_pid(sched, child->tid, thread__comm_str(child));
return 0;
}
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
struct sort_dimension {
const char *name;
sort_fn_t cmp;
struct list_head list;
};
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
static int
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
struct sort_dimension *sort;
int ret = 0;
BUG_ON(list_empty(list));
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
list_for_each_entry(sort, list, list) {
ret = sort->cmp(l, r);
if (ret)
return ret;
}
return ret;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static struct work_atoms *
thread_atoms_search(struct rb_root *root, struct thread *thread,
struct list_head *sort_list)
{
struct rb_node *node = root->rb_node;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms key = { .thread = thread };
while (node) {
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms *atoms;
int cmp;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
atoms = container_of(node, struct work_atoms, node);
cmp = thread_lat_cmp(sort_list, &key, atoms);
if (cmp > 0)
node = node->rb_left;
else if (cmp < 0)
node = node->rb_right;
else {
BUG_ON(thread != atoms->thread);
return atoms;
}
}
return NULL;
}
static void
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
__thread_latency_insert(struct rb_root *root, struct work_atoms *data,
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
struct list_head *sort_list)
{
struct rb_node **new = &(root->rb_node), *parent = NULL;
while (*new) {
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms *this;
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
int cmp;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
this = container_of(*new, struct work_atoms, node);
parent = *new;
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
cmp = thread_lat_cmp(sort_list, data, this);
if (cmp > 0)
new = &((*new)->rb_left);
else
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
new = &((*new)->rb_right);
}
rb_link_node(&data->node, parent, new);
rb_insert_color(&data->node, root);
}
static int thread_atoms_insert(struct perf_sched *sched, struct thread *thread)
{
struct work_atoms *atoms = zalloc(sizeof(*atoms));
if (!atoms) {
pr_err("No memory at %s\n", __func__);
return -1;
}
atoms->thread = thread;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
INIT_LIST_HEAD(&atoms->work_list);
__thread_latency_insert(&sched->atom_root, atoms, &sched->cmp_pid);
return 0;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static char sched_out_state(u64 prev_state)
{
const char *str = TASK_STATE_TO_CHAR_STR;
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
return str[prev_state];
}
static int
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
add_sched_out_event(struct work_atoms *atoms,
char run_state,
u64 timestamp)
{
struct work_atom *atom = zalloc(sizeof(*atom));
if (!atom) {
pr_err("Non memory at %s", __func__);
return -1;
}
perf tools: Fix processing of randomly serialized sched traces Currently it's possible to meet such too high latency results with 'perf sched latency'. ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- xfce4-panel | 0.222 ms | 2 | avg: 4718.345 ms | max: 9436.493 ms | scsi_eh_3 | 3.962 ms | 36 | avg: 55.957 ms | max: 1977.829 ms | The origin is on traces that are sometimes badly serialized across cpus. For example the raw traces that raised such results for xfce4-panel: (1) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (2) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (3) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] The traces are processed in the order they arrive. Then in (2), xfce4-panel sleeps, it is first waken up in (3) and eventually scheduled in (5). The latency reported is then 1504 - 1495 = 9 secs, as reported by perf sched. But this is wrong, we are confident in the fact the traces are nicely serialized while we should actually more trust the timestamps. If we reorder by timestamps we get: (1) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (2) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (3) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] Now the trace make more sense, xfce4-panel is sleeping. Then it is woken up in (1), scheduled in (2) It goes to sleep in (3), woken up in (4) and scheduled in (5). Now, latency captured between (1) and (2) is of 39 us. And between (4) and (5) it is 2.1 ms. Such pattern of bad serializing is the origin of the high latencies reported by perf sched. Basically, we need to check whether wake up time is higher than schedule out time. If it's not the case, we need to tag the current work atom as invalid. Beside that, we may need to work later on a better ordering of the traces given by the kernel. After this patch: xfce4-session | 0.221 ms | 1 | avg: 0.538 ms | max: 0.538 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 03:01:12 +02:00
atom->sched_out_time = timestamp;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (run_state == 'R') {
atom->state = THREAD_WAIT_CPU;
perf tools: Fix processing of randomly serialized sched traces Currently it's possible to meet such too high latency results with 'perf sched latency'. ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- xfce4-panel | 0.222 ms | 2 | avg: 4718.345 ms | max: 9436.493 ms | scsi_eh_3 | 3.962 ms | 36 | avg: 55.957 ms | max: 1977.829 ms | The origin is on traces that are sometimes badly serialized across cpus. For example the raw traces that raised such results for xfce4-panel: (1) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (2) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (3) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] The traces are processed in the order they arrive. Then in (2), xfce4-panel sleeps, it is first waken up in (3) and eventually scheduled in (5). The latency reported is then 1504 - 1495 = 9 secs, as reported by perf sched. But this is wrong, we are confident in the fact the traces are nicely serialized while we should actually more trust the timestamps. If we reorder by timestamps we get: (1) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (2) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (3) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] Now the trace make more sense, xfce4-panel is sleeping. Then it is woken up in (1), scheduled in (2) It goes to sleep in (3), woken up in (4) and scheduled in (5). Now, latency captured between (1) and (2) is of 39 us. And between (4) and (5) it is 2.1 ms. Such pattern of bad serializing is the origin of the high latencies reported by perf sched. Basically, we need to check whether wake up time is higher than schedule out time. If it's not the case, we need to tag the current work atom as invalid. Beside that, we may need to work later on a better ordering of the traces given by the kernel. After this patch: xfce4-session | 0.221 ms | 1 | avg: 0.538 ms | max: 0.538 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 03:01:12 +02:00
atom->wake_up_time = atom->sched_out_time;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
list_add_tail(&atom->list, &atoms->work_list);
return 0;
}
static void
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
add_runtime_event(struct work_atoms *atoms, u64 delta,
u64 timestamp __maybe_unused)
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
{
struct work_atom *atom;
BUG_ON(list_empty(&atoms->work_list));
atom = list_entry(atoms->work_list.prev, struct work_atom, list);
atom->runtime += delta;
atoms->total_runtime += delta;
}
static void
add_sched_in_event(struct work_atoms *atoms, u64 timestamp)
{
struct work_atom *atom;
u64 delta;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (list_empty(&atoms->work_list))
return;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
atom = list_entry(atoms->work_list.prev, struct work_atom, list);
if (atom->state != THREAD_WAIT_CPU)
return;
if (timestamp < atom->wake_up_time) {
atom->state = THREAD_IGNORE;
return;
}
atom->state = THREAD_SCHED_IN;
atom->sched_in_time = timestamp;
delta = atom->sched_in_time - atom->wake_up_time;
atoms->total_lat += delta;
if (delta > atoms->max_lat) {
atoms->max_lat = delta;
atoms->max_lat_at = timestamp;
}
atoms->nb_atoms++;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static int latency_switch_event(struct perf_sched *sched,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine)
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
next_pid = perf_evsel__intval(evsel, sample, "next_pid");
const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms *out_events, *in_events;
struct thread *sched_out, *sched_in;
u64 timestamp0, timestamp = sample->time;
int cpu = sample->cpu;
s64 delta;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
timestamp0 = sched->cpu_last_switched[cpu];
sched->cpu_last_switched[cpu] = timestamp;
if (timestamp0)
delta = timestamp - timestamp0;
else
delta = 0;
if (delta < 0) {
pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
return -1;
}
sched_out = machine__findnew_thread(machine, 0, prev_pid);
sched_in = machine__findnew_thread(machine, 0, next_pid);
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (!out_events) {
if (thread_atoms_insert(sched, sched_out))
return -1;
out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
if (!out_events) {
pr_err("out-event: Internal tree error");
return -1;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
return -1;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (!in_events) {
if (thread_atoms_insert(sched, sched_in))
return -1;
in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
if (!in_events) {
pr_err("in-event: Internal tree error");
return -1;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
/*
* Take came in we have not heard about yet,
* add in an initial atom in runnable state:
*/
if (add_sched_out_event(in_events, 'R', timestamp))
return -1;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
add_sched_in_event(in_events, timestamp);
return 0;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static int latency_runtime_event(struct perf_sched *sched,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine)
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const u32 pid = perf_evsel__intval(evsel, sample, "pid");
const u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
struct thread *thread = machine__findnew_thread(machine, 0, pid);
struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
u64 timestamp = sample->time;
int cpu = sample->cpu;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
if (!atoms) {
if (thread_atoms_insert(sched, thread))
return -1;
atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
if (!atoms) {
pr_err("in-event: Internal tree error");
return -1;
}
if (add_sched_out_event(atoms, 'R', timestamp))
return -1;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
add_runtime_event(atoms, runtime, timestamp);
return 0;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static int latency_wakeup_event(struct perf_sched *sched,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine)
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const u32 pid = perf_evsel__intval(evsel, sample, "pid"),
success = perf_evsel__intval(evsel, sample, "success");
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms *atoms;
struct work_atom *atom;
struct thread *wakee;
u64 timestamp = sample->time;
/* Note for later, it may be interesting to observe the failing cases */
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (!success)
return 0;
wakee = machine__findnew_thread(machine, 0, pid);
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
if (thread_atoms_insert(sched, wakee))
return -1;
atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
if (!atoms) {
pr_err("wakeup-event: Internal tree error");
return -1;
}
if (add_sched_out_event(atoms, 'S', timestamp))
return -1;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
BUG_ON(list_empty(&atoms->work_list));
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
atom = list_entry(atoms->work_list.prev, struct work_atom, list);
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
/*
* You WILL be missing events if you've recorded only
* one CPU, or are only looking at only one, so don't
* make useless noise.
*/
if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
sched->nr_state_machine_bugs++;
sched->nr_timestamps++;
perf tools: Implement counter output multiplexing Finish the -M/--multiplex option implementation: - separate it out from group_fd - correctly set it via the ioctl and dont mmap counters that are multiplexed - modify the perf record event loop to deal with buffer-less counters. - remove the -g option from perf sched record - account for unordered events in perf sched latency - (add -f to perf sched record to ease measurements) - skip idle threads (pid==0) in latency output The result is better latency output by 'perf sched latency': ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- ksoftirqd/8 | 0.071 ms | 2 | avg: 0.458 ms | max: 0.913 ms | at-spi-registry | 0.609 ms | 19 | avg: 0.013 ms | max: 0.023 ms | perf | 3.316 ms | 16 | avg: 0.013 ms | max: 0.054 ms | Xorg | 0.392 ms | 19 | avg: 0.011 ms | max: 0.018 ms | sleep | 0.537 ms | 2 | avg: 0.009 ms | max: 0.009 ms | ----------------------------------------------------------------------------------- TOTAL: | 4.925 ms | 58 | --------------------------------------------- Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 18:15:54 +02:00
if (atom->sched_out_time > timestamp) {
sched->nr_unordered_timestamps++;
return 0;
perf tools: Implement counter output multiplexing Finish the -M/--multiplex option implementation: - separate it out from group_fd - correctly set it via the ioctl and dont mmap counters that are multiplexed - modify the perf record event loop to deal with buffer-less counters. - remove the -g option from perf sched record - account for unordered events in perf sched latency - (add -f to perf sched record to ease measurements) - skip idle threads (pid==0) in latency output The result is better latency output by 'perf sched latency': ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- ksoftirqd/8 | 0.071 ms | 2 | avg: 0.458 ms | max: 0.913 ms | at-spi-registry | 0.609 ms | 19 | avg: 0.013 ms | max: 0.023 ms | perf | 3.316 ms | 16 | avg: 0.013 ms | max: 0.054 ms | Xorg | 0.392 ms | 19 | avg: 0.011 ms | max: 0.018 ms | sleep | 0.537 ms | 2 | avg: 0.009 ms | max: 0.009 ms | ----------------------------------------------------------------------------------- TOTAL: | 4.925 ms | 58 | --------------------------------------------- Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 18:15:54 +02:00
}
perf tools: Fix processing of randomly serialized sched traces Currently it's possible to meet such too high latency results with 'perf sched latency'. ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- xfce4-panel | 0.222 ms | 2 | avg: 4718.345 ms | max: 9436.493 ms | scsi_eh_3 | 3.962 ms | 36 | avg: 55.957 ms | max: 1977.829 ms | The origin is on traces that are sometimes badly serialized across cpus. For example the raw traces that raised such results for xfce4-panel: (1) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (2) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (3) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] The traces are processed in the order they arrive. Then in (2), xfce4-panel sleeps, it is first waken up in (3) and eventually scheduled in (5). The latency reported is then 1504 - 1495 = 9 secs, as reported by perf sched. But this is wrong, we are confident in the fact the traces are nicely serialized while we should actually more trust the timestamps. If we reorder by timestamps we get: (1) Xorg-4276 [001] 1494.663860125: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (2) [init]-0 [000] 1494.663899990: sched_switch: task swapper:0 [140] (R) ==> xfce4-panel:4569 [120] (3) xfce4-panel-4569 [000] 1494.663928373: sched_switch: task xfce4-panel:4569 [120] (S) ==> swapper:0 [140] (4) Xorg-4276 [001] 1504.098252756: sched_wakeup: task xfce4-panel:4569 [120] success=1 [000] (5) perf-5219 [000] 1504.100353302: sched_switch: task perf:5219 [120] (S) ==> xfce4-panel:4569 [120] Now the trace make more sense, xfce4-panel is sleeping. Then it is woken up in (1), scheduled in (2) It goes to sleep in (3), woken up in (4) and scheduled in (5). Now, latency captured between (1) and (2) is of 39 us. And between (4) and (5) it is 2.1 ms. Such pattern of bad serializing is the origin of the high latencies reported by perf sched. Basically, we need to check whether wake up time is higher than schedule out time. If it's not the case, we need to tag the current work atom as invalid. Beside that, we may need to work later on a better ordering of the traces given by the kernel. After this patch: xfce4-session | 0.221 ms | 1 | avg: 0.538 ms | max: 0.538 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 03:01:12 +02:00
atom->state = THREAD_WAIT_CPU;
atom->wake_up_time = timestamp;
return 0;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static int latency_migrate_task_event(struct perf_sched *sched,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine)
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const u32 pid = perf_evsel__intval(evsel, sample, "pid");
u64 timestamp = sample->time;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
struct work_atoms *atoms;
struct work_atom *atom;
struct thread *migrant;
/*
* Only need to worry about migration when profiling one CPU.
*/
if (sched->profile_cpu == -1)
return 0;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
migrant = machine__findnew_thread(machine, 0, pid);
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
if (!atoms) {
if (thread_atoms_insert(sched, migrant))
return -1;
register_pid(sched, migrant->tid, thread__comm_str(migrant));
atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
if (!atoms) {
pr_err("migration-event: Internal tree error");
return -1;
}
if (add_sched_out_event(atoms, 'R', timestamp))
return -1;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
}
BUG_ON(list_empty(&atoms->work_list));
atom = list_entry(atoms->work_list.prev, struct work_atom, list);
atom->sched_in_time = atom->sched_out_time = atom->wake_up_time = timestamp;
sched->nr_timestamps++;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
if (atom->sched_out_time > timestamp)
sched->nr_unordered_timestamps++;
return 0;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
}
static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
{
int i;
int ret;
u64 avg;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
if (!work_list->nb_atoms)
return;
perf tools: Implement counter output multiplexing Finish the -M/--multiplex option implementation: - separate it out from group_fd - correctly set it via the ioctl and dont mmap counters that are multiplexed - modify the perf record event loop to deal with buffer-less counters. - remove the -g option from perf sched record - account for unordered events in perf sched latency - (add -f to perf sched record to ease measurements) - skip idle threads (pid==0) in latency output The result is better latency output by 'perf sched latency': ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- ksoftirqd/8 | 0.071 ms | 2 | avg: 0.458 ms | max: 0.913 ms | at-spi-registry | 0.609 ms | 19 | avg: 0.013 ms | max: 0.023 ms | perf | 3.316 ms | 16 | avg: 0.013 ms | max: 0.054 ms | Xorg | 0.392 ms | 19 | avg: 0.011 ms | max: 0.018 ms | sleep | 0.537 ms | 2 | avg: 0.009 ms | max: 0.009 ms | ----------------------------------------------------------------------------------- TOTAL: | 4.925 ms | 58 | --------------------------------------------- Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 18:15:54 +02:00
/*
* Ignore idle threads:
*/
if (!strcmp(thread__comm_str(work_list->thread), "swapper"))
perf tools: Implement counter output multiplexing Finish the -M/--multiplex option implementation: - separate it out from group_fd - correctly set it via the ioctl and dont mmap counters that are multiplexed - modify the perf record event loop to deal with buffer-less counters. - remove the -g option from perf sched record - account for unordered events in perf sched latency - (add -f to perf sched record to ease measurements) - skip idle threads (pid==0) in latency output The result is better latency output by 'perf sched latency': ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- ksoftirqd/8 | 0.071 ms | 2 | avg: 0.458 ms | max: 0.913 ms | at-spi-registry | 0.609 ms | 19 | avg: 0.013 ms | max: 0.023 ms | perf | 3.316 ms | 16 | avg: 0.013 ms | max: 0.054 ms | Xorg | 0.392 ms | 19 | avg: 0.011 ms | max: 0.018 ms | sleep | 0.537 ms | 2 | avg: 0.009 ms | max: 0.009 ms | ----------------------------------------------------------------------------------- TOTAL: | 4.925 ms | 58 | --------------------------------------------- Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 18:15:54 +02:00
return;
sched->all_runtime += work_list->total_runtime;
sched->all_count += work_list->nb_atoms;
ret = printf(" %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
for (i = 0; i < 24 - ret; i++)
printf(" ");
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
avg = work_list->total_lat / work_list->nb_atoms;
printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %9.6f s\n",
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
(double)work_list->total_runtime / 1e6,
work_list->nb_atoms, (double)avg / 1e6,
(double)work_list->max_lat / 1e6,
(double)work_list->max_lat_at / 1e9);
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
if (l->thread->tid < r->thread->tid)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
return -1;
if (l->thread->tid > r->thread->tid)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
return 1;
return 0;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
u64 avgl, avgr;
if (!l->nb_atoms)
return -1;
if (!r->nb_atoms)
return 1;
avgl = l->total_lat / l->nb_atoms;
avgr = r->total_lat / r->nb_atoms;
if (avgl < avgr)
return -1;
if (avgl > avgr)
return 1;
return 0;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static int max_cmp(struct work_atoms *l, struct work_atoms *r)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
if (l->max_lat < r->max_lat)
return -1;
if (l->max_lat > r->max_lat)
return 1;
return 0;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static int switch_cmp(struct work_atoms *l, struct work_atoms *r)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
if (l->nb_atoms < r->nb_atoms)
return -1;
if (l->nb_atoms > r->nb_atoms)
return 1;
return 0;
}
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
static int runtime_cmp(struct work_atoms *l, struct work_atoms *r)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
if (l->total_runtime < r->total_runtime)
return -1;
if (l->total_runtime > r->total_runtime)
return 1;
return 0;
}
static int sort_dimension__add(const char *tok, struct list_head *list)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
size_t i;
static struct sort_dimension avg_sort_dimension = {
.name = "avg",
.cmp = avg_cmp,
};
static struct sort_dimension max_sort_dimension = {
.name = "max",
.cmp = max_cmp,
};
static struct sort_dimension pid_sort_dimension = {
.name = "pid",
.cmp = pid_cmp,
};
static struct sort_dimension runtime_sort_dimension = {
.name = "runtime",
.cmp = runtime_cmp,
};
static struct sort_dimension switch_sort_dimension = {
.name = "switch",
.cmp = switch_cmp,
};
struct sort_dimension *available_sorts[] = {
&pid_sort_dimension,
&avg_sort_dimension,
&max_sort_dimension,
&switch_sort_dimension,
&runtime_sort_dimension,
};
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
for (i = 0; i < ARRAY_SIZE(available_sorts); i++) {
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
if (!strcmp(available_sorts[i]->name, tok)) {
list_add_tail(&available_sorts[i]->list, list);
return 0;
}
}
return -1;
}
static void perf_sched__sort_lat(struct perf_sched *sched)
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
struct rb_node *node;
for (;;) {
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
struct work_atoms *data;
node = rb_first(&sched->atom_root);
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
if (!node)
break;
rb_erase(node, &sched->atom_root);
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
data = rb_entry(node, struct work_atoms, node);
__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
}
}
static int process_sched_wakeup_event(struct perf_tool *tool,
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
struct perf_sample *sample,
struct machine *machine)
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (sched->tp_handler->wakeup_event)
return sched->tp_handler->wakeup_event(sched, evsel, sample, machine);
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
return 0;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
struct perf_sample *sample, struct machine *machine)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
{
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
next_pid = perf_evsel__intval(evsel, sample, "next_pid");
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
struct thread *sched_out __maybe_unused, *sched_in;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
int new_shortname;
u64 timestamp0, timestamp = sample->time;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
s64 delta;
int cpu, this_cpu = sample->cpu;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
if (this_cpu > sched->max_cpu)
sched->max_cpu = this_cpu;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
timestamp0 = sched->cpu_last_switched[this_cpu];
sched->cpu_last_switched[this_cpu] = timestamp;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
if (timestamp0)
delta = timestamp - timestamp0;
else
delta = 0;
if (delta < 0) {
pr_err("hm, delta: %" PRIu64 " < 0 ?\n", delta);
return -1;
}
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
sched_out = machine__findnew_thread(machine, 0, prev_pid);
sched_in = machine__findnew_thread(machine, 0, next_pid);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
sched->curr_thread[this_cpu] = sched_in;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" ");
new_shortname = 0;
if (!sched_in->shortname[0]) {
sched_in->shortname[0] = sched->next_shortname1;
sched_in->shortname[1] = sched->next_shortname2;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
if (sched->next_shortname1 < 'Z') {
sched->next_shortname1++;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
} else {
sched->next_shortname1='A';
if (sched->next_shortname2 < '9') {
sched->next_shortname2++;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
} else {
sched->next_shortname2='0';
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
}
new_shortname = 1;
}
for (cpu = 0; cpu <= sched->max_cpu; cpu++) {
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
if (cpu != this_cpu)
printf(" ");
else
printf("*");
if (sched->curr_thread[cpu]) {
if (sched->curr_thread[cpu]->tid)
printf("%2s ", sched->curr_thread[cpu]->shortname);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
else
printf(". ");
} else
printf(" ");
}
printf(" %12.6f secs ", (double)timestamp/1e9);
if (new_shortname) {
printf("%s => %s:%d\n",
sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
} else {
printf("\n");
}
return 0;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
static int process_sched_switch_event(struct perf_tool *tool,
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
struct perf_sample *sample,
struct machine *machine)
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
int this_cpu = sample->cpu, err = 0;
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
next_pid = perf_evsel__intval(evsel, sample, "next_pid");
if (sched->curr_pid[this_cpu] != (u32)-1) {
/*
* Are we trying to switch away a PID that is
* not current?
*/
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (sched->curr_pid[this_cpu] != prev_pid)
sched->nr_context_switch_bugs++;
}
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (sched->tp_handler->switch_event)
err = sched->tp_handler->switch_event(sched, evsel, sample, machine);
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
sched->curr_pid[this_cpu] = next_pid;
return err;
}
static int process_sched_runtime_event(struct perf_tool *tool,
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
struct perf_sample *sample,
struct machine *machine)
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (sched->tp_handler->runtime_event)
return sched->tp_handler->runtime_event(sched, evsel, sample, machine);
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
return 0;
perf sched: Add support for sched:sched_stat_runtime events This allows more precise 'perf sched latency' output: --------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | --------------------------------------------------------------------------------------- ksoftirqd/0-4 | 0.010 ms | 2 | avg: 2.476 ms | max: 2.977 ms | perf-12328 | 15.844 ms | 66 | avg: 1.118 ms | max: 9.979 ms | bdi-default-235 | 0.009 ms | 1 | avg: 0.998 ms | max: 0.998 ms | events/1-8 | 0.020 ms | 2 | avg: 0.998 ms | max: 0.998 ms | events/0-7 | 0.018 ms | 2 | avg: 0.992 ms | max: 0.996 ms | sleep-12329 | 0.742 ms | 3 | avg: 0.906 ms | max: 2.289 ms | sshd-12122 | 0.163 ms | 2 | avg: 0.283 ms | max: 0.562 ms | loop-getpid-lon-12322 | 1023.636 ms | 69 | avg: 0.208 ms | max: 5.996 ms | loop-getpid-lon-12321 | 1038.638 ms | 5 | avg: 0.073 ms | max: 0.171 ms | migration/1-5 | 0.000 ms | 1 | avg: 0.006 ms | max: 0.006 ms | --------------------------------------------------------------------------------------- TOTAL: | 2079.078 ms | 153 | ------------------------------------------------- Also, streamline the code a bit more, add asserts for various state machine failures (they should be debugged if they occur) and fix a few odd ends. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-14 20:04:48 +02:00
}
static int perf_sched__process_fork_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
perf sched: Fix bad event alignment perf sched raises the following error when it meets a sched switch event: perf: builtin-sched.c:286: register_pid: Assertion `!(pid >= 65536)' failed. Abandon Currently in x86-64, the sched switch events have a hole in the middle of the structure: u16 common_type; u8 common_flags; u8 common_preempt_count; u32 common_pid; u32 common_tgid; char prev_comm[16]; u32 prev_pid; u32 prev_prio; <--- there u64 prev_state; char next_comm[16]; u32 next_pid; u32 next_prio; Gcc inserts a 4 bytes hole there for prev_state to be u64 aligned. And the events are exported to userspace with this hole. But in userspace, from perf sched, we fetch it using a structure that has a new field in the beginning: u32 size. This is because our trace is exported with its size as a field. But now that we have this new field, the hole in the middle disappears because it makes prev_state becoming well aligned. And since we are using a pointer to the raw trace using this struct, instead of reading prev_state, we are reading the hole. We could fix it by keeping the size seperate from the struct but actually there a lot of other potential problems: some fields may be saved as long in a 64 bits system and later read as long in a 32 bits system. Also this direct cast doesn't care about the endianness differences between the host traced machine and the machine in which we do the post processing. So instead of using such dangerous direct casts, fetch the values using the trace parsing API that already takes care of all these problems. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-12 02:43:45 +02:00
/* run the fork event through the perf machineruy */
perf_event__process_fork(tool, event, sample, machine);
/* and then run additional processing needed for this command */
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (sched->tp_handler->fork_event)
return sched->tp_handler->fork_event(sched, event, machine);
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
return 0;
perf sched: Implement the scheduling workload replay engine Integrate the schedbench.c bits with the raw trace events that we get from the perf machinery, and activate the workload replayer/simulator. Example of a captured 'make -j' workload: $ perf sched run measurement overhead: 90 nsecs sleep measurement overhead: 2724743 nsecs the run test took 1000081 nsecs the sleep test took 2981111 nsecs version = 0.5 ... nr_run_events: 70 nr_sleep_events: 66 nr_wakeup_events: 9 target-less wakeups: 71 multi-target wakeups: 47 run events optimized: 139 task 0 ( perf: 6607), nr_events: 2 task 1 ( perf: 6608), nr_events: 6 task 2 ( : 0), nr_events: 1 task 3 ( make: 6609), nr_events: 5 task 4 ( sh: 6610), nr_events: 4 task 5 ( make: 6611), nr_events: 6 task 6 ( sh: 6612), nr_events: 4 task 7 ( make: 6613), nr_events: 5 task 8 ( migration/11: 25), nr_events: 1 task 9 ( migration/13: 29), nr_events: 1 task 10 ( migration/15: 33), nr_events: 1 task 11 ( migration/9: 21), nr_events: 1 task 12 ( sh: 6614), nr_events: 4 task 13 ( make: 6615), nr_events: 5 task 14 ( sh: 6616), nr_events: 4 task 15 ( make: 6617), nr_events: 7 task 16 ( migration/3: 9), nr_events: 1 task 17 ( migration/5: 13), nr_events: 1 task 18 ( migration/7: 17), nr_events: 1 task 19 ( migration/1: 5), nr_events: 1 task 20 ( sh: 6618), nr_events: 4 task 21 ( make: 6619), nr_events: 5 task 22 ( sh: 6620), nr_events: 4 task 23 ( make: 6621), nr_events: 10 task 24 ( sh: 6623), nr_events: 3 task 25 ( gcc: 6624), nr_events: 4 task 26 ( gcc: 6625), nr_events: 4 task 27 ( gcc: 6626), nr_events: 5 task 28 ( collect2: 6627), nr_events: 5 task 29 ( sh: 6622), nr_events: 1 task 30 ( make: 6628), nr_events: 7 task 31 ( sh: 6630), nr_events: 4 task 32 ( gcc: 6631), nr_events: 4 task 33 ( sh: 6629), nr_events: 1 task 34 ( gcc: 6632), nr_events: 4 task 35 ( gcc: 6633), nr_events: 4 task 36 ( collect2: 6634), nr_events: 4 task 37 ( make: 6635), nr_events: 8 task 38 ( sh: 6637), nr_events: 4 task 39 ( sh: 6636), nr_events: 1 task 40 ( gcc: 6638), nr_events: 4 task 41 ( gcc: 6639), nr_events: 4 task 42 ( gcc: 6640), nr_events: 4 task 43 ( collect2: 6641), nr_events: 4 task 44 ( make: 6642), nr_events: 6 task 45 ( sh: 6643), nr_events: 5 task 46 ( sh: 6644), nr_events: 3 task 47 ( sh: 6645), nr_events: 4 task 48 ( make: 6646), nr_events: 6 task 49 ( sh: 6647), nr_events: 3 task 50 ( make: 6648), nr_events: 5 task 51 ( sh: 6649), nr_events: 5 task 52 ( sh: 6650), nr_events: 6 task 53 ( make: 6651), nr_events: 4 task 54 ( make: 6652), nr_events: 5 task 55 ( make: 6653), nr_events: 4 task 56 ( make: 6654), nr_events: 4 task 57 ( make: 6655), nr_events: 5 task 58 ( sh: 6656), nr_events: 4 task 59 ( gcc: 6657), nr_events: 9 task 60 ( ksoftirqd/3: 10), nr_events: 1 task 61 ( gcc: 6658), nr_events: 4 task 62 ( make: 6659), nr_events: 5 task 63 ( sh: 6660), nr_events: 3 task 64 ( gcc: 6661), nr_events: 5 task 65 ( collect2: 6662), nr_events: 4 ------------------------------------------------------------ #1 : 256.745, ravg: 256.74, cpu: 0.00 / 0.00 #2 : 439.372, ravg: 275.01, cpu: 0.00 / 0.00 #3 : 411.971, ravg: 288.70, cpu: 0.00 / 0.00 #4 : 385.500, ravg: 298.38, cpu: 0.00 / 0.00 #5 : 366.526, ravg: 305.20, cpu: 0.00 / 0.00 #6 : 381.281, ravg: 312.81, cpu: 0.00 / 0.00 #7 : 410.756, ravg: 322.60, cpu: 0.00 / 0.00 #8 : 368.009, ravg: 327.14, cpu: 0.00 / 0.00 #9 : 408.098, ravg: 335.24, cpu: 0.00 / 0.00 #10 : 368.582, ravg: 338.57, cpu: 0.00 / 0.00 I.e. we successfully analyzed the trace, replayed it via real threads and measured the replayed workload's scheduling properties. This is how it looked like in 'top' output: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7164 mingo 20 0 1434m 8080 888 R 57.0 0.1 0:02.04 :perf 7165 mingo 20 0 1434m 8080 888 R 41.8 0.1 0:01.52 :perf 7228 mingo 20 0 1434m 8080 888 R 39.8 0.1 0:01.44 :gcc 7225 mingo 20 0 1434m 8080 888 R 33.8 0.1 0:01.26 :gcc 7202 mingo 20 0 1434m 8080 888 R 31.2 0.1 0:01.16 :sh 7222 mingo 20 0 1434m 8080 888 R 25.2 0.1 0:00.96 :sh 7211 mingo 20 0 1434m 8080 888 R 21.9 0.1 0:00.82 :sh 7213 mingo 20 0 1434m 8080 888 D 19.2 0.1 0:00.74 :sh 7194 mingo 20 0 1434m 8080 888 D 18.6 0.1 0:00.72 :make There's still various kinks in it - more patches to come. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-11 12:12:54 +02:00
}
static int process_sched_migrate_task_event(struct perf_tool *tool,
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel,
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
struct perf_sample *sample,
struct machine *machine)
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
{
struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
perf sched: Don't read all tracepoint variables in advance Do it just at the actual consumer of these fields, that way we avoid needless lookups: [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 98.848272 task-clock # 0.993 CPUs utilized ( +- 0.48% ) 11 context-switches # 0.112 K/sec ( +- 2.83% ) 0 cpu-migrations # 0.003 K/sec ( +- 50.92% ) 7,604 page-faults # 0.077 M/sec ( +- 0.00% ) 332,216,085 cycles # 3.361 GHz ( +- 0.14% ) [82.87%] 100,623,710 stalled-cycles-frontend # 30.29% frontend cycles idle ( +- 0.53% ) [82.95%] 58,788,692 stalled-cycles-backend # 17.70% backend cycles idle ( +- 0.59% ) [67.15%] 609,402,433 instructions # 1.83 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.76%] 131,277,138 branches # 1328.067 M/sec ( +- 0.06% ) [83.77%] 1,117,871 branch-misses # 0.85% of all branches ( +- 0.32% ) [83.51%] 0.099580430 seconds time elapsed ( +- 0.48% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-kracdpw8wqlr0xjh75uk8g11@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
if (sched->tp_handler->migrate_task_event)
return sched->tp_handler->migrate_task_event(sched, evsel, sample, machine);
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
return 0;
perf sched: Add -C option to measure on a specific CPU To refresh, trying to sched record only one CPU results in bogus latencies as below. I fixed^Wmade it stop doing the bad thing today, by following task migration events properly. Before: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- Xorg:4943 | 1.290 ms | 1 | avg: 1670.132 ms | max: 1670.132 ms | hald-addon-stor:3569 | 0.091 ms | 3 | avg: 658.609 ms | max: 1975.797 ms | hald-addon-stor:3573 | 0.209 ms | 4 | avg: 499.138 ms | max: 1990.565 ms | audispd:4270 | 0.012 ms | 1 | avg: 0.015 ms | max: 0.015 ms | .... marge:/root/tmp # perf sched trace|grep 'Xorg:4943' swapper-0 [000] 401.184013288: sched_stat_runtime: task: Xorg:4943 runtime: 1233188 [ns], vruntime: 19105169779 [ns] rt2870TimerQHan-4947 [000] 402.854140127: sched_stat_wait: task: Xorg:4943 wait: 580073 [ns] rt2870TimerQHan-4947 [000] 402.854141770: sched_migrate_task: task Xorg:4943 [140] from: 1 to: 0 rt2870TimerQHan-4947 [000] 402.854143854: sched_stat_wait: task: Xorg:4943 wait: 0 [ns] rt2870TimerQHan-4947 [000] 402.854145397: sched_switch: task rt2870TimerQHan:4947 [140] (D) ==> Xorg:4943 [140] Xorg-4943 [000] 402.854193133: sched_stat_runtime: task: Xorg:4943 runtime: 56546 [ns], vruntime: 11766332500 [ns] Xorg-4943 [000] 402.854196842: sched_switch: task Xorg:4943 [140] (S) ==> swapper:0 [140] After: marge:/root/tmp # taskset -c 1 perf sched record -C 0 -- sleep 10 marge:/root/tmp # perf sched lat ----------------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------------- amarokapp:11150 | 271.297 ms | 878 | avg: 0.130 ms | max: 1.057 ms | konsole:5965 | 1.370 ms | 12 | avg: 0.092 ms | max: 0.855 ms | Xorg:4943 | 179.980 ms | 1109 | avg: 0.087 ms | max: 1.206 ms | hald-addon-stor:3574 | 0.212 ms | 9 | avg: 0.040 ms | max: 0.169 ms | hald-addon-stor:3570 | 0.223 ms | 9 | avg: 0.037 ms | max: 0.223 ms | klauncher:5864 | 0.550 ms | 8 | avg: 0.032 ms | max: 0.048 ms | The 'Maximum delay ms' results are now sane. Signed-off-by: Mike Galbraith <efault@gmx.de> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-10 14:46:04 +02:00
}
typedef int (*tracepoint_handler)(struct perf_tool *tool,
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
struct perf_evsel *evsel,
struct perf_sample *sample,
struct machine *machine);
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_unused,
union perf_event *event __maybe_unused,
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 20:57:40 +01:00
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
int err = 0;
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 20:57:40 +01:00
evsel->hists.stats.total_period += sample->period;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
if (evsel->handler != NULL) {
tracepoint_handler f = evsel->handler;
perf sched: Use perf_evsel__{int,str}val This patch also stops reading the common fields, as they were not being used except for one ->common_pid case that was replaced by sample->tid, i.e. the info is already in the perf_sample struct. Also it only fills the _event structures when there is a handler. [root@sandy ~]# perf sched record sleep 30s [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 8.585 MB perf.data (~375063 samples) ] Before: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 129.117838 task-clock # 0.994 CPUs utilized ( +- 0.28% ) 14 context-switches # 0.111 K/sec ( +- 2.10% ) 0 cpu-migrations # 0.002 K/sec ( +- 66.67% ) 7,654 page-faults # 0.059 M/sec ( +- 0.67% ) 438,121,661 cycles # 3.393 GHz ( +- 0.06% ) [83.06%] 150,808,605 stalled-cycles-frontend # 34.42% frontend cycles idle ( +- 0.14% ) [83.10%] 80,748,941 stalled-cycles-backend # 18.43% backend cycles idle ( +- 0.64% ) [66.73%] 758,605,879 instructions # 1.73 insns per cycle # 0.20 stalled cycles per insn ( +- 0.08% ) [83.54%] 162,164,321 branches # 1255.940 M/sec ( +- 0.10% ) [83.70%] 1,609,903 branch-misses # 0.99% of all branches ( +- 0.08% ) [83.62%] 0.129949153 seconds time elapsed ( +- 0.28% ) After: [root@sandy ~]# perf stat -r 10 perf sched lat > /dev/null Performance counter stats for 'perf sched lat' (10 runs): 103.592215 task-clock # 0.993 CPUs utilized ( +- 0.33% ) 12 context-switches # 0.114 K/sec ( +- 3.29% ) 0 cpu-migrations # 0.000 K/sec 7,605 page-faults # 0.073 M/sec ( +- 0.00% ) 345,796,112 cycles # 3.338 GHz ( +- 0.07% ) [82.90%] 106,876,796 stalled-cycles-frontend # 30.91% frontend cycles idle ( +- 0.38% ) [83.23%] 62,060,877 stalled-cycles-backend # 17.95% backend cycles idle ( +- 0.80% ) [67.14%] 628,246,586 instructions # 1.82 insns per cycle # 0.17 stalled cycles per insn ( +- 0.04% ) [83.64%] 134,962,057 branches # 1302.820 M/sec ( +- 0.10% ) [83.64%] 1,233,037 branch-misses # 0.91% of all branches ( +- 0.29% ) [83.41%] 0.104333272 seconds time elapsed ( +- 0.33% ) [root@sandy ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-weu9t63zkrfrazkn0gxj48xy@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-12 00:29:17 +02:00
err = f(tool, evsel, sample, machine);
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 20:57:40 +01:00
}
return err;
}
static int perf_sched__read_events(struct perf_sched *sched,
struct perf_session **psession)
{
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 20:57:40 +01:00
const struct perf_evsel_str_handler handlers[] = {
{ "sched:sched_switch", process_sched_switch_event, },
{ "sched:sched_stat_runtime", process_sched_runtime_event, },
{ "sched:sched_wakeup", process_sched_wakeup_event, },
{ "sched:sched_wakeup_new", process_sched_wakeup_event, },
{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
};
struct perf_session *session;
struct perf_data_file file = {
.path = input_name,
.mode = PERF_DATA_MODE_READ,
};
session = perf_session__new(&file, false, &sched->tool);
if (session == NULL) {
pr_debug("No Memory for session\n");
return -1;
}
if (perf_session__set_tracepoints_handlers(session, handlers))
goto out_delete;
perf tools: Save some loops using perf_evlist__id2evsel Since we already ask for PERF_SAMPLE_ID and use it to quickly find the associated evsel, add handler func + data to struct perf_evsel to avoid using chains of if(strcmp(event_name)) and also to avoid all the linear list searches via trace_event_find. To demonstrate the technique convert 'perf sched' to it: # perf sched record sleep 5m And then: Performance counter stats for '/tmp/oldperf sched lat': 646.929438 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,901 page-faults # 0.032 M/sec 1,290,144,450 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,606,158,439 instructions # 1.24 insns per cycle 339,088,395 branches # 524.151 M/sec 4,550,735 branch-misses # 1.34% of all branches 0.647524759 seconds time elapsed Versus: Performance counter stats for 'perf sched lat': 473.564691 task-clock # 0.999 CPUs utilized 9 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 20,903 page-faults # 0.044 M/sec 944,367,984 cycles # 1.994 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 1,442,385,571 instructions # 1.53 insns per cycle 308,383,106 branches # 651.195 M/sec 4,481,784 branch-misses # 1.45% of all branches 0.474215751 seconds time elapsed [root@emilia ~]# Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-28 20:57:40 +01:00
if (perf_session__has_traces(session, "record -R")) {
int err = perf_session__process_events(session, &sched->tool);
if (err) {
pr_err("Failed to process events, error %d", err);
goto out_delete;
}
sched->nr_events = session->stats.nr_events[0];
sched->nr_lost_events = session->stats.total_lost;
sched->nr_lost_chunks = session->stats.nr_events[PERF_RECORD_LOST];
}
if (psession)
*psession = session;
else
perf_session__delete(session);
return 0;
out_delete:
perf_session__delete(session);
return -1;
}
static void print_bad_events(struct perf_sched *sched)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
{
if (sched->nr_unordered_timestamps && sched->nr_timestamps) {
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" INFO: %.3f%% unordered timestamps (%ld out of %ld)\n",
(double)sched->nr_unordered_timestamps/(double)sched->nr_timestamps*100.0,
sched->nr_unordered_timestamps, sched->nr_timestamps);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
if (sched->nr_lost_events && sched->nr_events) {
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" INFO: %.3f%% lost events (%ld out of %ld, in %ld chunks)\n",
(double)sched->nr_lost_events/(double)sched->nr_events * 100.0,
sched->nr_lost_events, sched->nr_events, sched->nr_lost_chunks);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
if (sched->nr_state_machine_bugs && sched->nr_timestamps) {
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" INFO: %.3f%% state machine bugs (%ld out of %ld)",
(double)sched->nr_state_machine_bugs/(double)sched->nr_timestamps*100.0,
sched->nr_state_machine_bugs, sched->nr_timestamps);
if (sched->nr_lost_events)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" (due to lost events?)");
printf("\n");
}
if (sched->nr_context_switch_bugs && sched->nr_timestamps) {
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" INFO: %.3f%% context switch bugs (%ld out of %ld)",
(double)sched->nr_context_switch_bugs/(double)sched->nr_timestamps*100.0,
sched->nr_context_switch_bugs, sched->nr_timestamps);
if (sched->nr_lost_events)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" (due to lost events?)");
printf("\n");
}
}
static int perf_sched__lat(struct perf_sched *sched)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
{
struct rb_node *next;
struct perf_session *session;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
setup_pager();
/* save session -- references to threads are held in work_list */
if (perf_sched__read_events(sched, &session))
return -1;
perf_sched__sort_lat(sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf("\n ---------------------------------------------------------------------------------------------------------------\n");
printf(" Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | Maximum delay at |\n");
printf(" ---------------------------------------------------------------------------------------------------------------\n");
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
next = rb_first(&sched->sorted_atom_root);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
while (next) {
struct work_atoms *work_list;
work_list = rb_entry(next, struct work_atoms, node);
output_lat_thread(sched, work_list);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
next = rb_next(next);
}
printf(" -----------------------------------------------------------------------------------------\n");
printf(" TOTAL: |%11.3f ms |%9" PRIu64 " |\n",
(double)sched->all_runtime / 1e6, sched->all_count);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf(" ---------------------------------------------------\n");
print_bad_events(sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf("\n");
perf_session__delete(session);
return 0;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
static int perf_sched__map(struct perf_sched *sched)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
{
sched->max_cpu = sysconf(_SC_NPROCESSORS_CONF);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
setup_pager();
if (perf_sched__read_events(sched, NULL))
return -1;
print_bad_events(sched);
return 0;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
static int perf_sched__replay(struct perf_sched *sched)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
{
unsigned long i;
calibrate_run_measurement_overhead(sched);
calibrate_sleep_measurement_overhead(sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
test_calibrations(sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
if (perf_sched__read_events(sched, NULL))
return -1;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf("nr_run_events: %ld\n", sched->nr_run_events);
printf("nr_sleep_events: %ld\n", sched->nr_sleep_events);
printf("nr_wakeup_events: %ld\n", sched->nr_wakeup_events);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
if (sched->targetless_wakeups)
printf("target-less wakeups: %ld\n", sched->targetless_wakeups);
if (sched->multitarget_wakeups)
printf("multi-target wakeups: %ld\n", sched->multitarget_wakeups);
if (sched->nr_run_events_optimized)
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf("run atoms optimized: %ld\n",
sched->nr_run_events_optimized);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
print_task_traces(sched);
add_cross_task_wakeups(sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
create_tasks(sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
printf("------------------------------------------------------------\n");
for (i = 0; i < sched->replay_repeat; i++)
run_one_test(sched);
return 0;
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
}
static void setup_sorting(struct perf_sched *sched, const struct option *options,
const char * const usage_msg[])
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
{
char *tmp, *tok, *str = strdup(sched->sort_order);
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
for (tok = strtok_r(str, ", ", &tmp);
tok; tok = strtok_r(NULL, ", ", &tmp)) {
if (sort_dimension__add(tok, &sched->sort_list) < 0) {
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
error("Unknown --sort key: `%s'", tok);
usage_with_options(usage_msg, options);
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
}
}
free(str);
sort_dimension__add("pid", &sched->cmp_pid);
perf sched: Implement multidimensional sorting Implement multidimensional sorting on perf sched so that you can sort either by number of switches, latency average, latency maximum, runtime. perf sched -l -s avg,max (this is the default) ----------------------------------------------------------------------------------- Task | Runtime ms | Switches | Average delay ms | Maximum delay ms | ----------------------------------------------------------------------------------- gnome-power-man | 0.113 ms | 1 | avg: 4998.531 ms | max: 4998.531 ms | xfdesktop | 1.190 ms | 7 | avg: 136.475 ms | max: 940.933 ms | xfce-mcs-manage | 2.194 ms | 22 | avg: 38.534 ms | max: 735.174 ms | notification-da | 2.749 ms | 31 | avg: 27.436 ms | max: 731.791 ms | xfce4-session | 3.343 ms | 28 | avg: 26.796 ms | max: 734.891 ms | xfwm4 | 3.159 ms | 22 | avg: 12.406 ms | max: 241.333 ms | xchat | 42.789 ms | 214 | avg: 11.886 ms | max: 100.349 ms | xfce4-terminal | 5.386 ms | 22 | avg: 11.414 ms | max: 241.611 ms | firefox | 151.992 ms | 123 | avg: 9.543 ms | max: 153.717 ms | xfce4-panel | 24.324 ms | 47 | avg: 8.189 ms | max: 242.352 ms | :5090 | 6.932 ms | 111 | avg: 8.131 ms | max: 102.665 ms | events/0 | 0.758 ms | 12 | avg: 1.964 ms | max: 21.879 ms | Xorg | 280.558 ms | 340 | avg: 1.864 ms | max: 99.526 ms | geany | 63.391 ms | 295 | avg: 1.099 ms | max: 9.334 ms | reiserfs/0 | 0.039 ms | 2 | avg: 0.854 ms | max: 1.487 ms | kondemand/0 | 8.251 ms | 245 | avg: 0.691 ms | max: 34.372 ms | Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-13 03:36:29 +02:00
}
static int __cmd_record(int argc, const char **argv)
{
unsigned int rec_argc, i, j;
const char **rec_argv;
const char * const record_args[] = {
"record",
"-a",
"-R",
"-m", "1024",
"-c", "1",
"-e", "sched:sched_switch",
"-e", "sched:sched_stat_wait",
"-e", "sched:sched_stat_sleep",
"-e", "sched:sched_stat_iowait",
"-e", "sched:sched_stat_runtime",
"-e", "sched:sched_process_fork",
"-e", "sched:sched_wakeup",
"-e", "sched:sched_migrate_task",
};
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
return -ENOMEM;
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[i] = strdup(record_args[i]);
for (j = 1; j < (unsigned int)argc; j++, i++)
rec_argv[i] = argv[j];
BUG_ON(i != rec_argc);
return cmd_record(i, rec_argv, NULL);
}
perf tools: Use __maybe_used for unused variables perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:15:03 +02:00
int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
{
const char default_sort_order[] = "avg, max, switch, runtime";
struct perf_sched sched = {
.tool = {
.sample = perf_sched__process_tracepoint_sample,
.comm = perf_event__process_comm,
.lost = perf_event__process_lost,
.fork = perf_sched__process_fork_event,
.ordered_samples = true,
},
.cmp_pid = LIST_HEAD_INIT(sched.cmp_pid),
.sort_list = LIST_HEAD_INIT(sched.sort_list),
.start_work_mutex = PTHREAD_MUTEX_INITIALIZER,
.work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
.sort_order = default_sort_order,
.replay_repeat = 10,
.profile_cpu = -1,
.next_shortname1 = 'A',
.next_shortname2 = '0',
};
const struct option latency_options[] = {
OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
"sort by key(s): runtime, switch, avg, max"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_INTEGER('C', "CPU", &sched.profile_cpu,
"CPU to profile on"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_END()
};
const struct option replay_options[] = {
OPT_UINTEGER('r', "repeat", &sched.replay_repeat,
"repeat the workload replay N times (-1: infinite)"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_END()
};
const struct option sched_options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_END()
};
const char * const latency_usage[] = {
"perf sched latency [<options>]",
NULL
};
const char * const replay_usage[] = {
"perf sched replay [<options>]",
NULL
};
const char * const sched_usage[] = {
"perf sched [<options>] {record|latency|map|replay|script}",
NULL
};
struct trace_sched_handler lat_ops = {
.wakeup_event = latency_wakeup_event,
.switch_event = latency_switch_event,
.runtime_event = latency_runtime_event,
.migrate_task_event = latency_migrate_task_event,
};
struct trace_sched_handler map_ops = {
.switch_event = map_switch_event,
};
struct trace_sched_handler replay_ops = {
.wakeup_event = replay_wakeup_event,
.switch_event = replay_switch_event,
.fork_event = replay_fork_event,
};
unsigned int i;
for (i = 0; i < ARRAY_SIZE(sched.curr_pid); i++)
sched.curr_pid[i] = -1;
argc = parse_options(argc, argv, sched_options, sched_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc)
usage_with_options(sched_usage, sched_options);
/*
* Aliased to 'perf script' for now:
*/
if (!strcmp(argv[0], "script"))
return cmd_script(argc, argv, prefix);
symbol__init();
if (!strncmp(argv[0], "rec", 3)) {
return __cmd_record(argc, argv);
} else if (!strncmp(argv[0], "lat", 3)) {
sched.tp_handler = &lat_ops;
if (argc > 1) {
argc = parse_options(argc, argv, latency_options, latency_usage, 0);
if (argc)
usage_with_options(latency_usage, latency_options);
}
setup_sorting(&sched, latency_options, latency_usage);
return perf_sched__lat(&sched);
perf sched: Add 'perf sched map' scheduling event map printout This prints a textual context-switching outline of workload captured via perf sched record. For example, on a 16 CPU box it outputs: N1 O1 . . . S1 . . . B0 . *I0 C1 . M1 . 23002.773423 secs N1 O1 . *Q0 . S1 . . . B0 . I0 C1 . M1 . 23002.773423 secs N1 O1 . Q0 . S1 . . . B0 . *R1 C1 . M1 . 23002.773485 secs N1 O1 . Q0 . S1 . *S0 . B0 . R1 C1 . M1 . 23002.773478 secs *L0 O1 . Q0 . S1 . S0 . B0 . R1 C1 . M1 . 23002.773523 secs L0 O1 . *. . S1 . S0 . B0 . R1 C1 . M1 . 23002.773531 secs L0 O1 . . . S1 . S0 . B0 . R1 C1 *T1 M1 . 23002.773547 secs T1 => irqbalance:2089 L0 O1 . . . S1 . S0 . *P0 . R1 C1 T1 M1 . 23002.773549 secs *N1 O1 . . . S1 . S0 . P0 . R1 C1 T1 M1 . 23002.773566 secs N1 O1 . . . *J0 . S0 . P0 . R1 C1 T1 M1 . 23002.773571 secs N1 O1 . . . J0 . S0 *B0 P0 . R1 C1 T1 M1 . 23002.773592 secs N1 O1 . . . J0 . *U0 B0 P0 . R1 C1 T1 M1 . 23002.773582 secs N1 O1 . . . *S1 . U0 B0 P0 . R1 C1 T1 M1 . 23002.773604 secs N1 O1 . . . S1 . U0 B0 *. . R1 C1 T1 M1 . 23002.773615 secs N1 O1 . . . S1 . U0 B0 . . *K0 C1 T1 M1 . 23002.773631 secs N1 O1 . *M0 . S1 . U0 B0 . . K0 C1 T1 M1 . 23002.773624 secs N1 O1 . M0 . S1 . U0 *. . . K0 C1 T1 M1 . 23002.773644 secs N1 O1 . M0 . S1 . U0 . . . *R1 C1 T1 M1 . 23002.773662 secs N1 O1 . M0 . S1 . *. . . . R1 C1 T1 M1 . 23002.773648 secs N1 O1 . *. . S1 . . . . . R1 C1 T1 M1 . 23002.773680 secs N1 O1 . . . *L0 . . . . . R1 C1 T1 M1 . 23002.773717 secs *N0 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773709 secs *N1 O1 . . . L0 . . . . . R1 C1 T1 M1 . 23002.773747 secs Columns stand for individual CPUs, from CPU0 to CPU15, and the two-letter shortcuts stand for tasks that are running on a CPU. '*' denotes the CPU that had the event. A dot signals an idle CPU. New tasks are assigned new two-letter shortcuts - when they occur first they are printed. In the above example 'T1' stood for irqbalance: T1 => irqbalance:2089 Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-16 17:40:48 +02:00
} else if (!strcmp(argv[0], "map")) {
sched.tp_handler = &map_ops;
setup_sorting(&sched, latency_options, latency_usage);
return perf_sched__map(&sched);
} else if (!strncmp(argv[0], "rep", 3)) {
sched.tp_handler = &replay_ops;
if (argc) {
argc = parse_options(argc, argv, replay_options, replay_usage, 0);
if (argc)
usage_with_options(replay_usage, replay_options);
}
return perf_sched__replay(&sched);
} else {
usage_with_options(sched_usage, sched_options);
}
return 0;
}