OpenE2K/linux
6
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
a9ece53c40
linux/kernel
History
Jiri Pirko 1f10206cf8 getrusage: fill ru_maxrss value 
Make ->ru_maxrss value in struct rusage filled accordingly to rss hiwater
mark.  This struct is filled as a parameter to getrusage syscall.
->ru_maxrss value is set to KBs which is the way it is done in BSD
systems.  /usr/bin/time (gnu time) application converts ->ru_maxrss to KBs
which seems to be incorrect behavior.  Maintainer of this util was
notified by me with the patch which corrects it and cc'ed.

To make this happen we extend struct signal_struct by two fields.  The
first one is ->maxrss which we use to store rss hiwater of the task.  The
second one is ->cmaxrss which we use to store highest rss hiwater of all
task childs.  These values are used in k_getrusage() to actually fill
->ru_maxrss.  k_getrusage() uses current rss hiwater value directly if mm
struct exists.

Note:
exec() clear mm->hiwater_rss, but doesn't clear sig->maxrss.
it is intetionally behavior. *BSD getrusage have exec() inheriting.

test programs
========================================================

getrusage.c
===========
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <signal.h>
 #include <sys/mman.h>

 #include "common.h"

 #define err(str) perror(str), exit(1)

int main(int argc, char** argv)
{
	int status;

	printf("allocate 100MB\n");
	consume(100);

	printf("testcase1: fork inherit? \n");
	printf("  expect: initial.self ~= child.self\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
	} else {
		show_rusage("fork child");
		_exit(0);
	}
	printf("\n");

	printf("testcase2: fork inherit? (cont.) \n");
	printf("  expect: initial.children ~= 100MB, but child.children = 0\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
	} else {
		show_rusage("child");
		_exit(0);
	}
	printf("\n");

	printf("testcase3: fork + malloc \n");
	printf("  expect: child.self ~= initial.self + 50MB\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
	} else {
		printf("allocate +50MB\n");
		consume(50);
		show_rusage("fork child");
		_exit(0);
	}
	printf("\n");

	printf("testcase4: grandchild maxrss\n");
	printf("  expect: post_wait.children ~= 300MB\n");
	show_rusage("initial");
	if (__fork()) {
		wait(&status);
		show_rusage("post_wait");
	} else {
		system("./child -n 0 -g 300");
		_exit(0);
	}
	printf("\n");

	printf("testcase5: zombie\n");
	printf("  expect: pre_wait ~= initial, IOW the zombie process is not accounted.\n");
	printf("          post_wait ~= 400MB, IOW wait() collect child's max_rss. \n");
	show_rusage("initial");
	if (__fork()) {
		sleep(1); /* children become zombie */
		show_rusage("pre_wait");
		wait(&status);
		show_rusage("post_wait");
	} else {
		system("./child -n 400");
		_exit(0);
	}
	printf("\n");

	printf("testcase6: SIG_IGN\n");
	printf("  expect: initial ~= after_zombie (child's 500MB alloc should be ignored).\n");
	show_rusage("initial");
	signal(SIGCHLD, SIG_IGN);
	if (__fork()) {
		sleep(1); /* children become zombie */
		show_rusage("after_zombie");
	} else {
		system("./child -n 500");
		_exit(0);
	}
	printf("\n");
	signal(SIGCHLD, SIG_DFL);

	printf("testcase7: exec (without fork) \n");
	printf("  expect: initial ~= exec \n");
	show_rusage("initial");
	execl("./child", "child", "-v", NULL);

	return 0;
}

child.c
=======
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/time.h>
 #include <sys/resource.h>

 #include "common.h"

int main(int argc, char** argv)
{
	int status;
	int c;
	long consume_size = 0;
	long grandchild_consume_size = 0;
	int show = 0;

	while ((c = getopt(argc, argv, "n:g:v")) != -1) {
		switch (c) {
		case 'n':
			consume_size = atol(optarg);
			break;
		case 'v':
			show = 1;
			break;
		case 'g':

			grandchild_consume_size = atol(optarg);
			break;
		default:
			break;
		}
	}

	if (show)
		show_rusage("exec");

	if (consume_size) {
		printf("child alloc %ldMB\n", consume_size);
		consume(consume_size);
	}

	if (grandchild_consume_size) {
		if (fork()) {
			wait(&status);
		} else {
			printf("grandchild alloc %ldMB\n", grandchild_consume_size);
			consume(grandchild_consume_size);

			exit(0);
		}
	}

	return 0;
}

common.c
========
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <signal.h>
 #include <sys/mman.h>

 #include "common.h"
 #define err(str) perror(str), exit(1)

void show_rusage(char *prefix)
{
    	int err, err2;
    	struct rusage rusage_self;
    	struct rusage rusage_children;

    	printf("%s: ", prefix);
    	err = getrusage(RUSAGE_SELF, &rusage_self);
    	if (!err)
    		printf("self %ld ", rusage_self.ru_maxrss);
    	err2 = getrusage(RUSAGE_CHILDREN, &rusage_children);
    	if (!err2)
    		printf("children %ld ", rusage_children.ru_maxrss);

    	printf("\n");
}

/* Some buggy OS need this worthless CPU waste. */
void make_pagefault(void)
{
	void *addr;
	int size = getpagesize();
	int i;

	for (i=0; i<1000; i++) {
		addr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);
		if (addr == MAP_FAILED)
			err("make_pagefault");
		memset(addr, 0, size);
		munmap(addr, size);
	}
}

void consume(int mega)
{
    	size_t sz = mega * 1024 * 1024;
    	void *ptr;

    	ptr = malloc(sz);
    	memset(ptr, 0, sz);
	make_pagefault();
}

pid_t __fork(void)
{
	pid_t pid;

	pid = fork();
	make_pagefault();

	return pid;
}

common.h
========
void show_rusage(char *prefix);
void make_pagefault(void);
void consume(int mega);
pid_t __fork(void);

FreeBSD result (expected result)
========================================================
allocate 100MB
testcase1: fork inherit?
  expect: initial.self ~= child.self
initial: self 103492 children 0
fork child: self 103540 children 0

testcase2: fork inherit? (cont.)
  expect: initial.children ~= 100MB, but child.children = 0
initial: self 103540 children 103540
child: self 103564 children 0

testcase3: fork + malloc
  expect: child.self ~= initial.self + 50MB
initial: self 103564 children 103564
allocate +50MB
fork child: self 154860 children 0

testcase4: grandchild maxrss
  expect: post_wait.children ~= 300MB
initial: self 103564 children 154860
grandchild alloc 300MB
post_wait: self 103564 children 308720

testcase5: zombie
  expect: pre_wait ~= initial, IOW the zombie process is not accounted.
          post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 103564 children 308720
child alloc 400MB
pre_wait: self 103564 children 308720
post_wait: self 103564 children 411312

testcase6: SIG_IGN
  expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 103564 children 411312
child alloc 500MB
after_zombie: self 103624 children 411312

testcase7: exec (without fork)
  expect: initial ~= exec
initial: self 103624 children 411312
exec: self 103624 children 411312

Linux result (actual test result)
========================================================
allocate 100MB
testcase1: fork inherit?
  expect: initial.self ~= child.self
initial: self 102848 children 0
fork child: self 102572 children 0

testcase2: fork inherit? (cont.)
  expect: initial.children ~= 100MB, but child.children = 0
initial: self 102876 children 102644
child: self 102572 children 0

testcase3: fork + malloc
  expect: child.self ~= initial.self + 50MB
initial: self 102876 children 102644
allocate +50MB
fork child: self 153804 children 0

testcase4: grandchild maxrss
  expect: post_wait.children ~= 300MB
initial: self 102876 children 153864
grandchild alloc 300MB
post_wait: self 102876 children 307536

testcase5: zombie
  expect: pre_wait ~= initial, IOW the zombie process is not accounted.
          post_wait ~= 400MB, IOW wait() collect child's max_rss.
initial: self 102876 children 307536
child alloc 400MB
pre_wait: self 102876 children 307536
post_wait: self 102876 children 410076

testcase6: SIG_IGN
  expect: initial ~= after_zombie (child's 500MB alloc should be ignored).
initial: self 102876 children 410076
child alloc 500MB
after_zombie: self 102880 children 410076

testcase7: exec (without fork)
  expect: initial ~= exec
initial: self 102880 children 410076
exec: self 102880 children 410076

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-23 07:39:30 -07:00
..
gcov powerpc: Enable GCOV 2009-08-20 10:29:28 +10:00
irq Merge branch 'irq-threaded-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-11 13:21:31 -07:00
power oom: move oom_killer_enable()/oom_killer_disable to where they belong 2009-09-22 07:17:38 -07:00
time Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-18 09:15:24 -07:00
trace seq_file: constify seq_operations 2009-09-23 07:39:29 -07:00
.gitignore
acct.c bsdacct: switch credentials for writing to the accounting file 2009-08-24 11:33:40 +10:00
async.c async: Fix lack of boot-time console due to insufficient synchronization 2009-06-08 12:31:53 -07:00
audit_tree.c Fix rule eviction order for AUDIT_DIR 2009-06-24 00:02:38 -04:00
audit_watch.c Audit: clean up all op= output to include string quoting 2009-06-24 00:00:52 -04:00
audit.c Fix rule eviction order for AUDIT_DIR 2009-06-24 00:02:38 -04:00
audit.h Fix rule eviction order for AUDIT_DIR 2009-06-24 00:02:38 -04:00
auditfilter.c Audit: clean up all op= output to include string quoting 2009-06-24 00:00:52 -04:00
auditsc.c Fix rule eviction order for AUDIT_DIR 2009-06-24 00:02:38 -04:00
backtracetest.c
bounds.c
capability.c [CVE-2009-0029] System call wrappers part 04 2009-01-14 14:15:19 +01:00
cgroup_debug.c debug cgroup: remove unneeded cgroup_lock 2009-04-02 19:04:54 -07:00
cgroup_freezer.c freezer_cg: disable writing freezer.state of root cgroup 2008-11-12 17:17:16 -08:00
cgroup.c seq_file: constify seq_operations 2009-09-23 07:39:29 -07:00
compat.c signals: implement sys_rt_tgsigqueueinfo 2009-04-30 19:24:24 +02:00
configs.c
cpu.c Merge branch 'x86-pat-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-15 09:19:38 -07:00
cpuset.c cpuset,mm: update tasks' mems_allowed in time 2009-06-16 19:47:31 -07:00
cred-internals.h CRED: Inaugurate COW credentials 2008-11-14 10:39:23 +11:00
cred.c CRED: Allow put_cred() to cope with a NULL groups list 2009-09-15 09:10:57 +10:00
delayacct.c headers: taskstats_kern.h trim 2009-09-18 09:48:52 -07:00
dma.c
exec_domain.c Get rid of indirect include of fs_struct.h 2009-03-31 23:00:27 -04:00
exit.c getrusage: fill ru_maxrss value 2009-09-23 07:39:30 -07:00
extable.c Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-04-05 11:04:19 -07:00
fork.c getrusage: fill ru_maxrss value 2009-09-23 07:39:30 -07:00
freezer.c sched: fix nr_uninterruptible accounting of frozen tasks really 2009-07-18 14:19:53 +02:00
futex_compat.c futex: Fix compat_futex to be same as futex for REQUEUE_PI 2009-08-10 15:41:12 +02:00
futex.c Merge branch 'core-futexes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-11 13:16:22 -07:00
groups.c groups: move code to kernel/groups.c 2009-06-16 19:47:48 -07:00
hrtimer.c Merge branch 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-18 09:15:24 -07:00
hung_task.c softlockup: ensure the task has been switched out once 2009-02-11 11:04:16 +01:00
itimer.c timers: split process wide cpu clocks/timers 2009-02-05 13:04:33 +01:00
kallsyms.c kernel/kallsyms.c: replace deprecated __initcall with device_initcall and fix whitespace 2009-06-09 22:37:52 +02:00
Kconfig.freezer
Kconfig.hz
Kconfig.preempt rcu: provide RCU options on non-preempt architectures too 2008-12-25 09:31:28 +01:00
kexec.c kexec: fix omitting offset in extended crashkernel syntax 2009-07-29 19:10:34 -07:00
kfifo.c kfifo: Use "const" definitions 2009-09-19 13:13:17 -07:00
kgdb.c sysrq, intel_fb: fix sysrq g collision 2009-05-15 07:56:24 -05:00
kmod.c kmod: fix race in usermodehelper code 2009-09-23 07:39:28 -07:00
kprobes.c seq_file: constify seq_operations 2009-09-23 07:39:29 -07:00
ksysfs.c kernel/ksysfs.c:fix dependence on CONFIG_NET 2009-01-06 10:44:31 -08:00
kthread.c sched: Keep kthreads at default priority 2009-09-09 17:30:06 +02:00
latencytop.c sched, latencytop: incorporate review feedback from Andrew Morton 2009-02-11 10:18:04 +01:00
lockdep_internals.h lockdep: BFS cleanup 2009-07-24 10:53:29 +02:00
lockdep_proc.c seq_file: constify seq_operations 2009-09-23 07:39:29 -07:00
lockdep_states.h lockdep: move state bit definitions around 2009-02-14 23:27:59 +01:00
lockdep.c lockdep: Remove recursion stattistics 2009-08-29 13:22:36 +02:00
Makefile Merge branch 'perfcounters-rename-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-21 09:15:07 -07:00
module.c nommu: add support for Memory Protection Units (MPU) 2009-09-22 07:17:43 -07:00
mutex-debug.c mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
mutex-debug.h mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
mutex.c Merge branch 'linus' into perfcounters/core 2009-06-11 17:55:42 +02:00
mutex.h mutex: implement adaptive spinning 2009-01-14 18:09:02 +01:00
notifier.c Merge commit 'v2.6.28-rc6' into core/debug 2008-11-26 08:22:50 +01:00
ns_cgroup.c cgroups: relax ns_can_attach checks to allow attaching to grandchild cgroups 2009-04-02 19:04:53 -07:00
nsproxy.c nsproxy: extract create_nsproxy() 2009-06-18 13:03:56 -07:00
panic.c trivial: Correct print_tainted routine name in comment 2009-09-21 15:14:53 +02:00
params.c module_param: allow 'bool' module_params to be bool, not just int. 2009-06-12 21:46:58 +09:30
perf_event.c perf: Tidy up after the big rename 2009-09-21 14:34:11 +02:00
pid_namespace.c pidns: rewrite copy_pid_ns() 2009-06-18 13:03:55 -07:00
pid.c mm: also use alloc_large_system_hash() for the PID hash table 2009-09-22 07:17:38 -07:00
pm_qos_params.c
posix-cpu-timers.c posix_cpu_timers_exit_group(): Do not use thread_group_cputimer() 2009-08-08 18:30:25 +02:00
posix-timers.c time: Introduce CLOCK_REALTIME_COARSE 2009-08-21 21:43:46 +02:00
printk.c printk: add printk_delay to make messages readable for some scenarios 2009-09-23 07:39:28 -07:00
profile.c kernel/profile.c: Switch /proc/irq/prof_cpu_mask to seq_file 2009-09-20 20:15:40 +02:00
ptrace.c Merge branch 'master' into next 2009-07-14 00:30:40 +10:00
rcupdate.c rcu: Fix whitespace inconsistencies 2009-09-19 08:53:22 +02:00
rcutorture.c rcu: Fix whitespace inconsistencies 2009-09-19 08:53:22 +02:00
rcutree_plugin.h rcu: Fix whitespace inconsistencies 2009-09-19 08:53:22 +02:00
rcutree_trace.c rcu: Fix whitespace inconsistencies 2009-09-19 08:53:22 +02:00
rcutree.c rcu: Fix whitespace inconsistencies 2009-09-19 08:53:22 +02:00
rcutree.h rcu: Fix whitespace inconsistencies 2009-09-19 08:53:22 +02:00
relay.c Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-04-05 11:04:19 -07:00
res_counter.c memcg: add interface to reset limits 2009-06-18 13:03:48 -07:00
resource.c kernel/resource.c: fix sign extension in reserve_setup() 2009-06-30 18:56:00 -07:00
rtmutex_common.h rt_mutex: add proxy lock routines 2009-04-06 11:14:02 +02:00
rtmutex-debug.c
rtmutex-debug.h
rtmutex-tester.c
rtmutex.c rtmutex: Avoid deadlock in rt_mutex_start_proxy_lock() 2009-08-06 05:50:21 +02:00
rtmutex.h
rwsem.c
sched_clock.c sched_clock: Make it NMI safe 2009-09-18 20:47:30 +02:00
sched_cpupri.c sched: Add new prio to cpupri before removing old prio 2009-08-02 14:26:09 +02:00
sched_cpupri.h cpumask: remove cpumask_t from core 2009-03-30 22:05:17 +10:30
sched_debug.c sched: Add new wakeup preemption mode: WAKEUP_RUNNING 2009-09-17 10:17:25 +02:00
sched_fair.c Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-21 09:06:17 -07:00
sched_features.h sched: Add new wakeup preemption mode: WAKEUP_RUNNING 2009-09-17 10:17:25 +02:00
sched_idletask.c sched: Simplify sys_sched_rr_get_interval() system call 2009-09-21 09:53:55 +02:00
sched_rt.c sched: Simplify sys_sched_rr_get_interval() system call 2009-09-21 09:53:55 +02:00
sched_stats.h sched: remove unused fields from struct rq 2009-03-24 23:16:51 +01:00
sched.c cpuidle: fix the menu governor to boost IO performance 2009-09-22 07:17:45 -07:00
seccomp.c x86-64: seccomp: fix 32/64 syscall hole 2009-03-02 15:41:30 -08:00
semaphore.c
signal.c do_sigaltstack: small cleanups 2009-08-01 11:18:56 -07:00
slow-work.c slow-work: use round_jiffies() for thread pool's cull and OOM timers 2009-06-16 19:47:49 -07:00
smp.c generic-ipi: make struct call_function_data lockless 2009-09-23 07:39:28 -07:00
softirq.c softirq: add BLOCK_IOPOLL to softirq_to_name 2009-09-17 15:53:44 -04:00
softlockup.c softlockup: decouple hung tasks check from softlockup detection 2009-01-16 14:06:04 +01:00
spinlock.c locking: Allow arch-inlined spinlocks 2009-08-31 18:08:50 +02:00
srcu.c
stacktrace.c stacktrace: provide save_stack_trace_tsk() weak alias 2008-12-25 11:44:43 +01:00
stop_machine.c cpumask: remove cpumask_t from core 2009-03-30 22:05:17 +10:30
sys_ni.c perf: Do the big rename: Performance Counters -> Performance Events 2009-09-21 14:28:04 +02:00
sys.c getrusage: fill ru_maxrss value 2009-09-23 07:39:30 -07:00
sysctl_check.c net: add ARP notify option for devices 2009-02-01 01:04:33 -08:00
sysctl.c printk: add printk_delay to make messages readable for some scenarios 2009-09-23 07:39:28 -07:00
taskstats.c genetlink: make netns aware 2009-07-12 14:03:27 -07:00
test_kprobes.c kprobes: add tests for register_kprobes 2009-01-06 15:59:20 -08:00
time.c time: Prevent 32 bit overflow with set_normalized_timespec() 2009-09-15 10:17:30 +02:00
timeconst.pl
timer.c perf: Do the big rename: Performance Counters -> Performance Events 2009-09-21 14:28:04 +02:00
tracepoint.c trivial: fix typo "to to" in multiple files 2009-09-21 15:14:55 +02:00
tsacct.c Fix fixpoint divide exception in acct_update_integrals 2009-03-09 08:13:35 -07:00
uid16.c [CVE-2009-0029] System call wrappers part 19 2009-01-14 14:15:26 +01:00
up.c smp_call_function_single(): be slightly less stupid, fix #2 2009-01-12 16:04:37 +01:00
user_namespace.c Fix recursive lock in free_uid()/free_user_ns() 2009-02-27 16:26:21 -08:00
user.c sched: delayed cleanup of user_struct 2009-06-15 21:30:23 -07:00
utsname_sysctl.c proc_sysctl: use CONFIG_PROC_SYSCTL around ipc and utsname proc_handlers 2009-04-02 19:05:01 -07:00
utsname.c utsns: extract creeate_uts_ns() 2009-06-18 13:03:55 -07:00
wait.c locking, sched: Give waitqueue spinlocks their own lockdep classes 2009-08-10 14:43:09 +02:00
workqueue.c Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip 2009-09-11 13:23:18 -07:00