Commit Graph

13 Commits

Author SHA1 Message Date
Linus Torvalds c4efd6b569 Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (27 commits)
  sched: Use correct macro to display sched_child_runs_first in /proc/sched_debug
  sched: No need for bootmem special cases
  sched: Revert nohz_ratelimit() for now
  sched: Reduce update_group_power() calls
  sched: Update rq->clock for nohz balanced cpus
  sched: Fix spelling of sibling
  sched, cpuset: Drop __cpuexit from cpu hotplug callbacks
  sched: Fix the racy usage of thread_group_cputimer() in fastpath_timer_check()
  sched: run_posix_cpu_timers: Don't check ->exit_state, use lock_task_sighand()
  sched: thread_group_cputime: Simplify, document the "alive" check
  sched: Remove the obsolete exit_state/signal hacks
  sched: task_tick_rt: Remove the obsolete ->signal != NULL check
  sched: __sched_setscheduler: Read the RLIMIT_RTPRIO value lockless
  sched: Fix comments to make them DocBook happy
  sched: Fix fix_small_capacity
  powerpc: Exclude arch_sd_sibiling_asym_packing() on UP
  powerpc: Enable asymmetric SMT scheduling on POWER7
  sched: Add asymmetric group packing option for sibling domain
  sched: Fix capacity calculations for SMT4
  sched: Change nohz idle load balancing logic to push model
  ...
2010-08-06 09:39:22 -07:00
Peter Zijlstra c676329abb sched_clock: Add local_clock() API and improve documentation
For people who otherwise get to write: cpu_clock(smp_processor_id()),
there is now: local_clock().

Also, as per suggestion from Andrew, provide some documentation on
the various clock interfaces, and minimize the unsigned long long vs
u64 mess.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jens Axboe <jaxboe@fusionio.com>
LKML-Reference: <1275052414.1645.52.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-09 10:34:49 +02:00
Steven Rostedt 5168ae50a6 tracing: Remove ftrace_preempt_disable/enable
The ftrace_preempt_disable/enable functions were to address a
recursive race caused by the function tracer. The function tracer
traces all functions which makes it easily susceptible to recursion.
One area was preempt_enable(). This would call the scheduler and
the schedulre would call the function tracer and loop.
(So was it thought).

The ftrace_preempt_disable/enable was made to protect against recursion
inside the scheduler by storing the NEED_RESCHED flag. If it was
set before the ftrace_preempt_disable() it would not call schedule
on ftrace_preempt_enable(), thinking that if it was set before then
it would have already scheduled unless it was already in the scheduler.

This worked fine except in the case of SMP, where another task would set
the NEED_RESCHED flag for a task on another CPU, and then kick off an
IPI to trigger it. This could cause the NEED_RESCHED to be saved at
ftrace_preempt_disable() but the IPI to arrive in the the preempt
disabled section. The ftrace_preempt_enable() would not call the scheduler
because the flag was already set before entring the section.

This bug would cause a missed preemption check and cause lower latencies.

Investigating further, I found that the recusion caused by the function
tracer was not due to schedule(), but due to preempt_schedule(). Now
that preempt_schedule is completely annotated with notrace, the recusion
no longer is an issue.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-06-03 19:32:38 -04:00
Li Zefan e36673ec51 tracing: Fix lockdep warning in global_clock()
# echo 1 > events/enable
 # echo global > trace_clock

------------[ cut here ]------------
WARNING: at kernel/lockdep.c:3162 check_flags+0xb2/0x190()
...
---[ end trace 3f86734a89416623 ]---
possible reason: unannotated irqs-on.
...

There's no reason to use the raw_local_irq_save() in trace_clock_global.
The local_irq_save() version is fine, and does not cause the bug in lockdep.

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BA97FA1.7030606@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-03-29 15:16:44 -04:00
Frederic Weisbecker ae1f30384b tracing: Include irqflags headers from trace clock
trace_clock.c includes spinlock.h, which ends up including
asm/system.h, which in turn includes linux/irqflags.h in x86.

So the definition of raw_local_irq_save is luckily covered there,
but this is not the case in parisc:

   tip/kernel/trace/trace_clock.c:86: error: implicit declaration of function 'raw_local_irq_save'
   tip/kernel/trace/trace_clock.c:112: error: implicit declaration of function 'raw_local_irq_restore'

We need to include linux/irqflags.h directly from trace_clock.c
to avoid such build error.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-28 19:45:01 +01:00
Thomas Gleixner 0199c4e68d locking: Convert __raw_spin* functions to arch_spin*
Name space cleanup. No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
2009-12-14 23:55:32 +01:00
Thomas Gleixner edc35bd72e locking: Rename __RAW_SPIN_LOCK_UNLOCKED to __ARCH_SPIN_LOCK_UNLOCKED
Further name space cleanup. No functional change

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
2009-12-14 23:55:32 +01:00
Thomas Gleixner 445c89514b locking: Convert raw_spinlock to arch_spinlock
The raw_spin* namespace was taken by lockdep for the architecture
specific implementations. raw_spin_* would be the ideal name space for
the spinlocks which are not converted to sleeping locks in preempt-rt.

Linus suggested to convert the raw_ to arch_ locks and cleanup the
name space instead of using an artifical name like core_spin,
atomic_spin or whatever

No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
2009-12-14 23:55:32 +01:00
Steven Rostedt 8b2a5dac78 tracing: do not disable interrupts for trace_clock_local
Disabling interrupts in trace_clock_local takes quite a performance
hit to the recording of traces. Using perf top we see:

------------------------------------------------------------------------------
   PerfTop:     244 irqs/sec  kernel:100.0% [1000Hz cpu-clock-msecs],  (all, 4 CPUs)
------------------------------------------------------------------------------

             samples    pcnt   kernel function
             _______   _____   _______________

             2842.00 - 40.4% : trace_clock_local
             1043.00 - 14.8% : rb_reserve_next_event
              784.00 - 11.1% : ring_buffer_lock_reserve
              600.00 -  8.5% : __rb_reserve_next
              579.00 -  8.2% : rb_end_commit
              440.00 -  6.3% : ring_buffer_unlock_commit
              290.00 -  4.1% : ring_buffer_producer_thread 	[ring_buffer_benchmark]
              155.00 -  2.2% : debug_smp_processor_id
              117.00 -  1.7% : trace_recursive_unlock
              103.00 -  1.5% : ring_buffer_event_data
               28.00 -  0.4% : do_gettimeofday
               22.00 -  0.3% : _spin_unlock_irq
               14.00 -  0.2% : native_read_tsc
               11.00 -  0.2% : getnstimeofday

Where trace_clock_local is 40% of the tracing, and the time for recording
a trace according to ring_buffer_benchmark is 210ns. After converting
the interrupts to preemption disabling we have from perf top:

------------------------------------------------------------------------------
   PerfTop:    1084 irqs/sec  kernel:99.9% [1000Hz cpu-clock-msecs],  (all, 4 CPUs)
------------------------------------------------------------------------------

             samples    pcnt   kernel function
             _______   _____   _______________

             1277.00 - 16.8% : native_read_tsc
             1148.00 - 15.1% : rb_reserve_next_event
              896.00 - 11.8% : ring_buffer_lock_reserve
              688.00 -  9.1% : __rb_reserve_next
              664.00 -  8.8% : rb_end_commit
              563.00 -  7.4% : ring_buffer_unlock_commit
              508.00 -  6.7% : _spin_unlock_irq
              365.00 -  4.8% : debug_smp_processor_id
              321.00 -  4.2% : trace_clock_local
              303.00 -  4.0% : ring_buffer_producer_thread 	[ring_buffer_benchmark]
              273.00 -  3.6% : native_sched_clock
              122.00 -  1.6% : trace_recursive_unlock
              113.00 -  1.5% : sched_clock
              101.00 -  1.3% : ring_buffer_event_data
               53.00 -  0.7% : tick_nohz_stop_sched_tick

Where trace_clock_local drops from 40% to only taking 4% of the total time.
The trace time also goes from 210ns down to 179ns (31ns).

I talked with Peter Zijlstra about the impact that sched_clock may have
without having interrupts disabled, and he told me that if a timer interrupt
comes in, sched_clock may report a wrong time.

Balancing a seldom incorrect timestamp with a 15% performance boost, I'll
take the performance boost.

Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-11 23:38:33 -05:00
Steven Rostedt 6ca6cca31d tracing: optimize global_trace_clock cachelines
The prev_trace_clock_time is only read or written to when the
trace_clock_lock is taken. For better perfomance, they
should share the same cache line.

Reported-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-09-15 12:24:22 -04:00
Dmitri Vorobiev b8b9426533 tracing: fix four sparse warnings
Impact: cleanup.

This patch fixes the following sparse warnings:

 kernel/trace/trace.c:385:9: warning: symbol 'trace_seq_to_buffer' was
 not declared. Should it be static?

 kernel/trace/trace_clock.c:29:13: warning: symbol 'trace_clock_local'
 was not declared. Should it be static?

 kernel/trace/trace_clock.c:54:13: warning: symbol 'trace_clock' was not
 declared. Should it be static?

 kernel/trace/trace_clock.c:74:13: warning: symbol 'trace_clock_global'
 was not declared. Should it be static?

Signed-off-by: Dmitri Vorobiev <dmitri.vorobiev@movial.com>
LKML-Reference: <1237741871-5827-4-git-send-email-dmitri.vorobiev@movial.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 18:16:54 +01:00
Peter Zijlstra 6cc3c6e12b trace_clock: fix preemption bug
Using the function_graph tracer in recent kernels generates a spew of
preemption BUGs. Fix this by not requiring trace_clock_local() users
to disable preemption themselves.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-10 20:03:01 +01:00
Ingo Molnar 14131f2f98 tracing: implement trace_clock_*() APIs
Impact: implement new tracing timestamp APIs

Add three trace clock variants, with differing scalability/precision
tradeoffs:

 -   local: CPU-local trace clock
 -  medium: scalable global clock with some jitter
 -  global: globally monotonic, serialized clock

Make the ring-buffer use the local trace clock internally.

Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-26 18:44:06 +01:00