perf_counter: minimize context time updates

Push the update_context_time() calls up the stack so that we get less
invokations and thereby a less noisy output:

before:

 # ./perfstat -e 1:0 -e 1:1 -e 1:1 -e 1:1 -l ls > /dev/null

 Performance counter stats for 'ls':

      10.163691  cpu clock ticks      (msecs)  (scaled from 98.94%)
      10.215360  task clock ticks     (msecs)  (scaled from 98.18%)
      10.185549  task clock ticks     (msecs)  (scaled from 98.53%)
      10.183581  task clock ticks     (msecs)  (scaled from 98.71%)

 Wall-clock time elapsed:    11.912858 msecs

after:

 # ./perfstat -e 1:0 -e 1:1 -e 1:1 -e 1:1 -l ls > /dev/null

 Performance counter stats for 'ls':

       9.316630  cpu clock ticks      (msecs)
       9.280789  task clock ticks     (msecs)
       9.280789  task clock ticks     (msecs)
       9.280789  task clock ticks     (msecs)

 Wall-clock time elapsed:     9.574872 msecs

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090406094518.618876874@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index f4f7596f78414944bd2ea0676a09a8ac4041e6fd..863703b3158f8682bafdfe2d4618c4310cb63b4d 100644 (file)
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -319,6 +319,8 @@ static void __perf_counter_disable(void *info)
 
        spin_lock_irqsave(&ctx->lock, flags);
 
+       update_context_time(ctx);
+
        /*
         * If the counter is on, turn it off.
         * If it is in error state, leave it in error state.
@@ -797,6 +799,8 @@ void perf_counter_task_sched_out(struct task_struct *task, int cpu)
        if (likely(!cpuctx->task_ctx))
                return;
 
+       update_context_time(ctx);
+
        regs = task_pt_regs(task);
        perf_swcounter_event(PERF_COUNT_CONTEXT_SWITCHES, 1, 1, regs);
        __perf_counter_sched_out(ctx, cpuctx);
@@ -2336,7 +2340,6 @@ static void task_clock_perf_counter_update(struct perf_counter *counter)
        u64 prev, now;
        s64 delta;
 
-       update_context_time(counter->ctx);
        now = counter->ctx->time;
 
        prev = atomic64_xchg(&counter->hw.prev_count, now);
@@ -2349,7 +2352,6 @@ static int task_clock_perf_counter_enable(struct perf_counter *counter)
        struct hw_perf_counter *hwc = &counter->hw;
        u64 now;
 
-       update_context_time(counter->ctx);
        now = counter->ctx->time;
 
        atomic64_set(&hwc->prev_count, now);
@@ -2372,6 +2374,7 @@ static void task_clock_perf_counter_disable(struct perf_counter *counter)
 
 static void task_clock_perf_counter_read(struct perf_counter *counter)
 {
+       update_context_time(counter->ctx);
        task_clock_perf_counter_update(counter);
 }