lkml.org 
[lkml]   [2011]   [Mar]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    SubjectRe: [PATCH,RFC] perf: panic due to inclied cpu context task_ctx value
    From
    Date
    On Mon, 2011-03-28 at 17:15 +0200, Oleg Nesterov wrote:
    > On 03/28, Peter Zijlstra wrote:
    > >
    > > --- linux-2.6.orig/kernel/perf_event.c
    > > +++ linux-2.6/kernel/perf_event.c
    > > @@ -1767,7 +1767,6 @@ static void ctx_sched_out(struct perf_ev
    > > struct perf_event *event;
    > >
    > > raw_spin_lock(&ctx->lock);
    > > - perf_pmu_disable(ctx->pmu);
    > > ctx->is_active = 0;
    > > if (likely(!ctx->nr_events))
    > > goto out;
    > > @@ -1777,6 +1776,7 @@ static void ctx_sched_out(struct perf_ev
    > > if (!ctx->nr_active)
    > > goto out;
    > >
    > > + perf_pmu_disable(ctx->pmu);
    > > if (event_type & EVENT_PINNED) {
    > > list_for_each_entry(event, &ctx->pinned_groups, group_entry)
    > > group_sched_out(event, cpuctx, ctx);
    > > @@ -1786,8 +1786,8 @@ static void ctx_sched_out(struct perf_ev
    > > list_for_each_entry(event, &ctx->flexible_groups, group_entry)
    > > group_sched_out(event, cpuctx, ctx);
    > > }
    > > -out:
    > > perf_pmu_enable(ctx->pmu);
    > > +out:
    > > raw_spin_unlock(&ctx->lock);
    >
    > Yes, thanks.
    >
    > Probably this doesn't matter from the perfomance pov, but imho this
    > makes the code more understandable. This is important for occasional
    > readers like me ;)

    Could actually save quite a lot of cycles, pmu-disable/enable can be
    very expensive on some hardware.

    > Could you answer another question? It is not immediately clear why
    > ctx_sched_in() does not check nr_active != 0 before doing
    > ctx_XXX_sched_in(). I guess, the only reason is perf_rotate_context()
    > and the similar logic in perf_event_context_sched_in(). If we are
    > doing, say, cpu_ctx_sched_out(FLEXIBLE) + cpu_ctx_sched_in(FLEXIBLE)
    > then ->nr_active can be zero after cpu_ctx_sched_out().
    >
    > Is my understanding correct? Or is there another reason?

    nr_active counts the number of events that have been scheduled in, so
    its perfectly fine to have either nr_active or !nr_active at that
    point.


    \
     
     \ /
      Last update: 2011-03-28 18:31    [W:0.026 / U:1.864 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site