Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1703185

Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped events on mux interrupt

From Peter Zijlstra <peterz@infradead.org>
Newsgroups linux.kernel
Subject Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped events on mux interrupt
Date 2017-08-03 17:10 +0200
Message-ID <uapVc-1If-91@gated-at.bofh.it> (permalink)
References <u9X2N-7mD-15@gated-at.bofh.it> <u9X2O-7mD-25@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

On Wed, Aug 02, 2017 at 11:15:39AM +0300, Alexey Budankov wrote:
> @@ -772,6 +780,10 @@ struct perf_event_context {
>  	 */
>  	u64				time;
>  	u64				timestamp;
> +	/*
> +	 * Context cache for filtered out events;
> +	 */
> +	struct perf_event_tstamp	tstamp_data;
>  
>  	/*
>  	 * These fields let us detect when two contexts have both


> @@ -1379,6 +1379,9 @@ static void update_context_time(struct perf_event_context *ctx)
>  
>  	ctx->time += now - ctx->timestamp;
>  	ctx->timestamp = now;
> +
> +	ctx->tstamp_data.running += ctx->time - ctx->tstamp_data.stopped;
> +	ctx->tstamp_data.stopped = ctx->time;
>  }
>  
>  static u64 perf_event_time(struct perf_event *event)

It appears to me we have some redundancy here.


> @@ -1968,9 +1971,13 @@ event_sched_out(struct perf_event *event,
>  	 */
>  	if (event->state == PERF_EVENT_STATE_INACTIVE &&
>  	    !event_filter_match(event)) {
> +		delta = tstamp - event->tstamp->stopped;
> +		event->tstamp->running += delta;
> +		event->tstamp->stopped = tstamp;
> +		if (event->tstamp != &event->tstamp_data) {
> +			event->tstamp_data = *event->tstamp;

This,

> +			event->tstamp = &event->tstamp_data;
> +		}
>  	}
>  
>  	if (event->state != PERF_EVENT_STATE_ACTIVE)


> @@ -3239,8 +3246,11 @@ ctx_pinned_sched_in(struct perf_event *event, void *data)
>  
>  	if (event->state <= PERF_EVENT_STATE_OFF)
>  		return 0;
> -	if (!event_filter_match(event))
> +	if (!event_filter_match(event)) {
> +		if (event->tstamp != &params->ctx->tstamp_data)
> +			event->tstamp = &params->ctx->tstamp_data;

this and

>  		return 0;
> +	}
>  
>  	/* may need to reset tstamp_enabled */
>  	if (is_cgroup_event(event))
> @@ -3273,8 +3283,11 @@ ctx_flexible_sched_in(struct perf_event *event, void *data)
>  	 * Listen to the 'cpu' scheduling filter constraint
>  	 * of events:
>  	 */
> -	if (!event_filter_match(event))
> +	if (!event_filter_match(event)) {
> +		if (event->tstamp != &params->ctx->tstamp_data)
> +			event->tstamp = &params->ctx->tstamp_data;

this..

>  		return 0;
> +	}
>  
>  	/* may need to reset tstamp_enabled */
>  	if (is_cgroup_event(event))


Are the magic spots, right? And I'm not convinced its right.

Suppose I have two events in my context, and I created them 1 minute
apart. Then their respective tstamp_enabled are 1 minute apart as well.
But the above doesn't seem to preserve that difference.

A similar argument can be made for running I think. That is a per event
value and cannot be passed along to the ctx and back.

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v6 0/3] perf/core: addressing 4x slowdown during per-process  profiling of STREAM benchmark on Intel Xeon Phi Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-02 10:20 +0200
  [PATCH v6 3/3]: perf/core: add mux switch to skip to the current  CPU's events list on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-02 10:20 +0200
  [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped events  on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-02 10:20 +0200
    Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Peter Zijlstra <peterz@infradead.org> - 2017-08-03 15:10 +0200
    Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Peter Zijlstra <peterz@infradead.org> - 2017-08-03 16:10 +0200
      Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-03 18:00 +0200
        Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Peter Zijlstra <peterz@infradead.org> - 2017-08-04 14:40 +0200
    Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Peter Zijlstra <peterz@infradead.org> - 2017-08-03 17:10 +0200
      Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-03 20:50 +0200
        Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Peter Zijlstra <peterz@infradead.org> - 2017-08-04 14:40 +0200
          Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Peter Zijlstra <peterz@infradead.org> - 2017-08-04 15:00 +0200
            Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-04 16:30 +0200
          Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-04 16:30 +0200
      Re: [PATCH v6 2/3]: perf/core: use context tstamp_data for skipped  events on mux interrupt Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-10 18:00 +0200
  [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-02 10:20 +0200
    Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-03 15:10 +0200
      Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-03 22:40 +0200
        Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-04 16:40 +0200
          Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-07 09:20 +0200
            Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-07 10:40 +0200
              Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-07 11:20 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-07 17:40 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-07 18:00 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-07 18:30 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-07 19:00 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Andi Kleen <ak@linux.intel.com> - 2017-08-07 19:50 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-07 20:20 +0200
                Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-07 20:20 +0200
        Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Peter Zijlstra <peterz@infradead.org> - 2017-08-04 17:00 +0200
          Re: [PATCH v6 1/3] perf/core: use rb trees for pinned/flexible groups Alexey Budankov <alexey.budankov@linux.intel.com> - 2017-08-07 17:30 +0200

csiph-web