linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: jolsa@kernel.org, acme@kernel.org, linux-kernel@vger.kernel.org,
	Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH v5 07/13] perf stat: Use affinity for closing file descriptors
Date: Mon, 11 Nov 2019 14:30:52 +0100	[thread overview]
Message-ID: <20191111133052.GE12923@krava> (raw)
In-Reply-To: <20191107181646.506734-8-andi@firstfloor.org>

On Thu, Nov 07, 2019 at 10:16:40AM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Closing a perf fd can also trigger an IPI to the target CPU.
> Use the same affinity technique as we use for reading/enabling events
> to closing to optimize the CPU transitions.
> 
> Before on a large test case with 94 CPUs:
> 
> % time     seconds  usecs/call     calls    errors syscall
> ------ ----------- ----------- --------- --------- ----------------
>  32.56    3.085463          50     61483           close
> 
> After:
> 
>  10.54    0.735704          11     61485           close
> 
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
> 
> ---
> 
> v2: Use new iterator macros
> v3: Use new iterator macros
> Add missing affinity__cleanup
> v4:
> Update iterators again
> ---
>  tools/perf/util/evlist.c | 27 +++++++++++++++++++++++++--
>  1 file changed, 25 insertions(+), 2 deletions(-)
> 
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index dae6e846b2f8..0dcea66329e2 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -18,6 +18,7 @@
>  #include "debug.h"
>  #include "units.h"
>  #include <internal/lib.h> // page_size
> +#include "affinity.h"
>  #include "../perf.h"
>  #include "asm/bug.h"
>  #include "bpf-event.h"
> @@ -1169,9 +1170,31 @@ void perf_evlist__set_selected(struct evlist *evlist,
>  void evlist__close(struct evlist *evlist)
>  {
>  	struct evsel *evsel;
> +	struct affinity affinity;
> +	int cpu, i;
>  
> -	evlist__for_each_entry_reverse(evlist, evsel)
> -		evsel__close(evsel);
> +	if (!evlist->core.cpus) {

should this be evlist->all_cpus?

jirka

> +		evlist__for_each_entry_reverse(evlist, evsel)
> +			evsel__close(evsel);
> +		return;
> +	}
> +
> +	if (affinity__setup(&affinity) < 0)
> +		return;
> +	evlist__for_each_cpu (evlist, i, cpu) {
> +		affinity__set(&affinity, cpu);
> +
> +		evlist__for_each_entry_reverse(evlist, evsel) {
> +			if (evsel__cpu_iter_skip(evsel, cpu))
> +			    continue;
> +			perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1);
> +		}
> +	}
> +	affinity__cleanup(&affinity);
> +	evlist__for_each_entry_reverse(evlist, evsel) {
> +		perf_evsel__free_fd(&evsel->core);
> +		perf_evsel__free_id(&evsel->core);
> +	}
>  }
>  
>  static int perf_evlist__create_syswide_maps(struct evlist *evlist)
> -- 
> 2.23.0
> 


  reply	other threads:[~2019-11-11 13:31 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-07 18:16 Optimize perf stat for large number of events/cpus Andi Kleen
2019-11-07 18:16 ` [PATCH v5 01/13] perf pmu: Use file system cache to optimize sysfs access Andi Kleen
2019-11-07 18:16 ` [PATCH v5 02/13] perf affinity: Add infrastructure to save/restore affinity Andi Kleen
2019-11-07 18:16 ` [PATCH v5 03/13] perf cpumap: Maintain cpumaps ordered and without dups Andi Kleen
2019-11-07 18:16 ` [PATCH v5 04/13] perf evlist: Maintain evlist->all_cpus Andi Kleen
2019-11-11 13:31   ` Jiri Olsa
2019-11-07 18:16 ` [PATCH v5 05/13] perf evsel: Add iterator to iterate over events ordered by CPU Andi Kleen
2019-11-07 18:16 ` [PATCH v5 06/13] perf evsel: Add functions to close evsel on a CPU Andi Kleen
2019-11-07 18:16 ` [PATCH v5 07/13] perf stat: Use affinity for closing file descriptors Andi Kleen
2019-11-11 13:30   ` Jiri Olsa [this message]
2019-11-11 16:56     ` Andi Kleen
2019-11-07 18:16 ` [PATCH v5 08/13] perf stat: Factor out open error handling Andi Kleen
2019-11-07 18:16 ` [PATCH v5 09/13] perf evsel: Support opening on a specific CPU Andi Kleen
2019-11-11 13:30   ` Jiri Olsa
2019-11-12  0:41     ` Andi Kleen
2019-11-07 18:16 ` [PATCH v5 10/13] perf stat: Use affinity for opening events Andi Kleen
2019-11-11 13:30   ` Jiri Olsa
2019-11-11 13:30   ` Jiri Olsa
2019-11-11 13:31   ` Jiri Olsa
2019-11-11 17:02     ` Andi Kleen
2019-11-07 18:16 ` [PATCH v5 11/13] perf stat: Use affinity for reading Andi Kleen
2019-11-11 13:31   ` Jiri Olsa
2019-11-07 18:16 ` [PATCH v5 12/13] perf evsel: Add functions to enable/disable for a specific CPU Andi Kleen
2019-11-11 13:30   ` Jiri Olsa
2019-11-07 18:16 ` [PATCH v5 13/13] perf stat: Use affinity for enabling/disabling events Andi Kleen
2019-11-11 14:04   ` Jiri Olsa
2019-11-11 16:50     ` Andi Kleen
2019-11-11 20:06       ` Jiri Olsa
2019-11-11 23:31         ` Andi Kleen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20191111133052.GE12923@krava \
    --to=jolsa@redhat.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=andi@firstfloor.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).