All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: acme@kernel.org, jolsa@kernel.org, linux-kernel@vger.kernel.org,
	Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH v3 01/11] perf, tools: Support weak groups
Date: Fri, 1 Sep 2017 18:57:59 +0200	[thread overview]
Message-ID: <20170901165759.GA32113@krava> (raw)
In-Reply-To: <20170831194036.30146-2-andi@firstfloor.org>

On Thu, Aug 31, 2017 at 12:40:26PM -0700, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> Setting up groups can be complicated due to the
> complicated scheduling restrictions of different PMUs.
> User tools usually don't understand all these restrictions.
> Still in many cases it is useful to set up groups and
> they work most of the time. However if the group
> is set up wrong some members will not reported any values
> because they never get scheduled.
> 
> Add a concept of a 'weak group': try to set up a group,
> but if it's not schedulable fallback to not using
> a group. That gives us the best of both worlds:
> groups if they work, but still a usable fallback if they don't.
> 
> In theory it would be possible to have more complex fallback
> strategies (e.g. try to split the group in half), but
> the simple fallback of not using a group seems to work for now.
> 
> So far the weak group is only implemented for perf stat,
> not for record.
> 
> Here's an unschedulable group (on IvyBridge with SMT on)
> 
> % perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1
> 
>         73,806,067      branches
>          4,848,144      branch-misses             #    6.57% of all branches
>         14,754,458      l1d.replacement
>         24,905,558      l2_lines_in.all
>    <not supported>      l2_rqsts.all_code_rd         <------- will never report anything
> 
> With the weak group:
> 
> % perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}:W' -a sleep 1
> 
>        125,366,055      branches                                                      (80.02%)
>          9,208,402      branch-misses             #    7.35% of all branches          (80.01%)
>         24,560,249      l1d.replacement                                               (80.00%)
>         43,174,971      l2_lines_in.all                                               (80.05%)
>         31,891,457      l2_rqsts.all_code_rd                                          (79.92%)
> 
> The extra event scheduled with some extra multiplexing
> 
> v2: Move fallback code to separate function.
> Add comment on for_each_group_member
> Adjust to new perf_evsel__close interface
> v3:
> Fix debug print out.
> Signed-off-by: Andi Kleen <ak@linux.intel.com>

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

  reply	other threads:[~2017-09-01 16:58 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-31 19:40 Support standalone metrics and metric groups for perf Andi Kleen
2017-08-31 19:40 ` [PATCH v3 01/11] perf, tools: Support weak groups Andi Kleen
2017-09-01 16:57   ` Jiri Olsa [this message]
2017-09-01 17:00     ` Jiri Olsa
2017-09-04 16:51       ` Arnaldo Carvalho de Melo
2017-09-22 16:28   ` [tip:perf/core] perf tools: Support weak groups in 'perf stat' tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 02/11] perf, tools: Support metric_group and no event name in json parser Andi Kleen
2017-09-22 16:29   ` [tip:perf/core] perf vendor events: Support metric_group and no event name in JSON parser tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 03/11] perf, tools, stat: Factor out generic metric printing Andi Kleen
2017-09-22 16:29   ` [tip:perf/core] perf " tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 04/11] perf, tools: Print generic metric header even for failed expressions Andi Kleen
2017-09-22 16:30   ` [tip:perf/core] perf stat: " tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 05/11] perf, tools: Extract function to get json alias map Andi Kleen
2017-09-22 16:30   ` [tip:perf/core] perf pmu: Extract function to get JSON " tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 06/11] perf, tools, stat: Support JSON metrics in perf stat Andi Kleen
2017-09-04 17:11   ` Arnaldo Carvalho de Melo
2017-09-04 17:37     ` Andi Kleen
2017-09-05 18:09       ` Arnaldo Carvalho de Melo
2017-09-05 18:16         ` Arnaldo Carvalho de Melo
2017-09-05 18:32           ` Arnaldo Carvalho de Melo
2017-09-05 18:19         ` Andi Kleen
2017-09-05 18:52           ` Arnaldo Carvalho de Melo
2017-09-05 19:52             ` Andi Kleen
2017-09-05 20:07               ` Arnaldo Carvalho de Melo
2017-09-05 20:37                 ` Andi Kleen
2017-09-08 18:10                   ` Arnaldo Carvalho de Melo
2017-09-08 19:08                     ` Andi Kleen
2017-09-11 14:05                       ` Arnaldo Carvalho de Melo
2017-09-22 16:37               ` [tip:perf/core] perf vendor events: Add JSON metrics for Broadwell tip-bot for Andi Kleen
2017-09-22 16:38               ` [tip:perf/core] perf vendor events: Add JSON metrics for Skylake tip-bot for Andi Kleen
2017-09-22 16:38               ` [tip:perf/core] perf vendor events: Add JSON metrics for Sandy Bridge tip-bot for Andi Kleen
2017-09-22 16:31   ` [tip:perf/core] perf stat: Support JSON metrics in perf stat tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 07/11] perf, tools, list: Add metric groups to perf list Andi Kleen
2017-09-22 16:31   ` [tip:perf/core] perf " tip-bot for Andi Kleen
2017-10-13 14:50   ` [PATCH v3 07/11] perf, tools, " Arnaldo Carvalho de Melo
2017-08-31 19:40 ` [PATCH v3 08/11] perf, tools, stat: Don't use ctx for saved values lookup Andi Kleen
2017-09-22 16:31   ` [tip:perf/core] perf " tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 09/11] perf, tools, stat: Support duration_time for metrics Andi Kleen
2017-09-22 16:32   ` [tip:perf/core] perf " tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 10/11] perf, tools, stat: Hide internal duration_time counter Andi Kleen
2017-09-22 16:32   ` [tip:perf/core] perf " tip-bot for Andi Kleen
2017-08-31 19:40 ` [PATCH v3 11/11] perf, tools, stat: Update walltime_nsecs_stats in interval mode Andi Kleen
2017-09-22 16:33   ` [tip:perf/core] perf " tip-bot for Andi Kleen
2017-09-01 17:26 ` Support standalone metrics and metric groups for perf Jiri Olsa
2017-09-01 17:36   ` Jiri Olsa
2017-09-01 17:42   ` Andi Kleen
2017-09-01 17:50     ` Jiri Olsa

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=20170901165759.GA32113@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.