public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Andi Kleen <ak@linux.intel.com>, David Ahern <dsahern@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Stephane Eranian <eranian@google.com>
Subject: [PATCHv2 00/30] perf stat: Introduce --per-task option
Date: Sun, 14 Jun 2015 10:19:15 +0200	[thread overview]
Message-ID: <1434269985-521-1-git-send-email-jolsa@kernel.org> (raw)

hi,
adding the possibility to display stat data per thread.

Allowing following commands and output:

  $ perf stat  -e cycles,instructions --per-task -p 25388,25442 -a
  ^C
   Performance counter stats for process id '25388,25442':

  cat-25388               100,122      cycles
  vim-25442             4,167,876      cycles
  cat-25388                20,080      instructions
  vim-25442             3,232,735      instructions

         6.057130572 seconds time elapsed


Also works under interval mode:

  $ perf stat  -e cycles,instructions --per-task -p 25388,25442 -a -I 1000
  #           time task                      counts unit events
       1.000190002 cat-25388                54,196      cycles
       1.000190002 vim-25442                     0      cycles
       1.000190002 cat-25388                11,660      instructions
       1.000190002 vim-25442                     0      instructions
       2.000742579 cat-25388                55,247      cycles
       2.000742579 vim-25442             1,752,951      cycles
       2.000742579 cat-25388                11,872      instructions
       2.000742579 vim-25442             1,238,512      instructions
       3.001057871 cat-25388                     0      cycles
       3.001057871 vim-25442                     0      cycles
       3.001057871 cat-25388                     0      instructions
       3.001057871 vim-25442                     0      instructions
  ^C     3.242519732 cat-25388                     0      cycles
       3.242519732 vim-25442                     0      cycles
       3.242519732 cat-25388                     0      instructions
       3.242519732 vim-25442                     0      instructions


v2 changes:
  - renamed xyarray__zero to xyarray__reset
  - using atomic_t for cpu_map/thread_map refcnt
  - moving all stat functions into stat object
  - using init_stats to initialize 'struct stats*'
  - change TASK-$pid output into $comm-$pid
  - updated doc with --per-task option

thanks for comments,
jirka


---
Jiri Olsa (30):
      perf tools: Introduce xyarray__reset function
      perf tools: Add thread_map__(alloc|realloc) helpers
      perf tools: Change thread_map::map into struct
      perf tools: Add comm string into struct thread_map
      perf tests: Add thread_map object tests
      perf tools: Add reference counting for cpu_map object
      perf tools: Add reference counting for thread_map object
      perf tools: Propagate cpu maps through the evlist
      perf tools: Propagate thread maps through the evlist
      perf tools: Make perf_evsel__(nr_)cpus generic
      perf tools: Move perf_evsel__(alloc|free|reset)_counts into stat object
      perf stat: Introduce perf_counts__(alloc|free|reset) functions
      perf stat: Introduce perf_counts function
      perf stat: Use xyarray for cpu evsel counts
      perf stat: Make stats work over the thread dimension
      perf stat: Rename struct perf_counts::cpu member to values
      perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object
      perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts into stat object
      perf stat: Move perf_evlist__(alloc|free)_stats into evlist object
      perf stat: Introduce perf_evsel__alloc_stats function
      perf stat: Introduce perf_evsel__read function
      perf stat: Introduce read_counters function
      perf stat: Separate counters reading and processing
      perf stat: Move zero_per_pkg into counter process code
      perf stat: Move perf_stat initialization counter process code
      perf stat: Remove perf_evsel__read_cb function
      perf stat: Rename print_interval to process_interval
      perf stat: Using init_stats instead of memset
      perf stat: Introduce print_counters function
      perf stat: Introduce --per-task option

 tools/perf/Documentation/perf-stat.txt      |   3 +
 tools/perf/builtin-stat.c                   | 398 ++++++++++++++--------------
 tools/perf/builtin-trace.c                  |   4 +-
 tools/perf/tests/Build                      |   1 +
 tools/perf/tests/builtin-test.c             |   4 +
 tools/perf/tests/code-reading.c             |   4 +-
 tools/perf/tests/keep-tracking.c            |   4 +-
 tools/perf/tests/mmap-basic.c               |   4 +-
 tools/perf/tests/mmap-thread-lookup.c       |   2 +-
 tools/perf/tests/openat-syscall-all-cpus.c  |   9 +-
 tools/perf/tests/openat-syscall-tp-fields.c |   2 +-
 tools/perf/tests/openat-syscall.c           |   6 +-
 tools/perf/tests/switch-tracking.c          |   4 +-
 tools/perf/tests/tests.h                    |   1 +
 tools/perf/tests/thread-map.c               |  28 ++
 tools/perf/util/auxtrace.c                  |   4 +-
 tools/perf/util/cpumap.c                    |  25 +-
 tools/perf/util/cpumap.h                    |   6 +-
 tools/perf/util/event.c                     |   6 +-
 tools/perf/util/evlist.c                    |  38 ++-
 tools/perf/util/evlist.h                    |   1 -
 tools/perf/util/evsel.c                     |  47 ++--
 tools/perf/util/evsel.h                     |  43 ++-
 tools/perf/util/parse-events.c              |   5 +-
 tools/perf/util/python-ext-sources          |   2 +
 tools/perf/util/python.c                    |   4 +-
 tools/perf/util/record.c                    |   4 +-
 tools/perf/util/session.c                   |   2 +-
 tools/perf/util/stat.c                      | 134 ++++++++++
 tools/perf/util/stat.h                      |  46 ++++
 tools/perf/util/svghelper.c                 |   2 +-
 tools/perf/util/thread_map.c                | 131 +++++++--
 tools/perf/util/thread_map.h                |  17 +-
 tools/perf/util/xyarray.c                   |   8 +
 tools/perf/util/xyarray.h                   |   2 +
 35 files changed, 672 insertions(+), 329 deletions(-)
 create mode 100644 tools/perf/tests/thread-map.c

             reply	other threads:[~2015-06-14  8:19 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-14  8:19 Jiri Olsa [this message]
2015-06-14  8:19 ` [PATCH 01/30] perf tools: Introduce xyarray__reset function Jiri Olsa
2015-06-18  8:13   ` [tip:perf/core] " tip-bot for Jiri Olsa
2015-06-14  8:19 ` [PATCH 02/30] perf tools: Add thread_map__(alloc|realloc) helpers Jiri Olsa
2015-06-18  8:14   ` [tip:perf/core] " tip-bot for Jiri Olsa
2015-06-14  8:19 ` [PATCH 03/30] perf tools: Change thread_map::map into struct Jiri Olsa
2015-06-15 19:04   ` Arnaldo Carvalho de Melo
2015-06-15 21:33     ` Jiri Olsa
2015-06-14  8:19 ` [PATCH 04/30] perf tools: Add comm string into struct thread_map Jiri Olsa
2015-06-15 19:17   ` Arnaldo Carvalho de Melo
2015-06-15 21:55     ` Jiri Olsa
2015-06-14  8:19 ` [PATCH 05/30] perf tests: Add thread_map object tests Jiri Olsa
2015-06-14  8:19 ` [PATCH 06/30] perf tools: Add reference counting for cpu_map object Jiri Olsa
2015-06-14  8:19 ` [PATCH 07/30] perf tools: Add reference counting for thread_map object Jiri Olsa
2015-06-15 19:25   ` Arnaldo Carvalho de Melo
2015-06-15 21:28     ` Jiri Olsa
2015-06-14  8:19 ` [PATCH 08/30] perf tools: Propagate cpu maps through the evlist Jiri Olsa
2015-06-15 19:34   ` Arnaldo Carvalho de Melo
2015-06-15 21:29     ` Jiri Olsa
2015-06-14  8:19 ` [PATCH 09/30] perf tools: Propagate thread " Jiri Olsa
2015-06-14  8:19 ` [PATCH 10/30] perf tools: Make perf_evsel__(nr_)cpus generic Jiri Olsa
2015-06-14  8:19 ` [PATCH 11/30] perf tools: Move perf_evsel__(alloc|free|reset)_counts into stat object Jiri Olsa
2015-06-15 20:13   ` Arnaldo Carvalho de Melo
2015-06-18  8:14   ` [tip:perf/core] perf tools: Move perf_evsel__(alloc|free|reset) _counts " tip-bot for Jiri Olsa
2015-06-14  8:19 ` [PATCH 12/30] perf stat: Introduce perf_counts__(alloc|free|reset) functions Jiri Olsa
2015-06-15 20:16   ` Arnaldo Carvalho de Melo
2015-06-18  8:14   ` [tip:perf/core] perf stat: Introduce perf_counts__( new|delete|reset) functions tip-bot for Jiri Olsa
2015-06-14  8:19 ` [PATCH 13/30] perf stat: Introduce perf_counts function Jiri Olsa
2015-06-14  8:19 ` [PATCH 14/30] perf stat: Use xyarray for cpu evsel counts Jiri Olsa
2015-06-14  8:19 ` [PATCH 15/30] perf stat: Make stats work over the thread dimension Jiri Olsa
2015-06-14  8:19 ` [PATCH 16/30] perf stat: Rename struct perf_counts::cpu member to values Jiri Olsa
2015-06-14  8:19 ` [PATCH 17/30] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object Jiri Olsa
2015-06-14  8:19 ` [PATCH 18/30] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts " Jiri Olsa
2015-06-14  8:19 ` [PATCH 19/30] perf stat: Move perf_evlist__(alloc|free)_stats into evlist object Jiri Olsa
2015-06-14  8:19 ` [PATCH 20/30] perf stat: Introduce perf_evsel__alloc_stats function Jiri Olsa
2015-06-14  8:19 ` [PATCH 21/30] perf stat: Introduce perf_evsel__read function Jiri Olsa
2015-06-14  8:19 ` [PATCH 22/30] perf stat: Introduce read_counters function Jiri Olsa
2015-06-14  8:19 ` [PATCH 23/30] perf stat: Separate counters reading and processing Jiri Olsa
2015-06-14  8:19 ` [PATCH 24/30] perf stat: Move zero_per_pkg into counter process code Jiri Olsa
2015-06-14  8:19 ` [PATCH 25/30] perf stat: Move perf_stat initialization " Jiri Olsa
2015-06-14  8:19 ` [PATCH 26/30] perf stat: Remove perf_evsel__read_cb function Jiri Olsa
2015-06-14  8:19 ` [PATCH 27/30] perf stat: Rename print_interval to process_interval Jiri Olsa
2015-06-14  8:19 ` [PATCH 28/30] perf stat: Using init_stats instead of memset Jiri Olsa
2015-06-14  8:19 ` [PATCH 29/30] perf stat: Introduce print_counters function Jiri Olsa
2015-06-14  8:19 ` [PATCH 30/30] perf stat: Introduce --per-task option 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=1434269985-521-1-git-send-email-jolsa@kernel.org \
    --to=jolsa@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@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