New issue
Advanced search Search tips

Issue 763486 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 760566
Owner:
Closed: Oct 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

12.9% regression in media_perftests at 497845:497974

Project Member Reported by xhwang@google.com, Sep 8 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=763486

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=0cafde9eb172f49c7ac1b2c84cac9bcace124d7264b0de3e60ff2cc779d42f98


Bot(s) for this bug's original alert(s):

chromium-rel-mac11
Cc: crouleau@chromium.org wolenetz@chromium.org
Cc: -crouleau@chromium.org

=== BISECT JOB RESULTS ===
Bisect failed unexpectedly

Bisect was aborted with the following:
  Step('Check bisect finished on revision chromium@497943.fetch file 61706d49766e410bbb38cbea23f7cb15c1fa5080:DEPS') failed with return_code 1


Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media_perftests
  Metric       : clockless_playback/sfx_u8.wav

Revision             Result                  N
chromium@497844      12255.0 +- 1294.26      14      good
chromium@497909      11803.1 +- 1891.45      14      good
chromium@497942      11907.5 +- 1357.26      14      good
chromium@497943      11935.8 +- 839.882      9       good
chromium@497944      11119.0 +- 969.584      6       bad
chromium@497946      11339.9 +- 903.409      9       bad
chromium@497950      11339.9 +- 2015.79      21      bad
chromium@497958      11459.6 +- 1651.24      21      bad
chromium@497974      11274.5 +- 1228.64      14      bad

To Run This Test
  ./src/out/Release/media_perftests --single-process-tests

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8968992429175179184


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Sep 11 2017


=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media_perftests
  Metric       : clockless_playback/sfx_u8.wav
  Change       : 8.82% | 12512.9311141 -> 11409.492585

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/a6a7bd1aef62fe9634cc8db8d4fc89939eb6bbd0..7df4c7e49b7a6d2ae51a2dabd7bc59f1a06588fe


Revision             Result                  N
chromium@497844      12512.9 +- 871.926      6        good
chromium@497909      12419.3 +- 1807.27      9        good
chromium@497942      12707.2 +- 1608.35      9        good
chromium@497944      11811.7 +- 1765.1       14       good
chromium@497945      ---                     ---      build failure
chromium@497946      11429.9 +- 1964.77      14       bad
chromium@497950      11634.1 +- 1786.49      9        bad
chromium@497958      11714.7 +- 1300.01      9        bad
chromium@497974      11409.5 +- 909.875      6        bad

To Run This Test
  ./src/out/Release/media_perftests --single-process-tests

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8968716938960511264


For feedback, file a bug with component Speed>Bisection
Owner: xhw...@chromium.org
Status: Assigned (was: Untriaged)
Cc: rsesek@chromium.org
Owner: rsesek@chromium.org

=== Auto-CCing suspected CL author rsesek@chromium.org ===

Hi rsesek@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Robert Sesek
  Commit : 5cd8eef498e28e1aacb9109645c001bbbfe1bc26
  Date   : Mon Aug 28 19:51:25 2017
  Subject: [Mac] A potential fix for WaitableEvent::WaitMany on macOS 10.11.

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media_perftests
  Metric       : clockless_playback/sfx_u8.wav
  Change       : 6.37% | 11902.5783854 -> 11111.4992681

Revision             Result                  N
chromium@497844      11902.6 +- 1200.0       14      good
chromium@497849      11890.0 +- 1026.97      9       good
chromium@497850      11356.6 +- 1119.05      14      bad       <--
chromium@497851      11157.1 +- 1208.86      9       bad
chromium@497853      10917.7 +- 662.239      6       bad
chromium@497861      10932.9 +- 503.639      6       bad
chromium@497877      11537.0 +- 1735.42      21      bad
chromium@497909      11375.5 +- 1796.15      14      bad
chromium@497974      11111.5 +- 701.963      9       bad

To Run This Test
  ./src/out/Release/media_perftests --single-process-tests

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8966419628721768496


For feedback, file a bug with component Speed>Bisection
Mergedinto: 760566
Status: Duplicate (was: Assigned)

Sign in to add a comment