New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 696024 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 696857
Owner: ----
Closed: Mar 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

6.1% regression in media.tough_video_cases at 451238:451280

Project Member Reported by hubbe@google.com, Feb 24 2017

Issue description

See the link to graphs below.
 

Comment 1 by hubbe@google.com, Feb 24 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=696024

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgxNiVtgsM


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

chromium-rel-mac11
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Feb 24 2017


=== BISECT JOB RESULTS ===
NO Perf regression found, tests failed to produce values

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : gpu_average_frequency_hz/video.html?src_smpte_3840x2160_60fps_vp9.webm

Revision             Result                     N
chromium@451237      475085714 +- 41541797      21      good

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=video.html.src.smpte.3840x2160.60fps.vp9.webm media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8986741967573920096

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4628577011630080


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!
 Issue 696023  has been merged into this issue.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Mar 23 2017

Mergedinto: 696857
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : ccameron
  Commit : 3b6fe6da979b8d9e084160ce6d8b7bd83f3aa878
  Date   : Fri Feb 17 06:21:58 2017
  Subject: color: Don't use QCMS for transforms unless necessary

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : gpu_average_frequency_hz/video.html?src_smpte_3840x2160_60fps_vp9.webm
  Change       : 5.00% | 469185333.333 -> 492668000.0

Revision             Result                     N
chromium@451237      469185333 +- 14063400      6      good
chromium@451243      476010778 +- 22430213      9      good
chromium@451244      488066556 +- 22252182      9      bad       <--
chromium@451245      489436333 +- 13206790      6      bad
chromium@451246      493563000 +- 19555767      6      bad
chromium@451248      492850667 +- 15297354      6      bad
chromium@451259      491880333 +- 8499555       6      bad
chromium@451280      492668000 +- 20275875      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=video.html.src.smpte.3840x2160.60fps.vp9.webm media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8984378711861512704

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4628577011630080


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

Sign in to add a comment