New issue
Advanced search Search tips

Issue 710148 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 710143
Owner:
Closed: Apr 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

23.7%-37.2% regression in media.tough_video_cases at 460219:460348

Project Member Reported by wolenetz@chromium.org, Apr 10 2017

Issue description

These seem to be valid alerts.
 
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Apr 10 2017


=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : time_to_play/video.html?src_tulip2.webm

Revision             Result                  N
chromium@460283      75.5202 +- 59.9618      21      good
chromium@460348      74.139 +- 63.0427       21      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.tulip2.webm media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982669670586784736

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5892303744401408


| 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!
Hmm. Alert graphs showed a clear uptick. I'm unsure why the bisect failed on the outer range. Any ideas, crouleau@?
I'm trying a wider bisect range on one of the clearer uptick alerts just in case.
Project Member

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

Mergedinto: 710143
Status: Duplicate (was: Assigned)

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

Suspected Commit
  Author : dalecurtis
  Commit : 5285d00f561827da882c8faaa7bda1d571c4fc60
  Date   : Wed Mar 29 00:27:30 2017
  Subject: Use AudioUnit instead of AudioDevice properties to get channel count.

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : time_to_play/tulip2.webm
  Change       : 29.60% | 54.2841666667 -> 70.35

Revision             Result                  N
chromium@460014      54.2842 +- 3.00213      6      good
chromium@460211      54.5928 +- 2.23964      9      good
chromium@460236      116.589 +- 526.048      9      good
chromium@460249      53.9775 +- 2.19018      6      good
chromium@460250      66.8533 +- 11.9378      6      bad       <--
chromium@460251      71.1892 +- 13.2961      6      bad
chromium@460252      67.2892 +- 10.4427      6      bad
chromium@460255      69.115 +- 13.0354       6      bad
chromium@460261      64.9917 +- 9.92597      9      bad
chromium@460310      68.0992 +- 12.4003      6      bad
chromium@460408      68.31 +- 11.7293        6      bad
chromium@460802      70.35 +- 12.8409        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 media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982661504240696096

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5802484716535808


| 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