New issue
Advanced search Search tips

Issue 789713 link

Starred by 1 user
Status: Duplicate
Merged: issue 790001
Owner: ----
Closed: Nov 2017
Cc:
wolenetz@chromium.org
crouleau@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

5.5% regression in media.desktop at 518287:518407

Project Member Reported by wolenetz@chromium.org, Nov 29 2017 
Though this alert is invalid, on the right edge of the graph there looks to be a possible 0.5 watt divergence from ref trace. I'll kick a bisect for that later revision range and tie it to this bug.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Nov 29 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=789713

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=9c01475cdfa701c186dc7b4a1b051caf7a1981919c3443101d8361e2ace7a78d


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

win-high-dpi

Comment 4 by wolenetz@chromium.org, Nov 29 2017

Cc: crouleau@chromium.org
The bisect in #3 is for what I suspect might be a real regression.
Also, thanks to crouleau@ for highlighting that there might be a real regression shown in this graph.
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Nov 29 2017 


=== BISECT JOB RESULTS ===
Bisect failed for unknown reasons

Please contact the team (see below) and report the error.


Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : media.desktop
  Metric       : story:power_avg/video.html?src_garden2_10s.webm


To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=video.html.src.garden2.10s.webm media.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8961553406078062656


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

Comment 6 by 42576172...@developer.gserviceaccount.com, Nov 29 2017 


=== BISECT JOB RESULTS ===
Bisect failed for unknown reasons

Please contact the team (see below) and report the error.


Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : media.desktop
  Metric       : story:power_avg/video.html?src_garden2_10s.webm


To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=video.html.src.garden2.10s.webm media.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8961553314507383024


For feedback, file a bug with component Speed>Bisection

Comment 8 by wolenetz@chromium.org, Nov 30 2017 

 Bug 789759  is the Speed>Bisection bug I filed following #5-6. Hopefully #7 will succeed...
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Nov 30 2017

Mergedinto: 790001
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : liberato@chromium.org
  Commit : 53479ca91ac63d89a22c06db86a4292edcb2fa65
  Date   : Tue Nov 28 19:19:33 2017
  Subject: Avoid saturation when computing LayoutSize aspect ratio.

Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : media.desktop
  Metric       : story:power_avg/video.html?src_garden2_10s.webm
  Change       : 6.04% | 12.3282383332 -> 13.0729730157

Revision             Result                    N
chromium@519746      12.3282 +- 0.0928921      5      good
chromium@519777      12.2748 +- 0.2285         9      good
chromium@519781      12.5083 +- 1.30801        9      good
chromium@519783      12.3617 +- 0.221305       6      good
chromium@519784      13.206 +- 0.614693        6      bad       <--
chromium@519785      13.1089 +- 0.236674       9      bad
chromium@519793      13.1339 +- 0.0767784      6      bad
chromium@519808      13.0969 +- 0.158865       6      bad
chromium@519870      13.073 +- 0.137687        6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=video.html.src.garden2.10s.webm media.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8961481775140099504


For feedback, file a bug with component Speed>Bisection
►

Sign in to add a comment