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

Issue 777794 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 776765
Owner: ----
Closed: Oct 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

[likely a revert] 10% regression in smoothness.tough_canvas_cases at 509840:509938

Project Member Reported by kraynov@chromium.org, Oct 24 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Oct 24 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=777794

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=bfdb79eec0eb7bf5c0859d20eab1301a397fce95f1cc1845452c12638fbff786


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

win-high-dpi
Project Member

Comment 4 by 42576172...@developer.gserviceaccount.com, Oct 24 2017

Mergedinto: 776765
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Brian Salomon
  Commit : 43f8bf0f784f4182ed0fca9053ecf570caf7ad70
  Date   : Wed Oct 18 12:55:06 2017
  Subject: Move clear-as-draw workaround to GrGLGpu and expose via GrContextOptions.

Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : smoothness.tough_canvas_cases
  Metric       : frame_times/tough_canvas_cases_canvas2d_balls_common_bouncing_balls.html?ball_image_with_shadow_back_image
  Change       : 13.11% | 166.753583333 -> 188.616666336

Revision                             Result                  N
chromium@509839                      166.754 +- 4.648        6      good
chromium@509889                      167.985 +- 3.99028      6      good
chromium@509890                      170.149 +- 3.37427      6      good
chromium@509890,skia@57caa660c0      169.601 +- 3.19725      6      good
chromium@509890,skia@43f8bf0f78      185.374 +- 5.01606      6      bad       <--
chromium@509890,skia@43938b8533      183.795 +- 4.32468      6      bad
chromium@509891                      188.599 +- 14.9755      6      bad
chromium@509893                      197.807 +- 30.8829      6      bad
chromium@509896                      202.817 +- 10.8534      6      bad
chromium@509902                      192.564 +- 28.7702      6      bad
chromium@509914                      190.378 +- 4.90132      6      bad
chromium@509938                      188.617 +- 25.1936      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=tough.canvas.cases.canvas2d.balls.common.bouncing.balls.html.ball.image.with.shadow.back.image smoothness.tough_canvas_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8964861281426706560


For feedback, file a bug with component Speed>Bisection
Not a revert, likely a skia change (see comment #4)
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Oct 24 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: winx64_high_dpi_perf_bisect
  Benchmark    : smoothness.tough_canvas_cases
  Metric       : frame_times/tough_canvas_cases_canvas2d_balls_common_bouncing_balls.html?ball_image_with_shadow_back_image
  Change       : 9.07% | 195.07202653 -> 173.875281405

Suspected Commit Range
  3 commits in range
  https://chromium.googlesource.com/chromium/src/+log/fdac6853113863b7f6486781c465c8193b1c8ed9..9055c1faea785877d31113dc9d2f3d978fe16457


Revision             Result                  N
chromium@506703      195.072 +- 26.2786      9        good
chromium@506714      187.482 +- 6.54186      9        good
chromium@506719      189.618 +- 19.8171      14       good
chromium@506720      ---                     ---      build failure
chromium@506721      ---                     ---      build failure
chromium@506722      184.269 +- 6.4086       14       bad
chromium@506724      184.279 +- 2.78726      9        bad
chromium@506744      177.711 +- 27.8532      9        bad
chromium@506784      173.875 +- 3.68188      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=tough.canvas.cases.canvas2d.balls.common.bouncing.balls.html.ball.image.with.shadow.back.image smoothness.tough_canvas_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8964861235576405632


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment