New issue
Advanced search Search tips

Issue 708853 link

Starred by 2 users

Issue metadata

Status: Duplicate
Merged: issue 709782
Owner:
Closed: Apr 2017
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.9%-2.4% regression in smoothness.tough_canvas_cases at 460346:460527

Project Member Reported by ericrk@chromium.org, Apr 6 2017

Issue description

These test should not have been impacted by the regression they were grouped into. Splitting it out and re-bisecting.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=708853

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg3PCVogkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg3OL4pwoM


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

chromium-rel-win7-dual
chromium-rel-win7-x64-dual
Cc: bmeu...@chromium.org
Owner: bmeu...@chromium.org

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

Hi bmeurer@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 : bmeurer
  Commit : 9df5674bd53b4a262e72f45263df9e886842c269
  Date   : Wed Mar 29 07:41:17 2017
  Subject: [turbofan] Avoid going through ArgumentsAdaptorTrampoline for CSA/C++ builtins.

Bisect Details
  Configuration: win_x64_perf_bisect
  Benchmark    : smoothness.tough_canvas_cases
  Metric       : frame_times/frame_times
  Change       : 2.47% | 21.4870329357 -> 22.0184637366

Revision                           Result                    N
chromium@460361                    21.487 +- 0.14569         6      good
chromium@460372                    21.4954 +- 0.226419       6      good
chromium@460374                    21.4917 +- 0.130428       6      good
chromium@460374,v8@e2858f2adc      21.5223 +- 0.15974        6      good
chromium@460374,v8@f11719ce79      21.5515 +- 0.140423       6      good
chromium@460374,v8@9df5674bd5      21.9406 +- 0.191415       6      bad       <--
chromium@460374,v8@0554e36be0      21.969 +- 0.188014        6      bad
chromium@460375                    21.9041 +- 0.0972601      6      bad
chromium@460377                    22.0113 +- 0.322664       6      bad
chromium@460382                    21.9629 +- 0.173476       6      bad
chromium@460403                    21.9748 +- 0.267584       6      bad
chromium@460444                    21.9393 +- 0.149582       6      bad
chromium@460527                    22.0185 +- 0.331837       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 smoothness.tough_canvas_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8983104949532203312

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6066322531680256


| 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!
Status: Assigned (was: Untriaged)
Mergedinto: 709782
Status: Duplicate (was: Assigned)

Sign in to add a comment