New issue
Advanced search Search tips

Issue 705391 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 704732
Owner: ----
Closed: Mar 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

97.5%-181.7% regression in smoothness.top_25_smooth at 458495:458826

Project Member Reported by toyoshim@chromium.org, Mar 27 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=705391

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgrObR-AoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgrJntowoM


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

android-nexus6
chromium-rel-mac-retina
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Mar 27 2017


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

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : smoothness.top_25_smooth
  Metric       : mean_input_event_latency/Weather.com

Revision             Result                  N
chromium@458714      10.5624 +- 19.2286      21      good
chromium@458826      10.5758 +- 19.2805      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=Weather.com smoothness.top_25_smooth

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8983987596140077008

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5870407296483328


| 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!
kicked off another bisect with a wider revision range, since bad results would be ~25 regarding to the original report.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Mar 27 2017

Mergedinto: 704732
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : chongz
  Commit : 5a7f45dab8372cb7b80ee24dfb137a7ced2049ea
  Date   : Wed Mar 22 23:13:14 2017
  Subject: Enable VsyncAlignedInput to field trial

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : smoothness.top_25_smooth
  Metric       : mean_input_event_latency/Weather.com
  Change       : 191.98% | 8.62616666667 -> 25.1868333333

Revision             Result                   N
chromium@458714      8.62617 +- 0.356753      6      good
chromium@458843      8.44983 +- 1.61485       6      good
chromium@458908      10.1413 +- 10.0875       6      good
chromium@458916      8.179 +- 1.23239         6      good
chromium@458920      8.58617 +- 0.402018      6      good
chromium@458921      24.9238 +- 1.01954       6      bad       <--
chromium@458922      25.0052 +- 0.697518      6      bad
chromium@458924      25.3638 +- 0.562159      6      bad
chromium@458940      25.034 +- 0.695055       6      bad
chromium@458972      25.1868 +- 0.254025      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=Weather.com smoothness.top_25_smooth

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8983982125601995968

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5826155711561728


| 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