New issue
Advanced search Search tips

Issue 684480 link

Starred by 2 users

Issue metadata

Status: Duplicate
Owner:
Closed: Jan 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

10.5% regression in blink_perf.bindings at 444722:444804

Project Member Reported by toyoshim@chromium.org, Jan 24 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=684480

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg0NODpgoM


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

chromium-rel-win7-gpu-nvidia
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jan 24 2017

Cc: etienneb@chromium.org
Owner: etienneb@chromium.org

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

Hi etienneb@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 : etienneb
  Commit : c9e8aae171ee0999ed1ad766089d76cf40159fee
  Date   : Thu Jan 19 16:34:51 2017
  Subject: Fix ASAN default suppression symbol mangling on windows

Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : blink_perf.bindings
  Metric       : set-attribute/set-attribute
  Change       : 0.86% | 808.455672556 -> 815.425744309

Revision             Result                  N
chromium@444721      808.456 +- 20.6759      9      good
chromium@444763      794.398 +- 5.51726      6      good
chromium@444764      822.866 +- 9.60488      6      bad       <--
chromium@444765      818.73 +- 4.65103       6      bad
chromium@444766      804.802 +- 6.04016      6      bad
chromium@444769      803.534 +- 5.92349      6      bad
chromium@444774      807.796 +- 8.76986      6      bad
chromium@444784      815.142 +- 3.97616      6      bad
chromium@444804      815.426 +- 5.62538      8      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 blink_perf.bindings

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8989590649489580928

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4917987502456832


| 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 Tests>AutoBisect.  Thank you!

Comment 4 by etienneb@google.com, Jan 24 2017

This regression CAN'T be related this patch.

see: https://codereview.chromium.org/2631753002/

My change has no functional change.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Jan 24 2017

Mergedinto: 684394
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : yosin
  Commit : f34f5cb8f4f2f4a54afe4094dc7933193220116e
  Date   : Fri Jan 20 07:16:51 2017
  Subject: Introduce SynchronousMutationObserver::didChangeAttribute()

Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : blink_perf.bindings
  Metric       : set-attribute/set-attribute
  Change       : 10.24% | 777.582305549 -> 697.986804822

Revision             Result                  N
chromium@444721      777.582 +- 180.406      9      good
chromium@444886      791.981 +- 21.5635      6      good
chromium@444969      794.651 +- 16.1267      6      good
chromium@444990      803.899 +- 15.0979      6      good
chromium@445000      798.959 +- 6.89666      6      good
chromium@445005      794.264 +- 7.19725      6      good
chromium@445006      720.162 +- 6.69607      6      bad       <--
chromium@445007      732.507 +- 2.21684      5      bad
chromium@445008      716.383 +- 17.573       5      bad
chromium@445010      721.492 +- 10.4602      6      bad
chromium@445051      697.987 +- 22.0547      9      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 blink_perf.bindings

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8989569783834637216

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6366777279250432


| 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 Tests>AutoBisect.  Thank you!

Sign in to add a comment