New issue
Advanced search Search tips

Issue 699718 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 700085
Owner: ----
Closed: Mar 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

13.7%-46.4% regression in blink_perf.parser at 454722:454932

Project Member Reported by benhenry@google.com, Mar 8 2017

Issue description

See the link to graphs below.
 

=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

Error: INFRA_FAILURE

The bisect was able to narrow the range, you can try running with:
  good_revision: 5f0498f32748dd816a021ac5cd3c919693b679b7
  bad_revision : f193ee6d21e6548ed425746ec80fb71faa7998a5

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : blink_perf.parser
  Metric       : query-selector-all-id-deep/query-selector-all-id-deep

Revision             Result                  N
chromium@454721      995.962 +- 19.5515      6      good
chromium@454822      998.333 +- 16.9587      6      good
chromium@454850      873.325 +- 13.3298      6      bad
chromium@454877      853.9 +- 16.7496        6      bad
chromium@454932      893.236 +- 10.4719      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests blink_perf.parser

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8985654854293416864

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5833666619506688


| 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!
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Mar 10 2017

Mergedinto: 700085
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : mlippautz
  Commit : d8e518533a6a987997cdcf438ddc21573eb75de0
  Date   : Mon Mar 06 11:03:10 2017
  Subject: MutationObserver: Keep related nodes and callback alive through tracing

Bisect Details
  Configuration: linux_perf_bisect
  Benchmark    : blink_perf.parser
  Metric       : query-selector-all-class/query-selector-all-class
  Change       : 18.93% | 365.307928397 -> 296.160133245

Revision             Result                  N
chromium@454738      365.308 +- 9.13292      6      good
chromium@454842      357.118 +- 23.792       6      good
chromium@454846      343.143 +- 16.2526      6      good
chromium@454847      292.961 +- 8.28984      6      bad       <--
chromium@454848      290.981 +- 10.3845      6      bad
chromium@454849      294.085 +- 3.45742      6      bad
chromium@454855      287.762 +- 28.5036      6      bad
chromium@454868      295.209 +- 3.49071      6      bad
chromium@454894      293.505 +- 4.39157      6      bad
chromium@454946      296.16 +- 6.1092        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 blink_perf.parser

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8985593574906106048

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5859593458024448


| 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