New issue
Advanced search Search tips

Issue 771322 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 771192
Owner: ----
Closed: Oct 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

10.4% regression in thread_times.simple_mobile_sites at 505642:505737

Project Member Reported by majidvp@chromium.org, Oct 3 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=771322

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=ebff61b2fc5729c0c7cd1c95086acc6ea75d1cc861b0396a3670cf7bdf934f4b


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

android-webview-nexus6

=== BISECT JOB RESULTS ===
Bisect failed for unknown reasons

Please contact the team (see below) and report the error.


Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : thread_times.simple_mobile_sites
  Metric       : thread_other_cpu_time_per_frame/http___m.nytimes.com_


To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...m.nytimes.com. thread_times.simple_mobile_sites

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8966724784090670576


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Oct 13 2017

Mergedinto: 771192
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Benedikt Meurer
  Commit : 08db4d7652967c1ed12450a73ff53f5d6bbf1fdf
  Date   : Mon Oct 02 12:35:05 2017
  Subject: [ic] Properly handle polymorphic symbol accesses.

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : thread_times.simple_mobile_sites
  Metric       : thread_other_cpu_time_per_frame/http___m.nytimes.com_
  Change       : 10.80% | 2.30967266094 -> 2.55911821726

Revision                           Result                    N
chromium@505641                    2.30967 +- 0.0734204      6      good
chromium@505689                    2.31586 +- 0.0566007      6      good
chromium@505713                    2.32438 +- 0.0321791      6      good
chromium@505725                    2.30625 +- 0.0589556      6      good
chromium@505731                    2.30464 +- 0.0565226      6      good
chromium@505731,v8@08db4d7652      2.53537 +- 0.0693918      6      bad       <--
chromium@505731,v8@17d86d76fb      2.53755 +- 0.0609798      6      bad
chromium@505731,v8@1fa0f9ba4c      2.53978 +- 0.0634386      6      bad
chromium@505732                    2.53041 +- 0.0432088      6      bad
chromium@505733                    2.54941 +- 0.0114269      6      bad
chromium@505734                    2.55029 +- 0.101119       6      bad
chromium@505737                    2.55912 +- 0.0811061      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...m.nytimes.com. thread_times.simple_mobile_sites

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8965828702022519296


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment