New issue
Advanced search Search tips

Issue 767710 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 767608
Owner: ----
Closed: Oct 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.1%-17.3% regression in media.tough_video_cases_tbmv2 at 502559:502675

Project Member Reported by ulan@google.com, Sep 22 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Sep 22 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=767710

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=8363ff216ad4ba0535ac7685441132637e3ba43b8b93246b10f13e7077810575


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

android-nexus5X
android-nexus7v2
chromium-rel-win10
chromium-rel-win7-gpu-ati
chromium-rel-win7-gpu-intel
chromium-rel-win7-gpu-nvidia
chromium-rel-win7-x64-dual
chromium-rel-win8-dual
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Sep 22 2017


=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/video.html?src_garden2_10s.mp4
  Change       : 4.07% | 5200164.57143 -> 5316608.0

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/857f2d66dc9d75282c77a2fcd9b61c373c25d25a..f6118b75ca2e16d7d404b4aa7e9c7bea14d73937


Revision             Result                  N
chromium@502586      5200165 +- 1155474      14       good
chromium@502587      ---                     ---      build failure
chromium@502588      5387410 +- 939966       14       bad
chromium@502589      5499758 +- 1253288      14       bad
chromium@502592      5287481 +- 1077309      9        bad
chromium@502598      5403989 +- 957215       6        bad
chromium@502609      5403989 +- 957215       6        bad
chromium@502631      5316608 +- 642119       6        bad
chromium@502675      5316608 +- 642119       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 --story-filter=video.html.src.garden2.10s.mp4 media.tough_video_cases_tbmv2

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967792082810926464


For feedback, file a bug with component Speed>Bisection
Cc: mahmadi@chromium.org wuandy@chromium.org
+wuandy@, mahmadi@:

one of your changes caused Chrome to use between 1% and 17% more v8 heap memory. Is this expected?
My CL is iOS specific. I don't see any connection to V8 heap memory. It's probably wuandy@'s that contributed to this.
Cc: -mahmadi@chromium.org
Owner: wuandy@chromium.org
Status: Assigned (was: Untriaged)

Comment 9 by u...@chromium.org, Oct 17 2017

Cc: -wuandy@chromium.org
Owner: ----
Status: Untriaged (was: Assigned)
media.tough_video_cases_tbmv2 looks bi-modal.

I started bisect on system_health regression.
Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, Oct 17 2017

Mergedinto: 767608
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : peterwmwong
  Commit : 8dfdeae0f1c352b15238d0b9100f37956e16eaa9
  Date   : Sat Sep 16 07:18:32 2017
  Subject: [builtins] Convert String HTML functions (ex. anchor, big, bold) to CSA

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/load_search/load_search_taobao
  Change       : 0.76% | 3933924.0 -> 3963873.33333

Revision                           Result                  N
chromium@502584                    3933924 +- 27529.8      6      good
chromium@502590                    3927928 +- 20028.4      6      good
chromium@502590,v8@ee5c31f335      3937153 +- 17891.9      6      good
chromium@502590,v8@3d046986f0      3928622 +- 20360.3      6      good
chromium@502590,v8@8dfdeae0f1      3970409 +- 18617.0      6      bad       <--
chromium@502590,v8@8c89502008      3965669 +- 23399.3      6      bad
chromium@502591                    3961260 +- 20038.3      6      bad
chromium@502592                    3971905 +- 16538.7      6      bad
chromium@502593                    3964787 +- 25182.0      6      bad
chromium@502595                    3967703 +- 20427.1      6      bad
chromium@502606                    3969024 +- 20163.3      6      bad
chromium@502627                    3964861 +- 22663.0      6      bad
chromium@502670                    3963873 +- 22625.5      6      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

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 --story-filter=load.search.taobao system_health.memory_mobile

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8965501996383700816


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment