New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 726903 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 726902
Owner: ----
Closed: Jun 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1%-145% regression in system_health.memory_mobile at 474274:474399

Project Member Reported by briander...@chromium.org, May 26 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, May 27 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: android_one_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/browse_news/browse_news_toi
  Change       : 105.16% | 5698539.42857 -> 11690875.7143

Suspected Commit Range
  3 commits in range
  https://chromium.googlesource.com/chromium/src/+log/e87ca325b7641587a273968c077adac3a3fa5edb..962729847c531a6650831995d687080fc567c809


Revision             Result                    N
chromium@474273      5698539 +- 10125934       14       good
chromium@474336      6318558 +- 8959466        14       good
chromium@474349      5391521 +- 10477290       14       good
chromium@474350      ---                       ---      build failure
chromium@474351      ---                       ---      build failure
chromium@474352      10042656 +- 20732057      14       bad
chromium@474355      10920201 +- 24132284      21       bad
chromium@474362      12473191 +- 20557891      14       bad
chromium@474399      11690876 +- 17679125      14       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=browse.news.toi system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978491181573747120

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4564914435260416


| 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 6 by 42576172...@developer.gserviceaccount.com, Jun 13 2017

Mergedinto: 726902
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : fdoray
  Commit : b87bcfb8c3b17bbcad020186a94e935e2fd0d162
  Date   : Wed May 24 17:49:40 2017
  Subject: [reland] Use TaskScheduler instead of WorkerPool in v8_platform.cc.

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:malloc:effective_size_avg/load_media/load_media_imgur
  Change       : 5.32% | 30883085.3333 -> 32525861.3333

Revision             Result                   N
chromium@474100      30883085 +- 862941       6       good
chromium@474250      31232885 +- 1427041      6       good
chromium@474325      31291426 +- 2172957      9       good
chromium@474344      31404376 +- 1763918      9       good
chromium@474345      31513832 +- 889344       6       good
chromium@474346      32722229 +- 1184957      6       bad       <--
chromium@474347      32850936 +- 1441209      6       bad
chromium@474349      32513530 +- 1763026      14      bad
chromium@474354      32796183 +- 1618533      9       bad
chromium@474363      33032968 +- 984132       6       bad
chromium@474400      32525861 +- 665622       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-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.media.imgur system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976997598873000496

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6715591315947520


| 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 7 by 42576172...@developer.gserviceaccount.com, Jun 13 2017


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

Suspected Commit
  Author : fdoray
  Commit : b87bcfb8c3b17bbcad020186a94e935e2fd0d162
  Date   : Wed May 24 17:49:40 2017
  Subject: [reland] Use TaskScheduler instead of WorkerPool in v8_platform.cc.

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:malloc:effective_size_avg/background_media/background_media_imgur
  Change       : 2.79% | 31854397.1429 -> 32744256.5714

Revision             Result                   N
chromium@474100      31854397 +- 3901835      14      good
chromium@474275      30876677 +- 2868465      9       good
chromium@474319      31845219 +- 4582899      14      good
chromium@474341      31246660 +- 1343637      6       good
chromium@474344      31217104 +- 1811810      9       good
chromium@474345      30966204 +- 2393187      9       good
chromium@474346      32237046 +- 939102       9       bad       <--
chromium@474347      32552299 +- 1142333      6       bad
chromium@474352      32936869 +- 899857       6       bad
chromium@474363      32860030 +- 1034400      9       bad
chromium@474450      32744257 +- 1846439      14      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-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=background.media.imgur system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976997566500533968

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5833867144986624


| 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