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

Issue 751981 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
Closed: Sep 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

15.8% regression in system_health.memory_mobile at 490683:490685

Project Member Reported by alexclarke@chromium.org, Aug 3 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=751981

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=1543adac9daccba8775886829185f77eac8b52825be09d26c2b42575a6943904


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

android-nexus5

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:skia:effective_size_avg/browse_social/browse_social_facebook

Revision             Result                N
chromium@490682      752170 +- 400899      21      good
chromium@490685      731722 +- 298335      21      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.social.facebook 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/8972297703788238656


For feedback, file a bug with component Speed>Bisection

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:skia:effective_size_avg/browse_social/browse_social_facebook

Revision             Result                N
chromium@490600      751624 +- 398348      21      good
chromium@490700      767211 +- 482448      21      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.social.facebook 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/8972208180713374448


For feedback, file a bug with component Speed>Bisection
Both the previous bisects were on the skia regressions, which are under our new 128kib thresholds. Re-kicked bisects on some of the larger regressions.
Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, Sep 18 2017

Cc: xunji...@chromium.org
Owner: xunji...@chromium.org
Status: Assigned (was: Untriaged)

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

Hi xunjieli@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 : Helen Li
  Commit : 73f7cac54a1108eac07d5c7c3367f979a899a0bd
  Date   : Thu Jul 27 14:57:57 2017
  Subject: [wpr-go] Switch system_health_mobile.json to use go

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_os:system_memory:native_heap:proportional_resident_size_avg/browse_news/browse_news_qq
  Change       : 5.12% | 29290201.3333 -> 30788484.0

Revision             Result                  N
chromium@489564      29290201 +- 835426      6      good
chromium@489868      29391748 +- 787301      6      good
chromium@489906      29469743 +- 507149      6      good
chromium@489916      29515481 +- 371658      6      good
chromium@489921      29269209 +- 816316      6      good
chromium@489922      29317679 +- 524853      6      good
chromium@489923      30186031 +- 516085      6      bad       <--
chromium@489925      30006148 +- 251412      6      bad
chromium@489944      30073220 +- 531652      6      bad
chromium@490020      30163161 +- 492250      6      bad
chromium@490172      30126980 +- 471521      6      bad
chromium@490779      30788484 +- 155756      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=browse.news.qq 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/8968091553975460384


For feedback, file a bug with component Speed>Bisection
Status: WontFix (was: Assigned)
Project Member

Comment 12 by 42576172...@developer.gserviceaccount.com, Sep 18 2017


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

Suspected Commit
  Author : Helen Li
  Commit : 73f7cac54a1108eac07d5c7c3367f979a899a0bd
  Date   : Thu Jul 27 14:57:57 2017
  Subject: [wpr-go] Switch system_health_mobile.json to use go

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:cc:effective_size_avg/browse_news/browse_news_cricbuzz
  Change       : 4.83% | 27579216.0 -> 28911572.0

Revision             Result                   N
chromium@489564      27579216 +- 0.0          6      good
chromium@489868      27605377 +- 221986       9      good
chromium@489906      27605377 +- 221986       9      good
chromium@489916      27579216 +- 0.0          6      good
chromium@489921      27767632 +- 1031997      6      good
chromium@489922      27564273 +- 81844.4      6      good
chromium@489923      29288404 +- 1384569      6      bad       <--
chromium@489925      29476820 +- 1305384      6      bad
chromium@489944      28863472 +- 1988980      9      bad
chromium@490020      29288404 +- 1384569      6      bad
chromium@490172      28801640 +- 271877       6      bad
chromium@490779      28911572 +- 1031997      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=browse.news.cricbuzz 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/8968091539935234000


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

Comment 13 by 42576172...@developer.gserviceaccount.com, Sep 19 2017

Cc: u...@chromium.org
Owner: u...@chromium.org
Status: Assigned (was: WontFix)

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

Hi ulan@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 : Ulan Degenbaev
  Commit : 774a4c5e240569b551cc9d19ae8cac146891d4c4
  Date   : Fri Jul 28 19:42:31 2017
  Subject: Revert "[heap] Reland "[heap] Allow a minimum semi-space size of 512K.""

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:v8:effective_size_avg/load_games/load_games_bubbles
  Change       : 9.93% | 6959755.33333 -> 7650920.0

Revision                           Result                  N
chromium@489564                    6959755 +- 146443       6      good
chromium@490172                    6952525 +- 127420       6      good
chromium@490476                    6964333 +- 96709.5      6      good
chromium@490628                    6949805 +- 166036       6      good
chromium@490647                    6988666 +- 103104       6      good
chromium@490652                    6976465 +- 101749       6      good
chromium@490652,v8@59ddd6061c      6953093 +- 106045       6      good
chromium@490652,v8@e567dd3ab4      6931487 +- 98781.1      6      good
chromium@490652,v8@774a4c5e24      7674649 +- 106784       6      bad       <--
chromium@490652,v8@4a9718c777      7587918 +- 81969.0      6      bad
chromium@490653                    7644409 +- 126584       6      bad
chromium@490654                    7609918 +- 119124       6      bad
chromium@490655                    7624275 +- 74736.4      6      bad
chromium@490657                    7604845 +- 101610       6      bad
chromium@490666                    7583398 +- 162860       6      bad
chromium@490704                    7638042 +- 112493       6      bad
chromium@490779                    7650920 +- 108991       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.games.bubbles 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/8968091513833657072


For feedback, file a bug with component Speed>Bisection

Comment 14 by u...@chromium.org, Sep 29 2017

Status: WontFix (was: Assigned)
Regression comes from a reverted CL.

Sign in to add a comment