New issue
Advanced search Search tips

Issue 747027 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 744354
Owner:
Closed: Jul 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1%-37.5% regression in memory.top_10_mobile at 485991:487676

Project Member Reported by benhenry@google.com, Jul 20 2017

Issue description

Graphs to follow.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jul 20 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=747027

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=61ebc6c80c2d1ff8dece44ef9711d05c04996d8d9c4abf3de4b4e0c822fe9886


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

android-nexus5X
android-nexus6
android-nexus7v2
android-one
android-webview-nexus5X
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jul 21 2017

Cc: reed@google.com
Owner: reed@google.com

=== Auto-CCing suspected CL author reed@google.com ===

Hi reed@google.com, 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 : Mike Reed
  Commit : f6e9c3d9551fb627155335b02583de6d32037646
  Date   : Mon Jul 17 20:35:04 2017
  Subject: remove SK_SUPPORT_LEGACY_MASK_BLUR flag

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:skia:effective_size_avg/background/after_https_mobile_twitter_com_justinbieber_skip_interstitial_true
  Change       : 37.27% | 761664.0 -> 1045546.0

Revision             Result                  N
chromium@487220      761664 +- 0.0           6      good
chromium@487225      761664 +- 0.0           6      good
chromium@487227      756847 +- 26385.6       6      good
chromium@487228      1048492 +- 0.0          6      bad       <--
chromium@487230      1045533 +- 16208.9      6      bad
chromium@487239      1048519 +- 92.376       6      bad
chromium@487257      1048519 +- 92.376       6      bad
chromium@487293      1045546 +- 16223.7      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 memory.top_10_mobile

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8973531267650450416


For feedback, file a bug with component Speed>Bisection

Comment 4 by reed@chromium.org, Jul 21 2017

Cc: fmalita@chromium.org mtklein@chromium.org

Comment 5 by mtkl...@google.com, Jul 21 2017

This is from turning on Herb's new blur?

Comment 6 by reed@chromium.org, Jul 21 2017

yes
Project Member

Comment 7 by sheriffbot@chromium.org, Jul 21 2017

Labels: Hotlist-Google
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Jul 28 2017

Mergedinto: 744354
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Camillo Bruni
  Commit : 36421dc467bffcdcb71967ed39dddca1e33d48c6
  Date   : Wed Jul 12 19:11:04 2017
  Subject: [literals] Disable double lazy boilerplate for literals containing Arrays

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/browse_tools/browse_tools_maps
  Change       : 5.80% | 14408770.8571 -> 15274109.3333

Revision                           Result                  N
chromium@485990                    14408771 +- 240718      14      good
chromium@486191                    14506533 +- 244591      6       good
chromium@486240                    14378141 +- 187138      6       good
chromium@486247                    14507114 +- 432223      6       good
chromium@486248                    14444996 +- 217894      6       good
chromium@486248,v8@42c8df3f46      14445981 +- 202174      6       good
chromium@486248,v8@34874b3b19      14508897 +- 205629      6       good
chromium@486248,v8@36421dc467      14990677 +- 236566      6       bad       <--
chromium@486248,v8@fa4ec9fdbe      14948512 +- 215429      6       bad
chromium@486249                    14980309 +- 181464      6       bad
chromium@486250                    15079059 +- 249875      6       bad
chromium@486253                    14966469 +- 186281      6       bad
chromium@486266                    15040511 +- 193914      6       bad
chromium@486291                    15088125 +- 208592      6       bad
chromium@486391                    15020079 +- 166315      6       bad
chromium@486833                    15046231 +- 462599      14      bad
chromium@487676                    15274109 +- 473332      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=browse.tools.maps 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/8972905894456162912


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment