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

Issue 740880 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 740885
Owner:
OOO until 2019-02-10
Closed: Jul 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

7.9%-15.2% regression in system_health.memory_mobile at 485157:485157

Project Member Reported by petermarshall@chromium.org, Jul 11 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jul 11 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=740880

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=f3ca820923155f5b4f510da1e6ccc9f173b4eb9a0c9135acb243097fe2779be6


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

android-nexus6
Owner: yoshiki@chromium.org
Status: Assigned (was: Untriaged)
Directly points to 
4c03f6e Support child non-exo windows of the root surface in exo::SurfaceTreeHost
Cc: -petermarshall@chromium.org yoshiki@chromium.org
Owner: petermarshall@chromium.org
My change shouldn't affect to Android Chrome, since components/exo is built only on ChromeOS build.
https://chromium.googlesource.com/chromium/src/+log/4c03f6e2c0c72aea643810a67360057efbd31b13%5E..4c03f6e2c0c72aea643810a67360057efbd31b13?pretty=fuller


Is my change really the cause of the memory regression?
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Jul 11 2017

Mergedinto: 740885
Status: Duplicate (was: Assigned)

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

Suspected Commit
  Author : perezju
  Commit : 00b0c16c97088f5c06df9d3b27eaeb41f06173e5
  Date   : Sat Jul 08 09:18:52 2017
  Subject: Revert of [System Health] Extend dump time to 5 seconds (patchset #2 id:20001 of https://codereview.chromium.org/2946013004/ )

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/load_tools/load_tools_drive
  Change       : 14.81% | 15253168.8 -> 17512246.0

Revision                                 Result                   N
chromium@485130                          15253169 +- 129084       5       good
chromium@485145                          15208034 +- 464703       9       good
chromium@485146                          15298493 +- 382905       9       good
chromium@485146,catapult@00b0c16c97      17088919 +- 2031580      9       bad       <--
chromium@485147                          17259566 +- 2155143      6       bad
chromium@485149                          17340731 +- 2431351      9       bad
chromium@485153                          16662434 +- 6265650      14      bad
chromium@485160                          17308771 +- 2128067      9       bad
chromium@485190                          17512246 +- 415659       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.tools.drive 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/8974357621714044336


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment