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

Issue 760134 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
Last visit > 30 days ago
Closed: Aug 2017
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

9% regression in system_health.memory_mobile at 489897:493218

Project Member Reported by pmeenan@chromium.org, Aug 29 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Aug 29 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=760134

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=68d963bfb48ed02f296c95b0e54e3488ac820e9140fefaf50fa0cb7b66b682da


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

android-one
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Aug 30 2017

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

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

Hi jgruber@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 : jgruber
  Commit : 062bb7d487b934d9e73df5ade31e887fe6d0f83c
  Date   : Wed Aug 02 12:25:23 2017
  Subject: [regexp] Limit ATOM regexps to single-character patterns

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:effective_size_avg/load_search/load_search_yandex
  Change       : 7.59% | 5101794.0 -> 5488850.66667

Revision                           Result                  N
chromium@489896                    5101794 +- 33147.1      6       good
chromium@490727                    4993802 +- 34529.5      14      good
chromium@491142                    5110399 +- 1061245      21      good
chromium@491350                    5464059 +- 13281.1      6       good
chromium@491454                    5462142 +- 34560.9      6       good
chromium@491480                    5469903 +- 23574.4      6       good
chromium@491482                    5461706 +- 37610.2      6       good
chromium@491483                    5469279 +- 43891.2      9       good
chromium@491483,v8@069c2ac2a1      5475445 +- 26496.3      14      good
chromium@491483,v8@062bb7d487      5484566 +- 10175.6      9       bad       <--
chromium@491483,v8@c924a942e9      5485460 +- 12638.4      9       bad
chromium@491484                    5486643 +- 10855.7      6       bad
chromium@491487                    5487095 +- 10243.8      6       bad
chromium@491493                    5484861 +- 12264.8      6       bad
chromium@491506                    5487743 +- 12641.6      6       bad
chromium@491557                    5483472 +- 19284.6      14      bad
chromium@493218                    5488851 +- 43647.0      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.yandex 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/8969913149705231184


For feedback, file a bug with component Speed>Bisection
Cc: -pmeenan@chromium.org -jgruber@chromium.org
Owner: pmeenan@chromium.org
That CL has since been reverted: https://chromium-review.googlesource.com/599547. Assigning back for further triaging; although to me this just looks like an additional allocated page, and not actionable.
Status: WontFix (was: Assigned)
Dropped, popped back up again but the reference also moved and has a similar noisy->steady pattern.

Sign in to add a comment