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

Issue 752873 link

Starred by 1 user

Issue metadata

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



Sign in to add a comment

2.3%-2.5% regression in system_health.memory_mobile at 491269:491494

Project Member Reported by jgruber@chromium.org, Aug 7 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=752873

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=7b5220e277028615c9682e2333728fdabf43eb50e1419a758b43651f7b91ca2e


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

android-nexus5X
android-nexus7v2
Cc: jupvfranco@google.com
Owner: jupvfranco@google.com

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

Hi jupvfranco@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 : Juliana Franco
  Commit : 895c321948da03e4c2f7fbc1f7035e47bb709d7d
  Date   : Wed Aug 02 08:28:15 2017
  Subject: Replacing pc with trampoline on stack (gc-stress fix)

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/load_social/load_social_twitter
  Change       : 2.37% | 3245558.66667 -> 3322410.66667

Revision                           Result                  N
chromium@491268                    3245559 +- 10.8321      6      good
chromium@491325                    3312797 +- 92181.2      6      good
chromium@491353                    3329585 +- 6.733        6      good
chromium@491360                    3315617 +- 76537.3      6      good
chromium@491364                    3298748 +- 107509       6      good
chromium@491366                    3329589 +- 30.1552      6      good
chromium@491366,v8@5572a6ec73      3315540 +- 76571.6      6      good
chromium@491366,v8@a5230d81d1      3298652 +- 107454       6      good
chromium@491366,v8@895c321948      3344820 +- 9.79796      6      bad       <--
chromium@491366,v8@d4a742fdf1      3344787 +- 203.149      6      bad
chromium@491367                    3344857 +- 200.353      6      bad
chromium@491381                    3344813 +- 19.9332      6      bad
chromium@491494                    3322411 +- 72905.5      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.social.twitter 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/8971933152276893952


For feedback, file a bug with component Speed>Bisection
Cc: jarin@chromium.org

Comment 5 by jarin@chromium.org, Aug 21 2017

Cc: -jarin@chromium.org
Owner: jarin@chromium.org
Status: WontFix (was: Untriaged)
We need to introduce additional fields to safepoint tables, which does consume slightly more memory. This is part of a bigger effort to make code non-writable. We will try to mitigate this in subsequent CLs, but for now we have to take the regression.

Sign in to add a comment