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

Issue 730524 link

Starred by 4 users

Issue metadata

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



Sign in to add a comment

10.7% regression in blink_perf.bindings at 477304:477339

Project Member Reported by kouhei@google.com, Jun 7 2017

Issue description

See the link to graphs below.
 

Comment 1 by kouhei@google.com, Jun 7 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=730524

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpu7hpgoM


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

android-webview-nexus6
Cc: hpayer@chromium.org
Owner: hpayer@chromium.org

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

Hi hpayer@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 : hpayer
  Commit : 5ebd6fcd269de6ac85d6805049882e75e298ddb3
  Date   : Tue Jun 06 12:04:01 2017
  Subject: [heap] Lower external allocation limit when external memory shrinks.

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : blink_perf.bindings
  Metric       : structured-clone-long-string-serialize/structured-clone-long-string-serialize
  Change       : 9.22% | 12.6944 -> 13.8642133333

Revision                           Result                   N
chromium@477303                    12.6944 +- 0.329539      6      good
chromium@477312                    12.68 +- 0.492964        6      good
chromium@477317                    12.6972 +- 0.4229        6      good
chromium@477319                    12.6046 +- 0.692628      6      good
chromium@477320                    12.7287 +- 0.429967      6      good
chromium@477320,v8@4ca7022295      12.7067 +- 0.615091      6      good
chromium@477320,v8@5ebd6fcd26      14.1496 +- 0.421321      6      bad       <--
chromium@477320,v8@468446d5fc      13.9845 +- 0.482787      6      bad
chromium@477321                    14.1284 +- 0.429079      6      bad
chromium@477339                    13.8642 +- 0.70299       6      bad

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 blink_perf.bindings

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977450702864862784

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5785425316151296


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!
Cc: u...@chromium.org ulan@google.com
 Issue 731709  has been merged into this issue.
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Jun 10 2017

Cc: chcunningham@chromium.org
 Issue 731869  has been merged into this issue.

Comment 6 by hpayer@chromium.org, Jun 12 2017

Status: WontFix (was: Untriaged)
With this CL garbage collections trigger in the benchmarks a bit earlier due to the timing change. Closing as won't fix since this CL improves various memory bloat scenarios in the wild.
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Jun 14 2017

Cc: mlippautz@chromium.org
 Issue 733107  has been merged into this issue.

Sign in to add a comment