Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8975750926825388176

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

Hi cbruni@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 : Camillo Bruni
  Commit : c503b80595ded0e30ca9264689e026de07ce6f93
  Date   : Fri Jun 23 13:12:06 2017
  Subject: [runtime] Enable eager boilerplate creation again

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : v8.runtimestats.browsing_mobile
  Metric       : Parse:duration_avg/browse_social/browse_social_twitter
  Change       : 74.88% | 121.519166667 -> 212.511333333

Revision                           Result                  N
chromium@481957                    121.519 +- 8.71159      6      good
chromium@481961                    133.578 +- 56.06        6      good
chromium@481963                    137.249 +- 66.5138      6      good
chromium@481963,v8@2b99d09e62      123.202 +- 8.58116      6      good
chromium@481963,v8@c503b80595      210.17 +- 14.2035       6      bad       <--
chromium@481963,v8@28d6d14ad5      205.535 +- 98.6229      9      bad
chromium@481964                    211.59 +- 85.939        6      bad
chromium@481965                    201.002 +- 28.4786      6      bad
chromium@481972                    206.936 +- 33.7955      6      bad
chromium@481987                    212.511 +- 31.3935      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 --story-filter=browse.social.twitter v8.runtimestats.browsing_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975750926825388176

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5071130596999168


| 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!

Issue 736694 has been merged into this issue.

 Issue 737375  has been merged into this issue.

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=737375

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgzoD5mwgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgru7NpAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgrvyjtwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgjsHOtwsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgzovrtQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgztzy7QsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgzp7puQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgzoLVpgsM


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

android-nexus5
android-nexus7v2
android-one
android-webview-nexus6

These are expected regressions related to tweaking on how to handle javascript object literal boilerplates.
The initial CL was too aggressive (1. improvement) and got partially reverted (1. regression) and then partially enabled again (2. improvement).