All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=657272

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg7c-AqgoM


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

chromium-rel-mac-retina

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8998395377195165328

=== Auto-CCing suspected CL author caitp@igalia.com ===

Hi caitp@igalia.com, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [builtins] implement Array.prototype[@@iterator] in TFJ builtins
Author  : caitp
Commit description:
  
Implements the variations of CreateArrayIterator() in TFJ builtins
(ArrayPrototypeValues, ArrayPrototypeEntries and ArrayPrototypeKeys), and
provides two new Object types with numerous maps which identify certain
behaviours, which will be useful for inlining.

Removes src/js/array-iterator.js entirely

Also adds support for printing Symbol literals inserted by the Parser during
desugaring when FLAG_print_builtin_ast is set to true.

BUG= v8:5388 
R=bmeurer@chromium.org, cbruni@chromium.org
TBR=ulan@chromium.org

Review-Url: https://codereview.chromium.org/2405253006
Cr-Commit-Position: refs/heads/master@{#40373}
Commit  : 86d0dd362f627a7831b042d4fe8baa121c976fc4
Date    : Tue Oct 18 02:43:14 2016


===== TESTED REVISIONS =====
Revision                       Mean    Std Dev  N  Good?
chromium@425916                578277  2880.3   5  good
chromium@425923                577661  748.259  5  good
chromium@425925                577397  182.481  5  good
chromium@425925,v8@86d0dd362f  584754  294.504  5  bad    <--
chromium@425925,v8@cc07613674  584683  344.214  5  bad
chromium@425925,v8@3145befb3d  602952  41028.0  5  bad
chromium@425926                584824  232.826  5  bad
chromium@425927                584930  507.051  5  bad
chromium@425930                585035  275.484  5  bad
chromium@425943                584912  701.245  5  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 657272

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests oortonline_tbmv2
Test Metric: memory:chrome:renderer_processes:reported_by_chrome:v8:heap:map_space:effective_size_max/memory:chrome:renderer_processes:reported_by_chrome:v8:heap:map_space:effective_size_max
Relative Change: 1.15%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1752
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8998395377195165328


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5839737070288896

| 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 Tests>AutoBisect.  Thank you!

This CL adds 33 new Maps per native context at bootstrapping time, which looks like the likely cause of this.

CC Benedikt to discuss if it's worth creating these maps lazily

Not sure; we could add them lazily, but not sure it's worth it. Adding mvstanton@ for comments.

This regression has been included in a stable release and that stable channel is now deprecated. I'm closing this so that we won't have unresponsive performance regressions in the future.