All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=659048

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg3daXoAoM


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

linux-release

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8997836408391781040

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8997836375608424656

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

Hi leszeks@chromium.org, 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 : [compiler] Mark shared functions for optimization
Author  : leszeks
Commit description:
  
The current method of marking functions for optimization, which replaces
the JSFunction's code object with one that triggers optimization, would
never allow unnamed functions to be optimized. This is an issue for a
style of programming which heavily relies on passing around closures.

This patch sets a bit on the SharedFunctionInfo when a JSFunction is
marked. When another JSFunction referring to the same SharedFunctionInfo
is lazily compiled, it immediately triggers a non-concurrent optimize.

BUG= v8:5512 

Review-Url: https://chromiumcodereview.appspot.com/2437043002
Cr-Commit-Position: refs/heads/master@{#40506}
Commit  : 4a31323e973e0a03403a53c601dfd4f0237532e8
Date    : Fri Oct 21 13:13:07 2016


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev   N  Good?
chromium@426000                153.25   1.0351    8  good
chromium@426450                153.4    0.894427  5  good
chromium@426675                151.8    1.09545   5  good
chromium@426788                152.8    0.83666   5  good
chromium@426816                152.75   1.48805   8  good
chromium@426823                152.8    1.09545   5  good
chromium@426823,v8@a8e30c0e68  147.2    1.09545   5  good
chromium@426823,v8@a4ff04ab13  146.8    1.09545   5  good
chromium@426823,v8@4a31323e97  155.0    1.0       5  bad    <--
chromium@426823,v8@dd614f55ce  157.0    0.707107  5  bad
chromium@426824                155.8    0.447214  5  bad
chromium@426825                156.0    0.707107  5  bad
chromium@426827                156.0    0.707107  5  bad
chromium@426830                155.625  0.916125  8  bad
chromium@426844                156.0    1.22474   5  bad
chromium@426900                155.375  1.06066   8  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 659048

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests sunspider
Test Metric: Total/Total
Relative Change: 0.91%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6793
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8997836375608424656


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5773814120579072

| 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!

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


===== SUSPECTED CL(s) =====
Subject : [compiler] Mark shared functions for optimization
Author  : leszeks
Commit description:
  
The current method of marking functions for optimization, which replaces
the JSFunction's code object with one that triggers optimization, would
never allow unnamed functions to be optimized. This is an issue for a
style of programming which heavily relies on passing around closures.

This patch sets a bit on the SharedFunctionInfo when a JSFunction is
marked. When another JSFunction referring to the same SharedFunctionInfo
is lazily compiled, it immediately triggers a non-concurrent optimize.

BUG= v8:5512 

Review-Url: https://chromiumcodereview.appspot.com/2437043002
Cr-Commit-Position: refs/heads/master@{#40506}
Commit  : 4a31323e973e0a03403a53c601dfd4f0237532e8
Date    : Fri Oct 21 13:13:07 2016


===== TESTED REVISIONS =====
Revision                       Mean   Std Dev   N  Good?
chromium@426820                164.6  0.547723  5  good
chromium@426823                165.8  0.83666   5  good
chromium@426823,v8@a8e30c0e68  158.8  1.48324   5  good
chromium@426823,v8@a4ff04ab13  158.8  0.83666   5  good
chromium@426823,v8@4a31323e97  168.8  0.83666   5  bad    <--
chromium@426823,v8@dd614f55ce  170.4  1.14018   5  bad
chromium@426824                169.8  0.83666   5  bad
chromium@426825                170.0  2.0       5  bad
chromium@426829                170.0  0.707107  5  bad
chromium@426837                170.0  0.707107  5  bad
chromium@426853                169.6  0.547723  5  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 659048

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests sunspider
Test Metric: Total/Total
Relative Change: 3.04%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6792
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8997836408391781040


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4935037072441344

| 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!

Oh yeah, that's very likely to be me. I've put the change behind a flag for now ( https://codereview.chromium.org/2446673002) while we evaluate the impact, so we can close this.