All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=641019

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgvtnBrAkM


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

android-galaxy-s5

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9003338801247190320

Bisect failed: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_s5_perf_bisect/builds/957
Failure reason: the build has failed due to infrastructure failure.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9000695050746340720

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

Hi hajimehoshi@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 : Leak Detector: Count ScriptPromise and ActiveDOMObject on worker threads
Author  : hajimehoshi
Commit description:
  
This CL makes the leak detector count ScriptPromise and ActiveDOMObject
not only on the main thread but also on worker threads.

There was a bug that the worker threads don't wait for the termination
( crbug.com/507224 ) and we couldn't count those objects on worker
threads correctly, but now the bug has been fixed.

BUG= 506466 ,  506799 ,  507574 

Review-Url: https://codereview.chromium.org/2258873004
Cr-Commit-Position: refs/heads/master@{#413474}
Commit  : f3d1a58111d4763fb364d39498e2053cada1c50d
Date    : Mon Aug 22 18:06:11 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev   N  Good?
chromium@413449  107.025  0.635856  5  good
chromium@413462  108.955  1.78327   5  good
chromium@413469  108.245  1.43304   5  good
chromium@413472  108.189  1.26915   8  good
chromium@413473  108.993  2.0271    8  good
chromium@413474  103.439  1.59275   5  bad    <--
chromium@413475  102.77   0.543836  5  bad
chromium@413500  102.081  1.44678   5  bad

Bisect job ran on: android_s5_perf_bisect
Bug ID: 641019

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests dromaeo.domcoremodify
Test Metric: dom/dom
Relative Change: 4.62%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_s5_perf_bisect/builds/1027
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9000695050746340720


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5806026727620608

| 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!

Fixit ping: hajimehoshi, the bisect blamed your CL for this regression. Can you check whether that's the case?

Let me check...

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/964d6ecc9c556e80c53140a2254e93c92deb98a2

commit 964d6ecc9c556e80c53140a2254e93c92deb98a2
Author: hajimehoshi <hajimehoshi@chromium.org>
Date: Thu Oct 06 11:43:11 2016

Fix performance issue in InstanceCounters for DOM nodes

The instance counters have used atomic incrementing/decrementing, but
this caused performance issue for dromaeo.domcoremodify test where DOM
objects are injected and created. This CL fixes this issue by creating
another counter without locks or atomic barriers only for nodes.

BUG= 641019 

Review-Url: https://codereview.chromium.org/2393353003
Cr-Commit-Position: refs/heads/master@{#423501}

[modify] https://crrev.com/964d6ecc9c556e80c53140a2254e93c92deb98a2/third_party/WebKit/Source/core/dom/Node.cpp
[modify] https://crrev.com/964d6ecc9c556e80c53140a2254e93c92deb98a2/third_party/WebKit/Source/core/inspector/InstanceCounters.cpp
[modify] https://crrev.com/964d6ecc9c556e80c53140a2254e93c92deb98a2/third_party/WebKit/Source/core/inspector/InstanceCounters.h

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/964d6ecc9c556e80c53140a2254e93c92deb98a2

commit 964d6ecc9c556e80c53140a2254e93c92deb98a2
Author: hajimehoshi <hajimehoshi@chromium.org>
Date: Thu Oct 06 11:43:11 2016

Fix performance issue in InstanceCounters for DOM nodes

The instance counters have used atomic incrementing/decrementing, but
this caused performance issue for dromaeo.domcoremodify test where DOM
objects are injected and created. This CL fixes this issue by creating
another counter without locks or atomic barriers only for nodes.

BUG= 641019 

Review-Url: https://codereview.chromium.org/2393353003
Cr-Commit-Position: refs/heads/master@{#423501}

[modify] https://crrev.com/964d6ecc9c556e80c53140a2254e93c92deb98a2/third_party/WebKit/Source/core/dom/Node.cpp
[modify] https://crrev.com/964d6ecc9c556e80c53140a2254e93c92deb98a2/third_party/WebKit/Source/core/inspector/InstanceCounters.cpp
[modify] https://crrev.com/964d6ecc9c556e80c53140a2254e93c92deb98a2/third_party/WebKit/Source/core/inspector/InstanceCounters.h

[Automated comment] removing mislabelled merge-merged-2840