All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=648907

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg-YP0tAoM


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

linux-release

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9000920623957916464

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

Hi enne@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 : cc: Remove estimated parent draw time from renderer
Author  : enne
Commit description:
  
This is a display scheduler only concept now that unified begin frame is
turned on.  Renderers can just use the deadline passed to them from the
top level begin frame source.

This fixes a regression from https://codereview.chromium.org/2299003002
where Android was using the incorrect parent estimated draw time of
none and so thought it had less time for frames than it did.

R=brianderson@chromium.org
BUG= 646377 
CQ_INCLUDE_TRYBOTS=master.tryserver.blink:linux_precise_blink_rel

Review-Url: https://codereview.chromium.org/2352823002
Cr-Commit-Position: refs/heads/master@{#419617}
Commit  : bfdea7f114aded7866981b8bfe3edd0c75155f12
Date    : Tue Sep 20 01:11:26 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev    N  Good?
chromium@419548  16.6712  0.0219614  8  good
chromium@419600  16.6704  0.0305159  8  good
chromium@419613  16.6758  0.0253498  8  good
chromium@419615  16.6818  0.0213768  5  good
chromium@419616  16.6634  0.0105702  5  good
chromium@419617  16.827   0.101396   8  bad    <--
chromium@419620  16.8263  0.0848017  5  bad
chromium@419626  16.7888  0.0917052  5  bad
chromium@419652  16.8459  0.132705   8  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 648907

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests smoothness.image_decoding_cases
Test Metric: frame_times/frame_times
Relative Change: 1.05%
Score: 99.0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6718
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9000920623957916464


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4964049903681536

| 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 change is fixing another regression from https://codereview.chromium.org/2299003002.  All of these graphs got better and then got worse between that change and this change, because it's adjusting how much time the renderer has to produce a frame.