All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=606250

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgpMm1vgoM


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

android-one

the first run fails with "Exception steps exception device_status_check".
kicked another bisect.

cc test owner.

Failed steps failed gathering reference values.performance test 1 of 5 failed gathering reference values.reading chartjson results

kicked another bisect because the blocking issues were fixed

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

Hi sievers@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 : Android: Browser-side scheduling latency tweaks
Author  : sievers
Commit description:
  
    - Emit an immediate 'missed' BeginFrame when an
      BFObserver is added instead of waiting for next vsync
    - Remove unneeded requestRender() (=SetNeedsAnimate()) call

    The former helps both the browser compositor and display
    scheduler (now that it uses the same BeginFrameSource).

    Regarding the browser compositor:
    When the omnibox is hiding (or selection handles are showing)
    we need to browser composite with the correct scroll offset
    for a given renderer frame.

    Without this patch we run:
    ScrollBegin VSync SwapCompositorFrame VSync BrowserComposite

    Now we do:
    ScrollBegin VSync SwapCF MissedBF BrowserComposite VSync

    In the next interval, this works because if nothing changed yet,
    the scheduler will defer the BeginMainFrame until there is
    another change in the browser compositor tree (MODE_LATE).

    Calling SetNeedsAnimate()) from CompositorViewHolder when the
    top control offset changes is unnecessary, since this is a
    renderer-driven animation (causes an invalidation in the browser
    compositor tree), so will already cause the necessary
    UpdateLayerTreeHost(). Requesting SetNeedsAnimate()
    causes an extra BeginMainFrame() (SingleThreadProxy+scheduler
    are not particularly good at tracking these between needs_commit
    and needs_animate) and puts us into high latency mode otherwise.
    Fileed bug  crbug.com/602489  to make this more robust in
    SingleThreadProxy and scheduler.

TBR=dtrainor@chromium.org
BUG= 591725 , 602489 , 602485 , 604007 

Review URL: https://codereview.chromium.org/1879833002

Cr-Commit-Position: refs/heads/master@{#389248}
Commit  : 6414a4526b77dd087581d8a9c1cec50affc66333
Date    : Fri Apr 22 21:34:42 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@389241         18.186701   0.16032     12          good
chromium@389245         18.175835   0.108114    8           good
chromium@389247         18.152087   0.135831    5           good
chromium@389248         19.320142   0.463929    8           bad         <-
chromium@389254         19.283257   0.61726     5           bad
chromium@389267         19.138223   0.683429    8           bad
chromium@389292         19.299694   0.688139    12          bad
chromium@389343         19.163483   0.546408    9           bad

Bisect job ran on: android_one_perf_bisect
Bug ID: 606250

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests smoothness.top_25_smooth
Test Metric: frame_times/LinkedIn
Relative Change: 4.84%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1286
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9014341600795302832


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5892503945871360

| 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!

Moving this nonessential bug to the next milestone.

For more details visit https://www.chromium.org/issue-tracking/autotriage - Your friendly Sheriffbot

This issue has been moved once and is lower than Pri-1. Removing the milestone.

For more details visit https://www.chromium.org/issue-tracking/autotriage - Your friendly Sheriffbot

Related to 591725 and 604007