New issue
Advanced search Search tips

Issue 652797 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 652670
Owner: ----
Closed: Oct 2016
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

16.5% regression in smoothness.key_desktop_move_cases at 422483:422541

Project Member Reported by tdres...@chromium.org, Oct 4 2016

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=652797

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg1bzRoQoM


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

chromium-rel-win7-x64-dual
Mergedinto: 652670
Status: Duplicate (was: Untriaged)

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


===== SUSPECTED CL(s) =====
Subject : Revert of Move synthetic gesture input to be aligned with BeginFrame. (patchset #2 id:20001 of https://codereview.chromium.org/2372873003/ )
Author  : dtapuska
Commit description:
  
Reason for revert:
Appears RenderWidgetHostViewChildFrame ends up calling a virtual during the constructor and this isn't getting called. This is an existing bug.

But the change in this CL reveals this bug so reverting this change for now.

Original issue's description:
> Move synthetic gesture input to be aligned with BeginFrame.
>
> The timing of synthetic events seems almost random. It is best to align
> it with something that doesn't fluctuate. Android already rAF aligns its
> synthetic input so do this for aura and mac as well.
>
> BUG= 646369 
>
> Committed: https://crrev.com/5248d2a4cc2ac706f0404b6c6edf196f5b491539
> Cr-Commit-Position: refs/heads/master@{#421528}

TBR=sadrul@chromium.org
# Not skipping CQ checks because original CL landed more than 1 days ago.
BUG= 646369 

Review-Url: https://codereview.chromium.org/2390813002
Cr-Commit-Position: refs/heads/master@{#422509}
Commit  : dfb4211ebbd9934c01cca376edf70fe44daa381f
Date    : Mon Oct 03 20:23:19 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev   N  Good?
chromium@422482  18.4498  0.488318  5  good
chromium@422497  18.3744  0.26506   5  good
chromium@422505  18.1536  0.174471  5  good
chromium@422507  18.4749  0.275825  5  good
chromium@422508  18.5227  0.104164  5  good
chromium@422509  20.7122  0.154301  5  bad    <--
chromium@422512  21.0602  0.503175  5  bad
chromium@422541  20.9582  0.362526  5  bad

Bisect job ran on: win_x64_perf_bisect
Bug ID: 652797

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests smoothness.key_desktop_move_cases
Test Metric: mean_frame_time/mean_frame_time
Relative Change: 13.60%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_x64_perf_bisect/builds/1494
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8999707215119864400


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5837298283839488

| 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!

Sign in to add a comment