New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 629195 link

Starred by 2 users

Issue metadata

Status: WontFix
Owner:
Last visit > 30 days ago
Closed: Oct 2016
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

12.7% regression in blink_perf.canvas at 404915:404948

Project Member Reported by m...@chromium.org, Jul 18 2016

Issue description

Probably due to this commit:

commit	892c18d6f403629c7ba584e37d150f2334baa80c	
author	junov <junov@chromium.org>	Wed Jul 13 02:39:05 2016
committer	Commit bot <commit-bot@chromium.org>	Wed Jul 13 02:41:14 2016
Temporarily disabling 2d canvas getImageData optimization
 

Comment 1 by m...@chromium.org, Jul 18 2016

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=629195

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgioDEpQkM


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

chromium-rel-mac10
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jul 18 2016

Cc: junov@chromium.org

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

Hi junov@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 : Temporarily disabling 2d canvas getImageData optimization
Author  : junov
Commit description:
  
Disabling the optimization that makes getImageData disable
GPU acceleration in order to resolve a memory error.

BUG=626188, 627434 

Review-Url: https://codereview.chromium.org/2144573003
Cr-Commit-Position: refs/heads/master@{#404919}
Commit  : 892c18d6f403629c7ba584e37d150f2334baa80c
Date    : Wed Jul 13 02:41:14 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev   N  Good?
chromium@404914  455.778  0.641585  5  good
chromium@404917  454.087  2.18149   5  good
chromium@404918  455.764  1.41994   5  good
chromium@404919  399.731  2.03898   5  bad    <--
chromium@404923  399.634  1.52158   5  bad
chromium@404931  398.976  1.75094   5  bad
chromium@404948  397.136  2.17542   5  bad

Bisect job ran on: mac_10_10_perf_bisect
Bug ID: 629195

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.canvas
Test Metric: putImageData/putImageData
Relative Change: 12.87%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_10_perf_bisect/builds/2213
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9006766373794615424


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5833496342298624

| 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!
Seems like this was known to cause a regression. junov, any purpose for us to keep this open?
Perf sheriff ping: reminder to follow up on possible performance issues

Comment 6 by junov@chromium.org, Oct 6 2016

Status: WontFix (was: Assigned)
Performance recovered with this commit, which re-nable the optimization that was disabled by the culprit CL.
https://chromium.googlesource.com/chromium/src/+/e56410217e3d336d0c2d1dbc442180aefba935c5

Sign in to add a comment