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

Issue 698039 link

Starred by 2 users

Issue metadata

Status: Assigned
Owner:
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

A zero-to-nonzero regression in media.tough_video_cases at 453212:453346

Project Member Reported by tguilbert@chromium.org, Mar 2 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=698039

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpIW6sgkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpIW6sgoM


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

chromium-rel-win7-gpu-intel
Cc: ericrk@chromium.org
Owner: ericrk@chromium.org

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

Hi ericrk@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : ericrk
  Commit : 028009c724049003f9e3e25cbcaef43f26bf59c8
  Date   : Mon Feb 27 21:09:16 2017
  Subject: Remove OS level filter from Windows GPU raster blacklist

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : dropped_frame_count/crowd720_vp9.webm

Revision             Result                    N
chromium@453211      0.0 +- 0.0                9      good
chromium@453279      0.0 +- 0.0                9      good
chromium@453313      0.0 +- 0.0                9      good
chromium@453330      0.0 +- 0.0                9      good
chromium@453332      0.0 +- 0.0                9      good
chromium@453333      0.0 +- 0.0                9      good
chromium@453334      0.666667 +- 1.41421       9      bad       <--
chromium@453338      0.833333 +- 0.912871      6      bad
chromium@453346      0.666667 +- 1.41421       9      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8986197140628585424

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5814592434864128


| 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 Speed>Bisection.  Thank you!

Comment 4 by ericrk@chromium.org, Mar 10 2017

Owner: jbau...@chromium.org
Status: Assigned (was: Untriaged)
Seems like an interaction between video and GPU raster. jbauman@, if you have some time, can you take a look? Otherwise assign back to me and I'll get to it in the next week or two. Thanks!
Cc: jbau...@chromium.org
Owner: ericrk@chromium.org
Oops, completely forgot about this
It seems like the issue is still ongoing. Is there anything that can be done?

Sign in to add a comment