New issue
Advanced search Search tips

Issue 710526 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
Closed: Apr 2017
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

7.4%-515.4% regression in media.tough_video_cases memory usage for ogv and webm at 463171:463205

Project Member Reported by crouleau@chromium.org, Apr 11 2017

Issue description

See the link to graphs below.
 
Cc: johnchen@chromium.org
Components: Internals>Media
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Apr 18 2017


=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : vm_working_set_delta_size/garden2_10s.webm_gpu

Revision             Result                  N
chromium@463170      22478.4 +- 302.319      21      good
chromium@463267      22518.8 +- 241.42       21      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/8982041732571290336

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5837705998499840


| 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!
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Apr 18 2017

Cc: stkhapugin@chromium.org
Owner: stkhapugin@chromium.org

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

Hi stkhapugin@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 : stkhapugin
  Commit : b32bd33d9cc8fe5878699aec420309bdabaaec7e
  Date   : Mon Apr 10 12:44:39 2017
  Subject: [ObjC ARC] Converts ios/public/provider/chrome/browser/user_feedback:test_support to ARC.

Bisect Details
  Configuration: winx64intel_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : vm_working_set_delta_size/garden2_10s.webm_gpu
  Change       : 0.31% | 22461.0 -> 22530.6666667

Revision             Result                  N
chromium@463170      22461.0 +- 240.179      14      good
chromium@463219      22425.3 +- 346.936      14      good
chromium@463230      22415.8 +- 146.163      9       good
chromium@463233      22437.3 +- 79.0274      6       good
chromium@463234      22517.3 +- 224.403      14      bad       <--
chromium@463235      22512.9 +- 212.861      14      bad
chromium@463238      22546.2 +- 141.829      9       bad
chromium@463243      22514.0 +- 156.128      14      bad
chromium@463267      22530.7 +- 126.965      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/8982016492776703024

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5837705998499840


| 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!
Cc: -stkhapugin@chromium.org
Owner: ----
This perf test regression on a windows configuration shouldn't be related to an iOS CL.  
Cc: -crouleau@google.com
Owner: crouleau@google.com
Status: Assigned (was: Untriaged)
as per c#8, assign back to crouleau@ to check windows configuration on repro device.
Status: WontFix (was: Assigned)
Thanks Yining.

Bisect isn't working correctly, so we're just going to have to WontFix this one. The new bisect tool, Pinpoint, should be able to help with this kind of scenario in the future.

Sign in to add a comment