New issue
Advanced search Search tips

Issue 699775 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 697879
Owner:
Closed: Mar 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

28.4% regression in media.tough_video_cases at 454741:454950

Project Member Reported by liberato@google.com, Mar 8 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=699775

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDglJ_zqgkM


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

chromium-rel-win10

=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

Error: INFRA_FAILURE

The bisect was able to narrow the range, you can try running with:
  good_revision: a5dfa06213d12fcabc014e6eacb73c199fd5a53e
  bad_revision : a35616e32425b2ff9d044bdc705ccc3542077b51

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : vm_working_set_delta_size/tulip2.mp3_renderer

Revision                           Result                  N
chromium@454740                    1919.33 +- 418.011      6      good
chromium@454790                    1900.0 +- 187.702       6      good
chromium@454793                    1908.0 +- 405.719       6      good
chromium@454793,v8@2362f869a4      1926.67 +- 230.802      6      good
chromium@454793,v8@08d84f6d23      1892.67 +- 266.618      6      good
chromium@454793,v8@a5dfa06213      1992.67 +- 423.147      6      good
chromium@454793,v8@a35616e324      2479.33 +- 162.423      6      bad
chromium@454793,v8@a6b20adbf9      2688.67 +- 331.272      6      bad
chromium@454793,v8@59c9e6ff69      2694.67 +- 253.151      6      bad
chromium@454794                    2560.67 +- 252.819      6      bad
chromium@454795                    2604.0 +- 207.846       6      bad
chromium@454796                    2670.67 +- 260.379      6      bad
chromium@454802                    2693.33 +- 140.93       6      bad
chromium@454812                    2662.67 +- 295.062      6      bad
chromium@454833                    2610.0 +- 408.029       6      bad
chromium@454950                    2588.67 +- 290.732      6      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/8985647773935677136

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5212813796048896


| 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 5 by 42576172...@developer.gserviceaccount.com, Mar 11 2017

Mergedinto: 697879
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Toon Verwaest
  Commit : 6477f0777f57736411a02837301451ffb0e349ff
  Date   : Tue Feb 28 14:08:05 2017
  Subject: [api] Mark api prototypes as prototype before configuring them

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : vm_working_set_delta_size/tulip2.mp3_renderer
  Change       : 28.25% | 1956.66666667 -> 2509.33333333

Revision                           Result                  N
chromium@454740                    1956.67 +- 482.839      6      good
chromium@454793                    1818.67 +- 252.011      6      good
chromium@454793,v8@2362f869a4      1908.67 +- 305.02       6      good
chromium@454793,v8@08d84f6d23      1939.33 +- 353.832      6      good
chromium@454793,v8@a5dfa06213      1958.0 +- 383.865       6      good
chromium@454793,v8@6477f0777f      2537.33 +- 282.258      6      bad       <--
chromium@454793,v8@a35616e324      2544.0 +- 185.041       6      bad
chromium@454793,v8@a6b20adbf9      2590.67 +- 259.086      6      bad
chromium@454793,v8@59c9e6ff69      2659.33 +- 202.34       6      bad
chromium@454794                    2633.33 +- 200.852      6      bad
chromium@454795                    2710.67 +- 196.747      6      bad
chromium@454797                    2674.67 +- 287.87       6      bad
chromium@454800                    2636.0 +- 255.937       6      bad
chromium@454806                    2598.0 +- 309.722       6      bad
chromium@454819                    2658.67 +- 194.539      6      bad
chromium@454845                    2567.33 +- 219.557      6      bad
chromium@454950                    2509.33 +- 157.243      6      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/8985491271611551120

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6169927662174208


| 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 11 2017

Cc: verwa...@chromium.org
Owner: verwa...@chromium.org

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

Hi verwaest@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 : Toon Verwaest
  Commit : 6477f0777f57736411a02837301451ffb0e349ff
  Date   : Tue Feb 28 14:08:05 2017
  Subject: [api] Mark api prototypes as prototype before configuring them

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : vm_working_set_delta_size/tulip2.mp3_renderer
  Change       : 38.78% | 1875.33333333 -> 2602.66666667

Revision                           Result                  N
chromium@454740                    1875.33 +- 344.298      6      good
chromium@454793                    1917.33 +- 267.233      6      good
chromium@454793,v8@2362f869a4      1855.33 +- 195.585      6      good
chromium@454793,v8@08d84f6d23      1978.67 +- 279.867      6      good
chromium@454793,v8@a5dfa06213      1994.0 +- 189.631       6      good
chromium@454793,v8@6477f0777f      2592.0 +- 238.126       6      bad       <--
chromium@454793,v8@a35616e324      2535.33 +- 421.1        6      bad
chromium@454793,v8@a6b20adbf9      2596.0 +- 213.016       6      bad
chromium@454793,v8@59c9e6ff69      2757.33 +- 224.618      6      bad
chromium@454794                    2696.0 +- 337.331       6      bad
chromium@454795                    2610.67 +- 177.779      6      bad
chromium@454797                    2635.33 +- 334.253      6      bad
chromium@454800                    2542.67 +- 305.557      6      bad
chromium@454806                    2625.33 +- 120.355      6      bad
chromium@454819                    2638.0 +- 242.107       6      bad
chromium@454845                    2521.33 +- 457.425      6      bad
chromium@454950                    2602.67 +- 250.546      6      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/8982651832089021088

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5212813796048896


| 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!

Sign in to add a comment