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

Issue 704325 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 704329
Owner: ----
Closed: Mar 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

47.4%-127.5% regression in system_health.common_desktop at 458173:458311

Project Member Reported by jasontiller@chromium.org, Mar 22 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Mar 23 2017


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

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : loading.mobile
  Metric       : timeToFirstMeaningfulPaint_avg/Regular-3G/https___www.pokedex.org_

Revision             Result                  N
chromium@458242      4124.34 +- 981.47       21      good
chromium@458284      4212.32 +- 1520.15      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=https...www.pokedex.org. loading.mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8984381532716931808

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6341281808121856


| 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 6 by 42576172...@developer.gserviceaccount.com, Mar 23 2017

Mergedinto: 704329
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : ericrk
  Commit : 45b88dc78af5c27d0cd462889fe44b62e313a189
  Date   : Mon Mar 20 21:38:21 2017
  Subject: Enable GPU Raster on all GCN1+ Cards

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/load_tools/load_tools_gmail
  Change       : 93.14% | 779.269277778 -> 1505.04344444

Revision             Result                  N
chromium@458172      779.269 +- 121.352      6      good
chromium@458189      809.502 +- 295.015      6      good
chromium@458193      790.495 +- 109.534      6      good
chromium@458195      775.127 +- 121.011      6      good
chromium@458196      895.781 +- 408.953      6      good
chromium@458197      1383.76 +- 540.396      6      bad       <--
chromium@458205      1337.27 +- 425.061      6      bad
chromium@458237      1331.39 +- 398.43       6      bad
chromium@458302      1505.04 +- 818.618      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 --story-filter=load.tools.gmail system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8984374625135884544

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6415050018914304


| 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, Mar 23 2017


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

Suspected Commit
  Author : ericrk
  Commit : 45b88dc78af5c27d0cd462889fe44b62e313a189
  Date   : Mon Mar 20 21:38:21 2017
  Subject: Enable GPU Raster on all GCN1+ Cards

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/load_tools/load_tools_drive
  Change       : 46.08% | 922.222444444 -> 1347.16994444

Revision             Result                  N
chromium@458172      922.222 +- 425.837      9      good
chromium@458189      924.478 +- 404.253      9      good
chromium@458193      857.668 +- 108.025      6      good
chromium@458195      945.183 +- 219.647      6      good
chromium@458196      899.037 +- 59.3233      6      good
chromium@458197      1318.33 +- 350.42       6      bad       <--
chromium@458205      1308.14 +- 302.923      6      bad
chromium@458237      1302.43 +- 305.361      6      bad
chromium@458302      1347.17 +- 376.94       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 --story-filter=load.tools.drive system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8984374619126643856

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6373444402282496


| 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