New issue
Advanced search Search tips

Issue 737391 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 737394
Owner: ----
Closed: Jun 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

23.4%-25.7% regression in system_health.common_desktop at 481734:481815

Project Member Reported by sullivan@chromium.org, Jun 28 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jun 28 2017


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

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/load_news/load_news_hackernews

Revision             Result                  N
chromium@481733      1655.76 +- 5082.4       21      good
chromium@481815      2353.25 +- 10722.5      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 --story-filter=load.news.hackernews system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975579953238933856

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6155000289427456


| 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!
This is pretty noisy, and only on one bot. Kicked off another bisect, may close if it doesn't repro.
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Jun 28 2017


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

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/load_news/load_news_hackernews

Revision             Result                  N
chromium@481733      1819.21 +- 6960.49      21      good
chromium@481815      2551.36 +- 12739.3      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 --story-filter=load.news.hackernews system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975573666233500272

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6155000289427456


| 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 8 by 42576172...@developer.gserviceaccount.com, Jun 28 2017


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

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/load_search/load_search_google

Revision             Result                  N
chromium@481733      1733.37 +- 5599.56      21      good
chromium@481815      1900.61 +- 6710.49      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 --story-filter=load.search.google system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975572993243847840

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5004519211008000


| 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 10 by 42576172...@developer.gserviceaccount.com, Jun 28 2017


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

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/load_search/load_search_google

Revision             Result                  N
chromium@481733      1793.17 +- 5838.52      21      good
chromium@481815      1686.14 +- 4192.95      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 --story-filter=load.search.google system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975566115249280528

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5004519211008000


| 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!
Tried a bisect on a wider range.
Project Member

Comment 13 by 42576172...@developer.gserviceaccount.com, Jun 28 2017

Mergedinto: 737394
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Alexandr Ilin
  Commit : db57d232f21b4f2b09c362d6fabeb2a2286cd863
  Date   : Thu Jun 22 20:39:52 2017
  Subject: predictors: Replace BrowserThread::DB with TaskScheduler API.

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstMeaningfulPaint_avg/load_search/load_search_google
  Change       : 41.40% | 1367.40121429 -> 1547.109

Revision             Result                  N
chromium@481632      1367.4 +- 4493.1        14      good
chromium@481644      1115.46 +- 1083.39      9       good
chromium@481650      1116.92 +- 906.825      9       good
chromium@481653      1196.15 +- 1997.38      9       good
chromium@481654      1458.9 +- 2447.7        9       bad       <--
chromium@481655      1211.39 +- 556.0        21      bad
chromium@481678      1209.63 +- 739.496      21      bad
chromium@481724      1390.09 +- 2469.7       14      bad
chromium@481815      1547.11 +- 1885.6       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 --story-filter=load.search.google system_health.common_desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975515842224352128

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4539974340313088


| 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