New issue
Advanced search Search tips

Issue 768292 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 768063
Owner: ----
Closed: Sep 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

12.2%-86.2% regression in v8.runtimestats.browsing_desktop at 503495:503661

Project Member Reported by mlippautz@chromium.org, Sep 25 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Sep 25 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=768292

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=db25cddc25aeec36e5bd8b807e32306c960f548effa912b6e59a365860fa72c4


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

chromium-rel-mac-retina
chromium-rel-mac11
chromium-rel-mac12-mini-8gb
chromium-rel-win7-dual
chromium-rel-win7-gpu-ati
chromium-rel-win8-dual
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Sep 25 2017


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-total_avg/browse_news/browse_news_nytimes

Revision             Result                  N
chromium@503499      1.90254 +- 1.52354      21      good
chromium@503599      1.76969 +- 1.84941      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=browse.news.nytimes v8.runtimestats.browsing_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967498746289030304


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Sep 29 2017


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

Bisect Details
  Configuration: win_x64_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-start_sum/browse_media/browse_media_tumblr

Revision             Result                   N
chromium@503575      1.16743 +- 0.573056      21      good
chromium@503621      1.11133 +- 0.697619      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=browse.media.tumblr v8.runtimestats.browsing_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967132646284541392


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Sep 29 2017


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

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-total_avg/browse_media/browse_media_youtube

Revision             Result                    N
chromium@503494      0.632492 +- 0.143754      21      good
chromium@503656      0.641812 +- 0.151406      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=browse.media.youtube v8.runtimestats.browsing_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967132630432983248


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, Sep 29 2017

Mergedinto: 768063
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Ulan Degenbaev
  Commit : a76d0a771e430dbc8716624febc549aede738d96
  Date   : Thu Sep 21 12:35:10 2017
  Subject: Reland "[heap] Enable concurrent marking for x86 and x64."

Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-total_avg/browse_media/browse_media_tumblr
  Change       : 36.47% | 0.383988088585 -> 0.524046122285

Revision                           Result                     N
chromium@503437                    0.383988 +- 0.0308315      6      good
chromium@503483                    0.396194 +- 0.0568283      6      good
chromium@503489                    0.39306 +- 0.0380025       6      good
chromium@503491                    0.390644 +- 0.0662109      6      good
chromium@503491,v8@2857dab5cb      0.389916 +- 0.0657926      6      good
chromium@503491,v8@a76d0a771e      0.498697 +- 0.0437034      6      bad       <--
chromium@503492                    0.503197 +- 0.0985684      6      bad
chromium@503495                    0.516288 +- 0.063578       6      bad
chromium@503506                    0.490345 +- 0.0514476      6      bad
chromium@503529                    0.514486 +- 0.118622       6      bad
chromium@503620                    0.524046 +- 0.109462       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=browse.media.tumblr v8.runtimestats.browsing_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967132624057412720


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 11 by 42576172...@developer.gserviceaccount.com, Sep 29 2017


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

Suspected Commit
  Author : Ulan Degenbaev
  Commit : a76d0a771e430dbc8716624febc549aede738d96
  Date   : Thu Sep 21 12:35:10 2017
  Subject: Reland "[heap] Enable concurrent marking for x86 and x64."

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-start_avg/browse_media/browse_media_pinterest
  Change       : 40.48% | 0.214653835979 -> 0.301549764653

Revision                           Result                     N
chromium@503455                    0.214654 +- 0.507193       21      good
chromium@503480                    0.143244 +- 0.0515578      14      good
chromium@503486                    0.205984 +- 0.507715       21      good
chromium@503489                    0.160288 +- 0.173238       9       good
chromium@503491                    0.218711 +- 0.577381       14      good
chromium@503491,v8@2857dab5cb      0.16387 +- 0.141443        6       good
chromium@503491,v8@a76d0a771e      0.286424 +- 0.675908       21      bad       <--
chromium@503492                    0.250906 +- 0.243394       14      bad
chromium@503504                    0.319177 +- 0.830139       21      bad
chromium@503553                    0.30155 +- 0.91087         21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=browse.media.pinterest v8.runtimestats.browsing_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967132618533650512


For feedback, file a bug with component Speed>Bisection

Sign in to add a comment