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

Issue 761936 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
OOO until 2019-02-10
Closed: Oct 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

95.7%-99.6% regression in v8.runtimestats.browsing_desktop at 499208:499284

Project Member Reported by petermarshall@chromium.org, Sep 5 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=761936

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=37b57863686391200382a6c019418c557f93481737d85c9c180e55fca49e0f7b


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

chromium-rel-win7-dual

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_tech/browse_tech_discourse_infinite_scroll

Revision             Result                  N
chromium@499207      12.9032 +- 7.73702      21      good
chromium@499284      12.0277 +- 7.15895      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.tech.discourse.infinite.scroll 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/8969305350981642928


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_media/browse_media_flickr_infinite_scroll

Revision             Result                  N
chromium@499207      9.18176 +- 4.91138      21      good
chromium@499284      9.97695 +- 6.81624      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.flickr.infinite.scroll 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/8969283843835472288


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_tech/browse_tech_discourse_infinite_scroll

Revision             Result                  N
chromium@499123      11.6467 +- 6.22022      21      good
chromium@499406      11.5838 +- 5.99307      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.tech.discourse.infinite.scroll 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/8969283815070230832


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_media/browse_media_flickr_infinite_scroll

Revision             Result                 N
chromium@498391      12.396 +- 9.42306      21      good
chromium@499527      11.297 +- 8.42769      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.flickr.infinite.scroll 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/8969198795332422048


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_tech/browse_tech_discourse_infinite_scroll

Revision             Result                  N
chromium@499207      11.4959 +- 7.2387       21      good
chromium@499284      11.7136 +- 7.45179      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.tech.discourse.infinite.scroll 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/8969175039668285232


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_media/browse_media_flickr_infinite_scroll

Revision             Result                  N
chromium@499207      11.6145 +- 7.21425      21      good
chromium@499284      11.3155 +- 10.1799      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.flickr.infinite.scroll 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/8969175011773555264


For feedback, file a bug with component Speed>Bisection

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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_search/browse_search_google_india

Revision             Result                  N
chromium@499207      3.13214 +- 9.03411      21      good
chromium@499284      3.42786 +- 3.06853      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.search.google.india 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/8969174996939751696


For feedback, file a bug with component Speed>Bisection
Cc: kmarshall@chromium.org
Owner: kmarshall@chromium.org
Status: Assigned (was: Untriaged)

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

Hi kmarshall@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 : Kevin Marshall
  Commit : dc4c6c9095ed380ecdbd21f7a5dc1ccb252c3852
  Date   : Wed Aug 30 17:01:03 2017
  Subject: Fuchsia: modify Fuchsia runner GN templs to emit exe's runtime_deps.

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : v8-gc-incremental-step_max/browse_tech/browse_tech_discourse_infinite_scroll
  Change       : 21.73% | 12.5404444444 -> 10.1526666667

Revision             Result                  N
chromium@497755      12.5404 +- 3.87042      9       good
chromium@498194      12.0498 +- 3.95533      14      good
chromium@498412      11.9789 +- 3.39622      14      good
chromium@498468      12.2297 +- 4.22183      14      good
chromium@498496      12.4919 +- 3.41002      14      good
chromium@498499      11.9772 +- 3.54762      9       good
chromium@498501      11.8454 +- 3.31218      9       good
chromium@498502      9.194 +- 3.25242        6       bad       <--
chromium@498507      11.2684 +- 5.89744      21      bad
chromium@498524      10.5654 +- 5.16914      14      bad
chromium@498632      10.8662 +- 5.01947      14      bad
chromium@499509      10.1527 +- 5.89736      9       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.tech.discourse.infinite.scroll 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/8969198822189907584


For feedback, file a bug with component Speed>Bisection
Owner: petermarshall@chromium.org
The guess doesn't seem right? My CL should have no effect on Windows builds. Could there have been any changes in the build or runtime environments that happened at the same time?
Status: WontFix (was: Assigned)
Yeah I can't see how your CL could be at fault here. I'll close, as the graphs all seem to have returned to normal (with noise), and the bisect doesn't provide any help, so there's nothing more to do.

Sign in to add a comment