Issue metadata
Sign in to add a comment
|
3.9%-268.8% regression in loading.desktop at 489888:490089 |
||||||||||||||||||||||
Issue descriptionMost likely caused by switching WPRGo on. The change causes some sites to be served on HTTP/2 instead of HTTP 1.0 which may be affecting these. i.e., issue 750299
,
Jul 31 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972531659246193648
,
Jul 31 2017
nvm #1, WPRGo was enabled for mobile system health in that range so probably unrelated.
,
Aug 1 2017
=== 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: 16aacd97378a2956fc6ac97a173d3c78dc8e5038 bad_revision : dde1afca9fb6b691f8bdc42a92051a7d1ccdcbda If failures persist contact the team (see below) and report the error. Bisect Details Configuration: mac_10_12_mini_8gb_perf_bisect Benchmark : loading.desktop Metric : timeToFirstMeaningfulPaint_avg/pcv1-cold/FarsNews Revision Result N chromium@489887 1233.39 +- 2767.75 9 good chromium@489921 831.52 +- 214.197 5 good chromium@489938 953.367 +- 634.398 6 good chromium@489947 3729.84 +- 2139.64 6 bad chromium@489955 3203.65 +- 4144.31 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=FarsNews loading.desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8972531659246193648 For feedback, file a bug with component Speed>Bisection
,
Aug 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970612943720663616
,
Aug 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970612940477266464
,
Aug 21 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970612929084186464
,
Aug 22 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Ken Buchanan Commit : aaf6b58123e9bc49391a8f8cfe057b7c3269e9ef Date : Thu Jul 27 15:46:12 2017 Subject: Ensure overlapping compositor locks can time out Bisect Details Configuration: mac_air_perf_bisect Benchmark : loading.desktop Metric : cpuTimeToFirstMeaningfulPaint_avg/pcv1-warm/Haraj Change : 87.27% | 214.995166667 -> 402.617166667 Revision Result N chromium@489897 214.995 +- 6.63926 6 good chromium@489920 216.9 +- 7.25847 6 good chromium@489932 214.882 +- 9.82069 6 good chromium@489938 219.565 +- 23.7172 6 good chromium@489941 215.671 +- 7.93292 6 good chromium@489942 374.028 +- 170.752 6 bad <-- chromium@489943 372.118 +- 167.614 6 bad chromium@489988 372.872 +- 169.319 6 bad chromium@490078 402.617 +- 12.3235 6 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=Haraj loading.desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8970612943720663616 For feedback, file a bug with component Speed>Bisection
,
Aug 22 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: mac_air_perf_bisect Benchmark : loading.desktop Metric : timeToFirstMeaningfulPaint_avg/pcv1-cold/ArsTechnica Revision Result N chromium@489897 458.533 +- 219.867 21 good chromium@490078 551.258 +- 611.573 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=ArsTechnica loading.desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8970612940477266464 For feedback, file a bug with component Speed>Bisection
,
Aug 22 2017
=== 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: 16aacd97378a2956fc6ac97a173d3c78dc8e5038 bad_revision : dde1afca9fb6b691f8bdc42a92051a7d1ccdcbda If failures persist contact the team (see below) and report the error. Bisect Details Configuration: mac_10_12_mini_8gb_perf_bisect Benchmark : loading.desktop Metric : timeToFirstMeaningfulPaint_avg/pcv1-cold/FarsNews Revision Result N chromium@489887 1041.13 +- 854.036 9 good chromium@489921 1095.81 +- 863.867 9 good chromium@489938 1267.76 +- 3373.08 9 good chromium@489947 3521.14 +- 4100.07 14 bad chromium@489955 3657.57 +- 2903.99 8 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=FarsNews loading.desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8970612929084186464 For feedback, file a bug with component Speed>Bisection |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Jul 31 2017