Issue metadata
Sign in to add a comment
|
3.3%-38.3% regression in timeToFirst{Meaningful,Contentful}Paint at 503941:504150 |
||||||||||||||||||||
Issue descriptionBoth in system_health.common_mobile and system_health.common_desktop
,
Oct 2 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8966811558907274688
,
Oct 3 2017
=== BISECT JOB RESULTS ===
Bisect failed unexpectedly
Bisect was aborted with the following:
Step('Check bisect finished on revision chromium@503978.fetch file b11a5c74b938f4dc7fb657d3c8fc791820aeb257:DEPS') failed with return_code 1
Bisect Details
Configuration: android_nexus7_perf_bisect
Benchmark : system_health.common_mobile
Metric : timeToFirstContentfulPaint_avg/long_running_tools/long_running_tools_gmail-background
Revision Result N
chromium@503974 831.89 +- 76.9982 9 good
chromium@503977 861.341 +- 326.51 9 good
chromium@503978 835.464 +- 34.2973 6 good
chromium@503979 1095.87 +- 76.3721 9 bad
chromium@503984 1101.29 +- 108.776 6 bad
chromium@503994 1114.62 +- 117.105 6 bad
chromium@504014 1140.37 +- 322.012 6 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=long.running.tools.gmail.background system_health.common_mobile
More information on addressing performance regressions:
http://g.co/ChromePerformanceRegressions
Debug information about this bisect:
https://chromeperf.appspot.com/buildbucket_job_status/8966811558907274688
For feedback, file a bug with component Speed>Bisection
,
Oct 3 2017
Kicked another bisect. FYI, the regression coincides with ~25% improvements in system_health.common_desktop/story:power_avg.
,
Oct 3 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8966742147556387216
,
Oct 3 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8966742129895123152
,
Oct 3 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8966742111114956784
,
Oct 3 2017
=== Auto-CCing suspected CL author ksakamoto@chromium.org === Hi ksakamoto@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 : ksakamoto Commit : a8018a6284d053d1c80ee0119ee33bd80ff7fae9 Date : Mon Sep 25 03:24:44 2017 Subject: Update error page URL in loading_metric blacklist Bisect Details Configuration: android_nexus5X_perf_bisect Benchmark : system_health.common_mobile Metric : timeToFirstContentfulPaint_avg/background_tools/background_tools_gmail Change : 30.45% | 445.006166667 -> 580.499388889 Revision Result N chromium@503964 445.006 +- 20.0582 6 good chromium@503973 449.871 +- 19.762 6 good chromium@503978 448.249 +- 22.4463 6 good chromium@503978,catapult@a8018a6284 584.594 +- 28.3357 6 bad <-- chromium@503979 578.312 +- 18.2126 6 bad chromium@503980 574.377 +- 39.6771 6 bad chromium@503982 580.499 +- 65.7335 6 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=background.tools.gmail system_health.common_mobile More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8966742111114956784 For feedback, file a bug with component Speed>Bisection
,
Oct 3 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : ksakamoto Commit : a8018a6284d053d1c80ee0119ee33bd80ff7fae9 Date : Mon Sep 25 03:24:44 2017 Subject: Update error page URL in loading_metric blacklist Bisect Details Configuration: mac_10_12_perf_bisect Benchmark : system_health.common_desktop Metric : timeToFirstMeaningfulPaint_avg/load_tools/load_tools_gmail Change : 25.59% | 482.994750006 -> 606.605833328 Revision Result N chromium@503964 482.995 +- 106.238 6 good chromium@503973 477.083 +- 71.6202 6 good chromium@503977 475.75 +- 59.3239 6 good chromium@503978 485.68 +- 43.4887 6 good chromium@503978,catapult@a8018a6284 616.668 +- 49.24 6 bad <-- chromium@503979 592.357 +- 86.471 6 bad chromium@503981 606.606 +- 85.5189 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=load.tools.gmail system_health.common_desktop More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8966742129895123152 For feedback, file a bug with component Speed>Bisection
,
Oct 3 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : ksakamoto Commit : a8018a6284d053d1c80ee0119ee33bd80ff7fae9 Date : Mon Sep 25 03:24:44 2017 Subject: Update error page URL in loading_metric blacklist Bisect Details Configuration: win_x64_perf_bisect Benchmark : system_health.common_desktop Metric : timeToFirstMeaningfulPaint_avg/load_tools/load_tools_gmail Change : 31.45% | 1177.858875 -> 1548.25394444 Revision Result N chromium@503978 1177.86 +- 117.106 6 good chromium@503978,catapult@a8018a6284 1520.27 +- 669.354 6 bad <-- chromium@503979 1635.48 +- 1211.08 6 bad chromium@503980 1644.12 +- 1083.06 6 bad chromium@503981 1518.56 +- 329.06 6 bad chromium@503983 1689.49 +- 1358.54 6 bad chromium@503988 1624.17 +- 1016.09 6 bad chromium@503998 1585.57 +- 586.596 6 bad chromium@504017 1548.25 +- 382.471 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 More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8966742147556387216 For feedback, file a bug with component Speed>Bisection
,
Oct 4 2017
This is expected, that CL fixed a bug of loading metric. |
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Oct 2 2017