Regression in v8-gc-total_percentage_in_v8_execute_avg |
||
Issue descriptionThe metric regressed at Chromium Commit Position range: 441101 - 441116 Chromium Git Hash range: 5d19cfe - 5fb9af5
,
Jan 9 2017
Most likely caused by 5e37ec3 Move bindings timers to frame-specific task runners. 124814c Use timer task runner for V8PerIsolate tasks https://chromium.googlesource.com/chromium/src/+log/5d19cfe16c85bb15280dcc5594282bb037b74ad1..5fb9af565efc05fe461fb27117a5419a6f04de69
,
Jan 9 2017
=== BISECT JOB RESULTS === NO Perf regression found Bisect Details Configuration: win_perf_bisect Benchmark : v8.infinite_scroll_tbmv2 Metric : v8-gc-total_percentage_in_v8_execute_avg/v8-gc-total_percentage_in_v8_execute_avg Revision Result N chromium@441100 0.218405 +- 0.672646 30 good chromium@441116 0.357761 +- 1.66411 30 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 v8.infinite_scroll_tbmv2 Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8990935458620462592 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5853755347566592 | 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 Tests>AutoBisect. Thank you!
,
Jan 9 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8990926750500661936
,
Jan 9 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : altimin Commit : 124814c8025c564a6f494a3c9d4c887d57b98f1e Date : Tue Jan 03 14:09:53 2017 Subject: Use timer task runner for V8PerIsolate tasks Bisect Details Configuration: win_perf_bisect Benchmark : v8.infinite_scroll_tbmv2 Metric : v8-gc-total_percentage_in_v8_execute_avg/flickr Change : 126.22% | 0.343489990315 -> 0.777034711433 Revision Result N chromium@441100 0.34349 +- 0.171079 6 good chromium@441108 0.28752 +- 0.21107 6 good chromium@441112 0.412539 +- 0.221537 6 good chromium@441113 0.31052 +- 0.180102 6 good chromium@441114 0.833436 +- 0.327074 6 bad <-- chromium@441116 0.777035 +- 0.357394 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=flickr v8.infinite_scroll_tbmv2 Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8990926750500661936 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5224147501711360 | 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 Tests>AutoBisect. Thank you! |
||
►
Sign in to add a comment |
||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Jan 9 2017