Issue metadata
Sign in to add a comment
|
14.6%-30.8% regression in v8.browsing_mobile at 471644:471724 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
May 30 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978194839154864176
,
May 30 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978194808514657888
,
May 30 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Yutaka Hirano Commit : f20d10a747ef558a18cdd6925df977352e477997 Date : Mon May 15 04:44:45 2017 Subject: Revert "Set URLResponseBodyConsumer::kMaxNumConsumedBytesInTask to 32K" Bisect Details Configuration: android_nexus6_perf_bisect Benchmark : v8.browsing_mobile Metric : v8-gc-incremental-step_sum/browse_chrome/browse_chrome_omnibox Change : 13.40% | 68.2745 -> 77.4251666667 Revision Result N chromium@471666 68.2745 +- 9.17573 6 good chromium@471668 65.8162 +- 5.9331 6 good chromium@471669 65.0592 +- 11.4614 6 good chromium@471670 78.2802 +- 7.73912 6 bad <-- chromium@471674 76.6783 +- 6.59073 6 bad chromium@471681 77.8722 +- 5.75896 6 bad chromium@471695 76.7908 +- 4.698 6 bad chromium@471724 77.4252 +- 7.02476 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=browse.chrome.omnibox v8.browsing_mobile Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8978194808514657888 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5208091852800000 | 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 Speed>Bisection. Thank you!
,
May 30 2017
=== BISECT JOB RESULTS === Perf regression found with culprit Suspected Commit Author : Yutaka Hirano Commit : f20d10a747ef558a18cdd6925df977352e477997 Date : Mon May 15 04:44:45 2017 Subject: Revert "Set URLResponseBodyConsumer::kMaxNumConsumedBytesInTask to 32K" Bisect Details Configuration: android_one_perf_bisect Benchmark : v8.browsing_mobile Metric : v8-gc-total_max/browse_chrome/browse_chrome_omnibox Change : 31.32% | 65.7113333333 -> 86.2908333333 Revision Result N chromium@471643 65.7113 +- 2.4663 6 good chromium@471661 66.7498 +- 2.48545 6 good chromium@471666 66.1398 +- 2.13062 6 good chromium@471668 65.828 +- 1.83563 6 good chromium@471669 65.7443 +- 3.07925 6 good chromium@471670 86.4637 +- 0.921853 6 bad <-- chromium@471678 86.2908 +- 0.923269 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=browse.chrome.omnibox v8.browsing_mobile Debug Info https://chromeperf.appspot.com/buildbucket_job_status/8978194839154864176 Is this bisect wrong? https://chromeperf.appspot.com/bad_bisect?try_job_id=5892464960864256 | 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 Speed>Bisection. Thank you! |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by jgruber@chromium.org
, May 30 2017