Issue metadata
Sign in to add a comment
|
59.9%-124.7% regression in memory.top_10_mobile at 500324:500358 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Sep 8 2017
Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8969004992655444176
,
Sep 9 2017
=== Auto-CCing suspected CL author xunjieli@chromium.org === Hi xunjieli@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 : xunjieli Commit : 724bb776bcdea642a5bc9cc20fe14bb0282b4900 Date : Wed Sep 06 14:29:20 2017 Subject: [Telemetry] Use --ignore-certificate-errors-spki-list to bypass cert errors Bisect Details Configuration: android_webview_nexus6_aosp_perf_bisect Benchmark : memory.top_10_mobile Metric : memory:webview:all_processes:reported_by_os:system_memory:java_heap:proportional_resident_size_avg/foreground/http_www_baidu_com_s_word_google Change : 123.20% | 3938304.0 -> 8790357.33333 Revision Result N chromium@500323 3938304 +- 180666 6 good chromium@500341 3944619 +- 164698 6 good chromium@500344 3936256 +- 183819 6 good chromium@500344,catapult@c5a474f50f 4010325 +- 149200 6 good chromium@500344,catapult@724bb776bc 9461248 +- 143855 6 bad <-- chromium@500344,catapult@80c47581b1 9368235 +- 111335 6 bad chromium@500344,catapult@4f611510b9 9304405 +- 169852 6 bad chromium@500344,catapult@442f46edf7 9287339 +- 200561 6 bad chromium@500345 9139883 +- 216685 6 bad chromium@500346 9048405 +- 141154 6 bad chromium@500350 8932352 +- 201653 6 bad chromium@500358 8790357 +- 313380 6 bad Please refer to the following doc on diagnosing memory regressions: https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md To Run This Test src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests memory.top_10_mobile More information on addressing performance regressions: http://g.co/ChromePerformanceRegressions Debug information about this bisect: https://chromeperf.appspot.com/buildbucket_job_status/8969004992655444176 For feedback, file a bug with component Speed>Bisection
,
Sep 11 2017
This is not a real regression. We changed from --ignore-certificate-errors to --ignore-certificate-errors-spki-list, a new startup flag which allows Chrome to bypass cert errors selectively and still exercise disk cache. I see //net MemoryDumpProvider shows a non-zero value for http cache, as expected. The metrics are consistent after flag change, so I will mark this as WontFix. +mariakhomenko@ as a FYI.
,
Sep 11 2017
Issue 763865 has been merged into this issue.
,
Sep 11 2017
,
Sep 11 2017
,
Sep 11 2017
Issue 763859 has been merged into this issue.
,
Sep 11 2017
Issue 763892 has been merged into this issue.
,
Sep 11 2017
Issue 763855 has been merged into this issue.
,
Sep 12 2017
Issue 763863 has been merged into this issue.
,
Sep 12 2017
,
Sep 12 2017
Issue 763875 has been merged into this issue.
,
Sep 13 2017
,
Sep 14 2017
,
Sep 14 2017
Issue 765277 has been merged into this issue.
,
Sep 15 2017
Issue 763680 has been merged into this issue.
,
Sep 15 2017
Issue 765238 has been merged into this issue.
,
Sep 15 2017
Issue 765238 has been merged into this issue.
,
Sep 28 2017
|
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Sep 8 2017