Issue metadata
Sign in to add a comment
|
7.7% regression in system_health.memory_desktop at 521690:521769 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Dec 7 2017
๐ Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/12a6b11c040000
,
Dec 7 2017
๐ Found significant differences after each of 2 commits. https://pinpoint-dot-chromeperf.appspot.com/job/12a6b11c040000 Round the scroll offset synced back to main thread instead of flooring By yigu@chromium.org ยท Tue Dec 05 15:49:54 2017 chromium @ a3ce2d3110a3f9177a41935daadd43ede72db553 Turn on new image blur for chrome. Try 2 By herb@google.com ยท Tue Dec 05 17:22:57 2017 chromium @ 28a0d01c71f955054d79c3ff530f13db522cfa68 Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Jan 22 2018
herb, yigu: Bisect reproduces a ~1.5MiB jump at each of your CLs. Can you please take a look? You can get traces with full memory dumps by clicking either on the point in the perf dashboard, or by clicking on the values in pinpoint (see screenshot attached). +erikchen, who owns desktop memory benchmarks
,
Jan 22 2018
My patch does increase the memory consumption which is expected. See issue 792921 . herb@, please mark this bug as duplicate if you believe your patch is innocent.
,
Jan 22 2018
|
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Dec 7 2017