Issue metadata
Sign in to add a comment
|
12%-13.4% regression in blink_perf.svg at 526326:526357 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Jan 2 2018
๐ Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/1490bced040000
,
Jan 2 2018
๐ Found significant differences after each of 2 commits. https://pinpoint-dot-chromeperf.appspot.com/job/1490bced040000 [CI] Migrate hit-testing code in PaintLayer to use GeometryMapper. By chrishtr@chromium.org ยท Fri Dec 29 00:51:58 2017 chromium @ b7e2306fd4d8590a41f6fd103dfcc1013d6ca85e Generate synthethic RTT and throughput observations based on the By tbansal@chromium.org ยท Fri Dec 29 03:05:42 2017 chromium @ 6b0a6d4b55d8e89ff92f43c7d04776d8dbacc00f Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Jan 2 2018
I think the regression is related to the hit-testing change in b7e2306fd4d8590a41f6fd103dfcc1013d6ca85e, so I'm re-assigning to chrishtr. It looks like 6b0a6d4b55d8e89ff92f43c7d04776d8dbacc00f actually slightly improved the test slightly by reducing work by not querying the java external estimate provider.
,
Jan 2 2018
Thanks Ryan.
,
Jan 3 2018
|
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Jan 2 2018