Issue metadata
Sign in to add a comment
|
7.6%-20.5% regression in system_health.common_desktop at 525916:525952 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Jan 2 2018
๐ Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/14b17603040000
,
Jan 2 2018
๐ Found a significant difference after 1 commit. https://pinpoint-dot-chromeperf.appspot.com/job/14b17603040000 Reland "Statically link fontconfig on Linux" By thomasanderson@chromium.org ยท Fri Dec 22 06:20:09 2017 chromium @ 65f919d2d86e54c851b0327740a330d152b07ed5 Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Jan 25 2018
thomasanderson: have you had a chance to investigate this bug yet? Looks like your CL regressed expected queueing time on Linux. cc-ing metric owner tdresser in case there are questions.
,
Jan 25 2018
I haven't looked at this yet. The issue was caused by using a newer version of fontconfig, which is third party code. I think a fontconfig bisect will be necessary to track down the issue.
,
May 2 2018
thomasanderson@, are you the right owner to drive the fontconfig bisect? This regression still exists.
,
May 2 2018
Yes, I'm probably the right owner. Still getting to it :)
,
Jul 17
The graphs are showing system_health.common_desktop are currently at their lowest values of all time, so I'm closing this issue. |
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Jan 2 2018