Issue metadata
Sign in to add a comment
|
27.8%-34.3% regression in octane at 588394:588429 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Sep 4
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/17f378c9640000
,
Sep 5
📍 Found significant differences after each of 2 commits. https://pinpoint-dot-chromeperf.appspot.com/job/17f378c9640000 Include testing of significant impacts on a per story basis. by anthonyalridge@google.com https://chromium.googlesource.com/catapult/+/313f37ed7bc8369d51dbc1d5cb4afcbd48aa5dbb 1.223e+04 → 1.211e+04 (-119.4) Roll src/third_party/catapult 713e916190aa..88dc49aaadb0 (3 commits) by catapult-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com https://chromium.googlesource.com/chromium/src/+/fcfe9a6f17f02771890c03d666dcebf560eca909 1.211e+04 → 8816 (-3296) Assigning to sheriff sullivan@chromium.org because "Roll src/third_party/catapult 713e916190aa..88dc49aaadb0 (3 commits)" is a roll. Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Sep 5
anthonyalridge: the vast majority of the regression pinpoint caught was due to the catapult roll, which included a change "Limit CPU/GPU frequency for Nexus 5X". That is expected. It also caught a small change from your CL--was it expected to change octane results slightly? Either way, I think it's okay to WontFix, since it's a very small change, but just wanted to send it by you first. Assigning to mythria since anthonyalridge isn't a project member.
,
Sep 6
Anthony's cl is related to the new tool we are experimenting with. It should not impact Octane scores. Infact it should not be even used for anything. Since it is minor, I suspect it could be also noise. I think we can mark it as won't fix. |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Sep 4