Issue metadata
Sign in to add a comment
|
120.7% regression in smoothness.key_silk_cases at 542210:542276 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Mar 12 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/16ffb2c6440000
,
Mar 19 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/14c91919440000
,
Mar 20 2018
😿 Pinpoint job stopped with an error. https://pinpoint-dot-chromeperf.appspot.com/job/14c91919440000
,
Mar 26 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/158f2e33440000
,
Mar 26 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/15ad39e3440000
,
Mar 30 2018
📍 Found significant differences after each of 7 commits. https://pinpoint-dot-chromeperf.appspot.com/job/16ffb2c6440000 Don't set active_tree_needs_first_draw_ on invalidate by jamwalla@chromium.org https://chromium.googlesource.com/chromium/src/+/989dd34c86ee3a462c467d0c4200faa9046fa496 Triggering jobs on new macbook airs by eyaich@google.com https://chromium.googlesource.com/chromium/src/+/f7a01706593e214bbb25bc324dde00ba91cfd088 [scheduler] Add TaskDurationPerTaskType.{Foreground,Background} histograms. by altimin@chromium.org https://chromium.googlesource.com/chromium/src/+/9c6fb254a2122d0de0b5b8debed525538caa7e02 Move one TrayAccessibilityTest to ash_unittests by jamescook@chromium.org https://chromium.googlesource.com/chromium/src/+/78a058bc8c5ae34722e689a269682ff4806a42fa Attempt to get SharedSamplerTest.PhysicalMemory passing with libc++. by thakis@chromium.org https://chromium.googlesource.com/chromium/src/+/06ba28c97323401428c47c7daada5b2d86653ac5 Implement WebXR input for Oculus by bajones@chromium.org https://chromium.googlesource.com/chromium/src/+/1206426d2db5d3e5ca28636caa24e4b39c6b72f1 Change StackLayout#flingStacks() to take an int by rlanday@chromium.org https://chromium.googlesource.com/chromium/src/+/90930b84a060e1685307cb3b83045548eeae4108 Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Apr 2 2018
The tool's UI doesn't make sense and my CL is definitely not responsible. Closing
,
Apr 2 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/16977b00c40000
,
Apr 2 2018
I've started another bisect job and removed myself as owner as suggested here: https://chromium.googlesource.com/chromium/src/+/master/docs/speed/addressing_performance_regressions.md
,
Apr 3 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/16c0a540c40000
,
Apr 10 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/14ae0c3cc40000
,
Apr 10 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/14ac4d6cc40000
,
Apr 11 2018
😿 Pinpoint job stopped with an error. https://pinpoint-dot-chromeperf.appspot.com/job/14ae0c3cc40000
,
Apr 11 2018
😿 Pinpoint job stopped with an error. https://pinpoint-dot-chromeperf.appspot.com/job/16977b00c40000
,
Apr 11 2018
😿 Pinpoint job stopped with an error. https://pinpoint-dot-chromeperf.appspot.com/job/16c0a540c40000
,
Apr 13 2018
These was failing with swarming timeouts, not enough devices, retrying since we've increased capacity.
,
Apr 13 2018
📍 Pinpoint job started. https://pinpoint-dot-chromeperf.appspot.com/job/12f803eac40000
,
Apr 14 2018
📍 Found a significant difference after 1 commit. https://pinpoint-dot-chromeperf.appspot.com/job/12f803eac40000 Don't set active_tree_needs_first_draw_ on invalidate by jamwalla@chromium.org https://chromium.googlesource.com/chromium/src/+/989dd34c86ee3a462c467d0c4200faa9046fa496 Understanding performance regressions: http://g.co/ChromePerformanceRegressions
,
Apr 15 2018
Previous job on this bug failed due to https://github.com/catapult-project/catapult/issues/4393, retrying now that it's fixed.
,
Apr 15 2018
📍 Pinpoint job started. https://chromeperf.appspot.com/job/12d3e31ac40000
,
Apr 16 2018
+boliu Wontfix, we expected this change.
,
Apr 16 2018
(didnt mean to remove Sunny, sorry)
,
Apr 17 2018
Who's "we" and why was this expected? What CL caused it?
,
Apr 17 2018
CL is https://chromium.googlesource.com/chromium/src/+/989dd34c86ee3a462c467d0c4200faa9046fa496 This forces activation to wait for the previous frame to be drawn. Commit always needs to wait for previous activation, which means delay went up a bit. otoh, in absolute terms, it went up by 0.156ms only. So it's just an overly sensitive metric.
,
Apr 17 2018
0.156ms is 10% of your frame budget at 60fps. It's possible that that change is necessary, but I'm not sure I'd characterize the metric as overly sensitive if it finds changes that blow 10% of animation frame time.
,
Apr 17 2018
It's 1% of the 16ms budget
,
Apr 17 2018
D'oh, sorry, you're right of course. |
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by 42576172...@developer.gserviceaccount.com
, Mar 12 2018