New issue
Advanced search Search tips
Note: Color blocks (like █ or █) mean that a user may not be available. Tooltip shows the reason.

Issue 804319 link

Starred by 1 user
Status: WontFix
Owner:
ericrk@chromium.org
Closed: Jan 2018
Cc:
█ oetu...@nvidia.com
cwallez@chromium.org
█ bsalomon@chromium.org
█ pmeenan@chromium.org
eseckler@chromium.org
vmp...@chromium.org
qyears...@chromium.org
█ hamelphi@chromium.org
vmi...@chromium.org
sadrul@chromium.org
ericrk@chromium.org
skyos...@chromium.org
donnd@google.com
enne@chromium.org
chcunningham@chromium.org
dgozman@chromium.org
tsepez@chromium.org
wolenetz@chromium.org
█ donnd@chromium.org
chrishtr@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

27.3% regression in thread_times.key_silk_cases at 529870:530081

Project Member Reported by pmeenan@chromium.org, Jan 22 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jan 22 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=804319

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=a9e15fb3a12da4cedd3a393792f3a59f7c083e23214e6e3080aaac78b592b6af


Bot(s) for this bug's original alert(s):

android-nexus5
Project Member

Comment 2 by 42576172...@developer.gserviceaccount.com, Jan 22 2018 

馃搷 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/14addee8840000
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jan 22 2018

Cc: sadrul@chromium.org vmp...@chromium.org bsalomon@chromium.org enne@chromium.org chcunningham@chromium.org oetu...@nvidia.com cwallez@chromium.org dgozman@chromium.org qyears...@chromium.org ericrk@chromium.org chrishtr@chromium.org skyos...@chromium.org eseckler@chromium.org wolenetz@chromium.org tsepez@chromium.org hamelphi@chromium.org donnd@google.com
Owner: donnd@google.com
Status: Assigned (was: Untriaged)
馃搷 Found significant differences after each of 5 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/14addee8840000

Delete blink MSE config change tests to de-dup with upstream wpt.
By chcunningham@chromium.org 路 Wed Jan 17 20:39:28 2018
chromium @ 526d7db80ec822b446ba68478e553e3a1b0ba591

headless/cc/viz: Add animate_only BeginFrame param.
By eseckler@chromium.org 路 Wed Jan 17 23:45:53 2018
chromium @ 8af8c0e5516658a5758f32b24ff7cdd826ac23d4

Move tile half-width optimization after all rounding
By ericrk@chromium.org 路 Wed Jan 17 23:49:37 2018
chromium @ a78535de3d2153706ef21bf918333353e59ea496

Fix dxgi support table generation script
By oetuaho@nvidia.com 路 Wed Jan 17 19:37:41 2018
angle @ 28efd82c9119d8371154455b57d13dd14884e184

[TTS] Change tap duration to not rely on asserts.
By donnd@google.com 路 Thu Jan 18 00:11:28 2018
chromium @ ba2f69012d80caed7f4778bd732ebcc7e22e4f36

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 4 by donnd@google.com, Jan 23 2018

Cc: donnd@chromium.org vmi...@chromium.org
Owner: ----
Status: Untriaged (was: Assigned)
vmiura@ I'm reverting the CL listed in #3, but don't understand which of the owners of the other CLs should be assigned this bug next - can you help triage?

Comment 5 by chrishtr@chromium.org, Jan 23 2018

Components: Internals>Compositing
Owner: ericrk@chromium.org
Status: Assigned (was: Untriaged)
I'm pretty sure it was ericrk@'s patch.

Comment 6 by ericrk@chromium.org, Jan 23 2018 

I'm pretty sure this is my patch, investigating now. Please hold off on reverting your patch.
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Jan 25 2018 

馃搷 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/12f61b82840000
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jan 26 2018 

馃搷 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/12f61b82840000

Comment 9 by ericrk@chromium.org, Jan 29 2018

Status: WontFix (was: Assigned)
In this case, my change takes us back to our previous perf levels before https://chromium-review.googlesource.com/c/chromium/src/+/806994. This change was addressing other perf regressions from that change, so overall I think everything's behaving as expected.

Note there was a lot of noise in the graph recently, but local bisecting didn't clearly reveal why. Graph looks good now though, so going to just close this out.
►

Sign in to add a comment