New issue
Advanced search Search tips

Issue 808629 link

Starred by 1 user
Status: WontFix
Owner:
bsalo...@google.com
Closed: Apr 2018
Cc:
robertph...@google.com
npm@chromium.org
bsalo...@google.com
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

4% regression in thread_times.key_mobile_sites_smooth at 532471:532552

Project Member Reported by npm@chromium.org, Feb 2 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Feb 2 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=808629

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=596102358252708218a2b662ad115663b6f5068a85db166806401d597173d65d


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

android-nexus5
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Feb 4 2018

Cc: bsalo...@google.com robertph...@google.com
Owner: bsalo...@google.com
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/11e01aae840000

Reenable GrTextureOp antialiasing. by bsalomon@google.com
chromium @ 76a4d4d3c761cea62266bf8d1141b0d8ac84a60b

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

Comment 4 by bsalo...@google.com, Feb 5 2018 

 Issue 808630  has been merged into this issue.

Comment 5 by vmi...@chromium.org, Feb 5 2018

Components: Internals>GPU>Metrics

Comment 6 by npm@chromium.org, Mar 28 2018 

Ping - has this performance regression been looked at?

Comment 7 by bsalo...@google.com, Apr 2 2018 

I will take a look at this this week.

Comment 8 by bsalo...@google.com, Apr 2 2018

Status: Fixed (was: Assigned)

Comment 9 by bsalo...@google.com, Apr 2 2018

Status: Assigned (was: Fixed)
Oops wrong bug

Comment 10 by bsalo...@google.com, Apr 5 2018

Status: WontFix (was: Assigned)
On tip of tree I get 2.430 ms in thread_GPU_cpu_time_per_frame/slashdot on a N5 and I get 2.432 when I re-enable the old code path. This is with pageset-repeat set to 30. I ran the benchmark with the old code path multiple times and it seems consistent. AFAICT there is nothing to do here.
►

Sign in to add a comment