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

Issue 844584 link

Starred by 2 users
Status: Assigned
Owner:
g...@chromium.org
Cc:
npm@chromium.org
█ afdo-chr...@skia-buildbots.google.com.iam.gserviceaccount.com
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

10% regression in blink_perf.parser at 558153:558156

Project Member Reported by npm@chromium.org, May 18 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, May 18 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=844584

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=fa979dacbc5f3513db0d9c790e700c777bab6cbea7b86ce2f9940fde0a9d6957


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

android-nexus5
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, May 19 2018

Cc: afdo-chr...@skia-buildbots.google.com.iam.gserviceaccount.com
Owner: g...@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/16f5eff4240000

Roll AFDO from 68.0.3428.0_rc-r1 to 68.0.3429.0_rc-r1 by afdo-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com
https://chromium.googlesource.com/chromium/src/+/fcb575c8904446db7b5a84c93bf45cf06c5b50a8

Assigning to sheriff gbiv@chromium.org because "Roll AFDO from 68.0.3428.0_rc-r1 to 68.0.3429.0_rc-r1" is a roll.

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

Comment 4 by g...@chromium.org, May 22 2018 

Ack; thanks. Looks like this reverted to roughly normal, but a number of the dips/spikes in recent history have afdo rolls in them. I'll see if there's a sane way to stabilize this.
►

Sign in to add a comment