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

Issue 856041 link

Starred by 1 user
Status: WontFix
Owner:
clemensh@chromium.org
Closed: Jun 2018
Cc:
jgruber@chromium.org
█ alexclarke@chromium.org
szuend@google.com
clemensh@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

11.2% regression in blink_perf.bindings at 569862:569870

Project Member Reported by alexclarke@chromium.org, Jun 25 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jun 25 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=856041

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=e42dcaaeae0227d78e429930829b770ad94047eded37dd892544efa44ffd23e2


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

linux-perf
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jun 26 2018

Cc: clemensh@chromium.org
Owner: clemensh@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/139603a3240000

Revert "[array] Change QuickSort to TimSort for Array.p.sort" by clemensh@chromium.org
https://chromium.googlesource.com/v8/v8/+/8723374b4aa4dd1307315d994bae8828de19c950
1029 → 916.7 (-111.9)

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

Comment 4 by clemensh@chromium.org, Jun 26 2018

Status: WontFix (was: Assigned)
This is expected. The original CL landed to gather some performance data (see comments: https://crrev.com/c/1111959).
It improves performance, so the revert regresses performance.

Comment 5 by clemensh@chromium.org, Jun 26 2018

Cc: jgruber@chromium.org szuend@google.com

Comment 6 by jgruber@chromium.org, Jun 26 2018 

Pinpoint results look weird, the initial land of TimSort does not move the needle, but the revert does. Possibly flaky?

Comment 7 by clemensh@chromium.org, Jun 26 2018 

Yeah, maybe just a flake. It recovered a bit later. Still WontFix ;)
►

Sign in to add a comment