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

Issue 838726 link

Starred by 2 users
Status: Duplicate
Owner:
jgruber@chromium.org
Closed: May 2018
Cc:
wangxianzhu@chromium.org
jgruber@chromium.org
battre@chromium.org
█ roc...@chromium.org
robertshield@chromium.org
dpa...@chromium.org
thakis@chromium.org
mstarzinger@chromium.org
█ pilgrim@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression

Blocking:
issue 838041



Sign in to add a comment

14.8% regression in blink_perf.bindings at 554130:554292

Project Member Reported by wangxianzhu@chromium.org, May 1 2018 
See the link to graphs below.
Project Member

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

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=838726

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=7be17eeb34b12d5dc3816ef57b41a537bbd52db46376e1fa6332d6bdb3cb013f


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

chromium-rel-win10
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, May 2 2018

Cc: roc...@chromium.org mstarzinger@chromium.org jgruber@chromium.org pilgrim@chromium.org thakis@chromium.org robertshield@chromium.org battre@chromium.org mmenke@chromium.org dpa...@chromium.org
Owner: roc...@chromium.org
Status: Assigned (was: Untriaged)
📍 Found significant differences after each of 3 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/14a1f0a3c40000

Reland "[builtins] Introduce further constant & external reference indirections" by jgruber@chromium.org
https://chromium.googlesource.com/v8/v8/+/3f99a376ddfc1a724f94d55b4a39986e56cd33b2

Migrate BrandcodeConfigFetcher to SimpleURLLoader by pilgrim@chromium.org
https://chromium.googlesource.com/chromium/src/+/276d13940ba27627e1cc4c553f5132b03ceddb3f

Revert "Migrate BrandcodeConfigFetcher to SimpleURLLoader" by rockot@chromium.org
https://chromium.googlesource.com/chromium/src/+/7d0a5ff689f3970032b7d72329d3f9bf998e77c3

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

Comment 4 by mmenke@chromium.org, May 2 2018

Cc: -mmenke@chromium.org

Comment 5 by roc...@chromium.org, May 3 2018

Owner: jgruber@chromium.org
Can you investigate whether this is relevant to your change jgruber@?

I'm ruling out mine (and pilgrim@'s) since combined they're obviously a net zero change.

Comment 6 by jgruber@chromium.org, May 3 2018

Blocking: 838041
Interesting.. In general my CL does introduce performance regressions, see https://crbug.com/838041. I'm currently working on fixing those, but it'll take me a week or two to land the follow-up CLs.

In this particular case, I'm curious why graphs seem to improve almost back to baseline at Point ID: 555349. Possibly an independent improvement? Or perhaps something else is going on?

Comment 7 by jgruber@chromium.org, May 3 2018

Blocking: -838041
Mergedinto: 838041
Status: Duplicate (was: Assigned)

Comment 8 by jgruber@chromium.org, May 3 2018

Blocking: 838041
►

Sign in to add a comment