New issue
Advanced search Search tips

Issue 853168 link

Starred by 7 users
Status: WontFix
Owner:
mvstan...@chromium.org
Closed: Jul 2
Cc:
perezju@chromium.org
yhirano@chromium.org
mvstanton@google.com
kinuko@chromium.org
tzik@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.3%-110% regression in v8.browsing_mobile at 567084:567159

Project Member Reported by mvstanton@google.com, Jun 15 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jun 15 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=853168

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=c71ba5cbec9fc313027cd663a3b5df40a8742a57a93ee62e68eb9664b010951b


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

android-webview-nexus6
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jun 15 2018

Cc: yhirano@chromium.org
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/122739e9240000

Enable RendererSideResourceScheduler by yhirano@chromium.org
https://chromium.googlesource.com/chromium/src/+/0f9ea91ea461cb3d432a250ede3b9e3ddf6b522f
293.7 → 621.3 (+327.6)

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

Comment 4 by yhirano@chromium.org, Jun 15 2018

Cc: kinuko@chromium.org
I'm confused. The settings have already been used via  testing/variations/fieldtrial_testing_config.json and that change shouldn't change performance observed by perf bots.

Comment 5 by yhirano@chromium.org, Jul 2

Cc: tzik@chromium.org
Issue 853659 has been merged into this issue.

Comment 6 by yhirano@chromium.org, Jul 2

Cc: perezju@chromium.org
perezju@, do you have any insights?

Comment 7 Deleted

Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Jul 2 

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/14984c8b240000
Project Member

Comment 11 by 42576172...@developer.gserviceaccount.com, Jul 2 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/12984c8b240000

[DO NOT COMMIT] RendererSideResourceScheduler by yhirano@chromium.org
https://chromium-review.googlesource.com/c/chromium/src/+/1121948/2
601.2 → 296.7 (-304.5)

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

Comment 12 by yhirano@chromium.org, Jul 2 

According to #11 https://chromium-review.googlesource.com/c/chromium/src/+/1121948/2 fixes the regression. It looks in some circumstances fieldtrial_testing_config.json doesn't take effect.

Comment 13 by yhirano@chromium.org, Jul 2

Status: WontFix (was: Assigned)
The baseline seems to be set to (1, 10) which is unrealistic. The perf effect is evaluated at other places (https://docs.google.com/document/d/1oreWB98RmEhqGIM9vQgOs9s7llBLxHsxubhNyN8Cmrg/edit for example), so I'm closing this issue.
►

Sign in to add a comment