New issue
Advanced search Search tips

Issue 898907 link

Starred by 1 user

Issue metadata

Status: Assigned
Owner:
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.5%-83.7% regression in rendering.mobile/tasks_per_frame_total_all at 601213:601297

Project Member Reported by maxlg@chromium.org, Oct 25

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=898907

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=2f98100cf0509c6930d268c1350ac1b7e32afec0086e62bf9fa8029b341c79c1


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

Android Nexus5 Perf
android-nexus5x-perf

rendering.mobile - Benchmark documentation link:
  https://bit.ly/rendering-benchmarks
📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/141eb9cee40000
Cc: nzolghadr@chromium.org
Owner: nzolghadr@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/166be5ebe40000

Remove input metric ukm sampling by nzolghadr@chromium.org
https://chromium.googlesource.com/chromium/src/+/f509a32b60352f85ed29950b1a24752ad14ce35e
tasks_per_frame_total_all: 37.8 → 40.29 (+2.486)

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

Benchmark documentation link:
  https://bit.ly/rendering-benchmarks
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/129c7700140000

Remove input metric ukm sampling by nzolghadr@chromium.org
https://chromium.googlesource.com/chromium/src/+/f509a32b60352f85ed29950b1a24752ad14ce35e
tasks_per_frame_total_all: 37.87 → 40.22 (+2.345)

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

Benchmark documentation link:
  https://bit.ly/rendering-benchmarks
nzolghadr@, the bisect points to your change, could you take a look?
Cc: tdres...@chromium.org
Tim, do you think this is the effect of us reporting UKM for input metrics? Does that have that much overload?
It's possible. Might be worth an independent couple of perf tryjobs?

Sign in to add a comment