New issue
Advanced search Search tips

Issue 911554 link

Starred by 1 user
Status: Duplicate
Merged: issue 911591
Owner:
masonfreed@chromium.org
Closed: Dec 18
Cc:
masonfreed@chromium.org
toyoshim@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.7%-19.2% regression in system_health.common_desktop at 612650:612679

Project Member Reported by toyoshim@chromium.org, Dec 4 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Dec 4 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=911554

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=b955706a0f3c97f310e8c571029003b1b804447450cfeb37e29dd11a60d796d1


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

linux-perf
mac-10_12_laptop_low_end-perf

system_health.common_desktop - Benchmark documentation link:
  https://bit.ly/system-health-benchmarks
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Dec 4

Cc: masonfreed@chromium.org
Owner: masonfreed@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/145dad94140000

Removing the kInlineTransform compositing reason by masonfreed@chromium.org
https://chromium.googlesource.com/chromium/src/+/f6e075c54c8bc6130d49c09ad3df6944376ccba4
cpu_time_percentage: 0.6393 → 0.7677 (+0.1284)

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

Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

Comment 4 by masonfreed@chromium.org, Dec 18

Mergedinto: 911591
Status: Duplicate (was: Assigned)
Same general comments as 911591. This regression is mostly CPU time on infinite scrollers, which will likely require slightly more rasterization than before.
►

Sign in to add a comment