New issue
Advanced search Search tips

Issue 899850 link

Starred by 1 user
Status: WontFix
Owner:
dalecur...@chromium.org
Closed: Oct 30
Cc:
dalecur...@chromium.org
dougman@google.com
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

5.1%-11.6% regression in media.desktop at 602905:602971

Project Member Reported by dougman@chromium.org, Oct 29 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Oct 29 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=899850

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=85416a18feb6460e4ba6c127d6af798fa59adf253e338e7873c470d20595b557


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

linux-perf
mac-10_12_laptop_low_end-perf

media.desktop - Benchmark documentation link:
  None
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Oct 29

Cc: dalecur...@chromium.org
Owner: dalecur...@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/1748a1cee40000

Unify sw video decode thread count selection. by dalecurtis@chromium.org
https://chromium.googlesource.com/chromium/src/+/d063c4fe8d16c1be1110b0a78118ce0dbc2465ed
cpu_time_percentage: 0.3802 → 0.4157 (+0.03544)

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

Benchmark documentation link:
  None

Comment 4 by dalecur...@chromium.org, Oct 30

Status: WontFix (was: Assigned)
That patch removed an arbitrary cap on the thread count, so cpu usage going up slightly is expected.
►

Sign in to add a comment