New issue
Advanced search Search tips

Issue 900802 link

Starred by 1 user
Status: Closed
Owner:
ksolt@chromium.org
Closed: Nov 21
Cc:
andrescj@chromium.org
ksolt@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

52.1% regression in rendering.desktop/queueing_durations at 593864:604093

Project Member Reported by andrescj@chromium.org, Nov 1 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Nov 1 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=900802

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=3e325c27aa86ae04ef5fafe84acb969d2584104e9152089cd26da9696c2aec40


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

linux-perf

rendering.desktop - Benchmark documentation link:
  https://bit.ly/rendering-benchmarks
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Nov 1

Cc: ksolt@chromium.org
Owner: ksolt@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/14dc6409e40000

Removed several levels of calls to RenderWidget::DidReceiveCompositorFrameAck. by ksolt@chromium.org
https://chromium.googlesource.com/chromium/src/+/4d60b40e28c03273690c45f70e6fd9a53f8449f4
queueing_durations: 0.0148 → 0.0302 (+0.0154)

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

Benchmark documentation link:
  https://bit.ly/rendering-benchmarks

Comment 4 by ksolt@chromium.org, Nov 21

Status: Closed (was: Assigned)

Comment 5 by ksolt@chromium.org, Nov 21 

This is working as intended; a task which ran very often with a short queueing duration got removed entirely, which improved overall performance but bumped up this single metric.
►

Sign in to add a comment