New issue
Advanced search Search tips
Note: Color blocks (like or ) mean that a user may not be available. Tooltip shows the reason.

Issue 687589 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 672457
Owner:
Closed: Feb 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

19.4% regression in smoothness.top_25_smooth at 447113:447187

Project Member Reported by pmeenan@chromium.org, Feb 1 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=687589

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgiNPBgQgM


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

chromium-rel-mac11
Cc: smcgruer@chromium.org
Owner: smcgruer@chromium.org

=== Auto-CCing suspected CL author smcgruer@chromium.org ===

Hi smcgruer@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : smcgruer
  Commit : 2c04a7850056a21b6c1dcb6d63451c4a0f11e707
  Date   : Tue Jan 31 01:49:41 2017
  Subject: Force compositing inputs to be clean for location-related Element APIs

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : smoothness.top_25_smooth
  Metric       : mean_input_event_latency/https___plus.google.com_110031535020051778989_posts
  Change       : 19.36% | 24.3176666667 -> 29.025

Revision             Result                   N
chromium@447112      24.3177 +- 0.361936      6      good
chromium@447150      24.2497 +- 0.354682      6      good
chromium@447155      24.232 +- 0.792658       6      good
chromium@447157      24.108 +- 0.594209       6      good
chromium@447158      28.614 +- 0.233722       6      bad       <--
chromium@447160      28.6333 +- 0.564611      6      bad
chromium@447169      28.6168 +- 0.524148      6      bad
chromium@447187      29.025 +- 2.2624         6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=https...plus.google.com.110031535020051778989.posts smoothness.top_25_smooth

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8988847052558586928

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5556036821319680


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Tests>AutoBisect.  Thank you!
Mergedinto: 672457
Status: Duplicate (was: Untriaged)
CL has already been reverted for related issues (racy LayoutTest that broke due to perf change) - https://chromium.googlesource.com/chromium/src.git/+/66c36f258e7ef15d44b8fd7d2766943da38cc40c

However performance changes were expected as an outcome, so I'm going to merge this into the overall bug to further discussion on perf impact.

Sign in to add a comment