New issue
Advanced search Search tips

Issue 717128 link

Starred by 1 user

Issue metadata

Status: Fixed
Owner:
Closed: May 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

11% regression in blink_perf.paint at 468137:468225

Project Member Reported by nzolghadr@chromium.org, May 1 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=717128

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgsrmatAsM


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

chromium-rel-win7-dual
Cc: wangxianzhu@chromium.org
Owner: wangxianzhu@chromium.org

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

Hi wangxianzhu@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 : wangxianzhu
  Commit : c731464f86c6a5c5c3f2b64890e04b38750896fc
  Date   : Fri Apr 28 23:14:06 2017
  Subject: Optimize collapsed border calculation (step 1)

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : blink_perf.paint
  Metric       : large-table-background-change-with-visible-collapsed-borders/large-table-background-change-with-visible-collapsed-borders
  Change       : 12.47% | 112.845333333 -> 126.9135

Revision             Result                   N
chromium@468136      112.845 +- 0.806997      6      good
chromium@468159      114.91 +- 3.11411        6      good
chromium@468170      114.991 +- 1.07402       6      good
chromium@468173      114.334 +- 1.27902       6      good
chromium@468174      126.509 +- 3.38648       6      bad       <--
chromium@468175      128.483 +- 1.63145       6      bad
chromium@468181      125.439 +- 1.52686       6      bad
chromium@468225      126.914 +- 1.22241       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 blink_perf.paint

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980776661443196064

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5870948877598720


| 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 Speed>Bisection.  Thank you!
Project Member

Comment 4 by bugdroid1@chromium.org, May 5 2017

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/bfbe9c7802a991ba8aac2664970947fd18e4748c

commit bfbe9c7802a991ba8aac2664970947fd18e4748c
Author: wangxianzhu <wangxianzhu@chromium.org>
Date: Fri May 05 01:16:39 2017

Move condition in CollapsedBorderValue::Width() into constructor

This avoids the condition from being repeatedly checked.

Also tweek other methods to avoid unnecessary checks. Add test.

BUG= 717128 

Review-Url: https://codereview.chromium.org/2858143003
Cr-Commit-Position: refs/heads/master@{#469562}

[modify] https://crrev.com/bfbe9c7802a991ba8aac2664970947fd18e4748c/third_party/WebKit/Source/core/BUILD.gn
[modify] https://crrev.com/bfbe9c7802a991ba8aac2664970947fd18e4748c/third_party/WebKit/Source/core/layout/CollapsedBorderValue.h
[add] https://crrev.com/bfbe9c7802a991ba8aac2664970947fd18e4748c/third_party/WebKit/Source/core/layout/CollapsedBorderValueTest.cpp

Status: Fixed (was: Untriaged)

Sign in to add a comment