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

Issue 690687 link

Starred by 1 user

Issue metadata

Status: WontFix
Owner:
Closed: Mar 2017
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.8% regression in smoothness.top_25_smooth at 448114:448156

Project Member Reported by briander...@chromium.org, Feb 9 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=690687

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgqOX8jAgM


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

chromium-rel-win8-dual
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Feb 10 2017

Cc: chrishtr@chromium.org
Owner: chrishtr@chromium.org

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

Hi chrishtr@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 : chrishtr
  Commit : 4fa3275a1ee7439fb7057ac2d9986c15c9a2e396
  Date   : Sat Feb 04 02:15:20 2017
  Subject: Invalidate subsequence caching & empty paint phases if clips changed relative

Bisect Details
  Configuration: win_8_perf_bisect
  Benchmark    : smoothness.top_25_smooth
  Metric       : mean_input_event_latency/Docs  (1 open document tab)
  Change       : 4.61% | 5.7205 -> 5.98833333333

Revision             Result                   N
chromium@448113      5.7205 +- 0.225063       6       good
chromium@448135      5.76044 +- 0.14292       9       good
chromium@448146      6.00867 +- 1.94171       9       good
chromium@448147      5.98 +- 0.240632         14      bad       <--
chromium@448148      5.93793 +- 0.240726      14      bad
chromium@448149      5.96521 +- 0.201986      14      bad
chromium@448151      5.99164 +- 0.428293      14      bad
chromium@448156      5.98833 +- 0.181527      9       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=Docs...1.open.document.tab. smoothness.top_25_smooth

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8988096197487217824

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5806430227005440


| 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!
The magnitude of the latency regression is ~.1ms. I'm inclined to close as WontFix, unless there's an easy fix.
I have a CL in progress to optimize one of the painting cache data structures,
would like to keep this open to track that work.
Labels: Performance-Responsiveness
Components: Blink>Paint
Status: Assigned (was: Untriaged)
Status: WontFix (was: Assigned)
Labels: PaintTeamTriaged-20170317 BugSource-Chromium

Sign in to add a comment