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

Issue 780235 link

Starred by 1 user

Issue metadata

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



Sign in to add a comment

41.5% regression in blink_perf.bindings at 512171:512260

Project Member Reported by briander...@chromium.org, Oct 31 2017

Issue description

See the link to graphs below.
 
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Oct 31 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=780235

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=100def0957e597d6f9ccfada2f7793d3e8a70804fcf0dbb37f73f4d8f749d0eb


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

chromium-rel-win7-dual
Cc: bmeu...@chromium.org
Owner: bmeu...@chromium.org
Status: Assigned (was: Untriaged)

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

Hi bmeurer@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 : Benedikt Meurer
  Commit : c78a98bbc24262a2fa8d2476c05dd55b67ffde7b
  Date   : Fri Oct 27 08:03:26 2017
  Subject: [turbofan] Introduce SameValue operator.

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : blink_perf.bindings
  Metric       : first-child/first-child
  Change       : 56.94% | 665.514419554 -> 286.551265429

Revision                           Result                  N
chromium@512170                    665.514 +- 44.599       6      good
chromium@512182                    679.362 +- 21.8682      6      good
chromium@512188                    713.711 +- 36.8257      6      good
chromium@512191                    652.931 +- 51.5603      6      good
chromium@512191,v8@b2fcb649d5      647.583 +- 112.782      6      good
chromium@512191,v8@13802c8b09      694.513 +- 10.8955      6      good
chromium@512191,v8@03035038b9      668.704 +- 15.8272      6      good
chromium@512191,v8@c78a98bbc2      417.854 +- 55.1135      6      bad       <--
chromium@512192                    425.997 +- 132.561      6      bad
chromium@512193                    445.415 +- 32.7993      6      bad
chromium@512215                    467.147 +- 216.318      6      bad
chromium@512260                    286.551 +- 10.2452      6      bad

Please refer to the following doc on diagnosing blink_perf regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/speed/benchmark_harnesses/blink_perf.md

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.bindings

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8964184328665692992


For feedback, file a bug with component Speed>Bisection
Status: WontFix (was: Assigned)
The benchmark looks kinda bimodal, and doesn't seem to be related to Object.is / SameValue in any way.

Sign in to add a comment