Issue metadata
Sign in to add a comment
|
26.6%-47.1% regression in blink_perf.events at 397303:397341 |
||||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
Jun 3 2016
=== Auto-CCing suspected CL author hayato@chromium.org === Hi hayato@chromium.org, the bisect results pointed to your CL below as possibly causing a regression. Please have a look at this info and see whether your CL be related. ===== BISECT JOB RESULTS ===== Status: completed ===== SUSPECTED CL(s) ===== Subject : Remove Event.relatedTargetScoped and update event path calculation for relatedTarget Author : hayato Commit description: See the context: https://github.com/w3c/webcomponents/issues/486 The spec change: - https://github.com/w3c/webcomponents/commit/f113e26bfa999bac730c65ea7418fe787500313c - https://github.com/w3c/webcomponents/commit/b1433e5f3a013ca825f02fb8f7b0e9d6217c0125 BUG= 531990 Review-Url: https://codereview.chromium.org/2030513002 Cr-Commit-Position: refs/heads/master@{#397329} Commit : a4b8210a70c2b5315fbff25cadde8b756137d557 Date : Thu Jun 02 07:33:47 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@397328 26512.2 399.735 5 good chromium@397329 19203.6 239.236 5 bad <-- chromium@397330 19090.9 161.759 5 bad chromium@397332 19229.2 104.472 5 bad Bisect job ran on: mac_retina_perf_bisect Bug ID: 617113 Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.events Test Metric: EventsDispatchingInShadowTrees/EventsDispatchingInShadowTrees Relative Change: 27.47% Score: 99.9 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1318 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9010881671562665856 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5341494790062080 | 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!
,
Jun 6 2016
,
Jun 6 2016
I have an idea to make it faster, but, basically, this should be considered 'WONTFIX'. *The root cause* is that we forgot to update these benchmarks when Event.relatedTargetScoped was introduced. Thus, the score got improved *unintentionally* at that time. Now, the new spec requires that we have to retarget relatedTargets *always*. Thus, these micro benchmark's score becomes to the former level.
,
Jun 6 2016
The following revision refers to this bug: https://chromium.googlesource.com/chromium/src.git/+/6bd0c6392adc136ea7ac74a67fc0c676318a1b50 commit 6bd0c6392adc136ea7ac74a67fc0c676318a1b50 Author: hayato <hayato@chromium.org> Date: Mon Jun 06 06:12:44 2016 Cache the result of isScopedInV0 flag in Event object This makes the micro benchmarks (PerformanceTests/Events/) slightly faster. BUG= 531990 , 617113 Review-Url: https://codereview.chromium.org/2034413002 Cr-Commit-Position: refs/heads/master@{#397983} [modify] https://crrev.com/6bd0c6392adc136ea7ac74a67fc0c676318a1b50/third_party/WebKit/Source/core/events/Event.cpp [modify] https://crrev.com/6bd0c6392adc136ea7ac74a67fc0c676318a1b50/third_party/WebKit/Source/core/events/Event.h |
|||||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||||
Comment 1 by rmcilroy@chromium.org
, Jun 3 2016