Issue metadata
Sign in to add a comment
|
20.5% regression in blink_perf.bindings at 392564:392572 |
||||||||||||||||||||
Issue descriptionSee the link to graphs below.
,
May 11 2016
=== Auto-CCing suspected CL author mastiz@chromium.org === Hi mastiz@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 : [NTP Snippets] Add histogram with fetch time Author : mastiz Commit description: Client-side fetch latency can be useful to detect degradation in user experience and release qualification (i.e. migration to new backend). BUG= 584428 Review-Url: https://codereview.chromium.org/1961943002 Cr-Commit-Position: refs/heads/master@{#392569} Commit : 5dce6eed8747d19117ab4d928caffbe9568bc830 Date : Tue May 10 09:04:44 2016 ===== TESTED REVISIONS ===== Revision Mean Std Dev N Good? chromium@392563 69.7132 1.18315 5 good chromium@392568 68.3364 1.76673 8 good chromium@392569 62.6945 3.49502 8 bad <-- chromium@392570 63.4436 3.55325 8 bad chromium@392572 59.8772 1.16539 5 bad Bisect job ran on: android_nexus5_perf_bisect Bug ID: 611041 Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests blink_perf.bindings Test Metric: set-attribute/set-attribute Relative Change: 14.11% Score: 99.0 Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3684 Job details: https://chromeperf.appspot.com/buildbucket_job_status/9012953144569811120 Not what you expected? We'll investigate and get back to you! https://chromeperf.appspot.com/bad_bisect?try_job_id=5807132377612288 | 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!
,
May 11 2016
I seems very unlikely that this patch is the culprit, with only one UMA histogram added in a non-performance-critical codepath, where other histograms already were present.
,
May 20 2016
Charts suggest the performance degradation improved later, independently from this patch. I'll mark this as fixed unless I hear back after a grace period.
,
May 24 2016
|
|||||||||||||||||||||
►
Sign in to add a comment |
|||||||||||||||||||||
Comment 1 by tdres...@chromium.org
, May 11 2016