New issue
Advanced search Search tips

Issue 699709 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 697949
Owner: ----
Closed: Mar 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

58.7% regression in page_cycler_v2.intl_ar_fa_he at 454745:454885

Project Member Reported by benhenry@google.com, Mar 8 2017

Issue description

Bisect to follow. Looks multi-modal over last 100s of commits, so not sure if we'll find anything, may want to add benchmark owner.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=699709

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg1JK0pgsM


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

android-webview-nexus6
Mergedinto: 697949
Status: Duplicate (was: Untriaged)

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : binji
  Commit : 5a04f4fd68d1d35d704cdc0dee0719c5354a8094
  Date   : Mon Feb 27 22:26:27 2017
  Subject: This is a speculative chain of reverts to improve a Chrome

Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : page_cycler_v2.intl_ar_fa_he
  Metric       : timeToFirstMeaningfulPaint_avg/pcv1-warm/http___ynet.co.il_
  Change       : 57.01% | 1727.02566667 -> 2711.55983333

Revision                           Result                  N
chromium@454744                    1727.03 +- 65.4067      6       good
chromium@454776                    1721.69 +- 113.912      6       good
chromium@454788                    1847.21 +- 999.185      9       good
chromium@454791                    1723.26 +- 90.4852      9       good
chromium@454793                    1886.35 +- 1292.82      14      good
chromium@454793,v8@60991f990b      2020.52 +- 1731.08      14      good
chromium@454793,v8@bbeb6dc15d      2065.2 +- 1388.61       9       good
chromium@454793,v8@a2a2c1b9ee      2023.7 +- 1745.36       14      good
chromium@454793,v8@5a04f4fd68      2789.16 +- 55.2614      6       bad       <--
chromium@454793,v8@2362f869a4      2778.28 +- 91.4297      9       bad
chromium@454793,v8@59c9e6ff69      2730.44 +- 44.1495      6       bad
chromium@454794                    2699.38 +- 107.814      9       bad
chromium@454799                    2623.56 +- 957.689      9       bad
chromium@454822                    2722.12 +- 27.3463      6       bad
chromium@454885                    2711.56 +- 77.9655      6       bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...ynet.co.il. page_cycler_v2.intl_ar_fa_he

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8985656028472563696

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5836257290092544


| 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!

Sign in to add a comment