New issue
Advanced search Search tips

Issue 798613 link

Starred by 1 user
Status: Duplicate
Merged: issue 792452
Owner:
ericrk@chromium.org
Closed: Jan 2018
Cc:
ericrk@chromium.org
piman@chromium.org
chrishtr@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

5.5%-25.3% regression in thread_times.key_silk_cases at 521402:521486

Project Member Reported by ericrk@chromium.org, Jan 3 2018 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Jan 3 2018 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=798613

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=c1f6249e5c888aa682d61c37b9086d589da22da32e774c955248e8ad5dacf524


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

android-nexus5
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jan 3 2018 


=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_GPU_cpu_time_per_frame/http___jsfiddle.net_rF9Gh_7_show_

Revision             Result                  N
chromium@521401      6.76438 +- 1.48864      21      good
chromium@521486      6.71183 +- 1.72842      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...jsfiddle.net.rF9Gh.7.show. thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8958465820844368128


For feedback, file a bug with component Speed>Bisection

Comment 6 by sullivan@chromium.org, Jan 25 2018 

Trying to bisect with a wider range.
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Jan 25 2018

Cc: chrishtr@chromium.org piman@chromium.org
Owner: chrishtr@chromium.org
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/14d27c4c840000

[PE] Turn on half-width tiles for all platforms and devices.
By chrishtr@chromium.org · Tue Dec 05 01:51:58 2017
chromium @ a3e4477c29d087d3708dbcb4dc5a90985c2b45e3

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jan 25 2018 

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/148135cc840000

[PE] Turn on half-width tiles for all platforms and devices.
By chrishtr@chromium.org · Tue Dec 05 01:51:58 2017
chromium @ a3e4477c29d087d3708dbcb4dc5a90985c2b45e3

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 9 by chrishtr@chromium.org, Jan 25 2018

Owner: ericrk@chromium.org

Comment 10 by ericrk@chromium.org, Jan 25 2018

Mergedinto: 792452
Status: Duplicate (was: Assigned)
These are all expected changes, as the scenarios being benchmarked exceed view width (and probably aren't typical of mobile sites, which would be sized to the view).
►

Sign in to add a comment