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

Issue 751974 link

Starred by 1 user
Status: Duplicate
Merged: issue 751976
Owner: ----
Closed: Aug 2017
Cc:
█ alexclarke@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

9.5% regression in thread_times.tough_scrolling_cases at 489925:490022

Project Member Reported by alexclarke@chromium.org, Aug 3 2017 
See the link to graphs below.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Aug 3 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=751974

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=902dc9a54ee36095fea609d0e1e0f8641046cf3af876cfbb7ae834b66e22eabc


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

chromium-rel-mac-retina
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Aug 3 2017 


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

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : thread_times.tough_scrolling_cases
  Metric       : thread_raster_cpu_time_per_frame/canvas_60000_pixels_per_second

Revision             Result                   N
chromium@489924      1.55737 +- 0.737409      21      good
chromium@490022      1.53567 +- 0.642725      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=canvas.60000.pixels.per.second thread_times.tough_scrolling_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972297807082920800


For feedback, file a bug with component Speed>Bisection

Comment 5 by sullivan@chromium.org, Aug 21 2017 

Kicked off a bisect on a wider range because the regression seems to take multiple jumps up.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Aug 21 2017 


=== BISECT JOB RESULTS ===
Perf regression found but unable to continue

Bisect was stopped because a commit couldn't be classified as either
good or bad.


Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : thread_times.tough_scrolling_cases
  Metric       : thread_raster_cpu_time_per_frame/canvas_60000_pixels_per_second

Revision             Result                   N
chromium@489885      1.56714 +- 0.778513      21      good
chromium@490098      1.58002 +- 0.655482      21      good
chromium@490204      1.62964 +- 0.520599      21      unknown
chromium@490310      1.66779 +- 0.939157      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=canvas.60000.pixels.per.second thread_times.tough_scrolling_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970613757761923600


For feedback, file a bug with component Speed>Bisection

Comment 8 by sullivan@chromium.org, Aug 22 2017 

Trying one more.
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Aug 22 2017

Mergedinto: 751976
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : pdr
  Commit : 79fe848764520df822d23d9a234a7710a7ebfe83
  Date   : Fri Jul 28 03:03:35 2017
  Subject: Update transform tree scroll offset from PushScrollUpdatesFromMainThread

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : thread_times.tough_scrolling_cases
  Metric       : thread_raster_cpu_time_per_frame/canvas_60000_pixels_per_second
  Change       : 7.18% | 1.55795208873 -> 1.66977546203

Revision             Result                   N
chromium@489885      1.55795 +- 0.674915      21      good
chromium@490090      1.55858 +- 0.575563      21      good
chromium@490207      1.51993 +- 0.609094      14      good
chromium@490221      1.55898 +- 0.561121      14      good
chromium@490226      1.59717 +- 0.393933      21      good
chromium@490227      1.56822 +- 0.494304      14      good
chromium@490228      1.65441 +- 0.652512      14      bad       <--
chromium@490234      1.70036 +- 0.385994      9       bad
chromium@490259      1.69693 +- 0.449483      9       bad
chromium@490310      1.66978 +- 0.585079      14      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=canvas.60000.pixels.per.second thread_times.tough_scrolling_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970556368427793424


For feedback, file a bug with component Speed>Bisection
►

Sign in to add a comment