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

Issue 609773 link

Starred by 0 users

Issue metadata

Status: WontFix
Owner:
Last visit > 30 days ago
Closed: May 2016
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

16% regression in thread_times.tough_scrolling_cases at 391696:391730

Project Member Reported by alexclarke@chromium.org, May 6 2016

Issue description

I suspect this bug will be a duplicate since theres a bunch of thread time alerts.  Anyway lets see what the bots find.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=609773

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg1OHeuwoM


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

chromium-rel-mac11
Cc: l...@chromium.org
Owner: l...@chromium.org

=== Auto-CCing suspected CL author lpy@chromium.org ===

Hi lpy@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 : Include system time in Mac ThreadTicks.
Author  : lpy
Commit description:
  
Currently Mac ComputeThreadTicks doesn't only use user time, this patch includes
system time in order to get more accurate CPU time.

BUG= 608936 

Review-Url: https://codereview.chromium.org/1946303003
Cr-Commit-Position: refs/heads/master@{#391717}
Commit  : 89c5c64c72a737a52426df0f29146fb530b9129c
Date    : Thu May 05 00:39:36 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev    N  Good?
chromium@391695  7.88515  0.0778759  5  good
chromium@391713  7.91674  0.0610047  5  good
chromium@391716  7.89016  0.0704526  5  good
chromium@391717  10.148   0.0769621  5  bad    <--
chromium@391718  10.1403  0.0769086  5  bad
chromium@391722  10.1341  0.0897859  5  bad
chromium@391730  10.1288  0.0574126  5  bad

Bisect job ran on: mac_10_11_perf_bisect
Bug ID: 609773

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests thread_times.tough_scrolling_cases
Test Metric: thread_total_all_cpu_time_per_frame/thread_total_all_cpu_time_per_frame
Relative Change: 28.45%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_11_perf_bisect/builds/621
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013419602039161728


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5868791397875712

| 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!
This seems like intended behavior, originally we measured the thread user time only, this CL adds the system time that was part of the thread time to the number.
The addition itself it so minor that it is unlikely to be cause of the regression. So it seems that this benchmark was using a lot of system time (16% to be exact).

I recommend closing it as WontFix.

Comment 4 by l...@chromium.org, May 6 2016

Status: WontFix (was: Assigned)

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Include system time in Mac ThreadTicks.
Author  : lpy
Commit description:
  
Currently Mac ComputeThreadTicks doesn't only use user time, this patch includes
system time in order to get more accurate CPU time.

BUG= 608936 

Review-Url: https://codereview.chromium.org/1946303003
Cr-Commit-Position: refs/heads/master@{#391717}
Commit  : 89c5c64c72a737a52426df0f29146fb530b9129c
Date    : Thu May 05 00:39:36 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev    N  Good?
chromium@391640  9.16913  0.0364329  5  good
chromium@391715  7.9087   0.0276948  5  good
chromium@391716  7.84667  0.0337392  5  good
chromium@391717  10.0584  0.0916368  5  bad    <--
chromium@391718  10.0362  0.106581   5  bad
chromium@391720  10.1029  0.0731468  5  bad
chromium@391725  10.1149  0.0727486  5  bad
chromium@391734  10.031   0.0265051  5  bad
chromium@391753  10.0797  0.0513687  5  bad
chromium@391790  10.0628  0.0842765  5  bad

Bisect job ran on: mac_10_11_perf_bisect
Bug ID: 609773

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests thread_times.tough_scrolling_cases
Test Metric: thread_total_all_cpu_time_per_frame/thread_total_all_cpu_time_per_frame
Relative Change: 9.75%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_11_perf_bisect/builds/622
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013419583521352880


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5858281814228992

| 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!

Sign in to add a comment