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

Issue 719558 link

Starred by 1 user
Status: WontFix
Owner:
u...@chromium.org
Closed: Jul 2017
Cc:
█ kraynov@google.com
u...@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

14.7% regression in v8.mobile_infinite_scroll_tbmv2 at 469714:469773

Project Member Reported by kraynov@chromium.org, May 8 2017 
See the link to graphs below.

Comment 1 by kraynov@chromium.org, May 8 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=719558

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgysqqvAoM


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

android-nexus6
Project Member

Comment 4 by 42576172...@developer.gserviceaccount.com, May 8 2017

Cc: u...@chromium.org
Owner: u...@chromium.org

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

Hi ulan@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


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

Suspected Commit
  Author : ulan
  Commit : db13d8014fa5a6281b78323aae3636d8b5355b67
  Date   : Fri May 05 13:14:02 2017
  Subject: [heap] Reland "Make non-atomic markbit operations consistent with atomic ones."

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : v8.mobile_infinite_scroll_tbmv2
  Metric       : v8-gc-incremental-step_max/pinterest
  Change       : 12.21% | 10.7821666667 -> 12.0986666667

Revision                           Result                   N
chromium@469713                    10.7822 +- 0.590583      6      good
chromium@469721                    10.7325 +- 0.521377      6      good
chromium@469725                    10.5672 +- 0.416755      6      good
chromium@469726                    10.6822 +- 1.32333       6      good
chromium@469726,v8@2ed278f04a      10.6197 +- 0.759744      6      good
chromium@469726,v8@919530ac54      10.536 +- 0.588274       6      good
chromium@469726,v8@db13d8014f      12.3498 +- 0.599981      6      bad       <--
chromium@469727                    11.9812 +- 0.401371      6      bad
chromium@469728                    12.0313 +- 1.0175        6      bad
chromium@469743                    11.926 +- 0.447021       6      bad
chromium@469773                    12.0987 +- 0.240585      6      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=pinterest v8.mobile_infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980147080360330864

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5212645197611008


| 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!
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, May 8 2017 


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

Hi ulan@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


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

Suspected Commit
  Author : ulan
  Commit : db13d8014fa5a6281b78323aae3636d8b5355b67
  Date   : Fri May 05 13:14:02 2017
  Subject: [heap] Reland "Make non-atomic markbit operations consistent with atomic ones."

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : v8.mobile_infinite_scroll_tbmv2
  Metric       : v8-gc-incremental-step_max/pinterest
  Change       : 17.55% | 10.4208333333 -> 12.2498333333

Revision                           Result                   N
chromium@469713                    10.4208 +- 1.39712       6      good
chromium@469721                    10.4753 +- 0.365074      6      good
chromium@469725                    10.3408 +- 0.279096      6      good
chromium@469726                    10.4547 +- 0.278143      6      good
chromium@469726,v8@2ed278f04a      10.4848 +- 0.589991      6      good
chromium@469726,v8@919530ac54      10.3298 +- 0.536066      6      good
chromium@469726,v8@db13d8014f      12.0105 +- 0.299258      6      bad       <--
chromium@469727                    12.2363 +- 0.508831      6      bad
chromium@469728                    12.0628 +- 0.381689      6      bad
chromium@469743                    12.0495 +- 0.544286      6      bad
chromium@469773                    12.2498 +- 0.876034      6      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=pinterest v8.mobile_infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980147066390411376

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5791378082103296


| 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!
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, May 8 2017 


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

Suspected Commit
  Author : ulan
  Commit : db13d8014fa5a6281b78323aae3636d8b5355b67
  Date   : Fri May 05 13:14:02 2017
  Subject: [heap] Reland "Make non-atomic markbit operations consistent with atomic ones."

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : v8.mobile_infinite_scroll_tbmv2
  Metric       : v8-gc-incremental-step_max/pinterest
  Change       : 12.21% | 10.7821666667 -> 12.0986666667

Revision                           Result                   N
chromium@469713                    10.7822 +- 0.590583      6      good
chromium@469721                    10.7325 +- 0.521377      6      good
chromium@469725                    10.5672 +- 0.416755      6      good
chromium@469726                    10.6822 +- 1.32333       6      good
chromium@469726,v8@2ed278f04a      10.6197 +- 0.759744      6      good
chromium@469726,v8@919530ac54      10.536 +- 0.588274       6      good
chromium@469726,v8@db13d8014f      12.3498 +- 0.599981      6      bad       <--
chromium@469727                    11.9812 +- 0.401371      6      bad
chromium@469728                    12.0313 +- 1.0175        6      bad
chromium@469743                    11.926 +- 0.447021       6      bad
chromium@469773                    12.0987 +- 0.240585      6      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=pinterest v8.mobile_infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980147080360330864

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5212645197611008


| 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!

Comment 7 by u...@chromium.org, May 12 2017

Labels: -Performance-Sheriff Performance-SheriffPerformance-Sheriff-V8

Comment 8 by u...@chromium.org, Jul 24 2017

Status: WontFix (was: Untriaged)
The regression is expected.
►

Sign in to add a comment