Issue 727515 link

Starred by 1 user

Issue metadata

Status:	Duplicate
Merged:	issue 725949
Owner:	----
Closed:	Jun 2017
Cc:	toyoshim@chromium.org
Components:	Internals>GPU
EstimatedDays:	----
NextAction:	----
OS:	----
Pri:	2
Type:	Bug-Regression
Performance-Sheriff M-61

2.6%-13.3% regression in smoothness.key_desktop_move_cases at 473841:474058

Project Member Reported by toyoshim@chromium.org, May 30 2017

Issue description

See the link to graphs below.

Comment 1 by toyoshim@chromium.org, May 30 2017

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=727515

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-vbqpwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-uaG6AgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg2oOM2wgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-rqM4AkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDguv-lvwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDghqD7uwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-tytpQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-uWH_AoM


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

android-nexus5
android-nexus5X
android-webview-nexus5X
chromium-rel-mac11
chromium-rel-mac11-air
chromium-rel-win7-dual
chromium-rel-win7-x64-dual
chromium-rel-win8-dual

Project Member

Comment 2 by 42576172...@developer.gserviceaccount.com, May 30 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978194453456914848

Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, May 30 2017


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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : smoothness.key_desktop_move_cases
  Metric       : mean_frame_time/mean_frame_time

Revision             Result                  N
chromium@473840      28.3408 +- 1.07212      21      good
chromium@473949      28.5454 +- 2.40234      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 smoothness.key_desktop_move_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978194453456914848

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6666082925936640


| 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 4 by 42576172...@developer.gserviceaccount.com, May 30 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978185878531293264

Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, May 30 2017


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

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : smoothness.key_desktop_move_cases
  Metric       : mean_frame_time/mean_frame_time

Revision             Result                   N
chromium@473840      28.5537 +- 1.0708        21      good
chromium@473949      28.4758 +- 0.980613      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 smoothness.key_desktop_move_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978185878531293264

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6666082925936640


| 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 31 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978090576631183360

Comment 7 by toyoshim@chromium.org, May 31 2017

triggered another bisect with another test in the bug.
will close as WontFix if this also can not find regression.

Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, May 31 2017


=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

Error: INFRA_FAILURE

The bisect was able to narrow the range, you can try running with:
  good_revision: e3fe5e855cb0ecae33620fbfbb651ec3e0ed0d96
  bad_revision : d2eb8579c1d9977bb51c2041eecb431a0b5fabdc

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : smoothness.key_silk_cases
  Metric       : queueing_durations/queueing_durations

Revision             Result                      N
chromium@473887      0.409721 +- 0.01037         9      good
chromium@473918      0.408469 +- 0.0154568       8      good
chromium@473926      0.426771 +- 0.0235502       8      bad
chromium@473934      0.429008 +- 0.00453356      4      bad
chromium@473949      0.428885 +- 0.0121573       5      bad
chromium@474010      0.427835 +- 0.00920337      5      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 smoothness.key_silk_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978090576631183360

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6670260855373824


| 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 9 by 42576172...@developer.gserviceaccount.com, May 31 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978038654733300624

Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, May 31 2017


=== BISECT JOB RESULTS ===
Bisect was unable to run to completion

Error: INFRA_FAILURE

The bisect was able to narrow the range, you can try running with:
  good_revision: e3fe5e855cb0ecae33620fbfbb651ec3e0ed0d96
  bad_revision : d2eb8579c1d9977bb51c2041eecb431a0b5fabdc

If failures persist contact the team (see below) and report the error.


Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : smoothness.key_silk_cases
  Metric       : queueing_durations/queueing_durations

Revision             Result                      N
chromium@473887      0.409721 +- 0.01037         9      good
chromium@473918      0.408469 +- 0.0154568       8      good
chromium@473926      0.426771 +- 0.0235502       8      bad
chromium@473934      0.429008 +- 0.00453356      4      bad
chromium@473949      0.428885 +- 0.0121573       5      bad
chromium@474010      0.427835 +- 0.00920337      5      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 smoothness.key_silk_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978038654733300624

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6670260855373824


| 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 11 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8977940036045296208

Project Member

Comment 12 by 42576172...@developer.gserviceaccount.com, Jun 2 2017


=== BISECT JOB RESULTS ===
Bisect failed unexpectedly

Bisect was aborted with the following:
  Step('Bisecting revision.Post bisect results (3)') failed with return_code 1


Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : smoothness.key_silk_cases
  Metric       : queueing_durations/queueing_durations

Revision             Result                      N
chromium@473887      0.217314 +- 0.00955892      5      good
chromium@473918      0.222882 +- 0.0129235       6      good
chromium@473949      0.240012 +- 0.0124173       7      bad
chromium@474010      0.238074 +- 0.00961122      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 smoothness.key_silk_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977940036045296208

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5283852123111424


| 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 13 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8977906539015673648

Project Member

Comment 14 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8977864883385916608

Project Member

Comment 15 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Mergedinto: 725949
Status: Duplicate (was: Untriaged)


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

Suspected Commit
  Author : sadrul
  Commit : a6251cb3214b42349e7208d285a5e2e01276fe6f
  Date   : Tue May 23 16:06:27 2017
  Subject: input: Dispatch synthesized events at regular intervals.

Bisect Details
  Configuration: win_x64_perf_bisect
  Benchmark    : smoothness.key_desktop_move_cases
  Metric       : mean_frame_time/mean_frame_time
  Change       : 9.38% | 18.208 -> 19.915

Revision             Result                   N
chromium@473850      18.208 +- 0.468539       6      good
chromium@473916      18.0737 +- 1.05987       6      good
chromium@473921      18.028 +- 0.786018       6      good
chromium@473922      19.9646 +- 0.647931      6      bad       <--
chromium@473923      20.1309 +- 0.798918      6      bad
chromium@473925      19.852 +- 0.785272       6      bad
chromium@473933      19.9749 +- 0.822632      6      bad
chromium@473949      20.0539 +- 0.647016      6      bad
chromium@473982      19.915 +- 0.921307       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests smoothness.key_desktop_move_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977864883385916608

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6179389445767168


| 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 16 by 42576172...@developer.gserviceaccount.com, Jun 2 2017


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

Suspected Commit
  Author : sadrul
  Commit : a6251cb3214b42349e7208d285a5e2e01276fe6f
  Date   : Tue May 23 16:06:27 2017
  Subject: input: Dispatch synthesized events at regular intervals.

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : smoothness.key_silk_cases
  Metric       : queueing_durations/queueing_durations
  Change       : 7.58% | 0.221004125131 -> 0.237756840807

Revision             Result                      N
chromium@473887      0.221004 +- 0.0101764       6      good
chromium@473918      0.21874 +- 0.01289          6      good
chromium@473920      0.223937 +- 0.00952215      6      good
chromium@473921      0.219371 +- 0.00762211      6      good
chromium@473922      0.240989 +- 0.0158361       6      bad       <--
chromium@473926      0.241111 +- 0.008715        6      bad
chromium@473934      0.239098 +- 0.0105604       5      bad
chromium@473949      0.243371 +- 0.0112363       6      bad
chromium@474010      0.237757 +- 0.0100724       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 smoothness.key_silk_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977906539015673648

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5283852123111424


| 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!

►

Issue 727515 link

Issue metadata

2.6%-13.3% regression in smoothness.key_desktop_move_cases at 473841:474058

Issue description

Comment 1 by toyoshim@chromium.org, May 30 2017

Comment 1 Deleted

Comment 2 by 42576172...@developer.gserviceaccount.com, May 30 2017

Comment 2 Deleted

Comment 3 by 42576172...@developer.gserviceaccount.com, May 30 2017

Comment 3 Deleted

Comment 4 by 42576172...@developer.gserviceaccount.com, May 30 2017

Comment 4 Deleted

Comment 5 by 42576172...@developer.gserviceaccount.com, May 30 2017

Comment 5 Deleted

Comment 6 by 42576172...@developer.gserviceaccount.com, May 31 2017

Comment 6 Deleted

Comment 7 by toyoshim@chromium.org, May 31 2017

Comment 7 Deleted

Comment 8 by 42576172...@developer.gserviceaccount.com, May 31 2017

Comment 8 Deleted

Comment 9 by 42576172...@developer.gserviceaccount.com, May 31 2017

Comment 9 Deleted

Comment 10 by 42576172...@developer.gserviceaccount.com, May 31 2017

Comment 10 Deleted

Comment 11 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Comment 11 Deleted

Comment 12 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Comment 12 Deleted

Comment 13 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Comment 13 Deleted

Comment 14 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Comment 14 Deleted

Comment 15 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Comment 15 Deleted

Comment 16 by 42576172...@developer.gserviceaccount.com, Jun 2 2017

Comment 16 Deleted

Sign in to add a comment