New issue
Advanced search Search tips

Issue 736486 link

Starred by 1 user
Status: WontFix
Owner: ----
Closed: Jun 2017
Cc:
simonhatch@chromium.org
wolenetz@chromium.org
crouleau@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

14.5% regression in media.tough_video_cases_tbmv2 at 479969:480020

Project Member Reported by wolenetz@chromium.org, Jun 23 2017 
Appears like a legit regression - bisecting.

Comment 1 by wolenetz@chromium.org, Jun 23 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=736486

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgjpy1uwoM


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

chromium-rel-win7-gpu-ati
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jun 23 2017 


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : cpu_time_percentage_avg/video.html?src_crowd1080.webm

Revision             Result                     N
chromium@479968      0.18277 +- 0.0962541       21      good
chromium@480020      0.188495 +- 0.0895554      21      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 --story-filter=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975964037921608656

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4831942391889920


| 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, Jun 24 2017 


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : cpu_time_percentage_avg/video.html?src_crowd1080.webm

Revision             Result                     N
chromium@479968      0.187453 +- 0.102177       21      good
chromium@480020      0.183743 +- 0.0845162      21      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 --story-filter=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975954927901938064

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4831942391889920


| 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 wolenetz@chromium.org, Jun 24 2017 

#6 is a slightly widened bisect range.
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jun 24 2017 


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : cpu_time_percentage_avg/video.html?src_crowd1080.webm

Revision             Result                     N
chromium@479880      0.186214 +- 0.106146       21      good
chromium@480203      0.181117 +- 0.0961494      21      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 --story-filter=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975946834686711568

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5220383529107456


| 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 10 by 42576172...@developer.gserviceaccount.com, Jun 24 2017 


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : cpu_time_percentage_avg/video.html?src_crowd1080.webm

Revision             Result                     N
chromium@479880      0.190574 +- 0.113864       21      good
chromium@480203      0.193691 +- 0.0927862      21      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 --story-filter=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975939828647163136

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5220383529107456


| 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 11 by wolenetz@chromium.org, Jun 24 2017

Cc: crouleau@chromium.org
crouleau@, would you recommend this to be WontFixed? None of the bisect attempts, above, could reproduce the issue. Are the bisect bots different from the alerting bots?

Comment 12 by crouleau@chromium.org, Jun 24 2017

Cc: simonhatch@chromium.org
Status: WontFix (was: Untriaged)
+simonhatch, please reopen if you have any idea what we can do from here. Any idea why the bisect isn't matching the graph?

Probably marking WontFix is the only thing we can do.

Comment 14 by simonhatch@chromium.org, Jun 27 2017 

AFAIK the bot configuration should be the same. I tried widening the range and removing the filter.
Project Member

Comment 15 by 42576172...@developer.gserviceaccount.com, Jun 27 2017 


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : cpu_time_percentage_avg/video.html?src_crowd1080.webm

Revision             Result                     N
chromium@479564      0.191762 +- 0.0206887      21      good
chromium@480277      0.190301 +- 0.0448034      21      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 media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975623489179977024

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5040203544133632


| 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 17 by 42576172...@developer.gserviceaccount.com, Jun 28 2017 


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

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : cpu_time_percentage_avg/video.html?src_crowd1080.webm

Revision             Result                     N
chromium@479564      0.19202 +- 0.0190408       21      good
chromium@480277      0.191542 +- 0.0265875      16      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 media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8975588766039653168

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5040203544133632


| 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!
►

Sign in to add a comment