New issue
Advanced search Search tips

Issue 732465 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 728471
Owner: ----
Closed: Jun 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.3% regression in media.tough_video_cases_tbmv2 at 475922:476066

Project Member Reported by chcunningham@google.com, Jun 12 2017

Issue description

Bump in allocated objects size avg from chrome:memory:all_processes
 
Project Member

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


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

Bisect Details
  Configuration: win_8_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_avg/video.html?src_crowd1080.webm

Revision             Result                  N
chromium@475921      1910613 +- 16063.7      21      good
chromium@476066      1909842 +- 2891.13      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=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976970494240502992

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5312311683710976


| 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, Jun 12 2017


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

Bisect Details
  Configuration: win_8_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_avg/video.html?src_crowd1080.webm

Revision             Result                  N
chromium@475921      1910058 +- 9869.56      21      good
chromium@476066      1909682 +- 2267.85      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=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976962817070671984

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5312311683710976


| 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!
Looking closer, many of these do not have a ref graph, but those that do show a matching bump in both ref and tip of tree. Will try one last bisect on one of the ref-less graphs and close if no findings.
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jun 13 2017

Mergedinto: 728471
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : nednguyen
  Commit : 24245dde6fc83c8881775a3d2556797f5bba287b
  Date   : Wed May 31 11:04:00 2017
  Subject: Always execute network_quiescence.js script upon navigating to a page

Bisect Details
  Configuration: win_x64_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : memory:chrome:all_processes:reported_by_chrome:v8:allocated_objects_size_avg/video.html?src_crowd1080.webm
  Change       : 1.58% | 2988452.0 -> 3035604.0

Revision                                 Result                  N
chromium@475880                          2988452 +- 372.451      6      good
chromium@475893                          2988288 +- 471.118      6      good
chromium@475897                          2988745 +- 2063.36      6      good
chromium@475897,catapult@24245dde6f      3035808 +- 471.118      6      bad       <--
chromium@475898                          3035831 +- 355.513      6      bad
chromium@475899                          3035740 +- 568.929      6      bad
chromium@475900                          3035551 +- 2884.03      6      bad
chromium@475906                          3036035 +- 1871.34      6      bad
chromium@475932                          3035672 +- 192.333      6      bad
chromium@475984                          3035604 +- 166.565      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 --story-filter=video.html.src.crowd1080.webm media.tough_video_cases_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8976952061332126432

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5598343083851776


| 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