New issue
Advanced search Search tips

Issue 727516 link

Starred by 1 user

Issue metadata

Status: Duplicate
Merged: issue 724954
Owner: ----
Closed: May 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

19.9% regression in v8.browsing_desktop_classic at 473467:473516

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

Issue description

tumblr/youtube
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=727516

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg-uv1uAsM


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

win-high-dpi
Project Member

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

Mergedinto: 724954
Status: Duplicate (was: Untriaged)

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

Suspected Commit
  Author : Ross McIlroy
  Commit : de4a4095cf22bc3c9cfa13eb5f8be28eb7a5f031
  Date   : Thu May 18 10:41:48 2017
  Subject: [Heap] Disable code flushing in preparation to remove it.

Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : v8.browsing_desktop_classic
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size_avg/browse_media/browse_media_youtube
  Change       : 3.82% | 39369700.4664 -> 40874290.9961

Revision                           Result                   N
chromium@472758                    39369700 +- 1467681      6       good
chromium@472814                    39953172 +- 2312148      9       good
chromium@472842                    39979074 +- 2389794      9       good
chromium@472849                    40158001 +- 1145055      6       good
chromium@472853                    39686639 +- 1677576      6       good
chromium@472855                    39641166 +- 1094942      6       good
chromium@472855,v8@5e9939214e      39828516 +- 2104546      9       good
chromium@472855,v8@de4a4095cf      40872995 +- 1292286      9       bad       <--
chromium@472855,v8@cd1325a890      41042098 +- 1024463      6       bad
chromium@472855,v8@9fd599ef98      40952264 +- 750678       6       bad
chromium@472856                    41033957 +- 2001163      14      bad
chromium@472869                    41256474 +- 1538099      9       bad
chromium@472979                    40874291 +- 715335       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=browse.media.youtube v8.browsing_desktop_classic

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978194381828025616

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5216224373374976


| 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 30 2017


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

Suspected Commit
  Author : Ross McIlroy
  Commit : de4a4095cf22bc3c9cfa13eb5f8be28eb7a5f031
  Date   : Thu May 18 10:41:48 2017
  Subject: [Heap] Disable code flushing in preparation to remove it.

Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : v8.browsing_desktop_classic
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size_avg/browse_media/browse_media_tumblr
  Change       : 10.65% | 28478675.8837 -> 31511985.0864

Revision                           Result                   N
chromium@472758                    28478676 +- 1319005      6      good
chromium@472814                    28465297 +- 643473       6      good
chromium@472842                    28273793 +- 741162       6      good
chromium@472849                    28440275 +- 1326791      6      good
chromium@472853                    28045878 +- 1001577      6      good
chromium@472855                    28185801 +- 1141708      6      good
chromium@472855,v8@5e9939214e      28091661 +- 1522460      9      good
chromium@472855,v8@de4a4095cf      31684011 +- 378967       6      bad       <--
chromium@472855,v8@cd1325a890      31417425 +- 934184       6      bad
chromium@472855,v8@9fd599ef98      30861457 +- 5805670      9      bad
chromium@472856                    31770507 +- 674015       6      bad
chromium@472869                    31522424 +- 895488       6      bad
chromium@472979                    31511985 +- 606713       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=browse.media.tumblr v8.browsing_desktop_classic

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978194395721551056

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=4996382848450560


| 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 7 by 42576172...@developer.gserviceaccount.com, May 31 2017


=== BISECT JOB RESULTS ===
Bisect failed for unknown reasons

Please contact the team (see below) and report the error.


Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : v8.browsing_desktop_classic
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size_avg/browse_media


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 v8.browsing_desktop_classic

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978194416538030880

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6423853456162816


| 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


=== BISECT JOB RESULTS ===
Bisect failed for unknown reasons

Please contact the team (see below) and report the error.


Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : v8.browsing_desktop_classic
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:allocated_objects_size_avg/browse_media


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 v8.browsing_desktop_classic

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978102831311795712

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6423853456162816


| 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