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

Issue 752419 link

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



Sign in to add a comment

81.3%-89.3% improvement in memory.long_running_idle_gmail_background_tbmv2 at 490023:490131

Project Member Reported by alexclarke@chromium.org, Aug 4 2017 
Suspiciously large improvements, did something break?
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Aug 4 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=752419

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=8d9d6e25fd4b33e278ecf7c395b4e4a93bee80db7305a26796af802539476e59


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

chromium-rel-win7-gpu-ati
linux-release
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Aug 4 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 Degenbaev
  Commit : 2cc8fdfb47226101b958da465d64803368fb7c76
  Date   : Thu Jul 27 11:09:24 2017
  Subject: [heap] Re-implement weak cell tracking in the marker.

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : memory.long_running_idle_gmail_background_tbmv2
  Metric       : v8-gc-incremental-finalize_avg/v8-gc-incremental-finalize_avg
  Change       : 80.07% | 1.15737896825 -> 0.230621339445

Revision                           Result                     N
chromium@490022                    1.15738 +- 0.499326        6      good
chromium@490026                    1.24029 +- 0.644347        6      good
chromium@490027                    1.32697 +- 0.942805        6      good
chromium@490027,v8@2cc8fdfb47      0.277778 +- 0.0767851      6      bad       <--
chromium@490027,v8@6a75fcd4df      0.202049 +- 0.317371       6      bad
chromium@490027,v8@e4bbf92be3      0.236266 +- 0.357142       6      bad
chromium@490027,v8@9836cdb1ad      0.319721 +- 0.368852       6      bad
chromium@490028                    0.253374 +- 0.312931       6      bad
chromium@490029                    0.214054 +- 0.350047       6      bad
chromium@490036                    0.197649 +- 0.356836       6      bad
chromium@490050                    0.2214 +- 0.262948         6      bad
chromium@490077                    0.194448 +- 0.201813       6      bad
chromium@490131                    0.230621 +- 0.340852       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 memory.long_running_idle_gmail_background_tbmv2

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972207350450115360


For feedback, file a bug with component Speed>Bisection
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Aug 11 2017

Status: Assigned (was: Untriaged)

=== 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 Degenbaev
  Commit : 2cc8fdfb47226101b958da465d64803368fb7c76
  Date   : Thu Jul 27 11:09:24 2017
  Subject: [heap] Re-implement weak cell tracking in the marker.

Bisect Details
  Configuration: linux_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/browse_search/browse_search_google
  Change       : 2.22% | 15380859.5556 -> 15051849.7778

Revision                           Result                   N
chromium@490022                    15380860 +- 468452       9       good
chromium@490027                    15377985 +- 731308       14      good
chromium@490027,v8@2cc8fdfb47      15076672 +- 1019309      21      bad       <--
chromium@490027,v8@6a75fcd4df      15068567 +- 545838       14      bad
chromium@490027,v8@e4bbf92be3      15091539 +- 655486       14      bad
chromium@490027,v8@9836cdb1ad      15049962 +- 511560       14      bad
chromium@490028                    15030354 +- 556374       14      bad
chromium@490029                    15056902 +- 424130       9       bad
chromium@490031                    14941725 +- 265797       6       bad
chromium@490039                    15032428 +- 299083       6       bad
chromium@490055                    15081059 +- 779290       14      bad
chromium@490087                    15051850 +- 562559       9       bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

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=browse.search.google system_health.memory_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8971569952361498272


For feedback, file a bug with component Speed>Bisection

Comment 6 by u...@chromium.org, Aug 14 2017

Status: WontFix (was: Assigned)
This is an improvement.
►

Sign in to add a comment