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

Issue 719359 link

Starred by 3 users

Issue metadata

Status: Fixed
Owner:
Last visit > 30 days ago
Closed: May 2017
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

78.5% regression in v8.infinite_scroll_tbmv2 at 469653:469745

Project Member Reported by kraynov@chromium.org, May 8 2017

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=719359

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgitXxqQkM


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

chromium-rel-win7-gpu-nvidia

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

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


Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : v8.infinite_scroll_tbmv2
  Metric       : v8-gc-total_max/flickr


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=flickr v8.infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980177396901796208

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5262025644572672


| 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!

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

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


Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : v8.infinite_scroll_tbmv2
  Metric       : v8-gc-total_max/flickr


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=flickr v8.infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980177362878681408

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5818826949656576


| 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!
Cc: hpayer@chromium.org
Owner: hpayer@chromium.org

=== Auto-CCing suspected CL author hpayer@chromium.org ===

Hi hpayer@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 : hpayer
  Commit : 8833af23e9788c725b0887446915e4820383a385
  Date   : Fri May 05 11:24:02 2017
  Subject: [heap] Memory reducer calls GC with kGCCallbackFlagCollectAllExternalMemory flag.

Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : v8.infinite_scroll_tbmv2
  Metric       : v8-gc-total_max/flickr
  Change       : 74.81% | 4.72716666667 -> 8.26366666667

Revision                           Result                   N
chromium@469652                    4.72717 +- 1.10252       6      good
chromium@469654                    4.55083 +- 0.465576      6      good
chromium@469654,v8@25959abf79      4.59167 +- 0.230472      6      good
chromium@469654,v8@b7b3781b87      4.52917 +- 1.47563       6      good
chromium@469654,v8@8833af23e9      8.09967 +- 1.07426       6      bad       <--
chromium@469655                    8.413 +- 1.07612         6      bad
chromium@469658                    8.50417 +- 1.43633       6      bad
chromium@469664                    7.73222 +- 3.42775       9      bad
chromium@469676                    8.57 +- 2.02806          6      bad
chromium@469699                    8.30517 +- 1.85657       6      bad
chromium@469745                    8.26367 +- 1.56802       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=flickr v8.infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980175236417264032

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5262025644572672


| 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!

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

Suspected Commit
  Author : hpayer
  Commit : 8833af23e9788c725b0887446915e4820383a385
  Date   : Fri May 05 11:24:02 2017
  Subject: [heap] Memory reducer calls GC with kGCCallbackFlagCollectAllExternalMemory flag.

Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : v8.infinite_scroll_tbmv2
  Metric       : v8-gc-total_max/flickr
  Change       : 73.71% | 4.843 -> 8.41266666667

Revision                           Result                   N
chromium@469652                    4.843 +- 1.09984         6      good
chromium@469654                    4.71 +- 1.28567          6      good
chromium@469654,v8@25959abf79      4.73767 +- 0.583794      6      good
chromium@469654,v8@b7b3781b87      4.602 +- 0.955925        6      good
chromium@469654,v8@8833af23e9      8.71633 +- 1.44706       6      bad       <--
chromium@469655                    8.842 +- 1.55945         6      bad
chromium@469657                    7.45467 +- 3.70229       6      bad
chromium@469661                    9.08367 +- 1.75925       6      bad
chromium@469670                    8.41267 +- 2.37052       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=flickr v8.infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980175233630443312

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5818826949656576


| 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!

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

Suspected Commit
  Author : hpayer
  Commit : 8833af23e9788c725b0887446915e4820383a385
  Date   : Fri May 05 11:24:02 2017
  Subject: [heap] Memory reducer calls GC with kGCCallbackFlagCollectAllExternalMemory flag.

Bisect Details
  Configuration: winx64ati_perf_bisect
  Benchmark    : v8.infinite_scroll_tbmv2
  Metric       : v8-gc-total_max/tumblr
  Change       : 102.60% | 3.07055555556 -> 5.49766666667

Revision                           Result                  N
chromium@469626                    3.07056 +- 2.39714      9       good
chromium@469644                    3.15678 +- 2.94916      9       good
chromium@469653                    3.41056 +- 3.3307       9       good
chromium@469654                    3.13233 +- 2.58221      6       good
chromium@469654,v8@25959abf79      3.06644 +- 2.92774      9       good
chromium@469654,v8@b7b3781b87      2.89767 +- 2.7943       9       good
chromium@469654,v8@8833af23e9      5.52989 +- 1.73445      9       bad       <--
chromium@469655                    5.38036 +- 1.7986       14      bad
chromium@469657                    5.95789 +- 1.40626      9       bad
chromium@469661                    5.46778 +- 1.21525      9       bad
chromium@469695                    5.49767 +- 1.17599      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=tumblr v8.infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980176136530048576

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6013746658410496


| 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!

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

Suspected Commit
  Author : hpayer
  Commit : 8833af23e9788c725b0887446915e4820383a385
  Date   : Fri May 05 11:24:02 2017
  Subject: [heap] Memory reducer calls GC with kGCCallbackFlagCollectAllExternalMemory flag.

Bisect Details
  Configuration: winx64nvidia_perf_bisect
  Benchmark    : v8.infinite_scroll_tbmv2
  Metric       : v8-gc-total_max/tumblr
  Change       : 110.16% | 2.71416666667 -> 5.70416666667

Revision                           Result                   N
chromium@469652                    2.71417 +- 0.535937      6      good
chromium@469654                    3.2975 +- 1.75072        6      good
chromium@469654,v8@25959abf79      3.377 +- 2.18711         6      good
chromium@469654,v8@b7b3781b87      3.11633 +- 2.73758       9      good
chromium@469654,v8@8833af23e9      6.12833 +- 2.98446       6      bad       <--
chromium@469655                    5.6115 +- 1.3182         6      bad
chromium@469658                    6.00683 +- 1.74787       6      bad
chromium@469664                    5.54417 +- 0.84198       6      bad
chromium@469676                    5.42233 +- 1.43997       6      bad
chromium@469699                    5.68783 +- 1.57783       6      bad
chromium@469745                    5.70417 +- 1.59888       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=tumblr v8.infinite_scroll_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8980176203325101328

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5455395004350464


| 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!
Cc: mlippautz@chromium.org
 Issue 719404  has been merged into this issue.
 Issue 719405  has been merged into this issue.
 Issue 719403  has been merged into this issue.
 Issue 719483  has been merged into this issue.
 Issue 719534  has been merged into this issue.
 Issue 719534  has been merged into this issue.
 Issue 719494  has been merged into this issue.
Cc: -hpayer@chromium.org
Status: Assigned (was: Untriaged)
Project Member

Comment 22 by 42576172...@developer.gserviceaccount.com, May 10 2017

 Issue 719494  has been merged into this issue.
Cc: ryansturm@chromium.org
 Issue 719568  has been merged into this issue.
 Issue 719865  has been merged into this issue.
Project Member

Comment 25 by 42576172...@developer.gserviceaccount.com, May 11 2017

 Issue 719865  has been merged into this issue.
Project Member

Comment 26 by 42576172...@developer.gserviceaccount.com, May 11 2017

Cc: sullivan@chromium.org
 Issue 721094  has been merged into this issue.
Project Member

Comment 27 by 42576172...@developer.gserviceaccount.com, May 12 2017

 Issue 719884  has been merged into this issue.
Project Member

Comment 28 by bugdroid1@chromium.org, May 15 2017

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/2c9367ca48442529ac2669033478eac83b904ca0

commit 2c9367ca48442529ac2669033478eac83b904ca0
Author: hpayer <hpayer@chromium.org>
Date: Mon May 15 14:42:44 2017

Revert "Revert of Oilpan: Schedule an idle garbage collection after receiving the kGCCallbackScheduleIdleGarbageColle… (patchset #2 id:20001 of https://codereview.chromium.org/2871743002/ )"

This reverts commit bcf974f311836b1b26cdc3969e6e9bf3211c0550.

BUG= chromium:719359 , chromium:718484 

Review-Url: https://codereview.chromium.org/2881033002
Cr-Commit-Position: refs/heads/master@{#471756}

[modify] https://crrev.com/2c9367ca48442529ac2669033478eac83b904ca0/third_party/WebKit/Source/bindings/core/v8/V8GCController.cpp

Status: Fixed (was: Assigned)

Sign in to add a comment