New issue
Advanced search Search tips

Issue 642103 link

Starred by 1 user
Status: Fixed
Owner:
mlippautz@chromium.org
Closed: Aug 2016
Cc:
jochen@chromium.org
Components:
EstimatedDays: ----
NextAction: ----
OS: All
Pri: 2
Type: Bug-Regression



Sign in to add a comment

2.1%-5.6% regression in sunspider at 414883:414933

Project Member Reported by mustaq@chromium.org, Aug 29 2016 
See the link to graphs below.
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Aug 30 2016

Cc: mlippautz@chromium.org
Owner: mlippautz@chromium.org

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

Hi mlippautz@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [heap] GCTracer: Record details for incremental marking
Author  : mlippautz
Commit description:
  
Record details, such as cumulative duration, number of steps, and longest steps
in IncrementalMarkingDetails which get populated at a single callsite
(AddScopeSample). Remove member fields that thus become obsolete (unfortunately
not all of them).

Additional remove some dead code and refactor printing. Printing in a single
statement allows for using logcat on Android.

This should also address the regression in chromium:640524.

BUG= chromium:639818 ,chromium:640524
R=jochen@chromium.org

Review-Url: https://codereview.chromium.org/2269093002
Cr-Commit-Position: refs/heads/master@{#38912}
Commit  : 3866975f1b159f3703429ce50ca228bcdbf28306
Date    : Thu Aug 25 14:22:42 2016


===== TESTED REVISIONS =====
Revision                       Mean   Std Dev  N  Good?
chromium@414885                666.8  7.29383  5  good
chromium@414890                665.6  4.97996  5  good
chromium@414892                668.2  6.01664  5  good
chromium@414893                670.4  6.58027  5  good
chromium@414893,v8@6e67d04260  674.6  8.38451  5  good
chromium@414893,v8@a9fd19f4d1  672.6  7.66812  5  good
chromium@414893,v8@1f0c8d1e9a  663.2  4.96991  5  good
chromium@414893,v8@54f5558d52  667.6  5.59464  5  good
chromium@414893,v8@5e8acf6301  662.0  4.3589   5  good
chromium@414893,v8@3866975f1b  696.2  1.30384  5  bad    <--
chromium@414893,v8@2646749cbc  694.0  3.937    5  bad
chromium@414894                699.0  4.52769  5  bad
chromium@414903                709.0  6.12372  5  bad

Bisect job ran on: android_s5_perf_bisect
Bug ID: 642103

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests sunspider
Test Metric: Total/Total
Relative Change: 6.33%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_s5_perf_bisect/builds/968
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9002963551289928080


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5345142234415104

| 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 Tests>AutoBisect.  Thank you!
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Aug 30 2016 


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [heap] GCTracer: Record details for incremental marking
Author  : mlippautz
Commit description:
  
Record details, such as cumulative duration, number of steps, and longest steps
in IncrementalMarkingDetails which get populated at a single callsite
(AddScopeSample). Remove member fields that thus become obsolete (unfortunately
not all of them).

Additional remove some dead code and refactor printing. Printing in a single
statement allows for using logcat on Android.

This should also address the regression in chromium:640524.

BUG= chromium:639818 ,chromium:640524
R=jochen@chromium.org

Review-Url: https://codereview.chromium.org/2269093002
Cr-Commit-Position: refs/heads/master@{#38912}
Commit  : 3866975f1b159f3703429ce50ca228bcdbf28306
Date    : Thu Aug 25 14:22:42 2016


===== TESTED REVISIONS =====
Revision                       Mean   Std Dev   N  Good?
chromium@414882                591.0  1.58114   5  good
chromium@414892                592.4  0.894427  5  good
chromium@414893                593.4  1.51658   5  good
chromium@414893,v8@6e67d04260  594.0  2.82843   5  good
chromium@414893,v8@a9fd19f4d1  594.2  1.78885   5  good
chromium@414893,v8@1f0c8d1e9a  589.6  2.50998   5  good
chromium@414893,v8@54f5558d52  589.0  1.41421   5  good
chromium@414893,v8@5e8acf6301  589.6  1.51658   5  good
chromium@414893,v8@3866975f1b  611.8  3.27109   5  bad    <--
chromium@414893,v8@2646749cbc  613.4  1.51658   5  bad
chromium@414894                616.6  1.14018   5  bad
chromium@414895                615.4  2.88097   5  bad
chromium@414897                615.6  0.547723  5  bad
chromium@414902                616.4  1.81659   5  bad
chromium@414921                617.6  2.30217   5  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 642103

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests sunspider
Test Metric: Total/Total
Relative Change: 4.50%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/620
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9002962237534789312


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5859704549408768

| 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 Tests>AutoBisect.  Thank you!
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Aug 30 2016

Cc: jochen@chromium.org
Owner: jochen@chromium.org

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

Hi jochen@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Fully setup the catch variable for catch scopes
Author  : jochen
Commit description:
  
If the parser creates a catch scope, the variable is also added to
ordered_variables_ so just always do that.

Otherwise, it's not possible to create a ScopeInfo for that catch scope

R=verwaest@chromium.org
BUG=

Review-Url: https://codereview.chromium.org/2278963002
Cr-Commit-Position: refs/heads/master@{#38921}
Commit  : 1937d90085013ce5441bfdd346eaa6c32a2de027
Date    : Thu Aug 25 20:45:11 2016


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev   N   Good?
chromium@414883                195.8    0.447214  5   good
chromium@414889                195.0    1.22474   5   good
chromium@414892                194.6    1.14018   5   good
chromium@414893                195.0    1.0       5   good
chromium@414893,v8@3c1d076a85  196.4    1.14018   5   good
chromium@414893,v8@b7f796a6a4  198.5    1.51186   8   good
chromium@414893,v8@5558a50878  199.439  1.54998   41  good
chromium@414893,v8@1937d90085  200.732  2.07394   41  bad    <--
chromium@414893,v8@26fbac4b37  201.024  1.96835   41  bad
chromium@414893,v8@96886dc735  200.944  1.83021   18  bad
chromium@414893,v8@b143cb09d0  202.0    1.69031   8   bad
chromium@414894                202.6    2.07364   5   bad
chromium@414895                200.2    1.30384   5   bad
chromium@414906                200.0    1.87083   5   bad
chromium@414929                200.2    1.48324   5   bad

Bisect job ran on: win_x64_perf_bisect
Bug ID: 642103

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests sunspider
Test Metric: Total/Total
Relative Change: 2.25%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_x64_perf_bisect/builds/1456
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9002963514999042208


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5032279770923008

| 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 Tests>AutoBisect.  Thank you!

Comment 8 by mlippautz@chromium.org, Aug 30 2016

Cc: -mlippautz@chromium.org
Labels: OS-All
Owner: mlippautz@chromium.org
Status: Fixed (was: Assigned)
And this was related to GC tracer and is fixed with 33ffcc8f819d0cf8f86eabae6cd1860c693a4672 and any V8 starting from 5.5.11
►

Sign in to add a comment