New issue
Advanced search Search tips

Issue 593188 link

Starred by 0 users

Issue metadata

Status: Fixed
Owner: ----
Closed: Mar 2016
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

5.2% regression in startup.warm.blank_page at 379759:379773

Project Member Reported by ericwilligers@chromium.org, Mar 9 2016

Issue description

ChromiumPerf/chromium-rel-mac10/startup.warm.blank_page / first_main_frame_load_time
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=593188

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDAv_-dowoM


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

chromium-rel-mac10
Cc: tzik@chromium.org
Owner: tzik@chromium.org

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

Hi tzik@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 : Replace base::Tuple in //ipc with std::tuple
Author  : tzik
Commit description:
  
BUG= 554987 

Review URL: https://codereview.chromium.org/1770013002

Cr-Commit-Position: refs/heads/master@{#379759}
Commit  : 55e3e4d3c52bf99bd8a710e55b1dcccea5e3acc6
Date    : Tue Mar 08 05:50:35 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379758         576.757895  2.337399    5           good
chromium@379759         587.642105  3.768289    5           bad
chromium@379760         585.842105  3.242934    5           bad
chromium@379761         587.957895  2.113602    5           bad
chromium@379763         588.336842  5.019988    5           bad
chromium@379767         594.715789  20.651729   5           bad
chromium@379773         584.315789  1.653503    5           bad

Bisect job ran on: mac_10_10_perf_bisect
Bug ID: 593188

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.warm.blank_page
Test Metric: first_main_frame_load_time/first_main_frame_load_time
Relative Change: 1.31%
Score: 99.8

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_10_perf_bisect/builds/2029
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018709932033130464


| 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 label Cr-Tests-AutoBisect.  Thank you!

Comment 3 by tzik@chromium.org, Mar 9 2016

Really...? My change does mostly nothing to the executable. It just expanded a type alias and replacing MakeRefTuple with a std equivalent.
The delta of MakeRefTuple and std::tie is _NOEXCEPT_ addition only.
Owner: ericwilligers@chromium.org
Sorry for the noise, tzik. The bisect was looking for a 5% regression, and only found 1.3% at your CL, which is likely within the noise. We're working on making the bisect work better in cases like these.

For the original regression, looking at the other mac bots it's a little strange:
https://chromeperf.appspot.com/report?sid=34998f4d05383e5dfebcf44d8cbe9ce500cc2a97d3c09eeaa83e5a3a660fb895&rev=379773

The Mac 10 bot shows a 5% regression, Mac 11 and Retina show no regression, and the older Mac with a HDD shows a ~2% regression at a slightly earlier range. I'm going to kick off two additional bisects--one on the HDD mac, and one with an expanded range.

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


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379708         1265.736842 12.62724    24          good
chromium@379728         1267.940109 12.662616   29          bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 593188

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.warm.blank_page
Test Metric: first_main_frame_load_time/first_main_frame_load_time
Relative Change: 0.55%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/444
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018660218083875280


| 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 label Cr-Tests-AutoBisect.  Thank you!
Cc: jbudorick@chromium.org
Owner: jbudorick@chromium.org

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

Hi jbudorick@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 : Add jbudorick to //testing/android/OWNERS.
Author  : jbudorick
Commit description:
  
BUG=

Review URL: https://codereview.chromium.org/1775753002

Cr-Commit-Position: refs/heads/master@{#379709}
Commit  : 0bd9473b9553929068a7a2dcf4e50ccee084043b
Date    : Tue Mar 08 03:04:01 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379708         571.440546  3.157394    27          good
chromium@379709         578.915789  2.976966    5           bad
chromium@379710         580.484211  1.971191    5           bad
chromium@379712         585.157895  6.104583    5           bad
chromium@379715         579.394737  3.101991    4           bad
chromium@379724         583.810526  5.128353    5           bad
chromium@379739         588.210526  23.599732   5           bad
chromium@379773         574.866496  4.762825    41          bad

Bisect job ran on: mac_10_10_perf_bisect
Bug ID: 593188

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.warm.blank_page
Test Metric: first_main_frame_load_time/first_main_frame_load_time
Relative Change: 0.03%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_10_perf_bisect/builds/2031
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018660211869699216


| 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 label Cr-Tests-AutoBisect.  Thank you!
Owner: ----
Status: Available (was: Assigned)
try again, bisect bot.
I don't think bisect when through, so I kicked-off another one
https://chromeperf.appspot.com/buildbucket_job_status/9018085828378799456
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Mar 15 2016


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


===== SUSPECTED CL(s) =====
Subject : Replace base::Tuple in //ipc with std::tuple
Author  : tzik
Commit description:
  
BUG= 554987 

Review URL: https://codereview.chromium.org/1770013002

Cr-Commit-Position: refs/heads/master@{#379759}
Commit  : 55e3e4d3c52bf99bd8a710e55b1dcccea5e3acc6
Date    : Tue Mar 08 05:50:35 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@379758         578.614035  3.170093    6           good
chromium@379759         588.378947  2.988297    5           bad
chromium@379760         589.578947  2.912957    6           bad
chromium@379761         591.263158  1.759423    5           bad
chromium@379763         588.978947  1.616484    5           bad
chromium@379767         585.447368  2.538349    8           bad
chromium@379773         584.921053  2.805811    8           bad

Bisect job ran on: mac_10_10_perf_bisect
Bug ID: 593188

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests startup.warm.blank_page
Test Metric: first_main_frame_load_time/first_main_frame_load_time
Relative Change: 1.10%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_10_perf_bisect/builds/2042
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9018085828378799456


| 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 label Cr-Tests-AutoBisect.  Thank you!
Status: Fixed (was: Available)
This has since recovered.

Sign in to add a comment