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

Issue 599513 link

Starred by 0 users

Issue metadata

Status: Archived
Owner:
Closed: Jul 2016
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

1.5%-3.6% regression in page_cycler.intl_ko_th_vi at 383945:383980

Project Member Reported by majidvp@chromium.org, Mar 31 2016

Issue description

Fairly small regression but worth looking into none the less.
 
Project Member

Comment 2 by 42576172...@developer.gserviceaccount.com, Mar 31 2016


===== 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@383956         84113.3888892486.937241 18          good
chromium@383959         83216.7777781676.937494 18          bad

Bisect job ran on: linux_perf_bisect
Bug ID: 599513

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests page_cycler.typical_25
Test Metric: vm_private_dirty_final_renderer/vm_private_dirty_final_renderer
Relative Change: 0.10%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6365
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9016658697829544896


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=599513

| 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 3 by 42576172...@developer.gserviceaccount.com, Mar 31 2016


===== 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@383956         41911.416667842.796693  12          good
chromium@383976         41761.5     989.503135  12          bad

Bisect job ran on: android_nexus9_perf_bisect
Bug ID: 599513

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --also-run-disabled-tests page_cycler.intl_ar_fa_he
Test Metric: vm_private_dirty_final_browser/http___ynet.co.il_
Relative Change: 0.91%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/1699
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9016658491253014352


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=599513

| 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!
Cc: nyerramilli@chromium.org
Labels: TE-Triaged
just to update, previous bisect jobs are aborted and alerts are not yet recovered.

 majidvp@ could you please check the issue
Last one failed at device_status_check step, kick off another one in https://chromeperf.appspot.com/buildbucket_job_status/9014645727377478496
Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Apr 29 2016


===== 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     Std Dev  N  Good?
chromium@383948  46204.9  417.266  8  good
chromium@383969  48134.5  3050.24  8  bad

Bisect job ran on: android_nexus9_perf_bisect
Bug ID: 599513

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.typical_25
Test Metric: vm_private_dirty_final_browser/http___colorado.edu
Relative Change: 6.85%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/1764
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9014085114989083072


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5902295498227712

| 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!
Labels: Needs-Feedback
Navigated to "https://chromeperf.appspot.com/group_report?bug_id=599513" and observed that alerts on few Graphs have been recovered and few are not.
Could some one please look into the issue and update.
Thanks in Advance/
Cc: dtu@chromium.org pras...@chromium.org
===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@383948  46204.9  417.266  8  good
chromium@383969  48134.5  3050.24  8  bad

Dave, Prasad: can we bisect on std dev?
Cc: robert...@chromium.org
Some of the graphs had recovered, and there are few more which didn't recover.

#9: We do an option to kick-off bisect on std_dev, but Dave or Roberto might comment whether this is handled in statistical analysis of bisect results.
It is not handled, but dtu had mentioned before that the distributions should be different so bisect should catch it (IIUC). I filed a bad bisect report, we can chat more about it in today's meeting about bisects.
Labels: -performance-sheriff Performance-Sheriff
gentle ping.. 
Project Member

Comment 14 by 42576172...@developer.gserviceaccount.com, Jun 17 2016


===== 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     Std Dev  N   Good?
chromium@383947  84354.3  4052.26  17  good
chromium@383976  85905.7  3064.12  18  bad

Bisect job ran on: linux_perf_bisect
Bug ID: 599513

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.typical_25
Test Metric: vm_private_dirty_final_renderer/http___www.gamestop.com_ps3
Relative Change: 5.15%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/6539
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9009573779822456752


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5257068697616384

| 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 15 by 42576172...@developer.gserviceaccount.com, Jun 18 2016


===== 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     Std Dev  N  Good?
chromium@383948  39031.7  80.8595  6  good
chromium@383969  39053.5  101.915  8  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 599513

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.intl_ko_th_vi
Test Metric: vm_private_dirty_final_renderer/vm_private_dirty_final_renderer
Relative Change: 0.07%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3752
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9009573929909601344


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6438700892815360

| 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 16 by 42576172...@developer.gserviceaccount.com, Jun 18 2016


===== 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     Std Dev  N  Good?
chromium@383948  46512.5  915.384  8  good
chromium@383969  45949.4  589.152  8  bad

Bisect job ran on: android_nexus9_perf_bisect
Bug ID: 599513

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.typical_25
Test Metric: vm_private_dirty_final_browser/http___colorado.edu
Relative Change: 0.90%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/1831
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9009573606910063744


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5887046984400896

| 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!
Kicked off a bisect on ChromiumPerf/linux-release/page_cycler.typical_25 / vm_private_dirty_final_renderer / http___www.gamestop.com_ps3 which shows a very clear regression.


Status: Archived (was: Assigned)
3 months old at this point. I'm calling it.

Sign in to add a comment