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

Issue 630270 link

Starred by 2 users
Status: WontFix
Owner:
█ petrcermak@chromium.org
Last visit > 30 days ago
Closed: Aug 2016
Cc:
█ petrcermak@chromium.org
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

4.4%-7.6% regression in system_health.memory_mobile at 406283:406306

Project Member Reported by petrcermak@chromium.org, Jul 21 2016 
See the link to graphs below.
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jul 21 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@406282  63593459  970306   12  good
chromium@406306  66593096  2975000  8   bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 630270

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile
Test Metric: load_games-memory:chrome:all_processes:reported_by_os:system_memory:private_dirty_size_avg/load_games_bubbles
Relative Change: 5.35%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3853
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9006522802304758960


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5290269247799296

| 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 4 by petrcermak@chromium.org, Jul 21 2016 

I suspect this could be due to a Skia change (https://codereview.chromium.org/2166453002), but we're blocked on https://github.com/catapult-project/catapult/issues/2511

Comment 5 by alexclarke@chromium.org, Jul 29 2016 

These metrics have (probably) recovered, although the ref moved too. Petr shall we close this?

Comment 7 by petrcermak@chromium.org, Aug 5 2016 

#5: The apparent recovery was due to a change in the SH story set, so I kicked off another bisect.
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Aug 15 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@406282  104215708  10815302  12  good
chromium@406306  98666951   11896276  8   bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 630270

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile
Test Metric: load_games-memory:chrome:all_processes:reported_by_os:system_memory:proportional_resident_size_avg/load_games_bubbles
Relative Change: 3.00%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3993
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004246770719240848


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5895957724528640

| 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 11 by 42576172...@developer.gserviceaccount.com, Aug 20 2016 


===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@406282  63540552  975188   5  good
chromium@406300  63270216  1029970  8  good
chromium@406305  64830280  2471360  8  good
chromium@406309  70291272  2725516  8  bad
chromium@406317  73837077  535797   5  bad
chromium@406351  70285026  3501930  5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 630270

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile
Test Metric: load_games-memory:chrome:all_processes:reported_by_os:system_memory:private_dirty_size_avg/load_games_bubbles
Relative Change: 10.61%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4024
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003876563434874592


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5309744953163776

| 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 13 by 42576172...@developer.gserviceaccount.com, Aug 20 2016 


===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@406282  63540552  975188   5  good
chromium@406300  63270216  1029970  8  good
chromium@406305  64830280  2471360  8  good
chromium@406309  70291272  2725516  8  bad
chromium@406317  73837077  535797   5  bad
chromium@406351  70285026  3501930  5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 630270

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile
Test Metric: load_games-memory:chrome:all_processes:reported_by_os:system_memory:private_dirty_size_avg/load_games_bubbles
Relative Change: 10.61%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4024
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003876563434874592


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5309744953163776

| 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, Aug 21 2016

Cc: petrcermak@chromium.org

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

Hi petrcermak@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 : [system-health] Run all SH stories in memory benchmarks
Author  : petrcermak
Commit description:
  
This patch modifies SH memory benchmarks (system_health.memory_desktop
and system_health.memory_mobile) to run all SH stories:

  - load:*   (already running)
  - browse:* (NEW)

As a result, all SH stories will also run in the SH smoke test on the
Chromium CQ
(benchmarks.system_health_smoke_test.SystemHealthBenchmarkSmokeTest.*).

*** NOTE TO SHERIFF ***
This patch is very likely to cause failures in the System Health
benchmarks (perf waterfall) and smoke tests (regular CQ). Please contact
me before reverting.

BUG=589726
CQ_INCLUDE_TRYBOTS=master.tryserver.chromium.perf:mac_retina_perf_cq

Review-Url: https://codereview.chromium.org/2159733002
Cr-Commit-Position: refs/heads/master@{#406309}
Commit  : 77952f99e4ae203b6b57005ce9e3476895426b96
Date    : Tue Jul 19 18:03:07 2016


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N  Good?
chromium@406282  63258440  775962   8  good
chromium@406300  63959880  2244894  8  good
chromium@406305  66878792  3195105  8  good
chromium@406307  64289608  2072777  8  good
chromium@406308  64876667  2525282  5  good
chromium@406309  72504648  2970257  8  bad    <--
chromium@406317  70035989  2916757  5  bad
chromium@406351  70302229  3055319  5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 630270

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_mobile
Test Metric: load_games-memory:chrome:all_processes:reported_by_os:system_memory:private_dirty_size_avg/load_games_bubbles
Relative Change: 11.75%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4026
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003876563434874592


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5309744953163776

| 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 16 by petrcermak@chromium.org, Aug 22 2016

Status: WontFix (was: Assigned)
SH story set change.

Comment 17 by petrcermak@chromium.org, Aug 30 2016

Labels: SystemHealth-Sheriff

Comment 18 by petrcermak@chromium.org, Aug 30 2016

Labels: -Performance-Sheriff
►

Sign in to add a comment