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

Issue 629108 link

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

Blocked on:
issue 636755


Sign in to add a comment

1.1%-10.3% regression in system_health.memory_desktop at 405901:405918

Project Member Reported by petrcermak@chromium.org, Jul 18 2016 
See the link to graphs below.

Comment 4 by alexclarke@chromium.org, Jul 29 2016 

Trying another bisect.
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Jul 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@405900  41587456  0.0      12  good
chromium@405918  41587456  0.0      12  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 629108

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_media-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_media_9gag
Relative Change: 0.00%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1475
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005788164609822976


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5207955754975232

| 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 6 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@405900  79664112  9080935   12  good
chromium@405918  83361435  15011957  12  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 629108

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_media-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_media_dailymotion
Relative Change: 10.65%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1539
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005160398308815248


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5844247308140544

| 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 9 by 42576172...@developer.gserviceaccount.com, Aug 8 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@405900  93969163  3194.47  12  good
chromium@405918  93970785  3340.86  12  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 629108

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_tools-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_tools_drive
Relative Change: 0.00%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1547
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004901324138026384


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5877328454877184

| 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 9 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@405500  85131167  6233.07  12  good
chromium@406500  85131167  6233.07  12  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 629108

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_search-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_search_google
Relative Change: 0.01%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1554
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004798920765752240


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5786887650803712

| 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 10 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@405500  80739995  12807901  12  good
chromium@406500  82542235  13728827  12  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 629108

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_media-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_media_dailymotion
Relative Change: 0.00%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1560
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004716153894030016


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5286048024756224

| 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 15 by petrcermak@chromium.org, Aug 11 2016

Blockedon: 636755
Project Member

Comment 16 by 42576172...@developer.gserviceaccount.com, Aug 11 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@405500  80739995  12807901  12  good
chromium@406500  87031451  18361916  12  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 629108

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: load_media-memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/load_media_dailymotion
Relative Change: 11.52%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1563
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004630941239979552


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5251503065923584

| 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 18 by ericrk@chromium.org, Aug 15 2016

Status: WontFix (was: Assigned)
Per discussion in #16 of  crbug.com/636755  - there is a "regression" caused by https://codereview.chromium.org/2151393002, which disabled GPU rasterization on 10.9 systems. There's not much we can do about this regression, as GPU rasterization was disabled to prevent visual corruption. The change to enable GPU rasterization never made it to a stable release on 10.9, so no stable users will experience this "regression"

This would also explain why we have such a hard time bisecting - the bisect bot is at 10.11, so it was completely unaffected by the change.

Comment 19 by petrcermak@chromium.org, Aug 30 2016

Labels: SystemHealth-Sheriff

Comment 20 by petrcermak@chromium.org, Aug 30 2016

Labels: -Performance-Sheriff
►

Sign in to add a comment