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

Issue 628282 link

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



Sign in to add a comment

1%-12.9% regression in system_health.memory_mobile at 404887:404977

Project Member Reported by petrcermak@chromium.org, Jul 14 2016 
See the link to graphs below.
Project Member

Comment 4 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@404892  10461867  1762191  12  good
chromium@404931  11862016  1128635  12  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_media-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_media_9gag
Relative Change: 14.10%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/514
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004251547074844544


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5819641255952384

| 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 19 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@404892  10963285  1816162  12  good
chromium@404931  12339200  1195693  12  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_search-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_search_baidu
Relative Change: 5.74%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/542
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003875932206255072


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5511478359097344

| 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 8 by 42576172...@developer.gserviceaccount.com, Aug 23 2016 


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


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N   Good?
chromium@404892  10280619  1757903  12  good
chromium@404902  9601024   958460   5   good
chromium@404912  12108459  1018357  12  bad
chromium@404931  12691115  1489230  12  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_media-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_media_9gag
Relative Change: 15.12%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/553
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003619691993937360


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5838170852163584

| 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 10 by 42576172...@developer.gserviceaccount.com, Aug 23 2016 


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


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N   Good?
chromium@404892  10280619  1757903  12  good
chromium@404902  9601024   958460   5   good
chromium@404912  12108459  1018357  12  bad
chromium@404931  12691115  1489230  12  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_media-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_media_9gag
Relative Change: 15.12%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/553
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003619691993937360


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5838170852163584

| 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 12 by 42576172...@developer.gserviceaccount.com, Aug 23 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@404902  10310315  1760415  12  good
chromium@404912  12011520  1066202  12  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_media-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_media_9gag
Relative Change: 15.48%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/583
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003547055008912576


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5891130885931008

| 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 14 by 42576172...@developer.gserviceaccount.com, Aug 24 2016

Cc: piman@chromium.org
Owner: piman@chromium.org

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

Hi piman@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 : Simplify ppapi Graphics3D size propagation a bit
Author  : piman
Commit description:
  
- after https://codereview.chromium.org/2104403003/ we parse the attributes from
  the plugin side, so we know the correct size from the start, and we don't need
  to track the original size.
- we can also pass gfx::Size through IPC with some extra validation (negative
  coordinates) in common code.
- overall net fewer lines

BUG=None

Committed: https://crrev.com/1135d428cd8f5b19d458c5e67ba90776c4e09381
Review-Url: https://codereview.chromium.org/2136743002
Cr-Original-Commit-Position: refs/heads/master@{#404580}
Cr-Commit-Position: refs/heads/master@{#404893}
Commit  : b36392c2dc38c81c6165a591e217e37598605137
Date    : Wed Jul 13 02:14:51 2016


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N   Good?
chromium@404892  10139648  1740835  12  good
chromium@404893  12665856  1078049  8   bad    <--
chromium@404894  12371558  847400   5   bad
chromium@404895  12249771  1135703  12  bad
chromium@404897  12638891  1241452  12  bad
chromium@404902  12696781  1064564  5   bad
chromium@404912  12144640  929824   12  bad
chromium@404931  12134059  1339057  12  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_media-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_media_9gag
Relative Change: 17.23%
Score: 99.5

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/579
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003619691993937360


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5838170852163584

| 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 piman@chromium.org, Aug 24 2016

Owner: petrcermak@chromium.org
This is not the correct CL: it only touches Pepper code, which is not used on Android.
Project Member

Comment 17 by 42576172...@developer.gserviceaccount.com, Aug 24 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@404892  10214400  2045299  8  good
chromium@404931  12151808  1333659  8  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 628282

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_media-memory:chrome:all_processes:reported_by_os:system_memory:java_heap:private_dirty_size_avg/load_media_9gag
Relative Change: 16.84%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/596
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003428895883342144


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5788759199580160

| 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 petrcermak@chromium.org, Aug 30 2016

Labels: SystemHealth-Sheriff

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

Labels: -Performance-Sheriff

Comment 20 by robert...@chromium.org, Sep 9 2016

Status: WontFix (was: Assigned)
Bisect was unable to reproduce in most cases, the metric is very noisy (stddev is about as large as the supposed regression) also, the metrics have since recovered.

Closing this bug.
►

Sign in to add a comment