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

Issue 659058 link

Starred by 1 user

Issue metadata

Status: Duplicate
Owner: ----
Closed: Oct 2016
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

18.7% regression in smoothness.gpu_rasterization.polymer at 421078:421130

Project Member Reported by alexclarke@chromium.org, Oct 25 2016

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=659058

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgnd27vgoM


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

android-nexus5
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Oct 25 2016


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


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@421077  80.3606  2.21001  4  good

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 659058

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests smoothness.gpu_rasterization.polymer
Test Metric: mean_input_event_latency/mean_input_event_latency
Relative Change: None
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4278
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8997836141567675936


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5897955519758336

| 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, Oct 25 2016

Bisect failed: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4284
Failure reason: the build has failed.
Additional errors:
The metric was not found in the test output.
Either of the initial "good" or "bad" revisions failed to be tested or built.

Project Member

Comment 7 by 42576172...@developer.gserviceaccount.com, Oct 26 2016

Mergedinto: 650650
Status: Duplicate (was: Untriaged)

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


===== SUSPECTED CL(s) =====
Subject : Idle cleanup for worker context
Author  : ericrk
Commit description:
  
Currently, Skia flushes unused items out of its caches after ~1 second
of non-use (50 flushes). This works fine while Skia is in-use, but when
a worker context goes idle we stop calling into Skia altogether. This
means that Skia will never flush out unused cache items from the last
piece of work it did. This can lead to some rather large temporaries
being kept around (~20mb).

This change adds an idle cleanup process which flushes Skia's caches
and cleans up worker context resources after a worker context is idle
for 1 second.

BUG= 624630 
CQ_INCLUDE_TRYBOTS=master.tryserver.blink:linux_precise_blink_rel;master.tryserver.blink:linux_precise_blink_dbg

Committed: https://crrev.com/051ae83bf29b52cefd82235ebfb90f203912afbb
Review-Url: https://codereview.chromium.org/2353033003
Cr-Original-Commit-Position: refs/heads/master@{#420496}
Cr-Commit-Position: refs/heads/master@{#421092}
Commit  : 6714c23b526197220d8b9abdbd38b6d9c206d912
Date    : Tue Sep 27 03:37:20 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@421000  81.2824  1.44374  6  good
chromium@421050  79.7718  1.28733  5  good
chromium@421075  82.0015  2.97328  5  good
chromium@421088  80.5587  2.75012  5  good
chromium@421091  82.4658  2.54889  5  good
chromium@421092  102.547  4.3668   4  bad    <--
chromium@421093  100.359  2.49197  5  bad
chromium@421094  102.615  3.59997  4  bad
chromium@421100  100.19   1.90577  5  bad
chromium@421200  102.398  2.3867   6  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 659058

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests smoothness.gpu_rasterization.polymer
Test Metric: mean_input_event_latency/mean_input_event_latency
Relative Change: 26.79%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4283
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8997828738882999648


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5235001547816960

| 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, Apr 11 2017

Bisect failed: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4846
Failure reason: the build has failed due to infrastructure failure.

Sign in to add a comment