New issue
Advanced search Search tips

Issue 604009 link

Starred by 0 users

Issue metadata

Status: Duplicate
Merged: issue 604007
Owner:
Closed: Apr 2016
Cc:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

11.2% regression in rasterize_and_record_micro.key_silk_cases at 387379:387429

Project Member Reported by rsch...@chromium.org, Apr 15 2016

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=604009

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICghPr_swkM


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

android-one
Bisect never came back. Trying another.
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Apr 29 2016

Mergedinto: 604007
Status: Duplicate (was: Assigned)

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


===== SUSPECTED CL(s) =====
Subject : Hook up ui::Compositor to Display's BeginFrameSource
Author  : enne
Commit description:
  
This hooks up the first SurfaceFactoryClient to the real
BeginFrameSource owned by the OnScreenDisplayClient.  This is done by
adding an OutputSurfaceClient::SetBeginFrameSource method.  As the
SurfaceDisplayOutputSurface is also a SurfaceFactoryClient, it can hand
the real begin frame source directly to ui::Compositor's scheduler.

This allows the removal of some of the browser vsync plumbing, but not
all of it.  Once the renderer compositors have been hooked up to use
this path as well, then this and all of the VSyncObserver code can be
ripped out.

The BeginFrameSource is created by the BrowserCompositorOutputSurface
which updates it based on vsync information that it receives.  This
BeginFrameSource is passed to the Display (via OutputSurfaceClient),
which informs the SurfaceManager that the compositor using
that Display should be driven by that BeginFrameSource.  The
SurfaceManager then informs the SurfaceDisplayOutputSurface about
the BeginFrameSource, which passes it into the single thread proxy's
cc::Scheduler for that ui::Compositor's instance.  Plumbing!

The path from SurfaceManager to SurfaceDisplayOutputSurface was
added in https://codereview.chromium.org/1673783004, but the rest
of the plumbing is new to this patch.

CQ_INCLUDE_TRYBOTS=tryserver.blink:linux_blink_rel

Review URL: https://codereview.chromium.org/1821863002

Cr-Commit-Position: refs/heads/master@{#387228}
Commit  : 19c108580b99c469ed192066310e3162bf8c196e
Date    : Thu Apr 14 03:37:18 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev   N  Good?
chromium@386352  8.92012  0.342907  5  good
chromium@387082  8.57924  0.354297  5  good
chromium@387174  8.68248  0.553089  5  good
chromium@387220  8.7315   0.459566  5  good
chromium@387226  8.7492   0.458572  5  good
chromium@387227  8.95858  0.624727  5  good
chromium@387228  13.4147  0.657619  5  bad    <--
chromium@387229  13.4649  0.321134  5  bad
chromium@387232  13.1617  0.807489  5  bad
chromium@387243  13.4012  0.19725   5  bad
chromium@387265  13.6525  0.273109  5  bad
chromium@387447  13.0838  0.284038  5  bad
chromium@387812  13.74    0.429163  5  bad

Bisect job ran on: android_nexus7_perf_bisect
Bug ID: 604009

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests smoothness.pathological_mobile_sites
Test Metric: mean_input_event_latency/mean_input_event_latency
Relative Change: 54.03%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus7_perf_bisect/builds/2942
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9014084956927035648


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5872422926942208

| 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 4 by 42576172...@developer.gserviceaccount.com, Apr 29 2016

Cc: vmp...@chromium.org
Owner: vmp...@chromium.org

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

Hi vmpstr@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 : cc: Disable image hijack canvas when tiles don't have images.
Author  : vmpstr
Commit description:
  
This patch disables the image hijack canvas whenever the tile being
rasterized does not have images. This also deletes a function that is
no longer being used.

R=enne
CQ_INCLUDE_TRYBOTS=tryserver.blink:linux_blink_rel

Review URL: https://codereview.chromium.org/1892573003

Cr-Commit-Position: refs/heads/master@{#387429}
Commit  : 8623c9c8b645083ce4951054f117d1f3d03083c2
Date    : Thu Apr 14 21:23:47 2016


===== TESTED REVISIONS =====
Revision         Mean    Std Dev     N  Good?
chromium@385572  1.278   0.00924662  5  good
chromium@386692  1.3288  0.0110091   5  good
chromium@387252  1.3146  0.00527257  5  good
chromium@387392  1.3098  0.00906642  5  good
chromium@387427  1.3026  0.00391152  5  good
chromium@387428  1.305   0.00524404  5  good
chromium@387429  1.4112  0.00501996  5  bad    <--
chromium@387430  1.4052  0.00962808  5  bad
chromium@387432  1.4098  0.00438178  5  bad
chromium@387436  1.4106  0.00870632  5  bad
chromium@387446  1.4106  0.00444972  5  bad
chromium@387462  1.4046  0.0122597   5  bad
chromium@387532  1.3824  0.00391152  5  bad
chromium@387812  1.4312  0.00657267  5  bad

Bisect job ran on: android_nexus7_perf_bisect
Bug ID: 604009

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests rasterize_and_record_micro.key_silk_cases
Test Metric: rasterize_time/http___jsbin.com_UVIgUTa_38_quiet
Relative Change: 11.99%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus7_perf_bisect/builds/2944
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9014079596125597088


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5337392408428544

| 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!

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


===== SUSPECTED CL(s) =====
Subject : cc: Disable image hijack canvas when tiles don't have images.
Author  : vmpstr
Commit description:
  
This patch disables the image hijack canvas whenever the tile being
rasterized does not have images. This also deletes a function that is
no longer being used.

R=enne
CQ_INCLUDE_TRYBOTS=tryserver.blink:linux_blink_rel

Review URL: https://codereview.chromium.org/1892573003

Cr-Commit-Position: refs/heads/master@{#387429}
Commit  : 8623c9c8b645083ce4951054f117d1f3d03083c2
Date    : Thu Apr 14 21:23:47 2016


===== TESTED REVISIONS =====
Revision         Mean    Std Dev      N  Good?
chromium@387404  0.7682  0.000447214  5  good
chromium@387427  0.773   0.00640312   5  good
chromium@387428  0.78    0.0          5  good
chromium@387429  0.84    0.000707107  5  bad    <--
chromium@387430  0.84    0.00141421   5  bad
chromium@387432  0.8414  0.00336155   5  bad
chromium@387436  0.841   0.001        5  bad
chromium@387449  0.837   0.00524404   5  bad

Bisect job ran on: android_nexus6_perf_bisect
Bug ID: 604009

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests rasterize_and_record_micro.key_silk_cases
Test Metric: rasterize_time/http___jsbin.com_UVIgUTa_38_quiet
Relative Change: 8.96%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus6_perf_bisect/builds/2151
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9014084927318289936


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5789411845865472

| 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!

Sign in to add a comment