New issue
Advanced search Search tips

Issue 729233 link

Starred by 0 users
Status: Fixed
Owner:
robertph...@google.com
Closed: Jun 2017
Cc:
robertph...@google.com
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

3.5%-39.3% regression in smoothness.gpu_rasterization.tough_filters_cases at 476145:476182

Project Member Reported by m...@chromium.org, Jun 2 2017 
See the link to graphs below.
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Jun 4 2017

Cc: robertph...@google.com
Owner: robertph...@google.com

=== Auto-CCing suspected CL author robertphillips@google.com ===

Hi robertphillips@google.com, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Robert Phillips
  Commit : 5efd5ea4e146c47394d16c8b6f876264822a0bee
  Date   : Wed May 31 17:00:22 2017
  Subject: Update clearOp for split-OpList world (take 3)

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : smoothness.gpu_rasterization.tough_filters_cases
  Metric       : frame_times/http___static.bobdo.net_Analog_Clock.svg
  Change       : 39.67% | 100.711465935 -> 140.660642

Revision                             Result                  N
chromium@476146                      100.711 +- 1.24819      6      good
chromium@476155                      103.047 +- 0.84885      6      good
chromium@476156                      102.466 +- 1.68382      6      good
chromium@476156,skia@bef2852a8c      101.295 +- 1.1557       6      good
chromium@476156,skia@5efd5ea4e1      140.072 +- 6.67351      6      bad       <--
chromium@476156,skia@d32e237301      161.628 +- 8.18891      6      bad
chromium@476156,skia@d9fe700672      160.278 +- 9.48006      6      bad
chromium@476157                      157.4 +- 14.2486        6      bad
chromium@476158                      153.345 +- 25.1211      6      bad
chromium@476160                      132.679 +- 4.18969      6      bad
chromium@476164                      159.914 +- 9.80207      6      bad
chromium@476182                      140.661 +- 9.54178      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=http...static.bobdo.net.Analog.Clock.svg smoothness.gpu_rasterization.tough_filters_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8977856109977029328

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5279077528764416


| 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 Speed>Bisection.  Thank you!

Comment 4 by m...@chromium.org, Jun 5 2017

Cc: -miu@google.com

Comment 5 by alexclarke@chromium.org, Jun 12 2017 

Friendly Perf sheriff ping, any update on this?

Comment 6 by robertphillips@chromium.org, Jun 14 2017 

I have https://skia-review.googlesource.com/c/19495/ waiting in the wings but it is held up on a cc_unittests failure.
Project Member

Comment 9 by bugdroid1@chromium.org, Jun 14 2017 

The following revision refers to this bug:
  https://skia.googlesource.com/skia/+/c8ecb0328b69f08b4fb231469d1545d935d44567

commit c8ecb0328b69f08b4fb231469d1545d935d44567
Author: Robert Phillips <robertphillips@google.com>
Date: Wed Jun 14 17:55:18 2017

Revert "Drop the ref on the GrOpList's target in makeClosed"

This reverts commit dcd499caed823f23bc70c07df7804a6dc1306606.

Reason for revert: memory issue
Original change's description:
> Drop the ref on the GrOpList's target in makeClosed
> 
> Bug:  729233 
> Change-Id: Ifb66b745e604d7f7c22c2907bcffa91d2086236d
> Reviewed-on: https://skia-review.googlesource.com/19495
> Commit-Queue: Robert Phillips <robertphillips@google.com>
> Reviewed-by: Brian Salomon <bsalomon@google.com>

TBR=bsalomon@google.com,robertphillips@google.com

Change-Id: I4269c696c57a93cdd056e7c3a887c35b8765ac6d
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug:  729233 
Reviewed-on: https://skia-review.googlesource.com/19793
Reviewed-by: Robert Phillips <robertphillips@google.com>
Commit-Queue: Robert Phillips <robertphillips@google.com>

[modify] https://crrev.com/c8ecb0328b69f08b4fb231469d1545d935d44567/src/gpu/GrRenderTargetContext.cpp
[modify] https://crrev.com/c8ecb0328b69f08b4fb231469d1545d935d44567/src/gpu/GrOpList.cpp
[modify] https://crrev.com/c8ecb0328b69f08b4fb231469d1545d935d44567/src/gpu/GrOpList.h
[modify] https://crrev.com/c8ecb0328b69f08b4fb231469d1545d935d44567/src/effects/GrAlphaThresholdFragmentProcessor.cpp
[modify] https://crrev.com/c8ecb0328b69f08b4fb231469d1545d935d44567/src/gpu/GrGpuResourceRef.cpp

Comment 11 by robertph...@google.com, Jun 15 2017 

The CL in #10 rolled into Chrome on 6/14 in https://chromium-review.googlesource.com/c/536175 at 479586.

Comment 12 by senorblanco@chromium.org, Jun 20 2017

Status: Fixed (was: Untriaged)
►

Sign in to add a comment