New issue
Advanced search Search tips

Issue 851105 link

Starred by 1 user

Issue metadata

Status: Fixed
Owner:
Closed: Jun 2018
Cc:
Components:
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

2.8%-3.5% regression in system_health.memory_mobile at 564086:564172

Project Member Reported by mustaq@chromium.org, Jun 8 2018

Issue description

See the link to graphs below.
 
All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=851105

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=5fb2519de34abf106d8e172c9ec06d75edae1efcff52647668d0b973881ab0bc


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

android-webview-nexus5X
android-webview-nexus6
Cc: amyqiu@google.com
Owner: amyqiu@google.com
Status: Assigned (was: Untriaged)
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/14a420a1240000

Rename page in image_decoding_cases by amyqiu@google.com
https://chromium.googlesource.com/chromium/src/+/6152ceb09e2b37d0b51bd8c1366dd027eb8acae7
3.057e+07 → 3.169e+07 (+1.122e+06)

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 4 by dtu@chromium.org, Jun 11 2018

Cc: -amyqiu@google.com
Owner: dtu@chromium.org
The Pinpoint result is not right, my fault. Re-running now.
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Jun 11 2018

Cc: pdr@chromium.org
📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/148bae79240000

Do not downgrade full paint invalidation reasons by pdr@chromium.org
https://chromium.googlesource.com/chromium/src/+/a677dbcc62d15f21314618dca0027f3da951118d
3.069e+07 → 3.167e+07 (+9.796e+05)

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 7 by pdr@chromium.org, Jun 20 2018

Cc: -pdr@chromium.org
Components: Blink>Paint
Owner: pdr@chromium.org
It seems this is me. Investigating..
Project Member

Comment 8 by bugdroid1@chromium.org, Jun 22 2018

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/92958ccd0c4caf57408bf960713364fb963bedc6

commit 92958ccd0c4caf57408bf960713364fb963bedc6
Author: Philip Rogers <pdr@chromium.org>
Date: Fri Jun 22 16:08:13 2018

Only invalidate child clipping mask layer when needed

This patch only invalidates the child clipping mask layer if the size
actually changes. https://crrev.com/564140 regressed performance by
calling this unconditionally.

Because the same bug was made in https://crrev.com/565415, this patch
also updates the two GraphicsLayer::SetSize callsites from that patch.

Bug:  851105 
Cq-Include-Trybots: luci.chromium.try:linux_layout_tests_slimming_paint_v2;master.tryserver.blink:linux_trusty_blink_rel
Change-Id: I74bcda83054e8e21332e723d0fc816910086e2e4
Reviewed-on: https://chromium-review.googlesource.com/1111208
Reviewed-by: Xianzhu Wang <wangxianzhu@chromium.org>
Commit-Queue: Philip Rogers <pdr@chromium.org>
Cr-Commit-Position: refs/heads/master@{#569645}
[modify] https://crrev.com/92958ccd0c4caf57408bf960713364fb963bedc6/third_party/blink/renderer/core/paint/compositing/composited_layer_mapping.cc

Comment 9 by pdr@chromium.org, Jun 25 2018

Status: Fixed (was: Assigned)

Sign in to add a comment