Disabling
v8.browsing_mobile-future/browse:media:youtube
v8.browsing_mobile-future/browse:news:cnn 

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/a95dc41ca362d2578891dd81c7c9b1813bb4626a

commit a95dc41ca362d2578891dd81c7c9b1813bb4626a
Author: Emily Hanley <eyaich@google.com>
Date: Mon Jun 18 15:34:35 2018

Disabling v8.browsing_mobile-future stories

NOTRY=true
TBR=charliea@chromium.org

Bug:  853763 
Change-Id: I5e9b428c9f7b86160f391a8d0d74ed0434427af0
Reviewed-on: https://chromium-review.googlesource.com/1104316
Reviewed-by: Emily Hanley <eyaich@chromium.org>
Commit-Queue: Emily Hanley <eyaich@chromium.org>
Cr-Commit-Position: refs/heads/master@{#568016}
[modify] https://crrev.com/a95dc41ca362d2578891dd81c7c9b1813bb4626a/tools/perf/expectations.config

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/11abc54d240000

Thanks for disabling the story. Looks like it started failing recently and chrome is crashing for some reason. Here is the stack trace from one of the runs (https://ci.chromium.org/buildbot/chromium.perf/Android%20Nexus5X%20WebView%20Perf/1987):

signal 11 (SIGSEGV), code 1, fault addr 0x8 in tid 28557 (Media)
	pid: 28485, tid: 28557, name: Media  >>> org.chromium.webview_shell <<<
	signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0x8
	
	Stack Trace:
	  RELADDR   FUNCTION                                                                                FILE:LINE
	  v------>  media::VideoResourceUpdater::software_compositor() const                                ../../media/renderers/video_resource_updater.h:135:45
	  00000000010419fc  media::VideoResourceUpdater::CreateForSoftwarePlanes(scoped_refptr<media::VideoFrame>)  ../../media/renderers/video_resource_updater.cc:771:0
	  00000000010419c0  media::VideoResourceUpdater::CreateForSoftwarePlanes(scoped_refptr<media::VideoFrame>)  ../../media/renderers/video_resource_updater.cc:765:53

I started a bisect on youtube which seems to be failing consistently. 

📍 Found significant differences after each of 3 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/11abc54d240000

Fix UseSurfaceLayerForVideo GPU crash handling. by kylechar@chromium.org
https://chromium.googlesource.com/chromium/src/+/f77f6b8dba2776e23111c84c5d9333dbb03039fe
0 → 1 (+1)

Remove absolute paths from build files by thomasanderson@chromium.org
https://chromium.googlesource.com/chromium/src/+/8dbc0c8285460d36e204f7da9f4ddbaed792947d
1 → 1 (+0)

Revert "Remove absolute paths from build files" by jbudorick@chromium.org
https://chromium.googlesource.com/chromium/src/+/6cd7712159fb49eb10da71ba1de6da174b49ea5d
1 → 1 (+0)

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

I think the cl "Fix UseSurfaceLayerForVideo GPU crash handling" possibly caused these regressions. The cl "Remove absolute paths from build files" broke the builds but it got reverted. The actual crash is not related to these cls.

kylechar@, do you think these crashes could be caused by that cl?

mythria: This is the same issue as  crbug.com/853204 . There is more information there but the root cause is crbug.com/853832 and crbug.com/853609.