All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=877586

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=d2ed17439a10641569d3ea12f7686b358f926c99885049265c3ad66762ea943c


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

mac-10_12_laptop_low_end-perf
mac-10_13_laptop_high_end-perf

rendering.desktop - Benchmark documentation link:
  https://bit.ly/rendering-benchmarks

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/11c07fce640000

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/11c07fce640000

Add PassiveDocumentWheelEventListeners to fieldtrial_testing_config by sahel@chromium.org
https://chromium.googlesource.com/chromium/src/+/9187c7d059b7aa6342b39a19c7c32ba5aedd92cf
0.1412 → 0.1821 (+0.04091)

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

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/19a66a429489c8eb9fec304198548c18de59e5d2

commit 19a66a429489c8eb9fec304198548c18de59e5d2
Author: Sahel Sharify <sahel@chromium.org>
Date: Tue Nov 13 02:09:56 2018

Fix perf regression of PassiveDocumentWheelEventListeners.

JS_SCROLL_TEXT_ONLY and JS_SCROLL_200_LAYER_GRID both add event listeners
to the document that preventDefault wheel/touch events and call JS scrolling.
The tests regressed after landing the following cl:
https://chromium-review.googlesource.com/1183538

This is because with passive document level event listeners interventions
the wheel/mousewheel and touchstart/touchmove event listeners on a document
level target are treated as passive if not requested otherwise. This cl changes
the event listeners in both tests to passive:false to make sure that they
actually prevent scrolling.

Bug:  877586 
Change-Id: I25fb5c0563534b1d67f124bd43272d02d849fa23
Reviewed-on: https://chromium-review.googlesource.com/c/1329447
Commit-Queue: Sahel Sharify <sahel@chromium.org>
Reviewed-by: Charlie Andrews <charliea@chromium.org>
Cr-Commit-Position: refs/heads/master@{#607441}
[modify] https://crrev.com/19a66a429489c8eb9fec304198548c18de59e5d2/tools/perf/page_sets/data/rendering_desktop.json
[add] https://crrev.com/19a66a429489c8eb9fec304198548c18de59e5d2/tools/perf/page_sets/data/rendering_desktop_05c1f9e507.wprgo.sha1
[add] https://crrev.com/19a66a429489c8eb9fec304198548c18de59e5d2/tools/perf/page_sets/data/rendering_desktop_a2106b0095.wprgo.sha1
[modify] https://crrev.com/19a66a429489c8eb9fec304198548c18de59e5d2/tools/perf/page_sets/rendering/tough_compositor_cases.py

The graphs show that the regression has recovered after landing the fix in comment #5.