All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=759458

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=bd3b2f03cddfed7bd555c26535b1ac1d508bfd4f1251a112d43af8dbc6c1eb87


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

android-nexus7v2
android-webview-nexus6
chromium-rel-mac-retina
chromium-rel-mac11
chromium-rel-mac11-air
chromium-rel-mac11-pro
chromium-rel-mac12-mini-8gb
chromium-rel-win7-dual
linux-release

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970031525591752768

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

Hi sahel@chromium.org, 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 : Sahel Sharify
  Commit : f53825a1fb92e74b9a889b9501243e03de57094d
  Date   : Fri Aug 25 19:16:21 2017
  Subject: Wheel scroll latching and async wheel events flags enabled in testing config.

Bisect Details
  Configuration: mac_pro_perf_bisect
  Benchmark    : v8.runtimestats.browsing_desktop
  Metric       : Total:duration_avg/browse_social/browse_social_facebook_infinite_scroll
  Change       : 24.74% | 9124.02333333 -> 11381.5056667

Revision             Result                  N
chromium@497451      9124.02 +- 615.0        6      good
chromium@497478      9055.55 +- 286.964      6      good
chromium@497482      9092.07 +- 223.241      6      good
chromium@497483      11507.8 +- 403.208      6      bad       <--
chromium@497484      11457.2 +- 228.629      6      bad
chromium@497485      11482.6 +- 248.938      6      bad
chromium@497491      11310.2 +- 1345.09      6      bad
chromium@497504      11373.0 +- 588.08       6      bad
chromium@497557      11381.5 +- 291.506      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=browse.social.facebook.infinite.scroll v8.runtimestats.browsing_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970031525591752768


For feedback, file a bug with component Speed>Bisection

 Issue 759459  has been merged into this issue.

 Issue 759559  has been merged into this issue.

 Issue 759483  has been merged into this issue.

 Issue 759560  has been merged into this issue.

 Issue 760175  has been merged into this issue.

Pinpoint job started.
https://dev-simonhatch-68b443e7-dot-pinpoint-dot-chromeperf.appspot.com/job/14cb31aab80000

Pinpoint job failed!
https://dev-simonhatch-68b443e7-dot-pinpoint-dot-chromeperf.appspot.com/job/14cb31aab80000

Pinpoint job failed!
https://dev-simonhatch-68b443e7-dot-pinpoint-dot-chromeperf.appspot.com/job/14cb31aab80000

Pinpoint job failed!
https://dev-simonhatch-68b443e7-dot-pinpoint-dot-chromeperf.appspot.com/job/14cb31aab80000

Pinpoint job started.
https://dev-simonhatch-08905d55-dot-pinpoint-dot-chromeperf.appspot.com/job/1202c392b80000

Pinpoint job complete!
https://dev-simonhatch-08905d55-dot-pinpoint-dot-chromeperf.appspot.com/job/1202c392b80000

 Issue 759562  has been merged into this issue.

sahel@: Could you please respond to this issue?

The following revision refers to this bug:
  https://chromium.googlesource.com/chromium/src.git/+/1ef1786c67f2584f463ed0785458778d574261cb

commit 1ef1786c67f2584f463ed0785458778d574261cb
Author: sahel <sahel@chromium.org>
Date: Thu Sep 21 05:43:37 2017

Wheel end event must have its own timestamp.

The wheel end event generated by Mouse_wheel_phase_handler used to have
the timestamp of the last wheel event. This caused a 100ms+ latency to
handling this event since it is released 100ms after the last wheel
event. This cl adds proper timestamp to the synthetic wheel end event.

Bug:  759458 
Change-Id: Iebfe9638cb401618d178a5b4caa4d4108b1048ca
Reviewed-on: https://chromium-review.googlesource.com/672166
Reviewed-by: Dave Tapuska <dtapuska@chromium.org>
Reviewed-by: Timothy Dresser <tdresser@chromium.org>
Commit-Queue: Sahel Sharifymoghaddam <sahel@chromium.org>
Cr-Commit-Position: refs/heads/master@{#503364}
[modify] https://crrev.com/1ef1786c67f2584f463ed0785458778d574261cb/content/browser/renderer_host/input/mouse_wheel_phase_handler.cc
[modify] https://crrev.com/1ef1786c67f2584f463ed0785458778d574261cb/content/browser/renderer_host/render_widget_host_view_aura_unittest.cc

The NextAction date has arrived: 2017-09-25

This is an old perf regression bug related to wheel scroll latching that I could not get to the bottom of it. However  crbug.com/828235  is a related bug that got fixed later.

The issue was that during infinite scrolling we'd prioritize scrolling to content loading and with timer-based wheel scroll latching if the user keeps doing wheel scrolling at the bottom of the page, the scroll sequence would never break and it would delay content loading.