All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=785572

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=bf893d1c30f29e4fa47de307f7e6629913d1e2a0a32c365c7577d5ef362901dc


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

android-nexus5X
android-nexus6
android-nexus7v2
android-one

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8962812827364412960

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

Hi bokan@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 : David Bokan
  Commit : cbeb064ce8a422528be2e2e6eca1942333628f01
  Date   : Mon Nov 13 17:00:01 2017
  Subject: Fix telemetry gesture wheel scrolling on Android

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : smoothness.tough_scrolling_cases
  Metric       : mean_pixels_approximated/text_hover_30000_pixels_per_second

Revision             Result                  N
chromium@515942      7.75917 +- 10.4749      6      good
chromium@515955      10.1292 +- 5.02029      5      good
chromium@515961      13.2753 +- 4.86606      4      good
chromium@515964      10.8207 +- 6.74623      4      good
chromium@515966      10.9498 +- 6.74686      5      good
chromium@515967      0.0 +- 0.0              7      bad       <--
chromium@515992      0.0 +- 0.0              6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=text.hover.30000.pixels.per.second smoothness.tough_scrolling_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8962812827364412960


For feedback, file a bug with component Speed>Bisection

Ned, do you know what "mean_pixels_approximated" measures? The comment in smoothness.py isn't very helpful...

reveman@ may know more details about this metric.

 Issue 785574  has been merged into this issue.

From reveman@: "pixels we didn't have time to rasterize so we either used checkerboarding or background color for them". In that case, this makes sense - previously we scrolled so fast that we didn't even have to "checkerboard". Now that we scroll at more human speeds we end up unable to rasterize in time so the metric is now actually measuring something.