All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=750844

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=d7b6ab58d38478808df3e7d561e917c1eedb096ba91cbff07768b22e801acfb1


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

android-nexus5
android-webview-nexus6

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972521790853275872

=== BISECT JOB RESULTS ===
Perf regression found but unable to continue

Bisect was stopped because a commit couldn't be classified as either
good or bad.


Bisect Details
  Configuration: android_webview_nexus6_aosp_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_total_fast_path_cpu_time_per_frame/font_wipe.html

Revision             Result                   N
chromium@485907      10.6159 +- 0.533403      21      good
chromium@485987      10.7128 +- 0.742647      21      unknown
chromium@486067      10.7284 +- 0.498136      21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=font.wipe.html thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972521790853275872


For feedback, file a bug with component Speed>Bisection

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970614334528173536

Looks like the bisect didn't actually repro the regression. Trying one more time with a wider range.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8970607617916378384

=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_IO_cpu_time_per_frame/http___groupcloned.com_test_plain_sticky-using-webkit-backface-visibility.html
  Change       : 5.82% | 2.21390424926 -> 2.34267203241

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/3b4c6874fc78f6e2da1e1578c2bc5cf5a78348c4..785f2e5f17b252a5c6787dcdc32171095b0b9d5f


Revision             Result                    N
chromium@485735      2.2139 +- 0.0565043       6        good
chromium@485857      2.22809 +- 0.0324153      6        good
chromium@485915      2.23864 +- 0.0468022      6        good
chromium@485931      2.23943 +- 0.0826523      14       good
chromium@485932      ---                       ---      build failure
chromium@485933      2.25782 +- 0.0937447      14       bad
chromium@485935      2.31256 +- 0.070913       6        bad
chromium@485939      2.29252 +- 0.0243161      6        bad
chromium@485947      2.28345 +- 0.0790892      9        bad
chromium@485978      2.29939 +- 0.054852       6        bad
chromium@486221      2.29927 +- 0.0615023      6        bad
chromium@486706      2.33984 +- 0.0590305      6        bad
chromium@487676      2.34267 +- 0.0363417      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=http...groupcloned.com.test.plain.sticky.using.webkit.backface.visibility.html thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970614334528173536


For feedback, file a bug with component Speed>Bisection

=== BISECT JOB RESULTS ===
Bisect failed for unknown reasons

Please contact the team (see below) and report the error.


Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : thread_times.key_silk_cases
  Metric       : thread_IO_cpu_time_per_frame/http___groupcloned.com_test_plain_sticky-using-webkit-backface-visibility.html


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=http...groupcloned.com.test.plain.sticky.using.webkit.backface.visibility.html thread_times.key_silk_cases

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8970607617916378384


For feedback, file a bug with component Speed>Bisection

The IO thread time regression seems to line up with r485935.  Ken could you PTAl?

commit 474df01407e5d38c85364ae4d1709b8d9af16f16
Author: Ken Rockot <rockot@chromium.org>
Date:   Wed Jul 12 13:28:56 2017 +0000

    Mojo C++ Bindings: Lazy Serialization

    ...

    Change-Id: I85197b74a87bcf9fc9ff14b4c787c7eabc897829
    Reviewed-on: https://chromium-review.googlesource.com/562180
    Commit-Queue: Ken Rockot <rockot@chromium.org>
    Reviewed-by: Yuzhu Shen <yzshen@chromium.org>
    Cr-Commit-Position: refs/heads/master@{#485935}

ken, ping on #9?

Ken, will you have time to look at this? If not, Victor how important is it to find someone to dig in?

I would expect a small increase in CPU time. 4-6% seems higher than what I'd anticipate (would think more like < 1%) but:

a) auditing the change doesn't reveal anything obvious
b) attempts to profile in-depth to compare before-and-after have proven noisy and unhelpful

It's still a pretty small regression in any case, so I'm inclined to let it go. WDYT?

Closing per #13.