All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=727301

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDghobQuAkM


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

chromium-rel-win10

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978258376079267104

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

Hi samans@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 : samans
  Commit : f26257b9ee4b7e722cc05468ceecbcf3f920be22
  Date   : Fri May 26 16:37:45 2017
  Subject: Send BeginFrames for the renderer using Mojo

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : loading.desktop
  Metric       : cpuTimeToFirstMeaningfulPaint_avg/pcv1-warm/Vnexpress
  Change       : 125.45% | 67.417 -> 151.989666667

Revision             Result                  N
chromium@474981      67.417 +- 4.56711       6      good
chromium@475019      69.8305 +- 5.41033      6      good
chromium@475029      66.9595 +- 8.64921      6      good
chromium@475030      117.419 +- 108.121      9      bad       <--
chromium@475031      136.249 +- 51.4338      6      bad
chromium@475032      126.555 +- 35.8507      6      bad
chromium@475034      135.074 +- 76.6026      6      bad
chromium@475038      131.332 +- 71.1488      6      bad
chromium@475056      133.252 +- 56.8616      6      bad
chromium@475131      151.99 +- 36.0789       6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=Vnexpress loading.desktop

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978258376079267104

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5334422678667264


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

 Issue 727363  has been merged into this issue.

 Issue 727360  has been merged into this issue.

 Issue 727370  has been merged into this issue.

I'm almost used to timeToFirstContentfulPaint randomly regressing or improving. I'm inclined to mark this as WontFix but I'll discuss it with a few other people first.

 Issue 727368  has been merged into this issue.

 Issue 727362  has been merged into this issue.

 Issue 727366  has been merged into this issue.

 Issue 727367  has been merged into this issue.

 Issue 727365  has been merged into this issue.

 Issue 727361  has been merged into this issue.

Please discuss timeToFirstContentfulPaint regressions with metric owners ksakamoto and kouhei.

 Issue 727475  has been merged into this issue.

I think this is a WONTFIX as this is the change to testing infra (synthetic gestures).