All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=710134

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgnKDZ4AgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgnJfHtwoM


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

chromium-rel-mac11

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982670618157981264

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

Hi jbauman@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 : jbauman
  Commit : f4c12323bc9ef46575de81489ce7afbf57484d5c
  Date   : Mon Mar 27 23:20:00 2017
  Subject: Return overlay resources to renderers in larger batches.

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : idle_wakeups_renderer/video.html?src_crowd1080_vp9.webm_canvas_true
  Change       : 16.48% | 997.0 -> 1161.33333333

Revision             Result                  N
chromium@459866      997.0 +- 32.4962        6      good
chromium@459928      988.667 +- 97.9047      6      good
chromium@459929      1008.67 +- 63.2561      6      good
chromium@459930      1140.0 +- 110.463       6      bad       <--
chromium@459932      1153.33 +- 101.061      6      bad
chromium@459936      1113.83 +- 119.31       6      bad
chromium@459944      1147.33 +- 56.3678      6      bad
chromium@459959      1132.33 +- 71.4516      6      bad
chromium@459989      1161.33 +- 56.2613      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=video.html.src.crowd1080.vp9.webm.canvas.true media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982670618157981264

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5898086380994560


| 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!

I think the reduction in CPU usage (e.g. https://chromeperf.appspot.com/report?sid=84dcda54e190778342950d72d75e23115b6c7544d60ef25823f0d252dd3db3e0&rev=459989 ) causes the CPU to go idle more often in a frame, so it has to wakeup from idle more.