All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=710143

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg3P3o9QgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg3IO5vwkM


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

chromium-rel-mac11

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982670311647873056

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : time_to_play/video.html?src_garden2_10s.ogv

Revision             Result                  N
chromium@460054      200.067 +- 12.9269      21      good
chromium@460214      200.633 +- 19.7709      21      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.garden2.10s.ogv media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982670311647873056

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5510413506052096


| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982661640993672544

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982661620596353536

These two alerts showed a small uptick, yet the bisect shows no uptick and a significant amount of noise. I'll try a wider bisect just in case.

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

Hi dalecurtis@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 : dalecurtis
  Commit : 5285d00f561827da882c8faaa7bda1d571c4fc60
  Date   : Wed Mar 29 00:27:30 2017
  Subject: Use AudioUnit instead of AudioDevice properties to get channel count.

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media.tough_video_cases
  Metric       : time_to_play/video.html?src_garden2_10s.ogv
  Change       : 10.09% | 195.5525 -> 217.367777778

Revision             Result                  N
chromium@460041      195.553 +- 3.78641      6       good
chromium@460152      199.57 +- 1.59302       6       good
chromium@460207      201.624 +- 8.15577      9       good
chromium@460235      203.006 +- 21.4323      14      good
chromium@460249      201.488 +- 5.99826      6       good
chromium@460250      217.098 +- 35.5115      6       bad       <--
chromium@460251      225.024 +- 67.612       6       bad
chromium@460253      218.814 +- 33.3253      6       bad
chromium@460256      220.222 +- 32.334       6       bad
chromium@460262      217.368 +- 43.2167      9       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.garden2.10s.ogv media.tough_video_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8982661620596353536

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5881855175294976


| 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!

Hmm, can't download any log files from the bot, but I'd guess we're actually opening a real audio device now instead of using a fake because we got 0 channels in the past; so this is likely WontFix. It's small enough that I don't think this is worth digging too much into either.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982612123461198592

 Issue 710148  has been merged into this issue.

 Issue 710145  has been merged into this issue.