All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=698037

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpMmMmggM


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

chromium-rel-mac11

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8986197219799101936

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

Hi dvadym@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 : dvadym
  Commit : 584b59ac597f611fbac882fbbe90d538bf60db4e
  Date   : Tue Feb 28 10:14:06 2017
  Subject: Revert of Replace FFmpegDemuxer thread per element with base::TaskScheduler. (patchset #8 id:140001 of https://codereview.chromium.org/2710133003/ )

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media_perftests
  Metric       : clockless_video_playback_vp8/bear_silent.webm
  Change       : 23.69% | 179.286133126 -> 136.808193456

Revision             Result                  N
chromium@453542      179.286 +- 1.40538      6      good
chromium@453557      178.785 +- 1.82189      6      good
chromium@453561      179.556 +- 1.27388      6      good
chromium@453562      178.679 +- 1.62122      6      good
chromium@453563      148.984 +- 6.01678      6      bad       <--
chromium@453564      151.585 +- 6.29413      6      bad
chromium@453571      150.251 +- 3.81365      6      bad
chromium@453599      136.808 +- 1.26933      6      bad

To Run This Test
  ./src/out/Release/media_perftests --single-process-tests

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8986197219799101936

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5835196466724864


| 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!

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

Hi dvadym@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 : dvadym
  Commit : 584b59ac597f611fbac882fbbe90d538bf60db4e
  Date   : Tue Feb 28 10:14:06 2017
  Subject: Revert of Replace FFmpegDemuxer thread per element with base::TaskScheduler. (patchset #8 id:140001 of https://codereview.chromium.org/2710133003/ )

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : media_perftests
  Metric       : clockless_video_playback_vp8/bear_silent.webm
  Change       : 23.69% | 179.286133126 -> 136.808193456

Revision             Result                  N
chromium@453542      179.286 +- 1.40538      6      good
chromium@453557      178.785 +- 1.82189      6      good
chromium@453561      179.556 +- 1.27388      6      good
chromium@453562      178.679 +- 1.62122      6      good
chromium@453563      148.984 +- 6.01678      6      bad       <--
chromium@453564      151.585 +- 6.29413      6      bad
chromium@453571      150.251 +- 3.81365      6      bad
chromium@453599      136.808 +- 1.26933      6      bad

To Run This Test
  ./src/out/Release/media_perftests --single-process-tests

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8986197219799101936

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5835196466724864


| 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 this is safe to ignore. The CL is being re-landed. I will still keep it open until we get the test results.

-dvadym

Test results look good.