All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=741716

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=f596a53c6579fa5412d902dbaca7eb1697411a848e6d043a80c71425d6bd376d


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

chromium-rel-mac11
chromium-rel-win10
chromium-rel-win7-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8974256702577755936

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

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


Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : timeToFirstContentfulPaint_avg/browse_media/browse_media_flickr_infinite_scroll


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=browse.media.flickr.infinite.scroll system_health.common_desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8974256702577755936


For feedback, file a bug with component Speed>Bisection

Charlie - help!?

Actually - it looks like the power regression and the loading regressions are different? I'm going to try bisecting the power one.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8974147959806266384

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8974147952327779056

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Dan Elphick
  Commit : 67fac36a35318d03fe141887898821e42dfaecb4
  Date   : Fri Jul 07 08:57:32 2017
  Subject: Increase priority of compositor TQ in NONE Usecase

Bisect Details
  Configuration: mac_10_11_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : cpu_time_percentage_avg/load_news/load_news_nytimes
  Change       : 4.90% | 0.715406643905 -> 0.750361440714

Revision             Result                      N
chromium@484851      0.715407 +- 0.0223328       9       good
chromium@484860      0.720903 +- 0.0134848       6       good
chromium@484862      0.720168 +- 0.0203607       6       good
chromium@484863      0.747419 +- 0.0148191       6       bad       <--
chromium@484864      0.739359 +- 0.0127005       6       bad
chromium@484868      0.745568 +- 0.00693653      6       bad
chromium@484884      0.735693 +- 0.0901398       14      bad
chromium@484916      0.750361 +- 0.0196441       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=load.news.nytimes system_health.common_desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8974147952327779056


For feedback, file a bug with component Speed>Bisection

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Dan Elphick
  Commit : 67fac36a35318d03fe141887898821e42dfaecb4
  Date   : Fri Jul 07 08:57:32 2017
  Subject: Increase priority of compositor TQ in NONE Usecase

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : system_health.common_desktop
  Metric       : cpu_time_percentage_avg/load_news/load_news_nytimes
  Change       : 3.68% | 0.685316394773 -> 0.710513437217

Revision             Result                     N
chromium@484827      0.685316 +- 0.154607       21      good
chromium@484853      0.686317 +- 0.0935648      21      good
chromium@484859      0.69197 +- 0.0800904       14      good
chromium@484862      0.685393 +- 0.0787476      9       good
chromium@484863      0.721968 +- 0.0756991      14      bad       <--
chromium@484864      0.728037 +- 0.081146       9       bad
chromium@484875      0.710513 +- 0.125331       14      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=load.news.nytimes system_health.common_desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8974147959806266384


For feedback, file a bug with component Speed>Bisection

Looks like you figured it out.