All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=755296

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=3de3a1ca00576390449fc2ef49939484701a8d0e42ba684e22bcf172f3a4a23c


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

chromium-rel-mac-retina
chromium-rel-mac12
chromium-rel-mac12-mini-8gb
chromium-rel-win7-gpu-nvidia
win-high-dpi

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8971252742992238848

=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : loading.desktop
  Metric       : timeToFirstContentfulPaint_avg/pcv1-cold/Yandex
  Change       : 22.58% | 385.649928574 -> 472.746428575

Suspected Commit Range
  3 commits in range
  https://chromium.googlesource.com/chromium/src/+log/d9b2022d75e7ac3fbfe03fa554f504ee26f931cb..8295d8cc350374ffe3ee2c03e01a0571e330eb53


Revision             Result                  N
chromium@493392      385.65 +- 120.758       14       good
chromium@493394      384.396 +- 60.4487      6        good
chromium@493395      387.328 +- 40.198       6        good
chromium@493396      ---                     ---      build failure
chromium@493397      ---                     ---      build failure
chromium@493398      483.028 +- 286.328      14       bad
chromium@493401      454.866 +- 171.87       14       bad
chromium@493410      447.59 +- 192.275       14       bad
chromium@493427      460.972 +- 210.635      14       bad
chromium@493462      455.094 +- 209.426      14       bad
chromium@493533      472.746 +- 275.347      14       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=Yandex loading.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8971252742992238848


For feedback, file a bug with component Speed>Bisection

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8967816779252240128

The bisect repro-ed but couldn't narrow down the range. Re-kicked on another platform due to build failures.

But the only CL in the range r493396 - r493398 which isn't test-only is r493396: "Make initial number of SchedulerWorkers be at most |worker_capacity_|."

Monorail says jeffreyhe email bounces; assigning to reviewer gab to investigate and cc-ing other reviewers.

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

Hi ccameron@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 : ccameron chromium
  Commit : 28e0a3c183499e50b1b89231d4ed40bafb8883fe
  Date   : Fri Aug 11 04:59:46 2017
  Subject: Revert "Ensure overlapping compositor locks can time out"

Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : loading.desktop
  Metric       : timeToFirstContentfulPaint_avg/pcv1-cold/Kakaku
  Change       : 29.49% | 285.83 -> 373.112777778

Revision             Result                  N
chromium@492988      285.83 +- 58.5325       9      good
chromium@493331      329.784 +- 160.003      9      good
chromium@493502      314.385 +- 35.7872      6      good
chromium@493588      312.621 +- 44.3323      6      good
chromium@493631      314.271 +- 47.2328      6      good
chromium@493652      330.311 +- 156.693      9      good
chromium@493663      315.033 +- 39.1787      6      good
chromium@493668      346.762 +- 346.4        9      good
chromium@493670      319.587 +- 54.4203      6      good
chromium@493671      375.371 +- 78.5278      9      bad       <--
chromium@493673      373.113 +- 49.6734      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=Kakaku loading.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967816779252240128


For feedback, file a bug with component Speed>Bisection

This was a revert for correctness bugs a patch, so WontFix.