All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=790001

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=be6c1342d4c3b116c98e58c0fbd61a3061ad46f11553c5b660a57ba3518c8ca6


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

win-high-dpi

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8961483101452245280

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

Hi liberato@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 : liberato@chromium.org
  Commit : 53479ca91ac63d89a22c06db86a4292edcb2fa65
  Date   : Tue Nov 28 19:19:33 2017
  Subject: Avoid saturation when computing LayoutSize aspect ratio.

Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : media.desktop
  Metric       : dropped_frame_count_avg/video.html?src_smpte_3840x2160_60fps_vp9.webm_seek
  Change       : 48.03% | 25.3333333333 -> 37.5

Revision             Result                  N
chromium@519746      25.3333 +- 3.91578      6      good
chromium@519777      27.0 +- 3.4641          6      good
chromium@519781      22.8333 +- 6.54472      6      good
chromium@519783      23.8333 +- 9.53065      6      good
chromium@519784      41.1667 +- 7.53879      6      bad       <--
chromium@519785      36.5 +- 7.31437         6      bad
chromium@519793      36.3333 +- 7.70281      6      bad
chromium@519808      37.8333 +- 8.41625      6      bad
chromium@519870      37.5 +- 5.61249         6      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=video.html.src.smpte.3840x2160.60fps.vp9.webm.seek media.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8961483101452245280


For feedback, file a bug with component Speed>Bisection

i'll take a look.  since the video is large enough to run into the layoutsize bug, we might just be drawing more pixels now (correctly).

 Issue 789713  has been merged into this issue.

forgot to close this -- after some investigation, seems likely wai.