All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=779561

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=2afa3e1351d1670d651c8be6c3363b99af0c3d8afcef4118ff60ef0db94b207f


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

win-high-dpi

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8964300877512294112

=== 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    : media.desktop
  Metric       : story:power_avg/video.html?src_garden2_10s.mp4
  Change       : 19.55% | 0.581813561893 -> 0.468079897718

Suspected Commit Range
  2 commits in range
  https://chromium.googlesource.com/chromium/src/+log/317b4da8a227ef1c552258b7bb6c0762bf272a12..6d022127b59af5cfd68b519a50c6c69a5471e473


Revision             Result                     N
chromium@512003      0.581814 +- 0.112342       6        good
chromium@512029      0.540746 +- 0.188293       6        good
chromium@512042      0.489948 +- 0.0119684      6        good
chromium@512049      0.482609 +- 0.0244735      6        good
chromium@512052      0.469795 +- 0.0490631      14       good
chromium@512053      0.475215 +- 0.0424612      14       good
chromium@512054      ---                        ---      build failure
chromium@512055      0.461005 +- 0.054371       14       bad
chromium@512106      0.46808 +- 0.0196157       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.garden2.10s.mp4 media.desktop

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8964300877512294112


For feedback, file a bug with component Speed>Bisection

wangxianzhu: of the two commits in the bisect range, yours deals with painting.  the other CL seems to be limited to remoting.

would you mind taking a look to see if your CL is causing this regression?

thanks!

The performance of the ref and the test changed at the same time, indicating that the reason was not caused by change of chrome code, but was caused by change of measurement or testing environment.