All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=631461

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg-s-ZoAoM


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

chromium-rel-win10

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9006070930755562656

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

Hi robliao@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : Enable Per-Monitor DPI Unless Explicitly Disabled
Author  : robliao
Commit description:
  
                   Per Monitor DPI Settings
Flags              Before             After
No Flags           Disabled           Enabled
Enable             Enabled            Enabled
Enable + Disabled  Disabled           Disabled
Disabled           Disalbed           Disabled

BUG= 426656 

Review-Url: https://codereview.chromium.org/2175693004
Cr-Commit-Position: refs/heads/master@{#407508}
Commit  : 23364eecc5d1bb1770f8c22a7c0a320154e3eac7
Date    : Mon Jul 25 17:55:26 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev    N  Good?
chromium@407500  20.1013  0.384946   5  good
chromium@407506  20.332   0.415941   5  good
chromium@407507  20.0078  0.384546   5  good
chromium@407508  23.26    0.666113   5  bad    <--
chromium@407510  23.5637  0.896201   5  bad
chromium@407514  23.291   0.487463   5  bad
chromium@407528  23.0449  0.0718283  5  bad
chromium@407555  23.0873  0.168525   5  bad

Bisect job ran on: winx64_10_perf_bisect
Bug ID: 631461

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests smoothness.gpu_rasterization.tough_filters_cases
Test Metric: frame_times/http___letmespellitoutforyou.com_samples_svg_filter_terrain.svg
Relative Change: 14.85%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64_10_perf_bisect/builds/608
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9006070930755562656


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5775133810098176

| 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 Tests>AutoBisect.  Thank you!

Adding a test author.
senorblanco: What is the impact of 20ms to 23ms?

The change in question enables per-monitor DPI in Windows browser process-wide.

A 15% regression is non-negligible. However, it might be due to giving different results visually. Is it possible the test is running at a higher DPI than it was without your flag? Could you repro locally on a similar config? You can run this test by opening URL http://letmespellitoutforyou.com/samples/svg/filter_terrain.svg with --enable-gpu-rasterization. You could see if the results look different with and without your flag. If so it might be acceptable.

Perf sheriff ping: reminder to follow up on possible performance issues

Yep. I hope to do a preliminary investigation on this this week.

The latest graph appears to show the test running around 21ms. Adjusting priority to P3 and will continue to monitor.

Latest data has this metric at 22, spiking at 23. Is there an update here robliao@?

robertocn: The last update I had was from #9. The 23ms looks new, but it's trending back to 21-22ms.

Should we won't fix this?

At this point, I think so. Marking WontFix. If there are objections, feel free to reopen.

For the record, running the test page locally with and without --enable-gpu-rasterization seems to look fine.
Test Page: http://letmespellitoutforyou.com/samples/svg/filter_terrain.svg