All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=830677

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=a880a61ac37e693ba742623832cbc421befc4d5b8a928e0783eec000d72497bc


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

chromium-rel-win7-gpu-nvidia
chromium-rel-win8-dual

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/11f71ad4c40000

📍 Found significant differences after each of 6 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/11f71ad4c40000

[vr] Stop using UiElementIterator by vollick@chromium.org
https://chromium.googlesource.com/chromium/src/+/c80c58379af538a7a4968880ebca48ac63c98dae

Screen overridings are fixed by rkarasev@yandex-team.ru
https://chromium.googlesource.com/chromium/src/+/7225417065e86da749ad47afd22bf9b2f9e3d827

CSS: Use count negative background-size by ericwilligers@chromium.org
https://chromium.googlesource.com/chromium/src/+/55816db5c7307cb87943dc09dfc2a79b91582422

[DevTools] Show tracks for OOPIF processes on Timeline by dgozman@chromium.org
https://chromium.googlesource.com/chromium/src/+/acbb420a3b500ec7529a39ef734b3940b0a961bc

webauthn: add test for oversized credential IDs. by agl@chromium.org
https://chromium.googlesource.com/chromium/src/+/ce1605967091027c08692ee570366d8b808a72fb

Adding fieldtrial config for the IncompatibleApplicationsWarning feature by pmonette@chromium.org
https://chromium.googlesource.com/chromium/src/+/7a86e22e588d7941bde54bdb4a8c58c23e502836

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

This seems to be only an increase in cpu time, which is totally expected when enabling my feature.

My CL (Windows only) adds expensive work that runs on a background sequence with low priority and analyses loaded modules (IO work + Crypto API calls)

The Windows scheduler should be smart enough to only schedule these tasks when there are spare cycles, and thus should not impact this benchmark time-wise.

Of course that's the theory, but I don't see any proof of the contrary.

To the owners (charliea@chromium.org, nednguyen@chromium.org): It there another benchmark I should be looking at to confirm what I am thinking?

Thanks!