All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=697088

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpMeFuAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpKmWqQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpJPlrwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpNj1pAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgxJPerQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgpLT1_ggM


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

webrtc-android-tests-nexus6-lollipop
webrtc-linux-large-tests
webrtc-win-large-tests

It could be that the CL made the test behave differently.  I think that it's a good thing since the change makes the test behave slightly more like a ProcessThread would (albeit not completely).  In any case, it looks like the change is good and the one outlier, Nexus72, seems to have been suspiciously stuck at ~35 without much variation for a long time.

Removing R-V-G label (was set upon bug filing because the bot was incorrectly configured as internal)

Closing. The change was briefly good but has regressed since :(