All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=811450

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=7af1fe3bd5d924dd857af464ac01df2554d05c9dd906c9883203bf8466638ee5


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

android-nexus6
win-high-dpi

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/12972ff5840000

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/12972ff5840000

Move GrMakeCachedBitmapProxy work in lazy mode by egdaniel@google.com
https://skia.googlesource.com/skia/+/7e1912a8ab48134eb3a631f188ad8aa262e8eaa0

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

The graphs are really noisy, and the bisect didn't really repro this regression.

I actually think this may have been the same issue as, https://bugs.chromium.org/p/chromium/issues/detail?id=811452, which was actually fixed this week.

If you look at the graphs from: https://chromeperf.appspot.com/group_report?sid=7af1fe3bd5d924dd857af464ac01df2554d05c9dd906c9883203bf8466638ee5, on the second graph for the nexus6 you can see that the perf has good back to where it was before if you scroll to today.