All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=880830

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=4c4e4fd2c0a962d466531948de545a21346e84f507220336f3fdf961d58045d0


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

android-nexus5x-perf

rendering.mobile - Benchmark documentation link:
  https://bit.ly/rendering-benchmarks

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/155736c9640000

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/155736c9640000

Roll src/third_party/catapult 713e916190aa..88dc49aaadb0 (3 commits) by catapult-chromium-autoroll@skia-buildbots.google.com.iam.gserviceaccount.com
https://chromium.googlesource.com/chromium/src/+/fcfe9a6f17f02771890c03d666dcebf560eca909
18.16 → 18.71 (+0.5476)

Assigning to sheriff sullivan@chromium.org because "Roll src/third_party/catapult 713e916190aa..88dc49aaadb0 (3 commits)" is a roll.

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

Benchmark documentation link:
  https://bit.ly/rendering-benchmarks

+pasko, FYI. This is a little weird, but doesn't look like there's a good way to follow up. Most of the "regressions" from changing CPU/GPU frequency on N5X show the ref build changing too. In these graphs, the ref build is stable, but pinpoint blames the change on CPU/GPU frequency.

WontFix-ing because we knew the frequency change would cause changes. But feel free to re=open if this merits further investigation.

I might be doing something wrong, but I am not seeing the ref moving in these graphs. Also the new noise levels are worse than I expected, will investigate more.