All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=893853

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=5eb68223486f37b343bde1e1ad7e31770631ef6add0234a70b7027c0efc04d29


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

mac-10_12_laptop_low_end-perf

system_health.common_desktop - Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/155563f2e40000

📍 Found significant differences after each of 3 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/155563f2e40000

Migrate components/data_reduction_proxy/core/browser/warmup_url_fetcher.cc to using SimpleURLLoader by tonikitoo@igalia.com
https://chromium.googlesource.com/chromium/src/+/0d8fcd4caec30132336abfb44ba0426be5829ad2
cpu_time_percentage: 0.4069 → No values

Make ServiceWorker use the existing Response DataPipe if one is available. by wanderview@chromium.org
https://chromium.googlesource.com/chromium/src/+/8f03111ab0c26320037e340051bb66ee88ea7722
cpu_time_percentage: No values → 0.4049

Reland "synthetic gesture: Allow high-frequency dispatch." by sadrul@chromium.org
https://chromium.googlesource.com/chromium/src/+/a66784e0fd71f686f1d7152902137619608c6c80
cpu_time_percentage: 0.4059 → 0.4614 (+0.05549)

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

Benchmark documentation link:
  https://bit.ly/system-health-benchmarks

AFAICT the first two revs listed here are due to a flake where the tests failed to run in the pinpoint job.  The regression appears related to the last commit:

https://chromium.googlesource.com/chromium/src/+/a66784e0fd71f686f1d7152902137619608c6c80

The change is to dispatch synthesized input events at a higher frequency. So a little higher cpu usage is expected. The change is only for the synthesized events during the telemetry tests, so it does not affect production code.