All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=843666

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=541a6ea1f3088fe16477bf50614d2d78914222eb65cd4b82b12a4bbb7c16b1e9


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

linux-perf

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/17e141c8240000

😿 Pinpoint job stopped with an error.
https://pinpoint-dot-chromeperf.appspot.com/job/17e141c8240000

All of the attempts failed. See the individual attempts for details on each error.

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/119c2fe8240000

😿 Pinpoint job stopped with an error.
https://pinpoint-dot-chromeperf.appspot.com/job/119c2fe8240000

All of the attempts failed. See the individual attempts for details on each error.

I think these errors are related to the perf waterfall isolate migration.
It was fixed (https://chromium-review.googlesource.com/c/chromium/src/+/1057350)
But the fix is in Chromium, so the bisect, which is running old Chromium, doesn't contain the fix. I'm going to try running a bisect with a fix patch applied to the entire Job (beta feature).

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/105865e8240000

😿 Pinpoint job stopped with an error.
https://pinpoint-dot-chromeperf.appspot.com/job/105865e8240000

All of the attempts failed. See the individual attempts for details on each error.

Whoops, forgot to deploy. Rerunning again...

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/14b912c4240000

📍 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/14b912c4240000

The last bisect ran successfully and failed to reproduce. There are just two pages on one platform with this regression, and both are pretty noisy.