All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=657434

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg7Z7d_gkM


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

chromium-rel-mac-retina

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8998359654310317536

Good revision: 424422
 Bad revision: 426068

That... may be a problem.

Bisect failed: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1753
Failure reason: the build has failed.
Additional errors:
The metric was not found in the test output.
Either of the initial "good" or "bad" revisions failed to be tested or built.

It looks like a regression occurs on the reference build as well.

Here's the graph showing the regression on the ref build: https://chromeperf.appspot.com/report?sid=b30c260417747111ca87ee54f76c1e2c76e4c777254366c7faa0a94885dc8391&rev=426068

This is likely due to some condition in the environment (CPU temp, other processes running, etc.) that we need to look into now that we have the benchmarks running more reliably.

Closing this as WontFix because it's not a regression.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8982580518167224304