All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=722994

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6rLjpQoM


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

chromium-rel-mac-retina

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8979407619669359888

=== BISECT JOB RESULTS ===
Perf regression found but unable to narrow commit range

Build failures prevented the bisect from narrowing the range further.


Bisect Details
  Configuration: mac_retina_perf_bisect
  Benchmark    : smoothness.gpu_rasterization.tough_path_rendering_cases
  Metric       : frame_times/https___testdrive-archive.azurewebsites.net_performance_chalkboard_
  Change       : 0.80% | 32.3968582633 -> 32.5173982618

Suspected Commit Range
  49 commits in range
  https://chromium.googlesource.com/chromium/src/+log/1cc74004b24c8a79dcee523e913c1d929c1167da..a66d812aa78debb856c1938f439e98feabeaeada


Revision             Result                   N
chromium@471248      32.3969 +- 0.648925      14       good
chromium@471249      ---                      ---      build failure
---                  ---                      ---      too many build failures to list
chromium@471296      ---                      ---      build failure
chromium@471297      32.5174 +- 0.685324      14       bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=https...testdrive.archive.azurewebsites.net.performance.chalkboard. smoothness.gpu_rasterization.tough_path_rendering_cases

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8979407619669359888

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5339237915820032


| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
|  X  | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with component Speed>Bisection.  Thank you!

This regression also affected the reference result, so it's likely a false alert. It also appears to have gone away at 472528-472615.