Graphs:
https://chromeperf.appspot.com/group_report?bug_id=657168

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8998205593678624832

jgruber, please investigate. I kicked of a bisect. I would suggest waiting for the result

+Ulan since it's incremental marking times. 

This is caused by my changes in incremental marking heuristics.

Increase in average step size is expected.

===== BISECT JOB RESULTS =====
Status: failed


===== TESTED REVISIONS =====
Revision         Mean      Std Dev    N  Good?
chromium@421587  0.847198  0.0952551  5  good
chromium@421650  1.70829   0.142785   5  bad

Bisect job ran on: mac_hdd_perf_bisect
Bug ID: 657168

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests v8.browsing_desktop
Test Metric: v8-gc-total_avg/v8-gc-total_avg
Relative Change: 101.64%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_hdd_perf_bisect/builds/862
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8998205593678624832


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5872379996143616

| 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 Tests>AutoBisect.  Thank you!