All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=768063

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=4db0d45170b74ed1d4cadd2827b51fce1ffb9a210bb4e92c77e22f2945a42292


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

chromium-rel-mac-retina
chromium-rel-mac11-air
chromium-rel-mac12

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8967712162862673264

=== Auto-CCing suspected CL author ulan@chromium.org ===

Hi ulan@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Ulan Degenbaev
  Commit : a76d0a771e430dbc8716624febc549aede738d96
  Date   : Thu Sep 21 12:35:10 2017
  Subject: Reland "[heap] Enable concurrent marking for x86 and x64."

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : memory.long_running_idle_gmail_tbmv2
  Metric       : v8-gc-total_avg/v8-gc-total_avg
  Change       : 25.82% | 0.556564124785 -> 0.700268709039

Revision                           Result                     N
chromium@503429                    0.556564 +- 0.0640059      6      good
chromium@503472                    0.55702 +- 0.0634771       6      good
chromium@503483                    0.554667 +- 0.04014        6      good
chromium@503489                    0.536687 +- 0.022064       6      good
chromium@503491                    0.544112 +- 0.0419477      9      good
chromium@503491,v8@2857dab5cb      0.531149 +- 0.0266749      6      good
chromium@503491,v8@a76d0a771e      0.683506 +- 0.129157       6      bad       <--
chromium@503492                    0.639704 +- 0.120618       6      bad
chromium@503494                    0.679482 +- 0.201404       9      bad
chromium@503515                    0.700269 +- 0.0765964      6      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 memory.long_running_idle_gmail_tbmv2

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967712162862673264


For feedback, file a bug with component Speed>Bisection

 Issue 768155  has been merged into this issue.

The regression in gc-total_avg is expected. Concurrent marking reduced the number of marking steps by several factors. Since marking steps are short running events, reducing their number increases the average of GC events.

The total GC time decreased with concurrent marking decreased by factor of two:
https://chromeperf.appspot.com/report?sid=38f20e320313df12d67a7fdcd5fb5bc49962e806584c7be640a66fcc576969db&rev=503520

 Issue 768153  has been merged into this issue.

 Issue 768293  has been merged into this issue.

 Issue 768290  has been merged into this issue.

 Issue 768292  has been merged into this issue.

 Issue 768288  has been merged into this issue.

 Issue 768289  has been merged into this issue.

 Issue 768288  has been merged into this issue.

 Issue 768292  has been merged into this issue.

 Issue 768067  has been merged into this issue.

 Issue 768067  has been merged into this issue.