All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=664104

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgs7i2ugkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg08enoAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg092O6woM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgs-ic7AoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg09PrsAoM


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

chromium-rel-mac-hdd
chromium-rel-win7-gpu-ati
chromium-rel-win7-gpu-nvidia
chromium-rel-win7-x64-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8996382532464239824

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8996335333962691792

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8996335326003095888

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

Hi ulan@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [heap] Remove js call rate heuristic from memory reducer.
Author  : ulan
Commit description:
  
This is an experiment to check whether the heuristics is still useful.

BUG=

Review-Url: https://codereview.chromium.org/2482163002
Cr-Commit-Position: refs/heads/master@{#40833}
Commit  : 984e6aed3e8c597e8985ea53225f142257037a68
Date    : Tue Nov 08 13:48:11 2016


===== TESTED REVISIONS =====
Revision                       Mean     Std Dev  N   Good?
chromium@430614                13.0991  4.05956  8   good
chromium@430631                13.6693  6.6945   12  good
chromium@430640                13.694   3.21486  8   good
chromium@430641                13.7643  4.05611  12  good
chromium@430641,v8@a5d251defe  13.8091  2.36694  8   good
chromium@430641,v8@984e6aed3e  16.6666  2.27254  5   bad    <--
chromium@430641,v8@4d6ff7dfaa  17.1322  2.41025  5   bad
chromium@430642                16.5791  3.93452  8   bad
chromium@430644                16.9931  2.35519  8   bad
chromium@430648                17.638   4.57034  8   bad

Bisect job ran on: winx64nvidia_perf_bisect
Bug ID: 664104

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests memory.long_running_idle_gmail_tbmv2
Test Metric: v8-gc-total_max/v8-gc-total_max
Relative Change: 38.15%

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64nvidia_perf_bisect/builds/1952
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8996335326003095888


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5208646332448768

| 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!

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [heap] Remove js call rate heuristic from memory reducer.
Author  : ulan
Commit description:
  
This is an experiment to check whether the heuristics is still useful.

BUG=

Review-Url: https://codereview.chromium.org/2482163002
Cr-Commit-Position: refs/heads/master@{#40833}
Commit  : 984e6aed3e8c597e8985ea53225f142257037a68
Date    : Tue Nov 08 13:48:11 2016


===== TESTED REVISIONS =====
Revision                       Mean      Std Dev   N   Good?
chromium@430612                0.447431  0.179774  8   good
chromium@430629                0.495576  0.234801  12  good
chromium@430638                0.51901   0.350426  12  good
chromium@430640                0.477743  0.140918  5   good
chromium@430641                0.486407  0.175792  8   good
chromium@430641,v8@a5d251defe  0.508135  0.291142  8   good
chromium@430641,v8@984e6aed3e  0.644308  0.164755  12  bad    <--
chromium@430641,v8@4d6ff7dfaa  0.651152  0.117458  8   bad
chromium@430642                0.665701  0.155082  8   bad
chromium@430646                0.641834  0.145359  12  bad

Bisect job ran on: win_x64_perf_bisect
Bug ID: 664104

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests memory.long_running_idle_gmail_tbmv2
Test Metric: v8-gc-incremental-step_avg/v8-gc-incremental-step_avg
Relative Change: 38.85%

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_x64_perf_bisect/builds/1532
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8996335333962691792


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5822338841444352

| 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!

This is not a real regression if we zoom out:
https://chromeperf.appspot.com/report?sid=fbc072bb237c42641baae9a319d927fa06c2eea86199afc6b6f0f580f72ce0e1&rev=430737

There was a change recently that effectively disabled memory reducer due to increased js call rate. That change has also regressed memory.

This change reverts effects of the older change: more GC time, less memory usage.