All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=610721

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9JL8pgoM


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

chromium-rel-win7-single

2016-05-11 03:06:44 
===== BISECT JOB RESULTS =====
Status: started


===== TESTED REVISIONS =====
Revision         Mean      Std Dev  N   Good?
chromium@391560  32997928  454906   5   good
chromium@391605  33165140  513973   18  good
chromium@391625  31292845  2819520  18  good
chromium@391634  32771075  29150.4  5   good
chromium@391638  27648072  459119   5   bad
chromium@391642  27958846  673266   12  bad
chromium@391668  27439314  31195.9  5   bad

Bisect job ran on: win_perf_bisect
Bug ID: 610721

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests v8.infinite_scroll
Test Metric: memory:chrome:all:subsystem:v8:allocated_objects_max/tumblr
Relative Change: 16.85%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6508
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9013035471013917584


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5865192013955072

| 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!

Kicked off another bisect.
crrev.com/78980b9332da0264f52bd4ff0b6aeef23cdc21e9 is a bit suspicious so +hong.zheng@intel.com.

The CL reverted by https://crrev.com/78980b9332da0264f52bd4ff0b6aeef23cdc21e9 has been relanded in https://crrev.com/b28b53323cf9a4e487e081a63b546c210f4878b2. Could you verify the issue with it?

The reland didn't have any impact here.

I've kicked off another bisect here:
https://chromeperf.appspot.com/buildbucket_job_status/9012867699555216176

The only other suspicious patch is the v8 roll.
crrev.com/927c6b6030c0b53b20bcfa4fe27c38c7023d6643

jochen@, could this be a dupe of  issue 609581 ?

I'd be very surprised

Kicked off another bisect here:
https://chromeperf.appspot.com/buildbucket_job_status/9012775716555736560

Previous results point to a catapult roll that looks completely innocent.

2016-05-12 21:50:13 
===== BISECT JOB RESULTS =====
Status: started


===== TESTED REVISIONS =====
Revision                       Mean      Std Dev  N  Good?
chromium@391560                31724581  2654884  8  good
chromium@391605                32138360  1890514  8  good
chromium@391625                33201296  554949   5  good
chromium@391632                32967925  454821   5  good
chromium@391634                32982866  439320   5  good
chromium@391634,v8@ca5aa3c86a  28062000  597401   5  bad
chromium@391635                27893274  565112   5  bad
chromium@391638                27718206  469778   8  bad
chromium@391668                27713630  475863   8  bad

Bisect job ran on: win_perf_bisect
Bug ID: 610721

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests v8.infinite_scroll
Test Metric: memory:chrome:all:subsystem:v8:allocated_objects_max/tumblr
Relative Change: 10.46%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_perf_bisect/builds/6515
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9012867699555216176


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5879688870756352

| 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!

YAB: https://chromeperf.appspot.com/buildbucket_job_status/9012497290792813664

YAB: https://chromeperf.appspot.com/buildbucket_job_status/9012404626503759392

YAB: https://chromeperf.appspot.com/buildbucket_job_status/9012139015401162544

YAB just on the v8 roll: https://chromeperf.appspot.com/buildbucket_job_status/9011501650023147232

YAB: https://chromeperf.appspot.com/buildbucket_job_status/9011045062056206064

Moving this nonessential bug to the next milestone.

For more details visit https://www.chromium.org/issue-tracking/autotriage - Your friendly Sheriffbot

The latest bisect (not posted to bug) narrowed to this range:

https://chromium.googlesource.com/v8/v8/+log/82213ac6..e8e9c07

Given that, I'm really thinking this is the same as  issue 609581 . Jochen, can you take a look?

Jochen, can you please take a look?

the graph recovered (also, I don't really see how any of the changes in the bisect range would influence the size of allocated objects :-/ )