All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=612440

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjInHuQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjODXvgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9IuDtwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjMmarAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjMnlogoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjK6mpAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjLyjvwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjPzcqQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9IvZpgkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjJrzuwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjKSJvgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg9N3AoAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjIbjtQoM


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

android-nexus5
android-nexus5X
android-nexus6
android-nexus7v2
android-nexus9
android-one
linux-release

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

Hi bcwhite@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 : Support saving browser metrics to disk and reading them
Author  : bcwhite
Commit description:
  during next run.

This CL doesn't attempt to persist metrics during a
crash.  That will be addressed later.

BUG= 546019 
TBR=nasko
nasko: browser_main_runner.cc (moved existing creation code earlier but disable it until experiment is examined)

Review-Url: https://codereview.chromium.org/1891913002
Cr-Commit-Position: refs/heads/master@{#393521}
Commit  : 65e57d078b22b3695af734e0262c2b076a21b428
Date    : Fri May 13 14:40:48 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@393518  17815.7  141.681  6  good
chromium@393520  17890.4  167.56   5  good
chromium@393521  20873.8  79.8793  5  bad    <--
chromium@393522  20879.0  120.098  5  bad
chromium@393525  21057.2  105.089  5  bad

Bisect job ran on: android_one_perf_bisect
Bug ID: 612440

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.intl_es_fr_pt-BR
Test Metric: vm_private_dirty_final_browser/vm_private_dirty_final_browser
Relative Change: 18.45%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1319
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9012410453284716256


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5827259181563904

| 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!

I wouldn't expect my change to affect anything because it doesn't do anything new except always allocate a block of memory that may be used by an experiment.  Previously, the memory was allocated only when the experiment was enabled.

vm_private_dirty_final_browser/vm_private_dirty_final_browser must be memory though it would be useful to have a more descriptive subject.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004886073733839232

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

Hi bcwhite@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 : Support saving browser metrics to disk and reading them
Author  : bcwhite
Commit description:
  during next run.

This CL doesn't attempt to persist metrics during a
crash.  That will be addressed later.

BUG= 546019 
TBR=nasko
nasko: browser_main_runner.cc (moved existing creation code earlier but disable it until experiment is examined)

Review-Url: https://codereview.chromium.org/1891913002
Cr-Commit-Position: refs/heads/master@{#393521}
Commit  : 65e57d078b22b3695af734e0262c2b076a21b428
Date    : Fri May 13 14:40:48 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@393515  41456.0  317.121  5  good
chromium@393519  41932.8  830.509  5  good
chromium@393520  41559.2  128.276  5  good
chromium@393521  44917.8  885.658  5  bad    <--
chromium@393522  44701.6  29.1342  5  bad
chromium@393528  44929.8  754.323  5  bad

Bisect job ran on: android_nexus9_perf_bisect
Bug ID: 612440

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests page_cycler.intl_ar_fa_he
Test Metric: vm_private_dirty_final_browser/vm_private_dirty_final_browser
Relative Change: 8.38%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus9_perf_bisect/builds/1998
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004886073733839232


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5789863324942336

| 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!

Not sure why a bisect is running on a closed issues, but...

Two things together caused the extra memory to be allocated.  Both have been fixed:
https://codereview.chromium.org/1996843002/
https://codereview.chromium.org/2016013003/