All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=626273

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgsqjjpgoM


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

android-nexus5

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


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@403889  18855.4  120.751  12  good
chromium@403906  18821.5  130.048  8   bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 626273

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: 0.15%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3805
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007804858420888656


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5858512127655936

| 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!

Trying a slightly wider bisect, with more iterations. 

Probably just noise, but I kicked off another bisect with more iterations to be sure.

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


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@403870  18801.2  128.526  9  good
chromium@403950  18816.9  102.912  8  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 626273

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: 0.35%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/3806
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9007784168986382240


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5291204393041920

| 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!

Ref build also drops, so I think this is probably some hardware change.

I agree with ned, can't reproduce.