All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=650010

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg-YPg5QsM


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

android-galaxy-s5

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9000579140377584304

===== 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@420027  185.282  2.47583  18  good
chromium@420152  184.66   6.84568  18  bad

Bisect job ran on: android_s5_perf_bisect
Bug ID: 650010

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests dromaeo.domcoreattr
Test Metric: dom/dom
Relative Change: 3.00%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_s5_perf_bisect/builds/1033
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9000579140377584304


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5822503631454208

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8999799647305938480

===== 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@420027  186.169  2.76194  18  good
chromium@420152  180.275  11.3656  18  bad

Bisect job ran on: android_s5_perf_bisect
Bug ID: 650010

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests dromaeo.domcoreattr
Test Metric: dom/dom
Relative Change: 0.65%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_s5_perf_bisect/builds/1058
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8999799647305938480


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5809298318295040

| 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!

Roberto, Dave, can you help me figure out why bisect doesn't see this clear regression?

Looks like the build was green at #4085 (immediately before the regression), then it went purple (device failure) and the device was reset. Since this just happened on one device with no ref build, I think it is likely some consequence of device reset.