All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=637624

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgjoT-twoM


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

android-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004306556070971344

[1] shows the regression happens on only nexus5x.

[1] https://chromeperf.appspot.com/report?sid=7d5bfcb9a47231f10a14c8ba9cceef05362e9139dd29b828827f4df5a05612e0

===== 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@411586  23.8119  1.05052   18  good
chromium@411599  23.7789  0.982683  18  bad

Bisect job ran on: android_nexus5X_perf_bisect
Bug ID: 637624

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --also-run-disabled-tests service_worker.service_worker_micro_benchmark
Test Metric: concurrent_10_response_99_percentile/concurrent_10_response_99_percentile
Relative Change: 3.30%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5X_perf_bisect/builds/511
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004306556070971344


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5798689868611584

| 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!

Changes between 411587 - 411599 related to the microbenchmark seems https://crrev.com/2240053002 or https://crrev.com/2237813003. but I'm still not sure why only 99%-ile on nexus5x got slower constantly.

It looks like we somehow got our perf back around Sept 21: https://chromeperf.appspot.com/group_report?bug_id=637624

It slipped by our triage process though, after the initial bisect. We should make these Pri=1 and flag them as ongoing Action Items in the meeting notes.