All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=724344

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgmtmtqwkM


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

android-webview-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8979206498630736944

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : drott
  Commit : fbec38011870753cffb3cb2ff98aa0c00c63b25c
  Date   : Wed May 17 10:49:03 2017
  Subject: Reland: Compile FreeType with HarfBuzz support

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : service_worker.service_worker
  Metric       : page_load_1st_speed_index/page_load_1st_speed_index
  Change       : 9.09% | 947.333333333 -> 1033.41666667

Revision             Result                  N
chromium@472397      947.333 +- 23.6397      6      good
chromium@472411      948.75 +- 20.503        6      good
chromium@472412      943.167 +- 32.3393      6      good
chromium@472413      1032.92 +- 31.1883      6      bad       <--
chromium@472415      1025.25 +- 32.8082      6      bad
chromium@472418      1042.08 +- 32.7064      6      bad
chromium@472424      1033.42 +- 24.8034      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests service_worker.service_worker

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8979206498630736944

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5863162185777152


| 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 Speed>Bisection.  Thank you!