Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8960170186960666256

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8960170161463110608

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

Hi dalecurtis@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


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

Suspected Commit
  Author : Dale Curtis
  Commit : 74612b7459881f9194f4d404e4f6688efe0bd8f5
  Date   : Thu Dec 14 20:56:19 2017
  Subject: Plumb UKM PlayerID for WatchTime and VideoDecodeStats recording.

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : blink_perf.image_decoder
  Metric       : ImageFrameGenerator::decode/decode-png.html
  Change       : 0.93% | 144.717396429 -> 143.250064286

Revision             Result                  N
chromium@524108      144.717 +- 2.91934      14      good
chromium@524141      144.058 +- 3.21398      21      good
chromium@524158      144.029 +- 2.5971       14      good
chromium@524166      143.895 +- 2.28642      21      good
chromium@524167      138.607 +- 1.30364      6       bad       <--
chromium@524168      138.883 +- 1.28537      6       bad
chromium@524170      138.811 +- 1.25848      6       bad
chromium@524174      143.25 +- 2.45236       14      bad

Please refer to the following doc on diagnosing blink_perf regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/speed/benchmark_harnesses/blink_perf.md

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 --story-filter=decode.png.html blink_perf.image_decoder

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8960170161463110608


For feedback, file a bug with component Speed>Bisection

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

Hi ajwong@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


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

Suspected Commit
  Author : Albert J. Wong
  Commit : 8c29b757124e1ceb921ad61d023b6b741eda92d4
  Date   : Thu Dec 14 18:48:00 2017
  Subject: Enable frame pointers on arm32.

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : blink_perf.image_decoder
  Metric       : ImageFrameGenerator::decode/decode-png.html
  Change       : 2.49% | 300.001366667 -> 307.465575

Revision             Result                   N
chromium@524075      300.001 +- 0.660499      6      good
chromium@524106      300.226 +- 0.514386      6      good
chromium@524121      300.251 +- 1.31323       6      good
chromium@524125      299.933 +- 0.837817      6      good
chromium@524126      299.95 +- 0.894075       6      good
chromium@524127      307.506 +- 1.56375       6      bad       <--
chromium@524129      307.522 +- 1.9798        6      bad
chromium@524136      307.398 +- 1.0658        6      bad
chromium@524196      307.466 +- 1.76839       6      bad

Please refer to the following doc on diagnosing blink_perf regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/speed/benchmark_harnesses/blink_perf.md

To Run This Test
  src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=decode.png.html blink_perf.image_decoder

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8960170186960666256


For feedback, file a bug with component Speed>Bisection

Anyho, https://chromium-review.googlesource.com/c/chromium/src/+/826255 reverted by ajwong@ and the Android bots recovered afterward.

https://chromeperf.appspot.com/report?sid=c4dfef665436649947559a795146cef680e6a2ac1f0d5e531d36338ae0afbe79&start_rev=517032&end_rev=524664

Thanks Albert.