All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=751632

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=901ff9a32e880f8249ae0429ded35a5d4f67a396dd484924e598185c713a8e6a


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

android-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972368695808543600

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972368657248153392

I kicked off a second bisect on a wider range, since the chart goes up and down it's hard to tell where the regression occurred.

Yeah, hard to say what's going on here yet, but it's pretty plausible that we'll want to dup that on those other bugs too, especially if these Nexus 5x's are running 32-bit ARM builds.

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : thread_times.key_mobile_sites_smooth
  Metric       : thread_total_all_cpu_time_per_frame/http___cuteoverload.com

Revision             Result                  N
chromium@489954      35.73 +- 8.20392        21      good
chromium@490022      35.2202 +- 6.80307      21      bad

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=http...cuteoverload.com thread_times.key_mobile_sites_smooth

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972368695808543600


For feedback, file a bug with component Speed>Bisection

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

Suspected Commit
  Author : Charles Harrison
  Commit : 7847afc23c816960a019476e995c696143365cac
  Date   : Thu Jul 27 01:15:34 2017
  Subject: Remove the DocumentWriteEvaluator

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : thread_times.key_mobile_sites_smooth
  Metric       : thread_total_all_cpu_time_per_frame/http___cuteoverload.com
  Change       : 8.18% | 32.4868386603 -> 35.6466460325

Revision             Result                  N
chromium@489813      32.4868 +- 3.95394      14      good
chromium@489824      31.8657 +- 5.83532      14      good
chromium@489825      35.9295 +- 2.55496      6       bad       <--
chromium@489826      35.5513 +- 3.7609       6       bad
chromium@489827      36.3372 +- 2.702        6       bad
chromium@489830      35.4982 +- 5.3956       6       bad
chromium@489834      34.4485 +- 11.0136      21      bad
chromium@489860      34.8563 +- 11.1496      14      bad
chromium@489902      34.5975 +- 9.97843      21      bad
chromium@489999      34.8356 +- 5.61911      14      bad
chromium@490176      35.0771 +- 11.157       14      bad
chromium@490538      35.6466 +- 4.45361      6       bad

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=http...cuteoverload.com thread_times.key_mobile_sites_smooth

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8972368657248153392


For feedback, file a bug with component Speed>Bisection