All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=748279

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=cf19bfffe0866d28fc4c0c2242541e0ac46b6bcb4cc462f4e84fa451ccf00292


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

chromium-rel-win7-gpu-ati
chromium-rel-win7-gpu-intel
chromium-rel-win8-dual
win-high-dpi

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8973144886324747504

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

Hi ricea@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 : Adam Rice
  Commit : 2431d137d1016a82d007556eb15189f0500507b1
  Date   : Fri Jul 21 06:57:22 2017
  Subject: Wrap Promise manipulation methods in Stream API

Bisect Details
  Configuration: winx64_high_dpi_perf_bisect
  Benchmark    : media.tough_video_cases_tbmv2
  Metric       : memory:chrome:all_processes:reported_by_chrome:blink_gc:allocated_objects_size_avg/video.html?src_crowd1080_vp9.webm
  Change       : 75.24% | 227938.666667 -> 399429.333333

Revision             Result                 N
chromium@488461      227939 +- 1281.03      6      good
chromium@488542      227688 +- 931.991      6      good
chromium@488583      228224 +- 1858.96      6      good
chromium@488603      227712 +- 921.217      6      good
chromium@488604      228231 +- 1233.79      6      good
chromium@488605      394696 +- 7029.41      6      bad       <--
chromium@488606      398427 +- 15592.1      6      bad
chromium@488608      395779 +- 12914.3      6      bad
chromium@488613      396333 +- 11113.5      6      bad
chromium@488623      399429 +- 38686.9      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=video.html.src.crowd1080.vp9.webm media.tough_video_cases_tbmv2

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

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8973144886324747504


For feedback, file a bug with component Speed>Bisection

Yet another case of a minor change to the Streams implementation causing a regression in a completely unrelated memory benchmark.

My guess is that the test is sensitive to the exact layout of the V8 heap?

I don't think this is actionable anyway.

 Issue 748526  has been merged into this issue.

 Issue 748525  has been merged into this issue.

 Issue 748526  is the same benchmark but with memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg.

To me it just looks like the number of garbage collections that happened during the test changed.