All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=724656

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg2q_E5AgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDguoz-uwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg2uT99QgM


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

chromium-rel-mac12
win-high-dpi

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8979130169053176096

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

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : memory.long_running_idle_gmail_tbmv2
  Metric       : memory:chrome:renderer_processes:reported_by_os:system_memory:private_dirty_size_max/memory:chrome:renderer_processes:reported_by_os:system_memory:private_dirty_size_max

Revision             Result                      N
chromium@472460      309902725 +- 105390617      21      good
chromium@472573      302525370 +- 94321920       21      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests memory.long_running_idle_gmail_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8979130169053176096

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5015468919750656


| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8979114497532464048

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

Hi bccheng@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 : bccheng
  Commit : 1db0354a8c83ab43aeeebde0c05bbbf91b0e2864
  Date   : Wed May 17 16:18:26 2017
  Subject: Add OWNERS file for CrOS-specific Telemetry tests.

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : memory.long_running_idle_gmail_tbmv2
  Metric       : memory:chrome:renderer_processes:reported_by_os:system_memory:private_dirty_size_max/memory:chrome:renderer_processes:reported_by_os:system_memory:private_dirty_size_max
  Change       : 12.86% | 346084664.0 -> 301562209.333

Revision             Result                     N
chromium@472460      346084664 +- 5694391       9      good
chromium@472464      347635822 +- 10980489      9      good
chromium@472466      347449420 +- 5868814       9      good
chromium@472467      298921703 +- 47932680      6      bad       <--
chromium@472468      297925284 +- 56699754      9      bad
chromium@472475      301602314 +- 49206963      6      bad
chromium@472489      300685655 +- 47737103      6      bad
chromium@472517      299669951 +- 49530163      6      bad
chromium@472573      301562209 +- 48961283      6      bad

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests memory.long_running_idle_gmail_tbmv2

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8979114497532464048

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5015468919750656


| 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!

This is very unlikely the cause of a regression. Looking at the graphs, this seems like it's difficult to be bisect, so closing.