All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=639757

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgnquAuAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgrpLIhgkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgnqTWtAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgnoagvAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg7qjy8goM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgnuCAoQoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg7p2YsAkM


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

chromium-rel-mac-retina
chromium-rel-mac10
chromium-rel-mac11

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9003644084326152496

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9003644015879361136

===== BISECT JOB RESULTS =====
Status: completed


===== TESTED REVISIONS =====
Revision                             Mean     Std Dev   N  Good?
chromium@413333                      11.3851  5.94208   8  good
chromium@413333,catapult@8fdfb52f84  10.3146  1.464     5  good
chromium@413333,catapult@0389892bfa  9.77687  0.389629  5  good
chromium@413334                      25.2469  8.19968   8  bad
chromium@413335                      21.6688  1.84853   8  bad

Bisect job ran on: mac_10_10_perf_bisect
Bug ID: 639757

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests tab_switching.top_10
Test Metric: energy_consumption_mwh/energy_consumption_mwh
Relative Change: 76.26%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_10_perf_bisect/builds/2320
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003644084326152496


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5314774057877504

| 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 Tests>AutoBisect.  Thank you!

Marked this bisect as bad as the output is not actionable (?). Sheriff documentation needs pointers on how to convert revision identifiers to changelists and owners. Will have to seek help to proceed.

Appears to have reverted to baseline in chromium@413404 - chromium@413410.

===== BISECT JOB RESULTS =====
Status: completed


===== TESTED REVISIONS =====
Revision                             Mean     Std Dev  N  Good?
chromium@413328                      35.0135  2.22422  5  good
chromium@413332                      35.6827  2.28799  5  good
chromium@413333                      34.9875  1.82224  5  good
chromium@413333,catapult@8fdfb52f84  34.8684  1.59332  5  good
chromium@413333,catapult@0389892bfa  35.0273  1.90013  5  good
chromium@413334                      42.5374  1.65837  5  bad
chromium@413335                      42.8756  1.76816  5  bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 639757

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests tab_switching.tough_energy_cases
Test Metric: energy_consumption_mwh/energy_consumption_mwh
Relative Change: 22.45%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1597
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9003644015879361136


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5849269852962816

| 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 Tests>AutoBisect.  Thank you!

#7 skipped over the last revision in the roll, the issue has been fixed since.

The skipped over revision is: https://chromium.googlesource.com/external/github.com/catapult-project/catapult.git/+/30ce231266c6fb6147bb6df7c56a7eb75c23fccf



It turns out that implicitly initialize network controller
whenever platform instance is created is a bad idea. Although
it's more ergonomic, it hides the responsiblity of call sites
to clean up the network_controller (shutting down
ts_proxy_server).

This CL makes remove implicitly initializing network_controller
and requires call sites to be explicit about doing so & clean
it up when they finish using network_controller.

BUG=catapult:#2584
TBR=sullivan@chromium.org, pmeenan@chromium.org

Review-Url: https://codereview.chromium.org/2265593003


Ned, do you think this regression is related to your change?

Not at all. It should be mostly a no-op.

Recovered.