All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=684421

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg0LOsvwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg0Mu4qAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg0I699QkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgkIHlqQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg0LSWpAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgkNSe_AsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgkOLv7QoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgkJ2i_QgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgkLLxvQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4Jui8wgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg0Pz7qAoM


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

android-nexus5X
android-nexus7v2
android-one

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8989593715194586384

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

Hi jdufault@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 : jdufault
  Commit : 6229de84ea74dc067cce0a324211d0d2d4874716
  Date   : Fri Jan 20 23:10:26 2017
  Subject: cros: Fix crash from a stale ModelViewChannel reference.

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : memory.top_10_mobile_stress
  Metric       : memory:chrome:all_processes:reported_by_os:system_memory:java_heap:proportional_resident_size_avg/background/after_https_mobile_twitter_com_justinbieber_skip_interstitial_true
  Change       : 21.93% | 8113493.33333 -> 9892864.0

Revision             Result                  N
chromium@445129      8113493 +- 1042702      6      good
chromium@445165      8594091 +- 2131372      6      good
chromium@445183      8157525 +- 274289       6      good
chromium@445192      8536064 +- 277483       6      good
chromium@445196      8880128 +- 252660       6      good
chromium@445198      9137493 +- 163139       6      good
chromium@445199      9356971 +- 234107       6      good
chromium@445200      9892864 +- 90146.9      6      bad       <--

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.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=https.mobile.twitter.com.justinbieber.skip.interstitial.true memory.top_10_mobile_stress

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8989593715194586384

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5793051521318912


| 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!

That CL is cros only.

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8989562073221199136

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

Hi zqzhang@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 : zqzhang
  Commit : c3a579962e733b26ef12f564732260844d558a56
  Date   : Fri Jan 20 20:30:58 2017
  Subject: [Media>UI] Don't scale the icon if it's smaller than the ideal size

Bisect Details
  Configuration: android_one_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_os:system_memory:private_dirty_size_avg/foreground/http_m_youtube_com_results_q_science
  Change       : 2.07% | 33297094.2857 -> 32888079.4286

Revision             Result                   N
chromium@445126      33297094 +- 1812001      14      good
chromium@445146      33127695 +- 1181942      14      good
chromium@445147      32914801 +- 1517926      21      bad       <--
chromium@445148      32874914 +- 829077       14      bad
chromium@445149      32862918 +- 1039891      14      bad
chromium@445151      32862203 +- 730960       9       bad
chromium@445155      32813279 +- 355452       6       bad
chromium@445164      32888079 +- 1086401      14      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.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=http.m.youtube.com.results.q.science memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8989562073221199136

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6464820309655552


| 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!

Hi, I think you are bisecting on a wrong range or test suite. Can yo double check?
The last bisect is actually a memory usage reduction (which is caused by my CL) instead of an increase.

Feel free to throw back if you believe it's my problem.

Let me assign today's sheriff.

This is a revert of a recent improvement, so marking WontFix, as per the perf sheriffing instructions.