All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=682294

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4NGLtwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4L_4rwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4LyDtwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgoNKyiAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4Oi_qQkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4N-LpwkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4LyDtwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4N-ftgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4IfNrAoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4LzZpgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg4N-LpwoM


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

android-nexus5

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8990111798457662448

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

Hi hjd@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 : hjd
  Commit : 593ea0410890854382a2df7cd58400208410a89a
  Date   : Tue Jan 17 14:54:50 2017
  Subject: Reland of Stop bad results on first memory benchmark run (patchset #1 id:1 of https://codereview.chromium.org/2627323002/ )

Bisect Details
  Configuration: android_nexus5_perf_bisect
  Benchmark    : memory.top_10_mobile_stress
  Metric       : memory:chrome:all_processes:reported_by_os:gpu_memory:proportional_resident_size_avg/background/after_https_www_google_co_uk_hl_en_q_science
  Change       : 7.59% | 22953984.0 -> 24696149.3333

Revision             Result                   N
chromium@444038      22953984 +- 0.0          6      good
chromium@444046      22953984 +- 0.0          6      good
chromium@444050      22953984 +- 0.0          6      good
chromium@444051      24699563 +- 39465.0      6      bad       <--
chromium@444052      24691371 +- 40306.2      6      bad
chromium@444054      24699563 +- 39465.0      6      bad
chromium@444070      24696149 +- 88357.2      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.www.google.co.uk.hl.en.q.science memory.top_10_mobile_stress

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8990111798457662448

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6353640484241408


| 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!

Expected regression, we were undercounting memory for all reported_by_os:gpu_memory due to a bug in how we were flushing the system cache :( that CL fixes the bug.
I think there were a bunch of similar regressions, I meant to preemptively go through the alerts and comment on the likely ones today but then I got distracted, I'll have a look through them tomorrow.