All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=659532

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgvZruswoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgveCiugoM


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

android-one

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8997749526097653024

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

Hi dtapuska@chromium.org, the bisect results pointed to your CL below as possibly
causing a regression. Please have a look at this info and see whether
your CL be related.


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


===== SUSPECTED CL(s) =====
Subject : Define WebTextInputMode as a enum in the public API.
Author  : dtapuska
Commit description:
  
Change the WebString being passed back into at the public API layer
into an enum and move the string->enum conversion into blink.

Add missing enum types that match the spec as it is today. We are still
working out what we will ship.

BUG=634330
TBR=shuchen@chromium.org

Review-Url: https://codereview.chromium.org/2422663002
Cr-Commit-Position: refs/heads/master@{#427352}
Commit  : c4dd5befeeaffe92aa6973024ccc9537eddae3e3
Date    : Tue Oct 25 15:14:54 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@427329  1441792  0.0      5  good
chromium@427341  1454080  0.0      5  good
chromium@427347  1454080  0.0      5  good
chromium@427350  1454080  0.0      5  good
chromium@427351  1454080  0.0      5  good
chromium@427352  1478656  0.0      5  bad    <--
chromium@427353  1478656  0.0      5  bad

Bisect job ran on: android_one_perf_bisect
Bug ID: 659532

Test Command: src/tools/perf/run_benchmark -v --browser=android-chromium --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests memory.top_10_mobile
Test Metric: memory:chrome:all_processes:reported_by_os:system_memory:ashmem:proportional_resident_size_avg/background/after_http_m_youtube_com_results_q_science
Relative Change: 2.56%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_one_perf_bisect/builds/1761
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8997749526097653024


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6397425856544768

| 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!

The change in question moved some static data from the render_widget into pre-allocated atomic strings in blink. The data set is now smaller (it was a hashtable before, now it is a series of strings). However looking at the graphs it seems to have recovered to what it was before. 

Seems to me that a page is almost full it and allocates another one that causes the jump.

alexclarke@ WDYT?

Closing as it seems recovered.