All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=657071

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgre-HrQoM


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

android-nexus5

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8998442482090444016

Possibly related to MemoryCoordinatorDelegate code landing.

+bashi for FYI.

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

Hi rtoy@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 : Implement ConstantSourceNode
Author  : rtoy
Commit description:
  
Add implementation of ConstantSourceNode, including a factory method
and a constructor.

This serves as a very useful constant source node, and, because it has
an AudioParam, it can be used as a constructible AudioParam.

Feature: https://www.chromestatus.com/features/5647701588836352
Intent: https://groups.google.com/a/chromium.org/d/msg/blink-dev/9uoSMZftWfY/GJaqkCUNAAAJ
Spec: https://webaudio.github.io/web-audio-api/#ConstantSourceNode

BUG= 644438 
TEST=constant-source-basic.html, constant-source-output.html

Review-Url: https://codereview.chromium.org/2134813002
Cr-Commit-Position: refs/heads/master@{#425184}
Commit  : f61f1e00fc29d3e88ef4e3d7b1c63d5b469d92f2
Date    : Thu Oct 13 22:16:33 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@425160  2052096  0.0      5  good
chromium@425183  2060288  0.0      5  good
chromium@425184  2097152  0.0      5  bad    <--
chromium@425185  2094694  5495.36  5  bad
chromium@425186  2097152  0.0      5  bad
chromium@425189  2097152  0.0      5  bad
chromium@425194  2097152  0.0      5  bad
chromium@425205  2093056  0.0      5  bad

Bisect job ran on: android_nexus5_perf_bisect
Bug ID: 657071

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/foreground/http_m_intl_taobao_com_group_purchase_html
Relative Change: 2.00%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/android_nexus5_perf_bisect/builds/4257
Job details: https://chromeperf.appspot.com/buildbucket_job_status/8998442482090444016


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5240328313896960

| 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!

Does this mean that memory usage went from 2060288 to 2097152?  A new node was added for WebAudio, so I expect memory usage to go up some.

Yes, it looks like about a 30k regression. Is that appropriate/expected for this CL?

-cc: bashi. Misdiagnosed on my part. :)

I'll have to build on Android to be sure, but on my linux machine, the size of ConstantSourceNode.o is about 36K.  Other files would have their sizes go up slightly too to add support for this node.

Can you explain a bit more about WebAudio and if it's gone through the launch process? If it's justified, let's closed this as wontfix.

Not sure what you want to know about WebAudio, but the Blink intent to implement and ship ConstantSourceNode is here:  https://groups.google.com/a/chromium.org/d/msg/blink-dev/9uoSMZftWfY/GJaqkCUNAAAJ

Friendly Perf-Sheriff ping! Any update here?

Not sure if 30k is reasonable, but adding a new WebAudio node including the code for the node itself, all the V8 wrappers and virtual methods/tables could add up to that.

Doesn't look like we're going to address this 8 month old 30k regression.