All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=728471

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgxvaNpgsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgxrWLowoM


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

android-webview-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8978024391534722272

=== Auto-CCing suspected CL author nednguyen@google.com ===

Hi nednguyen@google.com, 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 : nednguyen
  Commit : 24245dde6fc83c8881775a3d2556797f5bba287b
  Date   : Wed May 31 11:04:00 2017
  Subject: Always execute network_quiescence.js script upon navigating to a page

Bisect Details
  Configuration: android_webview_arm64_aosp_perf_bisect
  Benchmark    : system_health.memory_mobile
  Metric       : memory:webview:all_processes:reported_by_chrome:v8:effective_size_avg/load_tools/load_tools_docs

Revision                                 Result                  N
chromium@475876                          3277272 +- 0.0          6      good
chromium@475891                          3273741 +- 19338.3      6      good
chromium@475895                          3277144 +- 0.0          6      good
chromium@475897                          3277144 +- 0.0          6      good
chromium@475897,catapult@24245dde6f      3698417 +- 776.241      6      bad       <--
chromium@475898                          3698383 +- 638.139      6      bad
chromium@475899                          3698309 +- 703.242      6      bad
chromium@475906                          3698360 +- 702.817      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-webview --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.tools.docs system_health.memory_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8978024391534722272

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5215950971863040


| 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 Speed>Bisection.  Thank you!

This is expected to cause some slight perf change, but I don't know that it's gonna be that big :-/

I think we can just close this as Won't fix since this is a regression due to test change and not Chrome change.

Juan: wdyt?

Agreed. At least on this bug, these are only a few small-ish (< 400KiB) regressions on just a couple of pages. So fine to close.

+benhrenry FYI, in case this shows up on system health (I'm doubtful) it would need to be discounted as they are not real regressions but changes in the way measurements are performed.

 Issue 728380  has been merged into this issue.

 Issue 729626  has been merged into this issue.

 Issue 729625  has been merged into this issue.

 Issue 729628  has been merged into this issue.

 Issue 729644  has been merged into this issue.

 Issue 729624  has been merged into this issue.

 Issue 728947  has been merged into this issue.

 Issue 730573  has been merged into this issue.

We might need to have a closer look at this. There may not be much we can do, but after many of the dupes, some of the larger regressions are of about ~20MiB.

See: https://chromeperf.appspot.com/group_report?bug_id=728471

+sullivan Also some of those alerts seem to have been triggered on summary metrics (e.g. browse_social) and not individual pages?

I think the triggering on summary metrics was caused by  bug 727234 .

 Issue 731873  has been merged into this issue.

 Issue 731866  has been merged into this issue.

 Issue 732465  has been merged into this issue.

I've had a look again. Large increases are all in v8:heap; I assume because we wait for network quiescence in more scenarios, more resources are being loaded.

Should be fine to WontFix.