All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=713576

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgopiQ_QgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgwv-IqQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgosCwvgoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgwt3-7QkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgwv_fowoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgwqeYtgoM


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

android-nexus6
android-webview-nexus6

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8981811122711143728

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

Hi hidehiko@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 : hidehiko
  Commit : ddefb10bee663f8d240c999309f37cc2f96d2e92
  Date   : Tue Apr 18 11:14:53 2017
  Subject: Revert of Back PaintRecord with PaintOpBuffer instead of SkPicture (patchset #42 id:810001 of https://codereview.chromium.org/2768143002/ )

Bisect Details
  Configuration: android_nexus6_perf_bisect
  Benchmark    : memory.top_10_mobile_stress
  Metric       : memory:chrome:all_processes:reported_by_chrome:gpu:effective_size_avg/foreground/https_mobile_twitter_com_justinbieber_skip_interstitial_true
  Change       : 316.52% | 9776436.0 -> 40720972.0

Revision             Result                   N
chromium@465186      9776436 +- 0.0           6      good
chromium@465191      9776436 +- 0.0           6      good
chromium@465194      10125961 +- 1914429      6      good
chromium@465195      9776436 +- 0.0           6      good
chromium@465196      40720972 +- 0.0          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 memory.top_10_mobile_stress

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8981811122711143728

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5527967989497856


| 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!

The CL is simple revert, because of ChromeOS breakage.
Looking at the graph, there seems good improvement around 7days ago, which is very close to the original CL's land date? If so I think this is un-avoidable regression. Marking WontFix.
Sorry for inconvenience. CC to the original author just in case.

I'm not sure I believe this?

land#1: 464555
revert: 464563
land#2: 464701
revert: 464745
land#3: 464809
revert: 465196

The bisect certainly indicates that the 465196 revert improved memory, but looking at graphs, I don't think any of the previous improvements were related.

 Issue 713580  has been merged into this issue.

I think we need to reland and watch a few graphs. I'll make a list in the doc.

 Issue 713090  has been merged into this issue.

 Issue 713578  has been merged into this issue.