All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=689840

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6NTuwwgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6NTugwsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgqMOn9AoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6MyE_ggM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6JGUsgsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6L7VjAkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6IXwvQsM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDg6MzpqAsM


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

android-nexus5X

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8988249402079828400

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

Hi ssid@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 : ssid
  Commit : efed310cc305f0d89f9d1aa49fb5e0d4ec9ff2cd
  Date   : Tue Feb 07 05:29:58 2017
  Subject: [memory-infra] Make client discardable segments non-weak

Bisect Details
  Configuration: android_nexus5X_perf_bisect
  Benchmark    : memory.top_10_mobile
  Metric       : memory:chrome:all_processes:reported_by_chrome:cc:effective_size_avg/foreground/http_www_amazon_com_gp_aw_s_k_nexus
  Change       : 28.69% | 25661544.0 -> 33022581.3333

Revision             Result                   N
chromium@448528      25661544 +- 0.0          6      good
chromium@448544      25661544 +- 0.0          6      good
chromium@448552      26313456 +- 3753313      6      good
chromium@448553      25647733 +- 75644.1      6      good
chromium@448554      32994435 +- 195006       6      bad       <--
chromium@448556      33050728 +- 0.0          6      bad
chromium@448559      33022581 +- 154166       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=http.www.amazon.com.gp.aw.s.k.nexus memory.top_10_mobile

Debug Info
  https://chromeperf.appspot.com/buildbucket_job_status/8988249402079828400

Is this bisect wrong?
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6060554482876416


| 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!

@ssid: I'm assuming a memory regression was expected. Is the magnitude small enough to close as WontFix?

Found some additional regression: https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgqJ_99QgM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDgqO-cugsM

Here is a few major regressions:
- 1300% - 50 MiB for imgur
- 80% - 80 MiB for facebook photos
- 40%  - 14 MiB for flipboard.com 

Those are major regressions and it seems like it is hitting hard image heavy sites. I like for benchmark owners to chime in before any decision to WontFix.

Sorry this is an expected regresison. Fixed the dump provider which accounts for memory correctly.

More data to support: The improvement caused by https://crrev.com/a083f971261bcccc53b64e40c911435857ce3bfd is because the accounting went wrong.
I verified that all graphs have exact same improvement at the pointed CL range as the regression now.