All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=767723

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=701fc03ef1620c267e620bb03fa2168f1b20b1b4c73a90ef68db8999e5d7f405


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

chromium-rel-mac11
chromium-rel-win7-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8967791642901608112

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

Hi albertnetymk@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 : Albert Mingkun Yang
  Commit : dbfdd4f9e9741df0a541afdd7516a34304102ee8
  Date   : Thu Sep 14 09:10:09 2017
  Subject: [heap] Turn on v8_enable_csa_write_barrier

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/load_social/load_social_vk
  Change       : 1.42% | 6656000.0 -> 6561792.0

Revision                           Result                 N
chromium@502412                    6656000 +- 0.0         9      good
chromium@502450                    6597746 +- 494303      9      good
chromium@502469                    6656000 +- 0.0         6      good
chromium@502470                    6656000 +- 0.0         6      good
chromium@502470,v8@46000a1244      6656000 +- 0.0         6      good
chromium@502470,v8@97b2a814e4      6656000 +- 0.0         6      good
chromium@502470,v8@dbfdd4f9e9      6470315 +- 478607      6      bad       <--
chromium@502470,v8@725c15c794      6470315 +- 478607      6      bad
chromium@502470,v8@70372dfc64      6557696 +- 0.0         6      bad
chromium@502471                    6557696 +- 0.0         6      bad
chromium@502472                    6557696 +- 0.0         6      bad
chromium@502474                    6557696 +- 0.0         6      bad
chromium@502478                    6557696 +- 0.0         6      bad
chromium@502487                    6561792 +- 0.0         9      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=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.social.vk system_health.memory_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967791642901608112


For feedback, file a bug with component Speed>Bisection

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8967506351692657056

Simon, fyi, the bisect in #3 found a CL that actually improves the memory usage.

I restarted bisect.

=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Albert Mingkun Yang
  Commit : dbfdd4f9e9741df0a541afdd7516a34304102ee8
  Date   : Thu Sep 14 09:10:09 2017
  Subject: [heap] Turn on v8_enable_csa_write_barrier

Bisect Details
  Configuration: win_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/load_social/load_social_vk
  Change       : 1.42% | 6656000.0 -> 6561792.0

Revision                           Result                 N
chromium@502412                    6656000 +- 0.0         6      good
chromium@502450                    6656000 +- 0.0         9      good
chromium@502469                    6597746 +- 494303      9      good
chromium@502470                    6656000 +- 0.0         6      good
chromium@502470,v8@46000a1244      6656000 +- 0.0         6      good
chromium@502470,v8@97b2a814e4      6656000 +- 0.0         6      good
chromium@502470,v8@dbfdd4f9e9      6557696 +- 0.0         6      bad       <--
chromium@502470,v8@725c15c794      6557696 +- 0.0         6      bad
chromium@502470,v8@70372dfc64      6557696 +- 0.0         6      bad
chromium@502471                    6557696 +- 0.0         9      bad
chromium@502472                    6557696 +- 0.0         9      bad
chromium@502474                    6470315 +- 478607      6      bad
chromium@502478                    6470315 +- 478607      6      bad
chromium@502487                    6561792 +- 0.0         9      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=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.social.vk system_health.memory_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8967506351692657056


For feedback, file a bug with component Speed>Bisection

Settled on the same cl, looks super bi-modal though. There seemed to be a similar movement on a mac bot around the same range, so I can try Pinpoint for this.

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/14f17a84780000

📍 Pinpoint job completed.
https://pinpoint-dot-chromeperf.appspot.com/job/14f17a84780000

Found significant differences after 1 commit:

[heap] Turn on v8_enable_csa_write_barrier
By albertnetymk@google.com · Thu Sep 14 09:10:09 2017
v8@dbfdd4f9e9741df0a541afdd7516a34304102ee8

 Issue 770074  has been merged into this issue.

Another one bisecting to the write barrier. Ulan, can you have a look?  Issue 770074  suggests browsing regressions.

The memory "regression" is actually improvement.