All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=755089

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=c9d7150ef2e189e1e88634062c8f85cbcd7ef4fe22288abe6a4ffc3cd0533946


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

chromium-rel-mac-retina
chromium-rel-mac11
chromium-rel-mac11-pro
chromium-rel-win7-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8971299435397475136

=== BISECT JOB RESULTS ===
NO Perf regression found

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_search/load_search_yandex

Revision             Result                 N
chromium@493349      8010606 +- 840731      21      good
chromium@493423      8085504 +- 0.0         21      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.search.yandex 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/8971299435397475136


For feedback, file a bug with component Speed>Bisection

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8971291206841821856

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

Hi ulan@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 : Ulan Degenbaev
  Commit : d09f9c424fbc0c5679fd7c370c70c8915b29d987
  Date   : Thu Aug 10 08:56:49 2017
  Subject: [runtime] Do not clear prototype map descriptors.

Bisect Details
  Configuration: mac_pro_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:renderer_processes:reported_by_chrome:v8:heap:effective_size_avg/load_search/load_search_baidu
  Change       : 1.91% | 6075826.66667 -> 6192022.66667

Revision                           Result                  N
chromium@493276                    6075827 +- 29344.9      6      good
chromium@493324                    6069145 +- 20462.8      6      good
chromium@493348                    6078205 +- 42215.7      6      good
chromium@493360                    6072465 +- 25669.4      6      good
chromium@493366                    6081095 +- 12317.2      6      good
chromium@493369                    6070752 +- 31107.8      6      good
chromium@493370                    6066185 +- 23187.1      6      good
chromium@493370,v8@80423e89b1      6070900 +- 24148.7      6      good
chromium@493370,v8@d09f9c424f      6186269 +- 108510       6      bad       <--
chromium@493371                    6192023 +- 65220.0      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=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.search.baidu 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/8971291206841821856


For feedback, file a bug with component Speed>Bisection

The CL may extend the lifetime of a descriptor array by couple of GC cycles. The descriptor array will be reclaimed eventually, so this regression is due to GC timing.

 Issue 755086  has been merged into this issue.

 Issue 755090  has been merged into this issue.

 Issue 755650  has been merged into this issue.

 Issue 755082  has been merged into this issue.

 Issue 733502  has been merged into this issue.