All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=631116

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg2vHzpgoM


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

chromium-rel-win8-dual

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9006145097835298576

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@406935  4182388  331850   12  good
chromium@406986  3997296  224383   8   bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 631116

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:dom_storage:effective_size_avg/browse_social_twitter
Relative Change: 6.06%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2052
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9006145097835298576


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5574419922026496

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9005154518166606560

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@406935  4025269  250737   12  good
chromium@407009  3909472  30600.1  8   bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 631116

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:dom_storage:effective_size_avg/browse_social_twitter
Relative Change: 3.17%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2096
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9005154518166606560


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5779140804870144

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004899886869831776

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@406935  4397885  290167   12  good
chromium@407072  4527627  18515.7  8   bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 631116

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:dom_storage:effective_size_avg/browse_social_twitter
Relative Change: 4.92%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2104
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004899886869831776


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5907862585344000

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004799185185314544

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@406806  4441154  249008   12  good
chromium@406986  4469488  224065   8   bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 631116

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:dom_storage:effective_size_avg/browse_social_twitter
Relative Change: 3.05%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2109
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004799185185314544


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6339968641794048

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004716003230107456

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@406806  4501829  182248   12  good
chromium@407114  4525499  13973.7  8   bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 631116

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:dom_storage:effective_size_avg/browse_social_twitter
Relative Change: 2.33%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2112
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004716003230107456


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=6450164819034112

| 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!

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9004630729766476864

===== BISECT JOB RESULTS =====
Status: completed


=== Bisection aborted ===
The bisect was aborted because The metric values for the initial "good" and "bad" revisions do not represent a clear regression.
Please contact the the team (see below) if you believe this is in error.

=== Warnings ===
The following warnings were raised by the bisect job:

 * Bisect failed to reproduce the regression with enough confidence.

===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N   Good?
chromium@406806  4290693  328426   12  good
chromium@407114  4521888  10821.5  8   bad

Bisect job ran on: win_8_perf_bisect
Bug ID: 631116

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: browse_social-memory:chrome:all_processes:reported_by_chrome:dom_storage:effective_size_avg/browse_social_twitter
Relative Change: 2.21%
Score: 0

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/win_8_perf_bisect/builds/2113
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9004630729766476864


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5832703811780608

| 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!

Temporarily declaring bankruptcy on the *desktop* system health benchmark.
The number of alerts became unmanageable and the overall process needs to be improved to make it sustainable.
The alerts have been turned off and I'm archiving the outstanding regressions.
Note: this is just about desktop, the mobile system health stays up.