All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=647613

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICg2ZG1uAoM


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

chromium-rel-win10

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/9001371874044908000

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. 

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


===== SUSPECTED CL(s) =====
Subject : scheduler: Don't throttle 0x0 frames
Author  : skyostil
Commit description:
  
This patch avoids throttling requestAnimationFrame and timers inside 0x0
frames. The reason is that some websites (e.g., GMail) use cross origin
0x0 frames to drive UI logic and throttling these frames causes
breakage. This change also makes us match Safari's behavior.

This patch also removes the test for throttling out-of-process iframes,
because it turns out the viewport intersection code is not able to
compute intersections across process boundaries. This capability will be
restored when IntersectionObserver gains support for out-of-process
iframes.

BUG= 644217 

Review-Url: https://codereview.chromium.org/2333653002
Cr-Commit-Position: refs/heads/master@{#418174}
Commit  : b83d755a52a7fe9792af9ee360e551c157ad576e
Date    : Tue Sep 13 05:18:45 2016


===== TESTED REVISIONS =====
Revision         Mean     Std Dev  N  Good?
chromium@418169  2422424  86131.4  5  good
chromium@418172  2452383  82325.5  5  good
chromium@418173  2375345  100373   5  good
chromium@418174  2901773  144822   5  bad    <--
chromium@418178  3025890  106569   5  bad
chromium@418187  2965971  129816   5  bad

Bisect job ran on: winx64_10_perf_bisect
Bug ID: 647613

Test Command: src/tools/perf/run_benchmark -v --browser=release_x64 --output-format=chartjson --upload-results --also-run-disabled-tests system_health.memory_desktop
Test Metric: memory:chrome:renderer_processes:reported_by_chrome:v8:heap:new_space:effective_size_avg/memory:chrome:renderer_processes:reported_by_chrome:v8:heap:new_space:effective_size_avg
Relative Change: 22.44%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/winx64_10_perf_bisect/builds/717
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9001371874044908000


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=5861248573374464

| 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!