health_manager/config/health_manager.yml at master · cloudfoundry-attic/health_manager · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
---
# Local_route is the IP address of a well known server on your network, it
# is used to choose the right ip address (think of hosts that have multiple nics
# and IP addresses assigned to them) of the host running the Health Manager. Default
# value of nil, should work in most cases.
local_route: 127.0.0.1

# message bus URI, adjust as needed.
# Can be overriden with MBUS_URI env variable.
mbus: nats://nats:nats@127.0.0.1:4233/

logging:
  level: info

# pid: /var/vcap/sys/run/healthmanager2.pid

# set this to your dev instance api url
# the default for the bulk_api host is http://api.vcap.me
bulk_api:
  host: http://api.vcap.me

intervals:

  # how often the desired state is updated
  desired_state_update: 60

  # if the desired state has not been updated for this period,
  # the desired stated is deemed lost
  # (e.g., application has been removed from the ccdb)
  desired_state_lost:   180

  # when a database update is requested but one is in progress,
  # the new update is postponed this many seconds
  postpone_update:       30

  # droplet is assumed lost after that many seconds of missing heartbeats
  droplet_lost:         30

  # droplets enumerated and analyzed every droplet_analysis seconds
  droplets_analysis:    20

  # when number of recent instance crashes exceeds flapping_death,
  # the instance is declared flapping
  flapping_death:        1

  # crashes are deemed recent for the purposes of flapping
  # determination if they happened within this timeout
  flapping_timeout:     500

  # for flapping apps, this is starting value of exponentially increasing
  # delays before a restart attempt
  min_restart_delay:     60

  # for flapping apps, this is the maximum, capping value of the capped
  # exponentially increasing delays before a restart attempt
  max_restart_delay:     480

  # delay time is randomized with noise not exceeding this value
  delay_time_noise:       10

  # stop attempting to restart flapping apps after this number of crashes.
  # use negative value to never give up!
  giveup_crash_number:     4

  # a batch of start/stop requests is dequed every request_queue seconds
  request_queue:           1

  # start/stop requests are dequeued in batches of this size
  queue_batch_size:        40

  # period of inactivity after which a droplet is garbage-collected
  droplet_gc_grace_period: 240

  # how often should the gc loop for droplets run
  droplet_gc:              300

# Used for /healthz and /vars endpoints. If not provided random
# values will be generated on component start. Uncomment to use
# static values.
status:
  port: 54321
  user: thin
  password: thin