summaryrefslogtreecommitdiffstats
path: root/health/health.d/scaleio.conf
blob: 3c0dc1168f1a528acf0978c4c5e79834ccef77cf (plain)
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
# make sure scaleio is running

 template: scaleio_last_collected_secs
       on: scaleio.system_capacity_total
    class: Storage
component: ScaleIO
     type: Latency
     calc: $now - $last_collected_t
    units: seconds ago
    every: 10s
     warn: $this > (($status >= $WARNING)  ? ($update_every) : ( 5 * $update_every))
     crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
    delay: down 5m multiplier 1.5 max 1h
     info: number of seconds since the last successful data collection
       to: sysadmin

# make sure Storage Pool capacity utilization is under limit

 template: scaleio_storage_pool_capacity_utilization
       on: scaleio.storage_pool_capacity_utilization
    class: Storage
component: ScaleIO
     type: Utilization
     calc: $used
    units: %
    every: 10s
     warn: $this > (($status >= $WARNING)  ? (80) : (90))
     crit: $this > (($status == $CRITICAL) ? (90) : (98))
    delay: down 15m multiplier 1.5 max 1h
     info: storage pool capacity utilization
       to: sysadmin


# make sure Sdc is connected to MDM

 template: scaleio_sdc_mdm_connection_state
       on: scaleio.sdc_mdm_connection_state
    class: Storage
component: ScaleIO
     type: Utilization
     calc: $connected
    every: 10s
     warn: $this != 1
    delay: up 30s down 5m multiplier 1.5 max 1h
     info: Data Client (SDC) to Metadata Manager (MDM) connection state (0: disconnected, 1: connected)
       to: sysadmin