master
conf 61 lines 1.96 KB
Raw
1 # you can disable an alarm notification by setting the 'to' line to: silent
2
3 # Controllers
4
5 template: storcli_controller_health_status
6 on: storcli.controller_health_status
7 class: Errors
8 type: System
9 component: RAID
10 lookup: average -1m unaligned percentage of healthy
11 units: %
12 every: 10s
13 crit: $this < 100
14 delay: down 5m multiplier 2 max 10m
15 summary: RAID controller ${label:controller_number} health
16 info: RAID controller ${label:controller_number} is unhealthy
17 to: sysadmin
18
19 template: storcli_controller_bbu_status
20 on: storcli.controller_bbu_status
21 class: Errors
22 type: System
23 component: RAID
24 lookup: average -1m unaligned percentage of healthy,na
25 units: %
26 every: 10s
27 crit: $this < 100
28 delay: down 5m multiplier 2 max 10m
29 summary: RAID controller ${label:controller_number} BBU health
30 info: RAID controller ${label:controller_number} BBU is unhealthy
31 to: sysadmin
32
33 # Physical Drives
34
35 template: storcli_phys_drive_errors
36 on: storcli.phys_drive_errors
37 class: Errors
38 type: System
39 component: RAID
40 lookup: sum -10s
41 units: errors
42 every: 10s
43 warn: $this > 0
44 delay: up 1m down 5m multiplier 2 max 10m
45 summary: RAID PD c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} errors
46 info: RAID physical drive c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} errors
47 to: sysadmin
48
49 template: storcli_phys_drive_predictive_failures
50 on: storcli.phys_drive_predictive_failures
51 class: Errors
52 type: System
53 component: RAID
54 lookup: sum -10s
55 units: failures
56 every: 10s
57 warn: $this > 0
58 delay: up 1m down 5m multiplier 2 max 10m
59 summary: RAID PD c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} predictive failures
60 info: RAID physical drive c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} predictive failures
61 to: sysadmin