blob: be71b517e6358867939648addb01eb4858676653 (
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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
|
# you can disable an alarm notification by setting the 'to' line to: silent
# Controllers
template: storcli_controller_health_status
on: storcli.controller_health_status
class: Errors
type: System
component: RAID
lookup: average -1m unaligned percentage of healthy
units: %
every: 10s
crit: $this < 100
delay: down 5m multiplier 2 max 10m
summary: RAID controller ${label:controller_number} health
info: RAID controller ${label:controller_number} is unhealthy
to: sysadmin
template: storcli_controller_bbu_status
on: storcli.controller_bbu_status
class: Errors
type: System
component: RAID
lookup: average -1m unaligned percentage of healthy,na
units: %
every: 10s
crit: $this < 100
delay: down 5m multiplier 2 max 10m
summary: RAID controller ${label:controller_number} BBU health
info: RAID controller ${label:controller_number} BBU is unhealthy
to: sysadmin
# Physical Drives
template: storcli_phys_drive_errors
on: storcli.phys_drive_errors
class: Errors
type: System
component: RAID
lookup: sum -10s
units: errors
every: 10s
warn: $this > 0
delay: up 1m down 5m multiplier 2 max 10m
summary: RAID PD c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} errors
info: RAID physical drive c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} errors
to: sysadmin
template: storcli_phys_drive_predictive_failures
on: storcli.phys_drive_predictive_failures
class: Errors
type: System
component: RAID
lookup: sum -10s
units: failures
every: 10s
warn: $this > 0
delay: up 1m down 5m multiplier 2 max 10m
summary: RAID PD c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} predictive failures
info: RAID physical drive c${label:controller_number}/e${label:enclosure_number}/s${label:slot_number} predictive failures
to: sysadmin
|
