health: apply megacli alarms for all adapters/physical disks (#10834)
Ilya Mashchenko committed
Mar 23, 2021 at 10:44 UTC
6fe27ffe0109d0c9bbeddaa893715cb389fb4234
1 file changed
+31
-23
health/health.d/megacli.conf
+31
-23
@@ -1,12 +1,40 @@
1
+
2
+## Adapters (controllers)
3
+
4
template: megacli_adapter_state
5
on: megacli.adapter_degraded
3
- units: is degraded
4
- lookup: sum -10s
6
+ lookup: max -10s foreach *
7
+ units: boolean
8
every: 10s
9
crit: $this > 0
7
- info: adapter state
10
+ delay: down 5m multiplier 2 max 10m
11
+ info: adapter state is degraded
12
+ to: sysadmin
13
+
14
+## Physical Disks
15
+
16
+template: megacli_pd_predictive_failures
17
+ on: megacli.pd_predictive_failure
18
+ lookup: sum -10s foreach *
19
+ units: predictive failures
20
+ every: 10s
21
+ warn: $this > 0
22
+ delay: up 1m down 5m multiplier 2 max 10m
23
+ info: physical drive predictive failures
24
+ to: sysadmin
25
+
26
+template: megacli_pd_media_errors
27
+ on: megacli.pd_media_error
28
+ lookup: sum -10s foreach *
29
+ units: media errors
30
+ every: 10s
31
+ warn: $this > 0
32
+ delay: up 1m down 5m multiplier 2 max 10m
33
+ info: physical drive media errors
34
to: sysadmin
35
36
+## Battery Backup Units (BBU)
37
+
38
template: megacli_bbu_relative_charge
39
on: megacli.bbu_relative_charge
40
units: percent
@@ -26,23 +54,3 @@ template: megacli_bbu_cycle_count
54
crit: $this >= 500
55
info: BBU cycle count
56
to: sysadmin
29
-
30
-template: megacli_pd_media_errors
31
- on: megacli.pd_media_error
32
- units: media errors
33
- lookup: sum -10s
34
- every: 10s
35
- warn: $this > 0
36
- delay: down 1m multiplier 2 max 10m
37
- info: physical drive media errors
38
- to: sysadmin
39
-
40
-template: megacli_pd_predictive_failures
41
- on: megacli.pd_predictive_failure
42
- units: predictive failures
43
- lookup: sum -10s
44
- every: 10s
45
- warn: $this > 0
46
- delay: down 1m multiplier 2 max 10m
47
- info: physical drive predictive failures
48
- to: sysadmin