blob: ca8df31b92d8e8de35e1d31b09986c9953d4e83b (
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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
|
# Common
template: hdfs_capacity_usage
on: hdfs.capacity
class: Utilization
type: Storage
component: HDFS
calc: ($used) * 100 / ($used + $remaining)
units: %
every: 10s
warn: $this > (($status >= $WARNING) ? (70) : (80))
crit: $this > (($status == $CRITICAL) ? (80) : (98))
delay: down 15m multiplier 1.5 max 1h
info: summary datanodes space capacity utilization
to: sysadmin
# NameNode
template: hdfs_missing_blocks
on: hdfs.blocks
class: Errors
type: Storage
component: HDFS
calc: $missing
units: missing blocks
every: 10s
warn: $this > 0
delay: down 15m multiplier 1.5 max 1h
info: number of missing blocks
to: sysadmin
template: hdfs_stale_nodes
on: hdfs.data_nodes
class: Errors
type: Storage
component: HDFS
calc: $stale
units: dead nodes
every: 10s
warn: $this > 0
delay: down 15m multiplier 1.5 max 1h
info: number of datanodes marked stale due to delayed heartbeat
to: sysadmin
template: hdfs_dead_nodes
on: hdfs.data_nodes
class: Errors
type: Storage
component: HDFS
calc: $dead
units: dead nodes
every: 10s
crit: $this > 0
delay: down 15m multiplier 1.5 max 1h
info: number of datanodes which are currently dead
to: sysadmin
# DataNode
template: hdfs_num_failed_volumes
on: hdfs.num_failed_volumes
class: Errors
type: Storage
component: HDFS
calc: $fsds_num_failed_volumes
units: failed volumes
every: 10s
warn: $this > 0
delay: down 15m multiplier 1.5 max 1h
info: number of failed volumes
to: sysadmin
|
