[root@prometheus ~]# vim /etc/prometheus/rules/ceph_exporter.yaml
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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
| groups:
- name: Ceph status
rules:
- alert: Ceph 实例不健康
expr: ceph_health_status != 0
for: 0m
labels:
severity: critical
annotations:
summary: Ceph 实例不健康{{ $labels.instance }})
description: "Ceph instance unhealthyn VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: 检测到Ceph监视器时钟偏差
expr: abs(ceph_monitor_clock_skew_seconds) > 0.2
for: 2m
labels:
severity: warning
annotations:
summary: Ceph monitor clock skew (instance {{ $labels.instance }})
description: "Ceph monitor clock skew detected. Please check ntp and hardware clock settingsn VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: Ceph监视器存储空间不足
expr: ceph_monitor_avail_percent < 10
for: 2m
labels:
severity: warning
annotations:
summary: Ceph monitor low space (instance {{ $labels.instance }})
description: "Ceph monitor storage is low.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: Ceph对象存储守护进程关闭
expr: ceph_osd_up == 0
for: 0m
labels:
severity: critical
annotations:
summary: Ceph OSD Down (instance {{ $labels.instance }})
description: "Ceph Object Storage Daemon Downn VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: Ceph高OSD延迟
expr: ceph_osd_perf_apply_latency_seconds > 5
for: 1m
labels:
severity: warning
annotations:
summary: Ceph high OSD latency (instance {{ $labels.instance }})
description: "Ceph Object Storage Daemon latency is high. Please check if it doesn't stuck in weird state.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: CephOSD空间不足
expr: ceph_osd_utilization > 90
for: 2m
labels:
severity: warning
annotations:
summary: Ceph OSD low space (instance {{ $labels.instance }})
description: "Ceph Object Storage Daemon is going out of space. Please add more disks.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: CephOSD重新加权
expr: ceph_osd_weight < 1
for: 2m
labels:
severity: warning
annotations:
summary: Ceph OSD reweighted (instance {{ $labels.instance }})
description: "Ceph Object Storage Daemon takes too much time to resize.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: CephPG下降
expr: ceph_pg_down > 0
for: 0m
labels:
severity: critical
annotations:
summary: Ceph PG down (instance {{ $labels.instance }})
description: "Some Ceph placement groups are down. Please ensure that all the data are available.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: CephPG不完整
expr: ceph_pg_incomplete > 0
for: 0m
labels:
severity: critical
annotations:
summary: Ceph PG incomplete (instance {{ $labels.instance }})
description: "Some Ceph placement groups are incomplete. Please ensure that all the data are available.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: CephPG不一致
expr: ceph_pg_inconsistent > 0
for: 0m
labels:
severity: warning
annotations:
summary: Ceph PG inconsistent (instance {{ $labels.instance }})
description: "Some Ceph placement groups are inconsistent. Data is available but inconsistent across nodes.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: CephPG激活时间长
expr: ceph_pg_activating > 0
for: 2m
labels:
severity: warning
annotations:
summary: Ceph PG activation long (instance {{ $labels.instance }})
description: "Some Ceph placement groups are too long to activate.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: Ceph PG回填已满
expr: ceph_pg_backfill_toofull > 0
for: 2m
labels:
severity: warning
annotations:
summary: Ceph PG backfill full (instance {{ $labels.instance }})
description: "Some Ceph placement groups are located on full Object Storage Daemon on cluster. Those PGs can be unavailable shortly. Please check OSDs, change weight or reconfigure CRUSH rules.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
- alert: Ceph PG不可用
expr: ceph_pg_total - ceph_pg_active > 0
for: 0m
labels:
severity: critical
annotations:
summary: Ceph PG unavailable (instance {{ $labels.instance }})
description: "Some Ceph placement groups are unavailable.n VALUE = {{ $value }}n LABELS = {{ $labels }}"
|
