repos / ops

infra for pico services
git clone https://github.com/picosh/ops.git

ops / monitoring / grafana / config / provisioning / alerting
Antonio Mika · 06 Nov 23

default.yml

 1apiVersion: 1
 2
 3groups:
 4  - orgId: 1
 5    name: General
 6    folder: Default
 7    interval: 1m
 8    rules:
 9      - uid: bbdb1e61-93c0-4ad1-a100-84059e9e322a
10        title: Targets Not Up
11        condition: C
12        data:
13          - refId: A
14            relativeTimeRange:
15              from: 600
16              to: 0
17            datasourceUid: PBFA97CFB590B2093
18            model:
19              editorMode: code
20              expr: up == 0
21              instant: true
22              intervalMs: 1000
23              legendFormat: __auto
24              maxDataPoints: 43200
25              range: false
26              refId: A
27          - refId: B
28            relativeTimeRange:
29              from: 600
30              to: 0
31            datasourceUid: __expr__
32            model:
33              conditions:
34                - evaluator:
35                    params: []
36                    type: gt
37                  operator:
38                    type: and
39                  query:
40                    params:
41                      - B
42                  reducer:
43                    params: []
44                    type: last
45                  type: query
46              datasource:
47                type: __expr__
48                uid: __expr__
49              expression: A
50              intervalMs: 1000
51              maxDataPoints: 43200
52              reducer: last
53              refId: B
54              type: reduce
55          - refId: C
56            relativeTimeRange:
57              from: 600
58              to: 0
59            datasourceUid: __expr__
60            model:
61              conditions:
62                - evaluator:
63                    params:
64                      - 1
65                    type: lt
66                  operator:
67                    type: and
68                  query:
69                    params:
70                      - C
71                  reducer:
72                    params: []
73                    type: last
74                  type: query
75              datasource:
76                type: __expr__
77                uid: __expr__
78              expression: B
79              intervalMs: 1000
80              maxDataPoints: 43200
81              refId: C
82              type: threshold
83        noDataState: OK
84        execErrState: Error
85        for: 1m
86        annotations:
87          description: 'Target {{ $labels.instance }} for job {{ $labels.job }} is down'
88          summary: 'Target {{ $labels.instance }} for job {{ $labels.job }} is down'
89        isPaused: false