273 lines
8.0 KiB
YAML
273 lines
8.0 KiB
YAML
apiVersion: 1
|
|
|
|
groups:
|
|
- orgId: 1
|
|
name: ppanel-core
|
|
folder: PPanel
|
|
interval: 1m
|
|
rules:
|
|
- uid: ppanel-target-down
|
|
title: PPanel monitoring target down
|
|
condition: C
|
|
for: 2m
|
|
noDataState: Alerting
|
|
execErrState: Error
|
|
annotations:
|
|
summary: "Monitoring target is down"
|
|
description: "{{ $labels.job }} on {{ $labels.instance }} has been down for more than 2 minutes."
|
|
labels:
|
|
severity: critical
|
|
service: ppanel
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange:
|
|
from: 300
|
|
to: 0
|
|
datasourceUid: prometheus
|
|
model:
|
|
datasource:
|
|
type: prometheus
|
|
uid: prometheus
|
|
editorMode: code
|
|
expr: 'up{job=~"grafana|prometheus|node-exporter|cadvisor|nginx-exporter|loki|tempo"}'
|
|
instant: true
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: A
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator:
|
|
params:
|
|
- 1
|
|
type: lt
|
|
operator:
|
|
type: and
|
|
query:
|
|
params:
|
|
- A
|
|
reducer:
|
|
type: last
|
|
type: query
|
|
datasource:
|
|
type: __expr__
|
|
uid: __expr__
|
|
expression: A
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: C
|
|
type: threshold
|
|
|
|
- uid: ppanel-host-disk-high
|
|
title: PPanel host disk usage high
|
|
condition: C
|
|
for: 10m
|
|
noDataState: NoData
|
|
execErrState: Error
|
|
annotations:
|
|
summary: "Host disk usage is high"
|
|
description: "{{ $labels.instance }} {{ $labels.mountpoint }} disk usage is above 85% for 10 minutes."
|
|
labels:
|
|
severity: warning
|
|
service: ppanel
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange:
|
|
from: 900
|
|
to: 0
|
|
datasourceUid: prometheus
|
|
model:
|
|
datasource:
|
|
type: prometheus
|
|
uid: prometheus
|
|
editorMode: code
|
|
expr: '100 - (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay|squashfs|aufs",mountpoint!~"/run.*|/var/lib/docker.*"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay|squashfs|aufs",mountpoint!~"/run.*|/var/lib/docker.*"} * 100)'
|
|
instant: true
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: A
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator:
|
|
params:
|
|
- 85
|
|
type: gt
|
|
operator:
|
|
type: and
|
|
query:
|
|
params:
|
|
- A
|
|
reducer:
|
|
type: last
|
|
type: query
|
|
datasource:
|
|
type: __expr__
|
|
uid: __expr__
|
|
expression: A
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: C
|
|
type: threshold
|
|
|
|
- uid: ppanel-host-memory-high
|
|
title: PPanel host memory usage high
|
|
condition: C
|
|
for: 10m
|
|
noDataState: NoData
|
|
execErrState: Error
|
|
annotations:
|
|
summary: "Host memory usage is high"
|
|
description: "{{ $labels.instance }} memory usage is above 90% for 10 minutes."
|
|
labels:
|
|
severity: warning
|
|
service: ppanel
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange:
|
|
from: 900
|
|
to: 0
|
|
datasourceUid: prometheus
|
|
model:
|
|
datasource:
|
|
type: prometheus
|
|
uid: prometheus
|
|
editorMode: code
|
|
expr: '(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100'
|
|
instant: true
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: A
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator:
|
|
params:
|
|
- 90
|
|
type: gt
|
|
operator:
|
|
type: and
|
|
query:
|
|
params:
|
|
- A
|
|
reducer:
|
|
type: last
|
|
type: query
|
|
datasource:
|
|
type: __expr__
|
|
uid: __expr__
|
|
expression: A
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: C
|
|
type: threshold
|
|
|
|
- uid: ppanel-host-cpu-high
|
|
title: PPanel host CPU usage high
|
|
condition: C
|
|
for: 10m
|
|
noDataState: NoData
|
|
execErrState: Error
|
|
annotations:
|
|
summary: "Host CPU usage is high"
|
|
description: "{{ $labels.instance }} CPU usage is above 90% for 10 minutes."
|
|
labels:
|
|
severity: warning
|
|
service: ppanel
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange:
|
|
from: 900
|
|
to: 0
|
|
datasourceUid: prometheus
|
|
model:
|
|
datasource:
|
|
type: prometheus
|
|
uid: prometheus
|
|
editorMode: code
|
|
expr: '100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)'
|
|
instant: true
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: A
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator:
|
|
params:
|
|
- 90
|
|
type: gt
|
|
operator:
|
|
type: and
|
|
query:
|
|
params:
|
|
- A
|
|
reducer:
|
|
type: last
|
|
type: query
|
|
datasource:
|
|
type: __expr__
|
|
uid: __expr__
|
|
expression: A
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: C
|
|
type: threshold
|
|
|
|
- uid: ppanel-container-restarts
|
|
title: PPanel container restarted
|
|
condition: C
|
|
for: 1m
|
|
noDataState: NoData
|
|
execErrState: Error
|
|
annotations:
|
|
summary: "Container restarted"
|
|
description: "{{ $labels.name }} restarted or changed start time in the last hour."
|
|
labels:
|
|
severity: warning
|
|
service: ppanel
|
|
data:
|
|
- refId: A
|
|
relativeTimeRange:
|
|
from: 3600
|
|
to: 0
|
|
datasourceUid: prometheus
|
|
model:
|
|
datasource:
|
|
type: prometheus
|
|
uid: prometheus
|
|
editorMode: code
|
|
expr: 'sum by (name) (changes(container_start_time_seconds{name!=""}[1h]))'
|
|
instant: true
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: A
|
|
- refId: C
|
|
datasourceUid: __expr__
|
|
model:
|
|
conditions:
|
|
- evaluator:
|
|
params:
|
|
- 0
|
|
type: gt
|
|
operator:
|
|
type: and
|
|
query:
|
|
params:
|
|
- A
|
|
reducer:
|
|
type: last
|
|
type: query
|
|
datasource:
|
|
type: __expr__
|
|
uid: __expr__
|
|
expression: A
|
|
intervalMs: 1000
|
|
maxDataPoints: 43200
|
|
refId: C
|
|
type: threshold
|