dashboard
This commit is contained in:
@ -2,6 +2,57 @@ groups:
|
||||
- name: example
|
||||
rules:
|
||||
|
||||
- name: targets
|
||||
rules:
|
||||
- alert: monitor_service_down
|
||||
expr: up == 0
|
||||
for: 30s
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Monitor service non-operational"
|
||||
description: "Service {{ $labels.instance }} is down."
|
||||
|
||||
- name: host
|
||||
rules:
|
||||
- alert: high_cpu_load
|
||||
expr: node_load1 > 1.5
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Server under high load"
|
||||
description: "Docker host is under high load, the avg load 1m is at {{ $value}}. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
|
||||
|
||||
- alert: high_memory_load
|
||||
expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 85
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Server memory is almost full"
|
||||
description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
|
||||
|
||||
- alert: high_storage_load
|
||||
expr: (node_filesystem_size_bytes{fstype="aufs"} - node_filesystem_free_bytes{fstype="aufs"}) / node_filesystem_size_bytes{fstype="aufs"} * 100 > 85
|
||||
for: 30s
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Server storage is almost full"
|
||||
description: "Docker host storage usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."
|
||||
|
||||
- name: containers
|
||||
rules:
|
||||
- alert: jenkins_down
|
||||
expr: absent(container_memory_usage_bytes{name="jenkins"})
|
||||
for: 30s
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Jenkins down"
|
||||
description: "Jenkins container is down for more than 30 seconds."
|
||||
|
||||
# Alert for any instance that is unreachable for >2 minutes.
|
||||
- alert: service_down
|
||||
expr: up == 0
|
||||
|
Reference in New Issue
Block a user