Prometheus之Alertmanager主机报警配置


groups:
- name: Host
 rules:
 - alert: HostMemory Usage
   expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 >  90
   for: 1m
   labels:
     name: Memory
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: "宿主机内存使用率超过90%."
     value: "{{ $value }}"
 - alert: HostCPU Usage
   expr: sum(avg without (cpu)(irate(node_cpu_seconds_total{mode!='idle'}[5m]))) by (instance,appname) > 0.8
   for: 1m
   labels:
     name: CPU
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: "宿主机CPU使用率超过80%."
     value: "{{ $value }}"
 - alert: HostLoad
   expr: node_load5 > 20
   for: 1m
   labels:
     name: Load
     severity: Warning
   annotations:
     summary: "{{ $labels.appname }} "
     description: " 主机负载5分钟超过20."
     value: "{{ $value }}"
 - alert: HostFilesystem Usage
   expr: (node_filesystem_size_bytes-node_filesystem_free_bytes)/node_filesystem_size_bytes*100>80
   for: 1m
   labels:
     name: Disk
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: " 宿主机 [ {{ $labels.mountpoint }} ]分区使用超过80%."
     value: "{{ $value }}%"
 - alert: HostDiskio writes
   expr: irate(node_disk_writes_completed_total{job=~"Host"}[1m]) > 10
   for: 1m
   labels:
     name: Diskio
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: " 宿主机 [{{ $labels.device }}]磁盘1分钟平均写入IO负载较高."
     value: "{{ $value }}iops"
 - alert: HostDiskio reads
   expr: irate(node_disk_reads_completed_total{job=~"Host"}[1m]) > 10
   for: 1m
   labels:
     name: Diskio
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: " 宿机 [{{ $labels.device }}]磁盘1分钟平均读取IO负载较高."
     value: "{{ $value }}iops"
 - alert: HostNetwork_receive
   expr: irate(node_network_receive_bytes_total{device!~"lo|bond[0-9]|cbr[0-9]|veth.*|virbr.*|ovs-system"}[5m]) / 1048576  > 10
   for: 1m
   labels:
     name: Network_receive
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: " 宿主机 [{{ $labels.device }}] 网卡5分钟平均接收流量超过10Mbps."
     value: "{{ $value }}3Mbps"
 - alert: hostNetwork_transmit
   expr: irate(node_network_transmit_bytes_total{device!~"lo|bond[0-9]|cbr[0-9]|veth.*|virbr.*|ovs-system"}[5m]) / 1048576  > 10
   for: 1m
   labels:
     name: Network_transmit
     severity: Warning
   annotations:
     summary: " {{ $labels.appname }} "
     description: " 宿主机 [{{ $labels.device }}] 网卡5分钟内平均发送流量超过10Mbps."
     value: "{{ $value }}3Mbps"