监控系统建设思维导图
可观测
1. 监控系统
Prometheus + grafana + alert
搭建方法网上很多，忽略。
2. 日志系统
loki，官方文档之外，可以参考“云原生小白”写的一系列loki的文章。https://blog.csdn.net/weixin_49366475
3. 链路追踪（未实现）
Jaeger，eBPF(https://developer.aliyun.com/article/875115?utm_content=g_1000329007)
可感知
监控以及告警规则使用k8s-sidecar配置，注册config-map，agent和alert监控该config-map名进行reload操作。
k8s-sidecat项目地址：https://github.com/kiwigrid/k8s-sidecar
1. 告警规则
NODE告警
nodealertrules:
groups:
- name: node_monitor
rules:
- alert: node_status
expr: up == 0
for: 5m
labels:
ds: 32
severity: error
annotations:
summary: "{{$labels.instance}}:不可用"
description: "{{$labels.instance}}:状态为down超过5分钟"
- alert: cpu_critical
expr: 100-(avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(ks_ops_haique_tech_com_nodegroup,instance,job)* 100) > 80 and count(node_cpu_seconds_total{mode='system'}) by (ks_ops_haique_tech_com_nodegroup,instance,job) > 1
for: 10m
labels:
ds: 32
severity: critical
annotations:
summary: "{{$labels.instance}} cpu使用率过高！"
description: "{{$labels.instance }} cpu使用大于80%(目前使用:{{$value}}%),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: cpu_softirq
expr: avg(irate(node_cpu_seconds_total{mode="softirq"}[5m])) by(ks_ops_haique_tech_com_nodegroup,instance,job)* 100 >40 and count(node_cpu_seconds_total{mode='system'}) by (ks_ops_haique_tech_com_nodegroup,instance,job) > 1
for: 10m
labels:
ds: 32
severity: error
annotations:
summary: "{{$labels.instance}} cpu软中断si使用率过高！"
description: "{{$labels.instance }} cpu软中断si使用率大于40%(目前使用:{{$value}}%),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: cpu_load5
expr: avg(node_load5) by (ks_ops_haique_tech_com_nodegroup,instance,job) - count(node_cpu_seconds_total{mode='system'}) by (ks_ops_haique_tech_com_nodegroup,instance,job) *2 > 0 and count(node_cpu_seconds_total{mode='system'}) by (ks_ops_haique_tech_com_nodegroup,instance,job) > 1
for: 10m
labels:
ds: 32
severity: error
annotations:
summary: "{{$labels.instance}} cpu负载高！"
description: "{{$labels.instance }} cpu平均负载持续10分钟超过cpu核数2倍(目前超过:{{$value}}),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: HostOutOfMemory
expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
for: 3m
labels:
ds: 32
severity: error
annotations:
summary: "{{$labels.instance}} 内存使用率过高！"
description: "{{$labels.instance}} 内存剩余小于10%(目前剩余:{{$value}}%),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: HostOomKillDetected
expr: increase(node_vmstat_oom_kill[1m]) > 0
for: 0m
labels:
ds: 32
severity: error
annotations:
summary: "{{ $labels.instance }}出现OOM"
description: "{{ $labels.instance }}出现OOM，出现{{$value}}次,{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: IO
expr: irate(node_disk_io_time_seconds_total{device=~"vd.*"}[1m]) *100 > 40
for: 5m
labels:
ds: 32
severity: error
annotations:
summary: "{{$labels.instance}} 磁盘I/O耗时高！"
description: "{{$labels.instance }} 磁盘I/O操作耗时占比大于40%(目前使用:{{$value}}),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: mount_error
expr: (node_filesystem_size_bytes{fstype=~"ext.*|xfs"}-node_filesystem_free_bytes{fstype=~"ext.*|xfs"}) *100/(node_filesystem_avail_bytes {fstype=~"ext.*|xfs"}+(node_filesystem_size_bytes{fstype=~"ext.*|xfs"}-node_filesystem_free_bytes{fstype=~"ext.*|xfs"})) > 80
for: 1m
labels:
ds: 32
severity: error
annotations:
summary: "{{$labels.instance}} {{$labels.mountpoint}} 磁盘分区使用率过高！"
description: "{{$labels.instance}} {{$labels.mountpoint }} 磁盘分区使用大于80%(目前使用:{{$value}}%),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: mount_critical
expr: (node_filesystem_size_bytes{fstype=~"ext.*|xfs"}-node_filesystem_free_bytes{fstype=~"ext.*|xfs"}) *100/(node_filesystem_avail_bytes {fstype=~"ext.*|xfs"}+(node_filesystem_size_bytes{fstype=~"ext.*|xfs"}-node_filesystem_free_bytes{fstype=~"ext.*|xfs"})) > 95
for: 1m
labels:
ds: 32
severity: critical
annotations:
summary: "{{$labels.instance}} {{$labels.mountpoint}} 磁盘分区使用率过高！"
description: "{{$labels.instance}} {{$labels.mountpoint }} 磁盘分区使用大于95%(目前使用:{{$value}}%),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
- alert: HostConntrackLimit
expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
for: 5m
labels:
ds: 32
severity: error
annotations:
summary: "{{ $labels.instance }} 连接数接近limit值"
description: "{{ $labels.instance }} 连接跟踪的数量与limit的比值大于0.8(目前使用:{{$value}}),{{$labels.ks_ops_haique_tech_com_nodegroup}}"
POD告警
poDalertrules: groups: - name: pod_monitor rules: - alert: pod_cpu expr: sum(rate(container_cpu_usage_seconds_total{container !="",container!="POD"}[2m])) by (container, pod) / sum(kube_pod_container_resource_limits{resource="cpu",unit="core",container !="",container!="POD"} > 0) by (container, pod) * 100 > 80 for: 10m labels: ds: 32 severity: warning annotations: summary: "{{$labels.pod}}:cpu使用率高于80%" description: "{{$labels.pod}},{{$labels.container}},cpu使用率{{$value}}%" - alert: pod_mem expr: sum(container_memory_working_set_bytes{container !="",container!="POD"}) by (container, pod) / sum(container_spec_memory_limit_bytes{container !="",container!="POD"} > 0) by (container, pod) * 100 > 80 for: 10m labels: ds: 32 severity: warning annotations: summary: "{{$labels.pod}}:mem使用率高于80%" description: "{{$labels.pod}},{{$labels.container}},mem使用率{{$value}}%" - alert: pod_restartNum expr: increase(kube_pod_container_status_restarts_total{container!="POD"}[3h])> 3 for: 0m labels: ds: 32 severity: error annotations: summary: "{{$labels.pod}}:容器经常重启" description: "{{$labels.pod}},{{$labels.container}},重启近3小时重启次数大于3,共重启{{$value}}次"
可预测
可参考我另一篇文章。