安装cube-state-metrics组件，在master节点操作
cat > kube-state-metrics-deploy.yaml <<EOF apiVersion: apps/v1 kind: Deployment metadata: name: kube-state-metrics namespace: kube-system spec: replicas: 1 selector: matchLabels: app: kube-state-metrics template: metadata: labels: app: kube-state-metrics spec: serviceAccountName: kube-state-metrics containers: - name: kube-state-metrics # image: gcr.io/google_containers/kube-state-metrics-amd64:v1.3.1 image: quay.io/coreos/kube-state-metrics:v1.9.0 ports: - containerPort: 8080 EOF
创建service，在master节点操作
cat >kube-state-metrics-svc.yaml <<EOF apiVersion: v1 kind: Service metadata: annotations: prometheus.io/scrape: 'true' name: kube-state-metrics namespace: kube-system labels: app: kube-state-metrics spec: ports: - name: kube-state-metrics port: 8080 protocol: TCP selector: app: kube-state-metrics EOF在Grafana web界面导入kubernetes Cluster和kubernetes cluster monitoring
链接：https://pan.baidu.com/s/1QAMqT8scsXx-lzEPI6MPgA 提取码：i4yd 安装和配置Alertmanager-发送报警到qq邮箱在k8s的master节点创建alertmanager-cm.yaml文件
cat >alertmanager-cm.yaml <<EOF kind: ConfigMap apiVersion: v1 metadata: name: alertmanager namespace: monitor-sa data: alertmanager.yml: |- global: resolve_timeout: 1m smtp_smarthost: 'smtp.163.com:25' smtp_from: '15011572657@163.com' smtp_auth_username: '15011572657' smtp_auth_password: 'BDBPRMLNZGKWRFJP' smtp_require_tls: false route: group_by: [alertname] group_wait: 10s group_interval: 10s repeat_interval: 10m receiver: default-receiver receivers: - name: 'default-receiver' email_configs: - to: 'y1486170457@qq.com' send_resolved: true EOFAlertmanager配置文件解释说明:
smtp_smarthost: 'smtp.163.com:25' #用于发送邮件的邮箱的SMTP服务器地址+端口 smtp_from: '15011572657@163.com' #这是指定从哪个邮箱发送报警 smtp_auth_username: '15011572657' #这是发送邮箱的认证用户，不是邮箱名 smtp_auth_password: 'BDBPRMLNZGKWRFJP' #这是发送邮箱的授权码而不是登录密码 email_configs: - to: 'y1486170457@qq.com' #to后面指定发送到哪个邮箱，我发送到我的qq邮箱，大家需要写自己的邮箱地址，不应该跟smtp_from的邮箱名字重复在master节点重新生成prometheus-cfg.yaml文件
kind: ConfigMap apiVersion: v1 metadata: labels: app: prometheus name: prometheus-config namespace: monitor-sa data: prometheus.yml: | rule_files: - /etc/prometheus/rules.yml alerting: alertmanagers: - static_configs: - targets: ["localhost:9093"] global: scrape_interval: 15s scrape_timeout: 10s evaluation_interval: 1m scrape_configs: - job_name: 'kubernetes-node' kubernetes_sd_configs: - role: node relabel_configs: - source_labels: [__address__] regex: '(.*):10250' replacement: '${1}:9100' target_label: __address__ action: replace - action: labelmap regex: __meta_kubernetes_node_label_(.+) - job_name: 'kubernetes-node-cadvisor' kubernetes_sd_configs: - role: node scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) - target_label: __address__ replacement: kubernetes.default.svc:443 - source_labels: [__meta_kubernetes_node_name] regex: (.+) target_label: __metrics_path__ replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor - job_name: 'kubernetes-apiserver' kubernetes_sd_configs: - role: endpoints scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name] action: keep regex: default;kubernetes;https - job_name: 'kubernetes-service-endpoints' kubernetes_sd_configs: - role: endpoints relabel_configs: - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape] action: keep regex: true - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme] action: replace target_label: __scheme__ regex: (https?) - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] action: replace target_label: __metrics_path__ regex: (.+) - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] action: replace target_label: __address__ regex: ([^:]+)(?::\d+)?;(\d+) replacement: $1:$2 - action: labelmap regex: __meta_kubernetes_service_label_(.+) - source_labels: [__meta_kubernetes_namespace] action: replace target_label: kubernetes_namespace - source_labels: [__meta_kubernetes_service_name] action: replace target_label: kubernetes_name - job_name: kubernetes-pods kubernetes_sd_configs: - role: pod relabel_configs: - action: keep regex: true source_labels: - __meta_kubernetes_pod_annotation_prometheus_io_scrape - action: replace regex: (.+) source_labels: - __meta_kubernetes_pod_annotation_prometheus_io_path target_label: __metrics_path__ - action: replace regex: ([^:]+)(?::\d+)?;(\d+) replacement: $1:$2 source_labels: - __address__ - __meta_kubernetes_pod_annotation_prometheus_io_port target_label: __address__ - action: labelmap regex: __meta_kubernetes_pod_label_(.+) - action: replace source_labels: - __meta_kubernetes_namespace target_label: kubernetes_namespace - action: replace source_labels: - __meta_kubernetes_pod_name target_label: kubernetes_pod_name - job_name: 'kubernetes-schedule' scrape_interval: 5s static_configs: - targets: ['172.16.9.3:10251'] - job_name: 'kubernetes-controller-manager' scrape_interval: 5s static_configs: - targets: ['172.16.9.3:10252'] - job_name: 'kubernetes-kube-proxy' scrape_interval: 5s static_configs: - targets: ['172.16.9.3:10249','172.16.9.4:10249'] - job_name: 'kubernetes-etcd' scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key scrape_interval: 5s static_configs: - targets: ['172.16.9.3:2379'] rules.yml: | groups: - name: example rules: - alert: kube-proxy的cpu使用率大于80% expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%" - alert: kube-proxy的cpu使用率大于90% expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 90 for: 2s labels: severity: critical annotations: description: "{{$lables.instance}}的{{$labels.job}}组件的cpu使用率超过90%" - alert: scheduler的cpu使用率大于80% expr: rate(process_cpu_seconds_total{job=~"kubernetes-schedule"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%" - alert: scheduler的cpu使用率大于90% expr: rate(process_cpu_seconds_total{job=~"kubernetes-schedule"}[1m]) * 100 > 90 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%" - alert: controller-manager的cpu使用率大于80% expr: rate(process_cpu_seconds_total{job=~"kubernetes-controller-manager"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%" - alert: controller-manager的cpu使用率大于90% expr: rate(process_cpu_seconds_total{job=~"kubernetes-controller-manager"}[1m]) * 100 > 0 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%" - alert: apiserver的cpu使用率大于80% expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%" - alert: apiserver的cpu使用率大于90% expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 90 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%" - alert: etcd的cpu使用率大于80% expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%" - alert: etcd的cpu使用率大于90% expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 90 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%" - alert: kube-state-metrics的cpu使用率大于80% expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%" value: "{{ $value }}%" threshold: "80%" - alert: kube-state-metrics的cpu使用率大于90% expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 0 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%" value: "{{ $value }}%" threshold: "90%" - alert: coredns的cpu使用率大于80% expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 80 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%" value: "{{ $value }}%" threshold: "80%" - alert: coredns的cpu使用率大于90% expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 90 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%" value: "{{ $value }}%" threshold: "90%" - alert: kube-proxy打开句柄数>600 expr: process_open_fds{job=~"kubernetes-kube-proxy"} > 600 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600" value: "{{ $value }}" - alert: kube-proxy打开句柄数>1000 expr: process_open_fds{job=~"kubernetes-kube-proxy"} > 1000 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000" value: "{{ $value }}" - alert: kubernetes-schedule打开句柄数>600 expr: process_open_fds{job=~"kubernetes-schedule"} > 600 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600" value: "{{ $value }}" - alert: kubernetes-schedule打开句柄数>1000 expr: process_open_fds{job=~"kubernetes-schedule"} > 1000 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000" value: "{{ $value }}" - alert: kubernetes-controller-manager打开句柄数>600 expr: process_open_fds{job=~"kubernetes-controller-manager"} > 600 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600" value: "{{ $value }}" - alert: kubernetes-controller-manager打开句柄数>1000 expr: process_open_fds{job=~"kubernetes-controller-manager"} > 1000 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000" value: "{{ $value }}" - alert: kubernetes-apiserver打开句柄数>600 expr: process_open_fds{job=~"kubernetes-apiserver"} > 600 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600" value: "{{ $value }}" - alert: kubernetes-apiserver打开句柄数>1000 expr: process_open_fds{job=~"kubernetes-apiserver"} > 1000 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000" value: "{{ $value }}" - alert: kubernetes-etcd打开句柄数>600 expr: process_open_fds{job=~"kubernetes-etcd"} > 600 for: 2s labels: severity: warnning annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600" value: "{{ $value }}" - alert: kubernetes-etcd打开句柄数>1000 expr: process_open_fds{job=~"kubernetes-etcd"} > 1000 for: 2s labels: severity: critical annotations: description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000" value: "{{ $value }}" - alert: coredns expr: process_open_fds{k8s_app=~"kube-dns"} > 600 for: 2s labels: severity: warnning annotations: description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过600" value: "{{ $value }}" - alert: coredns expr: process_open_fds{k8s_app=~"kube-dns"} > 1000 for: 2s labels: severity: critical annotations: description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过1000" value: "{{ $value }}" - alert: kube-proxy expr: process_virtual_memory_bytes{job=~"kubernetes-kube-proxy"} > 2000000000 for: 2s labels: severity: warnning annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G" value: "{{ $value }}" - alert: scheduler expr: process_virtual_memory_bytes{job=~"kubernetes-schedule"} > 2000000000 for: 2s labels: severity: warnning annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G" value: "{{ $value }}" - alert: kubernetes-controller-manager expr: process_virtual_memory_bytes{job=~"kubernetes-controller-manager"} > 2000000000 for: 2s labels: severity: warnning annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G" value: "{{ $value }}" - alert: kubernetes-apiserver expr: process_virtual_memory_bytes{job=~"kubernetes-apiserver"} > 2000000000 for: 2s labels: severity: warnning annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G" value: "{{ $value }}" - alert: kubernetes-etcd expr: process_virtual_memory_bytes{job=~"kubernetes-etcd"} > 2000000000 for: 2s labels: severity: warnning annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G" value: "{{ $value }}" - alert: kube-dns expr: process_virtual_memory_bytes{k8s_app=~"kube-dns"} > 2000000000 for: 2s labels: severity: warnning annotations: description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 使用虚拟内存超过2G" value: "{{ $value }}" - alert: HttpRequestsAvg expr: sum(rate(rest_client_requests_total{job=~"kubernetes-kube-proxy|kubernetes-kubelet|kubernetes-schedule|kubernetes-control-manager|kubernetes-apiservers"}[1m])) > 1000 for: 2s labels: team: admin annotations: description: "组件{{$labels.job}}({{$labels.instance}}): TPS超过1000" value: "{{ $value }}" threshold: "1000" - alert: Pod_restarts expr: kube_pod_container_status_restarts_total{namespace=~"kube-system|default|monitor-sa"} > 0 for: 2s labels: severity: warnning annotations: description: "在{{$labels.namespace}}名称空间下发现{{$labels.pod}}这个pod下的容器{{$labels.container}}被重启,这个监控指标是由{{$labels.instance}}采集的" value: "{{ $value }}" threshold: "0" - alert: Pod_waiting expr: kube_pod_container_status_waiting_reason{namespace=~"kube-system|default"} == 1 for: 2s labels: team: admin annotations: description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}启动异常等待中" value: "{{ $value }}" threshold: "1" - alert: Pod_terminated expr: kube_pod_container_status_terminated_reason{namespace=~"kube-system|default|monitor-sa"} == 1 for: 2s labels: team: admin annotations: description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}被删除" value: "{{ $value }}" threshold: "1" - alert: Etcd_leader expr: etcd_server_has_leader{job="kubernetes-etcd"} == 0 for: 2s labels: team: admin annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 当前没有leader" value: "{{ $value }}" threshold: "0" - alert: Etcd_leader_changes expr: rate(etcd_server_leader_changes_seen_total{job="kubernetes-etcd"}[1m]) > 0 for: 2s labels: team: admin annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 当前leader已发生改变" value: "{{ $value }}" threshold: "0" - alert: Etcd_failed expr: rate(etcd_server_proposals_failed_total{job="kubernetes-etcd"}[1m]) > 0 for: 2s labels: team: admin annotations: description: "组件{{$labels.job}}({{$labels.instance}}): 服务失败" value: "{{ $value }}" threshold: "0" - alert: Etcd_db_total_size expr: etcd_debugging_mvcc_db_total_size_in_bytes{job="kubernetes-etcd"} > 10000000000 for: 2s labels: team: admin annotations: description: "组件{{$labels.job}}({{$labels.instance}})：db空间超过10G" value: "{{ $value }}" threshold: "10G" - alert: Endpoint_ready expr: kube_endpoint_address_not_ready{namespace=~"kube-system|default"} == 1 for: 2s labels: team: admin annotations: description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.endpoint}}不可用" value: "{{ $value }}" threshold: "1" - name: 物理节点状态-监控告警 rules: - alert: 物理节点cpu使用率 expr: 100-avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(instance)*100 > 90 for: 2s labels: severity: ccritical annotations: summary: "{{ $labels.instance }}cpu使用率过高" description: "{{ $labels.instance }}的cpu使用率超过90%,当前使用率[{{ $value }}],需要排查处理" - alert: 物理节点内存使用率 expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 > 90 for: 2s labels: severity: critical annotations: summary: "{{ $labels.instance }}内存使用率过高" description: "{{ $labels.instance }}的内存使用率超过90%,当前使用率[{{ $value }}],需要排查处理" - alert: InstanceDown expr: up == 0 for: 2s labels: severity: critical annotations: summary: "{{ $labels.instance }}: 服务器宕机" description: "{{ $labels.instance }}: 服务器延时超过2分钟" - alert: 物理节点磁盘的IO性能 expr: 100-(avg(irate(node_disk_io_time_seconds_total[1m])) by(instance)* 100) < 60 for: 2s labels: severity: critical annotations: summary: "{{$labels.mountpoint}} 流入磁盘IO使用率过高！" description: "{{$labels.mountpoint }} 流入磁盘IO大于60%(目前使用:{{$value}})" - alert: 入网流量带宽 expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400 for: 2s labels: severity: critical annotations: summary: "{{$labels.mountpoint}} 流入网络带宽过高！" description: "{{$labels.mountpoint }}流入网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}" - alert: 出网流量带宽 expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400 for: 2s labels: severity: critical annotations: summary: "{{$labels.mountpoint}} 流出网络带宽过高！" description: "{{$labels.mountpoint }}流出网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}" - alert: TCP会话 expr: node_netstat_Tcp_CurrEstab > 1000 for: 2s labels: severity: critical annotations: summary: "{{$labels.mountpoint}} TCP_ESTABLISHED过高！" description: "{{$labels.mountpoint }} TCP_ESTABLISHED大于1000%(目前使用:{{$value}}%)" - alert: 磁盘容量 expr: 100-(node_filesystem_free_bytes{fstype=~"ext4|xfs"}/node_filesystem_size_bytes {fstype=~"ext4|xfs"}*100) > 80 for: 2s labels: severity: critical annotations: summary: "{{$labels.mountpoint}} 磁盘分区使用率过高！" description: "{{$labels.mountpoint }} 磁盘分区使用大于80%(目前使用:{{$value}}%)"同样需要手动添加$的变量。