摘要：
1.Alertmanager报警插件部署[root@VM_0_48_centosprometheus]#catalertmanager pvc.yamlapi版本：v1kind:PersistentVolumeClaimmetadata：name:alertmanagernamespace:kube systemlabels:kubernetes.io/cluster服务：“
1、alertmanager告警插件部署
[root@VM_0_48_centos prometheus]# cat alertmanager-pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: alertmanager
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: EnsureExists
spec:
storageClassName: managed-nfs-storage #必须动态PV，需要改为自己的名字
accessModes:
- ReadWriteOnce
resources:
requests:
[root@VM_0_48_centos prometheus]# cat alertmanager-deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: alertmanager
namespace: kube-system
labels:
k8s-app: alertmanager
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v0.14.0
spec:
replicas: 1
selector:
matchLabels:
k8s-app: alertmanager
version: v0.14.0
template:
metadata:
labels:
k8s-app: alertmanager
version: v0.14.0
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
spec:
priorityClassName: system-cluster-critical
containers:
- name: prometheus-alertmanager
image: "prom/alertmanager:v0.14.0"
imagePullPolicy: "IfNotPresent"
args:
- --config.file=/etc/config/alertmanager.yml
- --storage.path=/data
- --web.external-url=/
ports:
- containerPort: 9093
readinessProbe:
httpGet:
path: /#/status
port: 9093
initialDelaySeconds: 30
timeoutSeconds: 30
volumeMounts:
- name: config-volume
mountPath: /etc/config
- name: storage-volume
mountPath: "/data"
subPath: ""
resources:
limits:
cpu: 10m
memory: 50Mi
requests:
cpu: 10m
memory: 50Mi
- name: prometheus-alertmanager-configmap-reload
image: "jimmidyson/configmap-reload:v0.1"
imagePullPolicy: "IfNotPresent"
args:
- --volume-dir=/etc/config
- --webhook-url=http://localhost:9093/-/reload
volumeMounts:
- name: config-volume
mountPath: /etc/config
readOnly: true
resources:
limits:
cpu: 10m
memory: 10Mi
requests:
cpu: 10m
memory: 10Mi
volumes:
- name: config-volume
configMap:
name: alertmanager-config
- name: storage-volume
persistentVolumeClaim:
claimName: alertmanager
[root@VM_0_48_centos prometheus]# cat alertmanager-service.yaml
apiVersion: v1
kind: Service
metadata:
name: alertmanager
namespace: kube-system
labels:
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
kubernetes.io/name: "Alertmanager"
spec:
ports:
- name: http
port: 80
protocol: TCP
targetPort: 9093
selector:
k8s-app: alertmanager
type: "ClusterIP"
2、prometheus 查看服务是否正常
查看alertmanager服务是否正常 [root@VM_0_48_centos prometheus]# kubectl get svc -n kube-system NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE alertmanager ClusterIP 10.0.0.176 <none> 80/TCP 46h
3、 prometheus 配置告警规则和调用altermanager
[root@VM_0_48_centos prometheus]# cat prometheus-configmap.yaml # Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/ apiVersion: v1 kind: ConfigMap metadata: name: prometheus-config namespace: kube-system labels: kubernetes.io/cluster-service: "true" addonmanager.kubernetes.io/mode: EnsureExists data: prometheus.yml: | scrape_configs: - job_name: prometheus static_configs: - targets: - localhost:9090 - job_name: kubernetes-apiservers kubernetes_sd_configs: - role: endpoints relabel_configs: - action: keep regex: default;kubernetes;https source_labels: - __meta_kubernetes_namespace - __meta_kubernetes_service_name - __meta_kubernetes_endpoint_port_name scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token - job_name: kubernetes-nodes-kubelet kubernetes_sd_configs: - role: node relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token - job_name: kubernetes-nodes-cadvisor kubernetes_sd_configs: - role: node relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) - target_label: __metrics_path__ replacement: /metrics/cadvisor scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token - job_name: kubernetes-service-endpoints kubernetes_sd_configs: - role: endpoints relabel_configs: - action: keep regex: true source_labels: - __meta_kubernetes_service_annotation_prometheus_io_scrape - action: replace regex: (https?) source_labels: - __meta_kubernetes_service_annotation_prometheus_io_scheme target_label: __scheme__ - action: replace regex: (.+) source_labels: - __meta_kubernetes_service_annotation_prometheus_io_path target_label: __metrics_path__ - action: replace regex: ([^:]+)(?::d+)?;(d+) replacement: $1:$2 source_labels: - __address__ - __meta_kubernetes_service_annotation_prometheus_io_port target_label: __address__ - action: labelmap regex: __meta_kubernetes_service_label_(.+) - action: replace source_labels: - __meta_kubernetes_namespace target_label: kubernetes_namespace - action: replace source_labels: - __meta_kubernetes_service_name target_label: kubernetes_name - job_name: kubernetes-services kubernetes_sd_configs: - role: service metrics_path: /probe params: module: - http_2xx relabel_configs: - action: keep regex: true source_labels: - __meta_kubernetes_service_annotation_prometheus_io_probe - source_labels: - __address__ target_label: __param_target - replacement: blackbox target_label: __address__ - source_labels: - __param_target target_label: instance - action: labelmap regex: __meta_kubernetes_service_label_(.+) - source_labels: - __meta_kubernetes_namespace target_label: kubernetes_namespace - source_labels: - __meta_kubernetes_service_name 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 alerting: alertmanagers: - static_configs: - targets: ["alertmanager:80"] ####需要修改alertmanger服务名字，集群内部通过服务名调用
4、配置告警规则-创建告警规则的configmap
[root@VM_0_48_centos prometheus]# cat prometheus-rules.yaml # Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/ apiVersion: v1 kind: ConfigMap metadata: name: prometheus-rules-config namespace: kube-system labels: kubernetes.io/cluster-service: "true" addonmanager.kubernetes.io/mode: EnsureExists data: rules.yml: | groups: - name: node rules: - alert: memory_use expr: 100-(node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes)/node_memory_MemTotal_bytes*100 >= 90 for: 10s annotations: summary: "机器 {{ $labels.instance }} 内存使用的率超过90%" expr: 100-(node_memory_MemFree_bytes+node_memory_Cached_bytes+node_memory_Buffers_bytes)/node_memory_MemTotal_bytes*100 >= 80 for: 10s annotations: summary: "机器 {{ $labels.instance }} 内存使用的率超过80%"
5、配置告警规则-将告警规则挂载到promethues中
[root@VM_0_48_centos prometheus]# cat prometheus-statefulset.yaml
apiVersion: apps/v1
kind: StatefulSet
metadata:
name: prometheus
namespace: kube-system
labels:
k8s-app: prometheus
kubernetes.io/cluster-service: "true"
addonmanager.kubernetes.io/mode: Reconcile
version: v2.2.1
spec:
serviceName: "prometheus"
replicas: 1
podManagementPolicy: "Parallel"
updateStrategy:
type: "RollingUpdate"
selector:
matchLabels:
k8s-app: prometheus
template:
metadata:
labels:
k8s-app: prometheus
annotations:
scheduler.alpha.kubernetes.io/critical-pod: ''
spec:
priorityClassName: system-cluster-critical
serviceAccountName: prometheus
initContainers:
- name: "init-chown-data"
image: "busybox:latest"
imagePullPolicy: "IfNotPresent"
command: ["chown", "-R", "65534:65534", "/data"]
volumeMounts:
- name: prometheus-data
mountPath: /data
subPath: ""
containers:
- name: prometheus-server-configmap-reload
image: "jimmidyson/configmap-reload:v0.1"
imagePullPolicy: "IfNotPresent"
args:
- --volume-dir=/etc/config
- --webhook-url=http://localhost:9090/-/reload
volumeMounts:
- name: config-volume
mountPath: /etc/config
readOnly: true
resources:
limits:
cpu: 10m
memory: 10Mi
requests:
cpu: 10m
memory: 10Mi
- name: prometheus-server
image: "prom/prometheus:v2.2.1"
imagePullPolicy: "IfNotPresent"
args:
- --config.file=/etc/config/prometheus.yml
- --storage.tsdb.path=/data
- --web.console.libraries=/etc/prometheus/console_libraries
- --web.console.templates=/etc/prometheus/consoles
- --web.enable-lifecycle
ports:
- containerPort: 9090
readinessProbe:
httpGet:
path: /-/ready
port: 9090
initialDelaySeconds: 30
timeoutSeconds: 30
livenessProbe:
httpGet:
path: /-/healthy
port: 9090
initialDelaySeconds: 30
timeoutSeconds: 30
# based on 10 running nodes with 30 pods each
resources:
limits:
cpu: 200m
memory: 1000Mi
requests:
cpu: 200m
memory: 1000Mi
volumeMounts:
- name: config-volume
mountPath: /etc/config
- name: prometheus-data
mountPath: /data
subPath: ""
- name: rules-volume
mountPath: /etc/config/alert_rules
terminationGracePeriodSeconds: 300
volumes:
- name: config-volume
configMap:
name: prometheus-config
- name: rules-volume
configMap:
name: prometheus-rules-config ####挂载规则到服务目录下
- name: prometheus-data
persistentVolumeClaim:
claimName: prometheus-claim
6、配置告警规则 配置 prometheus启用告警规则
[root@VM_0_48_centos prometheus]# cat prometheus-configmap.yaml # Prometheus configuration format https://prometheus.io/docs/prometheus/latest/configuration/configuration/ apiVersion: v1 kind: ConfigMap metadata: name: prometheus-config namespace: kube-system labels: kubernetes.io/cluster-service: "true" addonmanager.kubernetes.io/mode: EnsureExists data: prometheus.yml: | scrape_configs: - job_name: prometheus static_configs: - targets: - localhost:9090 - job_name: node static_configs: - targets: - 172.19.0.48:9100 - 172.19.0.14:9100 - 172.19.0.9:9100 - 172.19.0.2:9100 - job_name: kubernetes-apiservers kubernetes_sd_configs: - role: endpoints relabel_configs: - action: keep regex: default;kubernetes;https source_labels: - __meta_kubernetes_namespace - __meta_kubernetes_service_name - __meta_kubernetes_endpoint_port_name scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token - job_name: kubernetes-nodes-kubelet kubernetes_sd_configs: - role: node relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token - job_name: kubernetes-nodes-cadvisor kubernetes_sd_configs: - role: node relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) - target_label: __metrics_path__ replacement: /metrics/cadvisor scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt insecure_skip_verify: true bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token - job_name: kubernetes-service-endpoints kubernetes_sd_configs: - role: endpoints relabel_configs: - action: keep regex: true source_labels: - __meta_kubernetes_service_annotation_prometheus_io_scrape - action: replace regex: (https?) source_labels: - __meta_kubernetes_service_annotation_prometheus_io_scheme target_label: __scheme__ - action: replace regex: (.+) source_labels: - __meta_kubernetes_service_annotation_prometheus_io_path target_label: __metrics_path__ - action: replace regex: ([^:]+)(?::d+)?;(d+) replacement: $1:$2 source_labels: - __address__ - __meta_kubernetes_service_annotation_prometheus_io_port target_label: __address__ - action: labelmap regex: __meta_kubernetes_service_label_(.+) - action: replace source_labels: - __meta_kubernetes_namespace target_label: kubernetes_namespace - action: replace source_labels: - __meta_kubernetes_service_name target_label: kubernetes_name - job_name: kubernetes-services kubernetes_sd_configs: - role: service metrics_path: /probe params: module: - http_2xx relabel_configs: - action: keep regex: true source_labels: - __meta_kubernetes_service_annotation_prometheus_io_probe - source_labels: - __address__ target_label: __param_target - replacement: blackbox target_label: __address__ - source_labels: - __param_target target_label: instance - action: labelmap regex: __meta_kubernetes_service_label_(.+) - source_labels: - __meta_kubernetes_namespace target_label: kubernetes_namespace - source_labels: - __meta_kubernetes_service_name 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 alerting: alertmanagers: - static_configs: - targets: ["alertmanager:80"] rule_files: - "/etc/config/alert_rules/*.yml" ####启用挂载的规则文件
5、配置告警媒介
[root@VM_0_48_centos prometheus]# cat alertmanager-configmap.yaml apiVersion: v1 kind: ConfigMap metadata: name: alertmanager-config namespace: kube-system labels: kubernetes.io/cluster-service: "true" addonmanager.kubernetes.io/mode: EnsureExists data: alertmanager.yml: | global: resolve_timeout: 5m smtp_smarthost: 'smtp.163.com:25' smtp_from: 'xjq18125012766@163.com' smtp_auth_username: '********@163.com' smtp_auth_password: '*******' smtp_require_tls: false route: group_by: ['alertname'] group_wait: 10s group_interval: 30s repeat_interval: 10s receiver: 'mail' receivers: - name: 'mail' email_configs: - to: '2654071080@qq.com'
6、告警结果展示
