alert告警部署 · kubernetes

準備docker鏡像 ``` docker pull docker.io/prom/alertmanager:v0.14.0 docker tag 23744b2d645c harbor.od.com/infra/alertmanager:v0.14.0 docker push harbor.od.com/infra/alertmanager:v0.14.0 ``` 準備目錄 ``` mkdir /data/k8s-yaml/alertmanager cd /data/k8s-yaml/alertmanager ``` 準備資源清單 cm.yaml ``` cat >cm.yaml <<'EOF' apiVersion: v1 kind: ConfigMap metadata: name: alertmanager-config namespace: infra data: config.yml: |- global: # 在沒有報警的情況下聲明為已解決的時間 resolve_timeout: 5m # 配置郵件發送信息 smtp_smarthost: 'smtp.163.com:25' smtp_from: 'xxx@163.com' smtp_auth_username: 'xxx@163.com' smtp_auth_password: 'xxxxxx' smtp_require_tls: false templates: - '/etc/alertmanager/*.tmpl' # 所有報警信息進入后的根路由，用來設置報警的分發策略 route: # 這里的標簽列表是接收到報警信息后的重新分組標簽，例如，接收到的報警信息里面有許多具有 cluster=A 和 alertname=LatncyHigh 這樣的標簽的報警信息將會批量被聚合到一個分組里面 group_by: ['alertname', 'cluster'] # 當一個新的報警分組被創建后，需要等待至少group_wait時間來初始化通知，這種方式可以確保您能有足夠的時間為同一分組來獲取多個警報，然后一起觸發這個報警信息。 group_wait: 30s # 當第一個報警發送后，等待'group_interval'時間來發送新的一組報警信息。 group_interval: 5m # 如果一個報警信息已經發送成功了，等待'repeat_interval'時間來重新發送他們 repeat_interval: 5m # 默認的receiver：如果一個報警沒有被一個route匹配，則發送給默認的接收器 receiver: default receivers: - name: 'default' email_configs: - to: 'xxxx@qq.com' send_resolved: true html: '{{ template "email.to.html" . }}' headers: { Subject: " {{ .CommonLabels.instance }} {{ .CommonAnnotations.summary }}" } email.tmpl: | {{ define "email.to.html" }} {{- if gt (len .Alerts.Firing) 0 -}} {{ range .Alerts }} 告警程序: prometheus_alert 告警級別: {{ .Labels.severity }} 告警類型: {{ .Labels.alertname }} 故障主機: {{ .Labels.instance }} 告警主題: {{ .Annotations.summary }} 觸發時間: {{ .StartsAt.Format "2006-01-02 15:04:05" }} {{ end }}{{ end -}} {{- if gt (len .Alerts.Resolved) 0 -}} {{ range .Alerts }} 告警程序: prometheus_alert 告警級別: {{ .Labels.severity }} 告警類型: {{ .Labels.alertname }} 故障主機: {{ .Labels.instance }} 告警主題: {{ .Annotations.summary }} 觸發時間: {{ .StartsAt.Format "2006-01-02 15:04:05" }} 恢復時間: {{ .EndsAt.Format "2006-01-02 15:04:05" }} {{ end }}{{ end -}} {{- end }} EOF ``` dp.yaml ``` cat >dp.yaml <<'EOF' apiVersion: extensions/v1beta1 kind: Deployment metadata: name: alertmanager namespace: infra spec: replicas: 1 selector: matchLabels: app: alertmanager template: metadata: labels: app: alertmanager spec: containers: - name: alertmanager image: harbor.zq.com/infra/alertmanager:v0.14.0 args: - "--config.file=/etc/alertmanager/config.yml" - "--storage.path=/alertmanager" ports: - name: alertmanager containerPort: 9093 volumeMounts: - name: alertmanager-cm mountPath: /etc/alertmanager volumes: - name: alertmanager-cm configMap: name: alertmanager-config imagePullSecrets: - name: harbor EOF ``` svc.yaml ``` cat ><<'EOF' apiVersion: v1 kind: Service metadata: name: alertmanager namespace: infra spec: selector: app: alertmanager ports: - port: 80 targetPort: 9093 EOF ``` 應用資源配置清單 ``` kubectl apply -f http://k8s-yaml.od.com/alertmanager/cm.yaml kubectl apply -f http://k8s-yaml.od.com/alertmanager/dp.yaml kubectl apply -f http://k8s-yaml.od.com/alertmanager/svc.yaml ``` k8s創建基礎報警規則文件 ``` cat >/data/nfs-volume/prometheus/etc/rules.yml <<'EOF' groups: - name: hostStatsAlert rules: - alert: hostCpuUsageAlert expr: sum(avg without (cpu)(irate(node_cpu{mode!='idle'}[5m]))) by (instance) > 0.85 for: 5m labels: severity: warning annotations: summary: "{{ $labels.instance }} CPU usage above 85% (current value: {{ $value }}%)" - alert: hostMemUsageAlert expr: (node_memory_MemTotal - node_memory_MemAvailable)/node_memory_MemTotal > 0.85 for: 5m labels: severity: warning annotations: summary: "{{ $labels.instance }} MEM usage above 85% (current value: {{ $value }}%)" - alert: OutOfInodes expr: node_filesystem_free{fstype="overlay",mountpoint ="/"} / node_filesystem_size{fstype="overlay",mountpoint ="/"} * 100 < 10 for: 5m labels: severity: warning annotations: summary: "Out of inodes (instance {{ $labels.instance }})" description: "Disk is almost running out of available inodes (< 10% left) (current value: {{ $value }})" - alert: OutOfDiskSpace expr: node_filesystem_free{fstype="overlay",mountpoint ="/rootfs"} / node_filesystem_size{fstype="overlay",mountpoint ="/rootfs"} * 100 < 10 for: 5m labels: severity: warning annotations: summary: "Out of disk space (instance {{ $labels.instance }})" description: "Disk is almost full (< 10% left) (current value: {{ $value }})" - alert: UnusualNetworkThroughputIn expr: sum by (instance) (irate(node_network_receive_bytes[2m])) / 1024 / 1024 > 100 for: 5m labels: severity: warning annotations: summary: "Unusual network throughput in (instance {{ $labels.instance }})" description: "Host network interfaces are probably receiving too much data (> 100 MB/s) (current value: {{ $value }})" - alert: UnusualNetworkThroughputOut expr: sum by (instance) (irate(node_network_transmit_bytes[2m])) / 1024 / 1024 > 100 for: 5m labels: severity: warning annotations: summary: "Unusual network throughput out (instance {{ $labels.instance }})" description: "Host network interfaces are probably sending too much data (> 100 MB/s) (current value: {{ $value }})" - alert: UnusualDiskReadRate expr: sum by (instance) (irate(node_disk_bytes_read[2m])) / 1024 / 1024 > 50 for: 5m labels: severity: warning annotations: summary: "Unusual disk read rate (instance {{ $labels.instance }})" description: "Disk is probably reading too much data (> 50 MB/s) (current value: {{ $value }})" - alert: UnusualDiskWriteRate expr: sum by (instance) (irate(node_disk_bytes_written[2m])) / 1024 / 1024 > 50 for: 5m labels: severity: warning annotations: summary: "Unusual disk write rate (instance {{ $labels.instance }})" description: "Disk is probably writing too much data (> 50 MB/s) (current value: {{ $value }})" - alert: UnusualDiskReadLatency expr: rate(node_disk_read_time_ms[1m]) / rate(node_disk_reads_completed[1m]) > 100 for: 5m labels: severity: warning annotations: summary: "Unusual disk read latency (instance {{ $labels.instance }})" description: "Disk latency is growing (read operations > 100ms) (current value: {{ $value }})" - alert: UnusualDiskWriteLatency expr: rate(node_disk_write_time_ms[1m]) / rate(node_disk_writes_completedl[1m]) > 100 for: 5m labels: severity: warning annotations: summary: "Unusual disk write latency (instance {{ $labels.instance }})" description: "Disk latency is growing (write operations > 100ms) (current value: {{ $value }})" - name: http_status rules: - alert: ProbeFailed expr: probe_success == 0 for: 1m labels: severity: error annotations: summary: "Probe failed (instance {{ $labels.instance }})" description: "Probe failed (current value: {{ $value }})" - alert: StatusCode expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400 for: 1m labels: severity: error annotations: summary: "Status Code (instance {{ $labels.instance }})" description: "HTTP status code is not 200-399 (current value: {{ $value }})" - alert: SslCertificateWillExpireSoon expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 30 for: 5m labels: severity: warning annotations: summary: "SSL certificate will expire soon (instance {{ $labels.instance }})" description: "SSL certificate expires in 30 days (current value: {{ $value }})" - alert: SslCertificateHasExpired expr: probe_ssl_earliest_cert_expiry - time() <= 0 for: 5m labels: severity: error annotations: summary: "SSL certificate has expired (instance {{ $labels.instance }})" description: "SSL certificate has expired already (current value: {{ $value }})" - alert: BlackboxSlowPing expr: probe_icmp_duration_seconds > 2 for: 5m labels: severity: warning annotations: summary: "Blackbox slow ping (instance {{ $labels.instance }})" description: "Blackbox ping took more than 2s (current value: {{ $value }})" - alert: BlackboxSlowRequests expr: probe_http_duration_seconds > 2 for: 5m labels: severity: warning annotations: summary: "Blackbox slow requests (instance {{ $labels.instance }})" description: "Blackbox request took more than 2s (current value: {{ $value }})" - alert: PodCpuUsagePercent expr: sum(sum(label_replace(irate(container_cpu_usage_seconds_total[1m]),"pod","$1","container_label_io_kubernetes_pod_name", "(.*)"))by(pod) / on(pod) group_right kube_pod_container_resource_limits_cpu_cores *100 )by(container,namespace,node,pod,severity) > 80 for: 5m labels: severity: warning annotations: summary: "Pod cpu usage percent has exceeded 80% (current value: {{ $value }}%)" EOF ``` 在prometheus配置文件中追加配置： ``` cat >>/data/nfs-volume/prometheus/etc/prometheus.yml <<'EOF' alerting: alertmanagers: - static_configs: - targets: ["alertmanager"] rule_files: - "/data/etc/rules.yml" EOF ``` 重載配置： ``` curl -X POST http://prometheus.od.com/-/reload ```