Longhorn のスナップショットを自動的にクリーンアップする方法

スナップショットを自動的にクリーンアップするには、以下のファイルを使用して cronjob を作成する必要があります。この cronjob を作成するには、kubectl apply -f snapshot-cleanup.yaml を実行します。必要に応じて、schedule パラメーターを変更できます。既定では、この cronjob は 10 日以上経過したスナップショットを削除します。この期間を短くするには、days 変数を更新します。

apiVersion: batch/v1
kind: CronJob
metadata:
  annotations:
  labels:
    job: uipath-snapshot-cleanup
  name: lh-snapshot-cleanup
  namespace: longhorn-system
spec:
  concurrencyPolicy: Forbid
  failedJobsHistoryLimit: 1
  jobTemplate:
    spec:
      backoffLimit: 3
      template:
        metadata:
          labels:
            job: uipath-snapshot-cleanup
          name: uipath-snapshot-cleanup
        spec:
          containers:
          - command:
            - sh
            args:
            - -ec
            - |
              url=$(kubectl get svc -n longhorn-system  longhorn-backend -o json | jq -r '.spec | (.clusterIP|tostring)  + ":" + (.ports[0].port|tostring)')
              days=10

              [[ -z "$url" ]] && echo "Missing longhorn URL" && exit 1

              curl -s --connect-timeout 30 ${url}/v1 >> /dev/null || { echo "Unable to connect to longhorn backend"; exit 1; }

               echo "Deleting snapshots older than $days days"

                vols=$( (curl -s -X GET ${url}/v1/volumes |jq -r '.data[].name') )

                function delete_snapshot() {
                        local vol=$1
                        local snap=$2

                        [[ -z "$vol" || -z "$snap" ]] && echo "Error: delete_snapshot: Empty argument" && return 1
                        curl -s -X POST ${url}/v1/volumes/${vol}?action=snapshotDelete -d '{"name": "'$snap'"}'
                        echo "Snapshot=$snap deleted for volume=$vol"
                }

                function cleanup_volume() {
                        local vol=$1
                        local deleted_snap=0

                        [[ -z "$vol" ]] && echo "Error: cleanup_volume: Empty argument" && return 1

                        # fetch list of snapshot
                        snaps=$( (curl -s -X POST ${url}/v1/volumes/${vol}?action=snapshotList | jq  -r '.data[] | select(.usercreated==true) | .name' ) )
                        for i in ${snaps[@]}; do
                                if [[ $i == "volume-head" ]]; then
                                        continue
                                fi

                                snapTime=$(curl -s -X POST ${url}/v1/volumes/${vol}?action=snapshotGet -d '{"name":"'$i'"}' |jq -r '.created')
                                currentTime=$(date "+%s")
                                timeDiff=$(($currentTime - ($(date -d $snapTime "+%s")) / 86400))
                                if [[ $timeDiff -lt $days ]]; then
                                        echo "Ignoring snapshot $i, since it is older than $timeDiff days"
                                        continue
                                fi

                                delete_snapshot $vol $i
                                deleted_snap=$((deleted_snap+1))
                        done

                        if [[ "$deleted_snap" -gt 0 ]]; then
                                curl -s -X POST ${url}/v1/volumes/${vol}?action=snapshotPurge >> /dev/null
                        fi

                }

                for i in ${vols[@]}; do
                        cleanup_volume $i
                done
                exit 0
            env:
            - name: POD_NAMESPACE
              valueFrom:
                fieldRef:
                  apiVersion: v1
                  fieldPath: metadata.namespace
            image: uipath/sf-k8-utils-rhel:0.9
            imagePullPolicy: IfNotPresent
            name: uipath-snapshot-cleanup
            resources: {}
            terminationMessagePath: /dev/termination-log
            terminationMessagePolicy: File
          dnsPolicy: ClusterFirst
          priorityClassName: system-cluster-critical
          restartPolicy: OnFailure
          schedulerName: default-scheduler
          securityContext: {}
          serviceAccount: longhorn-service-account
          serviceAccountName: longhorn-service-account
          terminationGracePeriodSeconds: 30
          tolerations:
          - effect: NoSchedule
            key: kubernetes.io/hostname
            operator: Equal
            value: server0
  schedule: '0 11 * * *'
  successfulJobsHistoryLimit: 1
  suspend: false