Migrate EBS based PVC to other cluster and/or availability zone

ebs-pvc-migrate.sh

#!/bin/bash
#
# 05-08-2024: Complete rewrite
#

usage()
{
  cat <<-EOF
	Usage: $0 <REQUIRED-PARAMETERS...> [OPTIONAL-PARAMETERS...]

	This script can clone a PV/PVC to:

	- A new PV/PVC in the same namespace (same cluster)
	- Another namespace (same or new cluster)
	- A new Availability Zone (same or new cluster)
	- A new cluster

	Both cluster and AZ must be from the same region and account.

	Required parameters
	-------------------

	  --source-namespace=''
	      Namespace to clone PVC from.

	  --source-pvc=''
	      PVC name to clone from.

	Optional parameters
	-------------------

	  --aws-profile=''
	      AWS profile name to use. AWS auth methods works as usual.

	  --delete-snapshot
	      Delete snapshot.

	  --dry-run
	      Only print changes.

	  --kubectl-bin-source='kubectl'
	      Kubectl binary. Usefull for when clusters have too far skewed version.

	  --kubectl-bin-target='kubectl'
	      Kubectl binary. Usefull for when clusters have too far skewed version.

	  --source-aws-zone=''
	      AWS zone of the volume. Auto discovered if unspecified.

	  --source-cluster=''
	      Kubeconfig context to read PVC/PV from. Defaults to current context.

	  --source-snapshot-id=''
	      Snapshot ID to create target volume from.

	  --source-workload=''
	      Kind/Name of the workload to stop/start during the cloning.

	  --target-aws-zone=''
	      AWS zone to restore the snapshot. Defaults to same as source.

	  --target-cluster=''
	      Kubeconfig context to create the target PVC/PV. Defaults to same cluster.

	  --target-cluster-id=''
	      AWS cluster ID for target volume. You can find it in AWS tag 'kubernetes.io/cluster/{ID}'.

	  --target-fs-type=''
	      Filesystem type for target volume. Defaults to same as source.

	  --target-namespace=''
	      Namespace to clone PVC to.

	  --target-pv=''
	      PV name for the clone. Defaults to CSI compliant random UUID.

	  --target-pvc=''
	      PVC name for the clone. Defaults to source PVC name.

	  --target-storage-class=''
	      Storage Class name for target PVC. This is required if target cluster
	      doesn't has a storageClass with same name.

	  --target-volumet-type=''
	      EBS volume type for target volume. Usually 'gp2' or 'gp3'.

	If --source-cluster and --target-cluster are the same, --source-pvc and --target-pvc can't have the
	same name if they are in the same namespace.
EOF
  exit ${1:-0}
}

if [ $# -eq 0 ]; then
  usage
fi

set -a # export all vars

SOURCE_KUBECTL=kubectl
TARGET_KUBECTL=kubectl
SOURCE_SNAPSHOT_ID=''
DELETE_SNAPSHOT=false
DRY_RUN=false
SOURCE_DRY_RUN=''
TARGET_DRY_RUN=''
DRY_RUN_CMD=''

declare -A BOOL_FLAGS

BOOL_FLAGS[--dry-run]=true
BOOL_FLAGS[--delete-snapshot]=true

while [ $# -gt 0 ]; do
  opt=$1
  val=""

  if [[ "$opt" =~ --[a-z0-9]+(-[a-z0-9]+){0,}= ]]; then
    val=${opt#*=}
    opt=${opt%%=*}
    shift
  else
    if ${BOOL_FLAGS[--dry-run]:-false}; then
      opt="$1"
      val="true"
      shift
    elif ${BOOL_FLAGS[--delete-snapshot]:-false}; then
      opt="$1"
      val="true"
      shift
    else
      opt="$1"
      val="$2"
      shift 2
    fi
  fi

  case $opt in
    --aws-profile)        AWS_PROFILE=$val               ;;
    --delete-snapshot)    DELETE_SNAPSHOT=true           ;;
    --dry-run)            DRY_RUN=true DRY_RUN_CMD=debug ;;
    --kubectl-bin-source) SOURCE_KUBECTL=$val            ;;
    --kubectl-bin-target) TARGET_KUBECTL=$val            ;;

    --source-aws-zone)    SOURCE_AWS_ZONE=$val    ;;
    --source-cluster)     SOURCE_CLUSTER=$val     ;;
    --source-namespace)   SOURCE_NAMESPACE=$val   ;; # required
    --source-pvc)         SOURCE_PVC=$val         ;; # required
    --source-snapshot-id) SOURCE_SNAPSHOT_ID=$val ;;
    --source-workload)    SOURCE_WORKLOAD=$val    ;;

    --target-aws-zone)      TARGET_AWS_ZONE=$val      ;;
    --target-cluster)       TARGET_CLUSTER=$val       ;;
    --target-cluster-id)    TARGET_CLUSTER_ID=$val    ;;
    --target-fs-type)       TARGET_FS_TYPE=$val       ;;
    --target-namespace)     TARGET_NAMESPACE=$val     ;; # required
    --target-pv)            TARGET_PV=$val            ;;
    --target-pvc)           TARGET_PVC=$val           ;;
    --target-storage-class) TARGET_STORAGE_CLASS=$val ;;
    --target-volume-type)   TARGET_VOLUME_TYPE=$val   ;;

    *) usage
  esac
done

function info()
{
  echo -e $'\E[1;96m+' "$*" $'\E[0m'
}

function debug()
{
  echo -e $'\E[2;96m+' "$*" $'\E[0m'
}

function err()
{
  echo -e $'\E[1;31m+' "$*" $'\E[0m'
}

if $DRY_RUN; then
  debug 'Dry-run: nothing will be created/changed'

  SOURCE_KUBECTL_VERSION_MINOR=$($SOURCE_KUBECTL version -o json --client | jq -r '.clientVersion.minor')
  TARGET_KUBECTL_VERSION_MINOR=$($TARGET_KUBECTL version -o json --client | jq -r '.clientVersion.minor')

  [ "$SOURCE_KUBECTL_VERSION_MINOR" -ge 18 ] && SOURCE_DRY_RUN='--dry-run=client -o yaml' || SOURCE_DRY_RUN='--dry-run=true -o yaml'
  [ "$TARGET_KUBECTL_VERSION_MINOR" -ge 18 ] && TARGET_DRY_RUN='--dry-run=client -o yaml' || TARGET_DRY_RUN='--dry-run=true -o yaml'
fi

for required in SOURCE_NAMESPACE SOURCE_PVC; do
  if ! [ -v $required ]; then
    param=${required,,}
    param=${param//_/-}
    err "Missing required parameter: $param"
    exit 1
  fi
done

if ! [ -v SOURCE_CLUSTER ]; then
  SOURCE_CLUSTER=$($SOURCE_KUBECTL config current-context)
fi

if ! [ -v TARGET_CLUSTER ]; then
  TARGET_CLUSTER="$SOURCE_CLUSTER"
fi

if ! [ -v TARGET_NAMESPACE ]; then
  TARGET_NAMESPACE=$SOURCE_NAMESPACE
fi

if ! [ -v TARGET_PVC ]; then
  TARGET_PVC=$SOURCE_PVC
fi

if [ "$SOURCE_CLUSTER" == "$TARGET_CLUSTER" ]; then
  if [ "$SOURCE_NAMESPACE" == "$TARGET_NAMESPACE" ]; then
    if [ "$SOURCE_PVC" == "$TARGET_PVC" ]; then
      err "Can't clone PVC to same cluster/namespace/name"
      exit 1
    fi
  fi
fi

info "Checking if can reach cluster(s)"

for context in "$SOURCE_CLUSTER" "$TARGET_CLUSTER"; do
  if ! $SOURCE_KUBECTL config get-contexts -o name | grep -q "^$context\$"; then
    err "Cluster not found: $context"
    exit 1
  fi

  if ! $SOURCE_KUBECTL version --context="$context" &>/dev/null; then
    err "Unable to reach cluster: $context"
    err "Please try it with: kubectl version --context=\"$context\""
    exit 1
  fi
done

SOURCE_KUBECTL+=" --context=$SOURCE_CLUSTER"
TARGET_KUBECTL+=" --context=$TARGET_CLUSTER"

if ! [ -v TARGET_PV ]; then
  TARGET_PV=pvc-$(</proc/sys/kernel/random/uuid)
fi

if [ -v SOURCE_WORKLOAD ]; then
  if ! [[ $SOURCE_WORKLOAD =~ .*/.* ]]; then
    err "Invalid workload name: Expecting kind/name. Got: $SOURCE_WORKLOAD"
    exit 1
  else
    info "Reading workload replicas"
    WORKLOAD_REPLICAS=$($SOURCE_KUBECTL get -n $SOURCE_NAMESPACE $SOURCE_WORKLOAD --template={{.spec.replicas}})
  fi
else
    SOURCE_WORKLOAD=""
    WORKLOAD_REPLICAS=0
fi

set -eu

info "Reading source PVC"

DATA_SOURCE_PVC="$($SOURCE_KUBECTL get -n $SOURCE_NAMESPACE pvc $SOURCE_PVC -o json)"

SOURCE_PV=$(jq -r '.spec.volumeName' <<<$DATA_SOURCE_PVC)
SOURCE_STORAGE=$(jq -r '.spec.resources.requests.storage // empty' <<<$DATA_SOURCE_PVC)
SOURCE_STORAGE_CLASS=$(jq -r '
  .spec.storageClassName
  // .metadata.annotations["volume.kubernetes.io/storage-class"]
  // .metadata.annotations["volume.beta.kubernetes.io/storage-class"]
  // empty' <<<$DATA_SOURCE_PVC)

if ! [ -v TARGET_STORAGE_CLASS ]; then
  DATA_TARGET_STORAGE_CLASS=$($TARGET_KUBECTL get sc -o json | jq -r '.items[] | select(.metadata.annotations["storageclass.kubernetes.io/is-default-class"]=="true") // empty')
  TARGET_STORAGE_CLASS=$(jq -r '.metadata.name' <<<$DATA_TARGET_STORAGE_CLASS)
fi

if ! [ -v TARGET_STORAGE_CLASS ] || [ -z "$TARGET_STORAGE_CLASS" ]; then
  err "Unable to find default target storageclass. Please specify one with --target-storage-class"
  exit 1
fi

DATA_SOURCE_STORAGE_CLASS="$($SOURCE_KUBECTL get sc $SOURCE_STORAGE_CLASS -o json)"
DATA_TARGET_STORAGE_CLASS="$($TARGET_KUBECTL get sc $TARGET_STORAGE_CLASS -o json)"

if [ -z "$DATA_SOURCE_STORAGE_CLASS" ]; then
  err "Source storage class not found: $SOURCE_STORAGE_CLASS"
  exit 1
elif [ -z "$DATA_TARGET_STORAGE_CLASS" ]; then
  err "Target storage class not found: $TARGET_STORAGE_CLASS"
  exit 1
fi

if ! [ -v TARGET_VOLUME_TYPE ]; then
  TARGET_VOLUME_TYPE=$(jq -r '.parameters.type // empty' <<<$DATA_TARGET_STORAGE_CLASS)
fi

if [ -z "$TARGET_VOLUME_TYPE" ]; then
  err "Unable to determine target EBS volume type"
  err "Please check field .parameters.type from target's storageclass/$TARGET_STORAGE_CLASS"
  exit 1
fi

info "Reading source PV"

DATA_SOURCE_PV="$($SOURCE_KUBECTL get -n $SOURCE_NAMESPACE pv $SOURCE_PV -o json)"

SOURCE_VOLUME_ID=$(jq -r '.spec.csi.volumeHandle // .spec.awsElasticBlockStore.volumeID // empty' <<<$DATA_SOURCE_PV | awk -F/ '{print $NF}')
SOURCE_FS_TYPE=$(jq -r '.spec.csi.fsType // .spec.awsElasticBlockStore.fsType // empty' <<<$DATA_SOURCE_PV)
SOURCE_VOLUME_MODE=$(jq -r '.spec.volumeMode // "Filesystem"' <<<$DATA_SOURCE_PV)

SOURCE_AWS_ZONE=$(jq -r 'try(
    .spec.nodeAffinity.required.nodeSelectorTerms[] |
    .matchExpressions[] |
    select(.key=="topology.ebs.csi.aws.com/zone" and .operator=="In") |
    .values[0]) // .spec.awsElasticBlockStore.volumeID | split("/")[2]' <<<$DATA_SOURCE_PV)

if ! [ -v SOURCE_AWS_ZONE ] || ! [[ "$SOURCE_AWS_ZONE" =~ [a-za-z]-[a-z]+-[0-9][a-z] ]]; then
  err "Unable to discover AWS Zone for source PV $SOURCE_PV"
  err "Please specify one with --source-aws-zone"
  err "Found zone: '$SOURCE_AWS_ZONE'"
  exit 1
fi

TARGET_STORAGE=$SOURCE_STORAGE
TARGET_VOLUME_MODE=$SOURCE_VOLUME_MODE

if ! [ -v TARGET_FS_TYPE ]; then
  TARGET_FS_TYPE=$SOURCE_FS_TYPE
fi

if ! [ -v TARGET_AWS_ZONE ]; then
  TARGET_AWS_ZONE=$SOURCE_AWS_ZONE
fi

export AWS_DEFAULT_REGION=${SOURCE_AWS_ZONE:0:-1}

info "Checking if can reach AWS"

DATA_SOURCE_VOLUME=$(aws ec2 describe-volumes --volume-ids $SOURCE_VOLUME_ID | jq -r '.Volumes[0] // empty' 2>/dev/null)

if [ -z "$DATA_SOURCE_VOLUME" ]; then
  err "Unable to read volume $SOURCE_VOLUME_ID from AWS Zone $SOURCE_AWS_ZONE"
  err "Maybe credentials are unset or invalid?"
  err "You can use flags --aws-profile and to specify your credentials"
  exit 1
fi

SOURCE_CLUSTER_ID=$(jq -r '.Tags[] | select(.Key|startswith("kubernetes.io/cluster/")) | .Key | split("/")[2] // empty' <<<$DATA_SOURCE_VOLUME)

if [ "$SOURCE_CLUSTER" == "$TARGET_CLUSTER" ]; then
  TARGET_CLUSTER_ID="$SOURCE_CLUSTER_ID"
fi

if ! [ -v TARGET_CLUSTER_ID ]; then
  err "Missing required parameter --target-cluster-id={ID}"
  exit 1
fi

if $TARGET_KUBECTL get -n $TARGET_NAMESPACE pvc $TARGET_PVC &>/dev/null; then
  err "Target PVC already exists: $TARGET_NAMESPACE/$TARGET_PVC"
  err "Please delete it first and try again"
  exit 1
fi

if $TARGET_KUBECTL get -n $TARGET_NAMESPACE pv $TARGET_PV &>/dev/null; then
  err "Target PV already exists: $TARGET_NAMESPACE/$TARGET_PV"
  err "Please delete it first and try again"
  exit 1
fi

TARGET_RETAIN_POLICY=$(jq -r '.reclaimPolicy // "Retain"' <<<$DATA_TARGET_STORAGE_CLASS)
TARGET_PROVISIONER=$(jq -r '.provisioner // empty' <<<$DATA_TARGET_STORAGE_CLASS)
TARGET_CSI_PROVISIONER_IDENTITY=''

case "$TARGET_PROVISIONER" in
  ebs.csi.aws.com)
    # don't need to be unique for each volume, only  for each provisioner
    # https://github.com/kubernetes-csi/external-provisioner/blob/1194963/cmd/csi-provisioner/csi-provisioner.go#L283
    #TARGET_CSI_PROVISIONER_IDENTITY=1722555589472-9999-ebs.csi.aws.com
    TARGET_CSI_PROVISIONER_IDENTITY=$($TARGET_KUBECTL get leases --all-namespaces -o json \
      | jq -r '.items[] | select(.metadata.name=="ebs-csi-aws-com") | .spec.holderIdentity // empty' \
      | sed 's/ebs-csi-aws-com/ebs.csi.aws.com/')
  ;;
  kubernetes.io/aws-ebs) :
  ;;
  *)
    err "Unable to determine storageclass provisioner for target volume"
    exit 1
esac

BOLD='\E[1m'
RESET='\E[0m'

echo -e $"
Sumary:
-------------------------------------------------------------------------------
  AWS:
    Profile:       $BOLD${AWS_PROFILE:-(none)}$RESET
    Region:        $BOLD$AWS_DEFAULT_REGION$RESET

  Source:
    Cluster:       $BOLD$SOURCE_CLUSTER (ID=$SOURCE_CLUSTER_ID)$RESET
    Namespace:     $BOLD$SOURCE_NAMESPACE$RESET
    PV/PVC:        $BOLD$SOURCE_PV/$SOURCE_PVC ($SOURCE_STORAGE)$RESET
    VolumeID:      $BOLD$SOURCE_VOLUME_ID$RESET
    VolumeMode:    $BOLD$SOURCE_VOLUME_MODE$RESET
    SnapshotID:    $BOLD${SOURCE_SNAPSHOT_ID:-auto}$RESET
    AWS Zone:      $BOLD$SOURCE_AWS_ZONE$RESET
    Workload:      $BOLD${SOURCE_WORKLOAD:-(none)} (Replicas: $WORKLOAD_REPLICAS)$RESET
    StorageClass:  $BOLD${SOURCE_STORAGE_CLASS:-(none)}$RESET

  Target:
    Cluster:       $BOLD$TARGET_CLUSTER (ID=$TARGET_CLUSTER_ID)$RESET
    Namespace:     $BOLD$TARGET_NAMESPACE$RESET
    PV/PVC:        $BOLD$TARGET_PV/$TARGET_PVC$RESET
    AWS Zone:      $BOLD$TARGET_AWS_ZONE$RESET
    ProvisionerID: $BOLD${TARGET_CSI_PROVISIONER_IDENTITY:-(none)}$RESET
    StorageClass:  $BOLD${TARGET_STORAGE_CLASS:-(none)}$RESET
-------------------------------------------------------------------------------
"

read -p 'Press [ENTER] to start '
echo


if [ "$($SOURCE_KUBECTL get pv $SOURCE_PV -o jsonpath={.spec.persistentVolumeReclaimPolicy})" != "Retain" ]; then
  info "Setting reclaimPolicy=Retain for source PV in orther to avoid accidental deletion"
  $DRY_RUN_CMD $SOURCE_KUBECTL patch pv $SOURCE_PV -p '{"spec":{"persistentVolumeReclaimPolicy":"Retain"}}'
fi

if [ -v SOURCE_WORKLOAD ]; then
  info "Refreshing workload replicas"
  WORKLOAD_REPLICAS=$($SOURCE_KUBECTL get -n $SOURCE_NAMESPACE $SOURCE_WORKLOAD --template={{.spec.replicas}})

  if [ $WORKLOAD_REPLICAS -gt 0 ]; then
    info "Scaling down $SOURCE_WORKLOAD: $WORKLOAD_REPLICAS -> 0"
    $DRY_RUN_CMD $SOURCE_KUBECTL scale -n $SOURCE_NAMESPACE $SOURCE_WORKLOAD --replicas=0

    while ! $DRY_RUN; do
      replicas="$($SOURCE_KUBECTL get -n $SOURCE_NAMESPACE $SOURCE_WORKLOAD --template={{.status.replicas}})"
      [ "$replicas" == "0" ] && break || true
      [ "$replicas" == "<no value>" ] && break || true
      debug "Waiting for pod(s) to terminate: $replicas remaining"
      sleep 1
    done
  fi
fi

function create_target_volume()
{
  if $DRY_RUN; then
    debug 'Dry-run: Skipping target volume creation'
    TARGET_VOLUME_ID='vol-00000000000000000'
    return
  fi

  DESCRIPTION="Cloned from cluster=$SOURCE_CLUSTER ns=$SOURCE_NAMESPACE, pvc=$SOURCE_PVC, pv=$SOURCE_PV, volumeId=$SOURCE_VOLUME_ID"

  info "Waiting for volume $SOURCE_VOLUME_ID to become available"
  debug "Tip: to force detach, execute in a separated terminal: aws ec2 detach-volume --volume-id $SOURCE_VOLUME_ID"
  aws ec2 wait volume-available --volume-id $SOURCE_VOLUME_ID

  if [ -n "$SOURCE_SNAPSHOT_ID" ]; then
    info "Using existing snapshot $SOURCE_SNAPSHOT_ID"
  else
    info "Creating snapshot from $SOURCE_VOLUME_ID"
    SOURCE_SNAPSHOT_ID=$(aws ec2 create-snapshot --volume-id $SOURCE_VOLUME_ID --description "$DESCRIPTION" --output text --query SnapshotId)
    SOURCE_SNAPSHOT_PROGRESS=''
    while [ "$SOURCE_SNAPSHOT_PROGRESS" != "100%" ]; do
      sleep 3
      SOURCE_SNAPSHOT_PROGRESS=$(aws ec2 describe-snapshots --snapshot-ids $SOURCE_SNAPSHOT_ID --query "Snapshots[*].Progress" --output text)
      info "Snapshot ID: $SOURCE_SNAPSHOT_ID $SOURCE_SNAPSHOT_PROGRESS"
    done
  fi

  aws ec2 wait snapshot-completed --filter Name=snapshot-id,Values=$SOURCE_SNAPSHOT_ID

  info "Creating volume from snapshot $SOURCE_SNAPSHOT_ID"
  TAG_SPEC="
  ResourceType=volume,
  Tags=[
    { Key=ebs.csi.aws.com/cluster,                  Value=true },
    { Key=kubernetes.io/cluster/$TARGET_CLUSTER_ID, Value=owned },
    { Key=CSIVolumeName,                            Value=$TARGET_PV },
    { Key=kubernetesCluster,                        Value=$TARGET_CLUSTER_ID },
    { Key=Name,                                     Value=$TARGET_CLUSTER_ID-dynamic-$TARGET_PV },
    { Key=kubernetes.io/created-for/pv/name,        Value=$TARGET_PV },
    { Key=kubernetes.io/created-for/pvc/name,       Value=$TARGET_PVC },
    { Key=kubernetes.io/created-for/pvc/namespace,  Value=$TARGET_NAMESPACE }
  ]"

  TARGET_VOLUME_ID=$(aws ec2 create-volume \
      --availability-zone $TARGET_AWS_ZONE \
      --snapshot-id $SOURCE_SNAPSHOT_ID \
      --volume-type $TARGET_VOLUME_TYPE \
      --output text \
      --query VolumeId \
      --tag-specifications "${TAG_SPEC//[[:space:]]/}")
}

create_target_volume

info "Created target volume: $TARGET_VOLUME_ID"

info "Creating target PVC $TARGET_NAMESPACE/$TARGET_PVC"

function yamlobj()
{
  local filename="$2"
  case "$1" in
    create) cat > "$filename"  ;;
    append) cat >> "$filename" ;;
    *) err "yamlobj: invalid parameter: $1"; exit 1
  esac
}

FILE_TARGET_PVC_YAML=$TARGET_PVC.yaml
yamlobj create $FILE_TARGET_PVC_YAML <<EOF
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: $TARGET_PVC
  namespace: $TARGET_NAMESPACE
  annotations:
    volume.beta.kubernetes.io/storage-provisioner: $TARGET_PROVISIONER
    volume.kubernetes.io/storage-provisioner: $TARGET_PROVISIONER
  finalizers:
  - kubernetes.io/pvc-protection
spec:
  accessModes:
  - ReadWriteOnce
  resources:
    requests:
      storage: $TARGET_STORAGE
  storageClassName: $TARGET_STORAGE_CLASS
  volumeMode: $TARGET_VOLUME_MODE
  volumeName: $TARGET_PV
EOF

$TARGET_KUBECTL apply -f $FILE_TARGET_PVC_YAML $TARGET_DRY_RUN

if $DRY_RUN; then
  DATA_TARGET_PVC='{"metadata":{"uid":"00000000-0000-0000-0000-000000000000"}}'
else
  DATA_TARGET_PVC=$($TARGET_KUBECTL get -n $TARGET_NAMESPACE pvc $TARGET_PVC -o json)
fi

TARGET_PVC_UID=$(jq -r '.metadata.uid' <<<$DATA_TARGET_PVC)

info "Creating target PV $TARGET_NAMESPACE/$TARGET_PV"

FILE_TARGET_PV_YAML=$TARGET_PV.yaml
yamlobj create $FILE_TARGET_PV_YAML <<EOF
apiVersion: v1
kind: PersistentVolume
metadata:
  name: $TARGET_PV
  labels:
    failure-domain.beta.kubernetes.io/region: $AWS_DEFAULT_REGION
    failure-domain.beta.kubernetes.io/zone: $TARGET_AWS_ZONE
EOF

if [ "$TARGET_PROVISIONER" == 'ebs.csi.aws.com' ]; then
  yamlobj append $FILE_TARGET_PV_YAML <<EOF
  annotations:
    pv.kubernetes.io/provisioned-by: $TARGET_PROVISIONER
    volume.kubernetes.io/provisioner-deletion-secret-name: ""
    volume.kubernetes.io/provisioner-deletion-secret-namespace: ""
EOF
fi

yamlobj append $FILE_TARGET_PV_YAML <<EOF
spec:
  accessModes:
  - ReadWriteOnce
  capacity:
    storage: $TARGET_STORAGE
  claimRef:
    apiVersion: v1
    kind: PersistentVolumeClaim
    name: $TARGET_PVC
    namespace: $TARGET_NAMESPACE
    uid: $TARGET_PVC_UID
  persistentVolumeReclaimPolicy: $TARGET_RETAIN_POLICY
  storageClassName: $TARGET_STORAGE_CLASS
  volumeMode: $TARGET_VOLUME_MODE
EOF

if [ "$TARGET_PROVISIONER" == 'ebs.csi.aws.com' ]; then
  yamlobj append $FILE_TARGET_PV_YAML <<EOF
  nodeAffinity:
    required:
      nodeSelectorTerms:
      - matchExpressions:
        - key: topology.ebs.csi.aws.com/zone
          operator: In
          values:
          - $TARGET_AWS_ZONE
  csi:
    driver: ebs.csi.aws.com
    fsType: $TARGET_FS_TYPE
    volumeAttributes:
      storage.kubernetes.io/csiProvisionerIdentity: $TARGET_CSI_PROVISIONER_IDENTITY
    volumeHandle: $TARGET_VOLUME_ID
EOF
elif [ "$TARGET_PROVISIONER" == 'kubernetes.io/aws-ebs' ]; then
  yamlobj append $FILE_TARGET_PV_YAML <<EOF
  awsElasticBlockStore:
    fsType: $TARGET_FS_TYPE
    volumeID: aws://$TARGET_AWS_ZONE/$TARGET_VOLUME_ID
EOF
fi

$TARGET_KUBECTL apply -f $FILE_TARGET_PV_YAML $TARGET_DRY_RUN

if $DRY_RUN; then
  debug "Dry-run: Skipping test pod creation"
  exit 0
fi

TEST_POD=test-$TARGET_PV
FILE_TEST_POD_YAML=$TEST_POD.yaml
yamlobj create $FILE_TEST_POD_YAML <<EOF
apiVersion: v1
kind: Pod
metadata:
  name: $TEST_POD
  namespace: $TARGET_NAMESPACE
spec:
  containers:
  - name: alpine
    image: alpine
    command:
    - /bin/cat
    tty: true
    stdin: true
    volumeMounts:
    - name: data
      mountPath: /data
      readOnly: true
  tolerations:
  - effect: NoSchedule
    operator: Exists
  volumes:
  - name: data
    persistentVolumeClaim:
      claimName: $TARGET_PVC
  restartPolicy: Never
  terminationGracePeriodSeconds: 0
EOF

info "Creating test pod $TEST_POD"

$TARGET_KUBECTL create -f $FILE_TEST_POD_YAML

$TARGET_KUBECTL wait -n $TARGET_NAMESPACE pod $TEST_POD --for=condition=Ready --timeout=180s

$TARGET_KUBECTL exec -n $TARGET_NAMESPACE -it $TEST_POD -- ls -la /data

info "Deleting test pod $TEST_POD"

$TARGET_KUBECTL delete pod -n $TARGET_NAMESPACE $TEST_POD

if ${DELETE_SNAPSHOT}; then
  info "Deleting created snapshot: $SOURCE_SNAPSHOT_ID"
  $DRY_RUN_CMD aws ec2 delete-snapshot --snapshot-id $SOURCE_SNAPSHOT_ID
fi

info Finished
echo
$TARGET_KUBECTL -n $TARGET_NAMESPACE get pv/$TARGET_PV pvc/$TARGET_PVC

Dear @caruccio
I have a use case for moving the PV to another availability zone. Can this script or the tool pv-migrate do?

Hi @laiminhtrung1997. This script was built for this exact use case: move a PVC from zone-X to zone-Y.
It works by creating a snapshot of the source EBS volume and creating a new volume, pv and pvc inside the target zone.

** This works only for AWS EBS backed PVCs**

Please, before anything, make a backup of your volumes and read the script carefully.

pv-migrate on the other hand, makes a local dump (tar.gz) of the f iles from the source PVC and send it to a new one. It works for any PVC from any cloud provider (including on-premisses)

Hey @derjohn, @rlanore. Thansk for your suggestions. I've just applied it in the script.

Complete rewrite.