usr-local-bin-aws-kubelet-providerid.yaml

mode: 0755
path: "/usr/local/bin/aws-kubelet-providerid"
contents:
  inline: |
    #!/bin/bash
    set -e -o pipefail

    NODEENV=/etc/kubernetes/node.env

    if [ -e "${NODEENV}" ] && grep -Fq "KUBELET_PROVIDERID" ${NODEENV}; then
        echo "Not replacing existing ${NODEENV}"
        exit 0
    fi

    # afterburn service is expected to be used for metadata retrival, see respective systemd unit.
    # However, on older OCP boot images does not contain afterburn service, check if afterburn variables are there
    # otherwise try to communicate IMDS here.
    # metadata related afterburn doc: https://coreos.github.io/afterburn/usage/attributes/
    
    INSTANCE_ID=${AFTERBURN_AWS_INSTANCE_ID:-}
    AVAILABILITY_ZONE=${AFTERBURN_AWS_AVAILABILITY_ZONE:-}
    if [[ -z "${INSTANCE_ID}" ]] || [[ -z "${AVAILABILITY_ZONE}" ]]; then
      INSTANCE_ID=$(curl -fSs http://169.254.169.254/2022-09-24/meta-data/instance-id)
      AVAILABILITY_ZONE=$(curl -fSs http://169.254.169.254/2022-09-24/meta-data/placement/availability-zone)
      if [[ -z "${INSTANCE_ID}" ]] || [[ -z "${AVAILABILITY_ZONE}" ]]; then
        echo "Can not obtain instance-id and availability zone info from the metadata service."
        exit 1
      fi 
    fi

    # Due to a potential mismatch between Hostname and PrivateDNSName with clusters that use custom DHCP Option Sets
    # which can cause issues in cloud controller manager node syncing
    # (see: https://github.com/kubernetes/cloud-provider-aws/issues/384),
    # set KUBELET_PROVIDERID to be a fully qualified AWS instace provider id.
    # This new variable is later used to populate the kubelet's `provider-id` flag, later set on the Node .spec
    # and used by the cloud controller manager's node controller to retrieve the Node's backing instance.
    cat >> "${NODEENV}" <<EOF
    KUBELET_PROVIDERID=aws:///${AVAILABILITY_ZONE}/${INSTANCE_ID}
    EOF

    # Remove the legacy node conf once we've written out the new file
    LEGACY_NODECONF=NODECONF=/etc/systemd/system/kubelet.service.d/20-aws-providerid.conf

    if [ -e "${LEGACY_NODECONF}" ]; then
        rm -f ${LEGACY_NODECONF}
        echo "Removed legacy ${LEGACY_NODECONF}"
    fi