Improved version of the ceph reboot status check script from [rook/rook - Pull Request: Added ceph-reboot-script using the Container Linux Update Operator #1492](https://github.com/rook/rook/pull/1492).

ceph-reboot-status-check.sh

#!/bin/bash

# preflightCheck checks for existence of "dependencies"
preflightCheck() {
    if [ ! -f "/var/run/secrets/kubernetes.io/serviceaccount/token" ]; then
        echo "$(date) | No Kubernetes ServiceAccount token found."
        exit 1
    fi
}

# updateNodeRebootAnnotation sets the `ceph-reboot-check` annotation to `true` on `$NODE`
updateNodeRebootAnnotation(){
    export PATCH="[{ \"op\": \"add\", \"path\": \"/metadata/annotations/ceph-reboot-check\", \"value\": \"true\" }]"
    KUBE_TOKEN="$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)"
    export KUBE_TOKEN

    TRIES=0
    until [ $TRIES -eq 10 ]; do
        if curl -sSk \
            --fail \
            -XPATCH \
            -H "Authorization: Bearer $KUBE_TOKEN" \
            -H "Accept: application/json" \
            -H "Content-Type:application/json-patch+json" \
            --data "$PATCH" \
            "https://$KUBERNETES_SERVICE_HOST:$KUBERNETES_PORT_443_TCP_PORT/api/v1/nodes/$NODE"; then
            echo "$(date) | Annotation \"ceph-reboot-check\" from node $NODE updated to \"true\". Reboot confirmed!"
            return 0
        else
            echo "$(date) | Kubernetes API server connection error, will retry in 5 seconds..."
            /bin/sleep 5
        fi
    done
    return 1
}

# checkCephClusterHealth checks `ceph health` command for `HEALTH_OK`
checkCephClusterHealth(){
    echo "$(date) | Running ceph health command"
    if /usr/bin/ceph health | grep -q "HEALTH_OK"; then
        echo "$(date) | Ceph cluster health is: OKAY"
        return 0
    fi
    return 1
}

preflightCheck

echo "$(date) | Running the rook toolbox config initiation script..."
/usr/local/bin/toolbox.sh &

TRIES=0
until [ -f /etc/ceph/ceph.conf ]; do
    [ $TRIES -eq 10 ] && { echo "$(date) | No Ceph config found after 10 tries. Exiting ..."; exit 1; }
    echo "$(date) | Waiting for Ceph config (try $TRIES from 10) ..."
    (( TRIES++ ))
    sleep 3
done

while true; do
    if checkCephClusterHealth; then
        if updateNodeRebootAnnotation; then
            while true; do
                echo "$(date) | Waiting for $NODE to reboot ..."
                /bin/sleep 30
            done
            exit 0
        else
            echo "$(date) | Failed updating annotation for $NODE. Exiting."
            exit 1
        fi
    fi
    echo "$(date) | Ceph cluster Health not HEALTH_OK currently. Checking again in 20 seconds ..."
    /bin/sleep 20
done