#!/bin/bash

# =================
#
#
#
#
# Copyright UiPath 2021
#
# =================
# LICENSE AGREEMENT
# -----------------
#   Use of paid UiPath products and services is subject to the licensing agreement
#   executed between you and UiPath. Unless otherwise indicated by UiPath, use of free
#   UiPath products is subject to the associated licensing agreement available here:
#   https://www.uipath.com/legal/trust-and-security/legal-terms (or successor website).
#   You must not use this file separately from the product it is a part of or is associated with.
#
#
#
# =================

fetch_hostname(){

    HOST_NAME_NODE=$(kubectl get nodes -o name | cut -d'/' -f2 | grep "$(hostname)")

    if ! [[ -n ${HOST_NAME_NODE} && "$(hostname)" == "$HOST_NAME_NODE" ]]; then
        for private_ip in $(hostname --all-ip-addresses); do
            output=$(kubectl get nodes -o jsonpath='{range .items[*]}{.metadata.name}{"\t"}{.status.addresses[?(@.type=="InternalIP")].address}{"\n"}{end}' | grep "$private_ip")
            ip_address=$(echo "$output" | cut -f2 -d$'\t')

            if [[ -n ${ip_address} && "$private_ip" == "$ip_address" ]]; then
                HOST_NAME_NODE=$(echo "$output" | cut -f1 -d$'\t')
                break
            fi
        done
    fi
}

set_kubeconfig(){
    export PATH=$PATH:/var/lib/rancher/rke2/bin:/usr/local/bin
    [[ -f "/var/lib/rancher/rke2/agent/kubelet.kubeconfig" ]] && export KUBECONFIG="/var/lib/rancher/rke2/agent/kubelet.kubeconfig"
    [[ -f "/etc/rancher/rke2/rke2.yaml" ]] && export KUBECONFIG="/etc/rancher/rke2/rke2.yaml"
}

is_kubectl_enabled(){
  local try=0
  local maxtry=60
  local status="notready"
  echo "Checking if node $HOST_NAME_NODE is ready to run kubectl command."
  while [[ ${status} == "notready" ]] && (( try != maxtry )) ; do
          try=$((try+1))
          kubectl cluster-info >/dev/null 2>&1  && status="ready"
          sleep 5;
  done

  if [[ ${status} == "notready" ]]; then
    echo "Node is not ready to accept kubectl command"
  else
    echo "Node is ready to accept kubectl command"
  fi
}

enable_ipforwarding() {
  local file_name="/etc/sysctl.conf"
  echo "Enable IP Forwarding..."

  if [[ ! -f "${file_name}" || -w "${file_name}" ]]; then
    # either file is not available or user doesn't have edit permission
    echo "Either file ${file_name} not present or file is not writable. Enabling ip forward using /proc/sys/net/ipv4/ip_forward..."
    echo 1 > /proc/sys/net/ipv4/ip_forward
  else
    echo "File ${file_name} is available and is writable. Checking and enabling ip forward..."
    is_ipforwarding_available=$(grep "net.ipv4.ip_forward" "${file_name}") || true
    if [[ -z ${is_ipforwarding_available} ]]; then
      echo "Adding net.ipv4.ip_forward = 1 in ${file_name}..."
      echo "net.ipv4.ip_forward = 1" >> ${file_name}
    else
      echo "Updating net.ipv4.ip_forward value with 1 in ${file_name}..."
      # shellcheck disable=SC2016
      sed -i -n -e '/^net.ipv4.ip_forward/!p' -e '$anet.ipv4.ip_forward = 1' ${file_name}
    fi
    sysctl -p
  fi
}

set_kubeconfig
is_kubectl_enabled
fetch_hostname

if [[ -n "$HOST_NAME_NODE" ]]; then
    # Pass an argument to uncordon the node. This is to cover reboot scenarios.
    if [ "$1" ]; then
        # enable ip forward
        enable_ipforwarding
        # uncordan node
        echo "Uncordon $HOST_NAME_NODE ..."
        kubectl uncordon "$HOST_NAME_NODE"
    else
        #If PDB is enabled and they are zero available replicas on other nodes, drain would fail for those pods but thats not the behaviour we want
        #Thats when the second command would come to rescue which will ignore the PDB and continue with the eviction of those pods for which eviction failed earlier https://github.com/kubernetes/kubernetes/issues/83307
        kubectl drain "$HOST_NAME_NODE" --delete-emptydir-data --ignore-daemonsets  --timeout=90s --skip-wait-for-delete-timeout=10 --force --ignore-errors || kubectl drain "$HOST_NAME_NODE" --delete-emptydir-data --ignore-daemonsets  --force  --disable-eviction=true --timeout=30s --ignore-errors --skip-wait-for-delete-timeout=10 --pod-selector 'app!=csi-attacher,longhorn.io/component!=instance-manager,k8s-app!=kube-dns'
        node_mounted_pv=$(kubectl get volumeattachment -o json | jq --arg node "${HOST_NAME_NODE}" -r '.items[] | select(.spec.nodeName==$node) | .metadata.name + ":" + .spec.source.persistentVolumeName')
        if [[ -n "${node_mounted_pv}" ]] ; then
          while IFS=$'\n' read -r VOL_ATTACHMENT_PV_ID
          do
            PV_ID=$(echo "${VOL_ATTACHMENT_PV_ID}" | cut -d':' -f2)
            VOL_ATTACHMENT_ID=$(echo "${VOL_ATTACHMENT_PV_ID}" | cut -d':' -f1)
            if [[ -n "${PV_ID}" ]] ; then
              mounts=$(grep "${PV_ID}" /proc/mounts  | awk '{print $2}')
              if [[ -n $mounts ]] ; then
                echo "Removing dangling mounts for pvc: ${PV_ID}"
                {
                  timeout 20s xargs umount -l <<< "${mounts}"
                  exitCode="$?"
                  if [[ $exitCode -eq 0 ]] ; then
                    echo "Command to remove dangling mounts for pvc ${PV_ID} executed successfully"
                    echo "Waiting to remove dangling mounts for pvc ${PV_ID}"
                    if timeout 1m bash -c "while grep -q '${PV_ID}' /proc/mounts ; do sleep 1 ; done"  ; then
                      kubectl delete volumeattachment "${VOL_ATTACHMENT_ID}"
                      if timeout 2m bash -c "while kubectl get node '${HOST_NAME_NODE}' -o yaml | grep -q '${PV_ID}' ; do sleep 1 ; done" ; then
                      #shellcheck disable=SC1012
                        find /var/lib/kubelet -name "${PV_ID}" -print0 | xargs -0 \rm -rf
                        echo "Removed dangling mounts for pvc: ${PV_ID} successfully"
                      else
                       echo "Timeout while waiting to remove node dangling mounts for pvc: ${PV_ID}"
                     fi
                    else
                      echo "Timeout while waiting to remove dangling mounts for pvc: ${PV_ID}"
                    fi
                  elif [[ $exitCode -eq 124 ]] ; then
                    echo "Timeout while executing remove dangling mounts for pvc: ${PV_ID}"
                  else
                    echo "Error while executing remove dangling mounts for pvc: ${PV_ID}"
                  fi
                } &
              fi
            fi
          done <<< "${node_mounted_pv}"
          wait
        fi
    fi
else
  echo "Not able to fetch hostname"
fi