Rolling restart of all nodes in an AKS cluster

aks-restart-nodes.sh

#!/bin/bash

set -e

resourceGroupDefault='<set your default here, to avoid having to specify in the common case>'
resourceGroup=${RESOURCE_GROUP:-$resourceGroupDefault}
clusterNameDefault='<set your default here>'
clusterName=${CLUSTER_NAME:-$clusterNameDefault}
regionDefault='<set your default here>'
region=${REGION:-$regionDefault}
force=false
dryrun=false
nodes=''

function print_usage() {
  echo "Usage: $0 [<options>]"
  echo ""
  echo "-n|--node <node>                    The name of a node to restart."
  echo "                                    By default, a rolling restart of all nodes"
  echo "                                    is performed."
  echo ""
  echo "--resource-group <group-name>       The resource group of the cluster."
  echo "                                    Can also be set by RESOURCE_GROUP"
  echo "                                    Default: $resourceGroupDefault"
  echo ""
  echo "--cluster-name <cluster-name>       The name of the cluster."
  echo "                                    Can also be set by CLUSTER_NAME"
  echo "                                    Default: $clusterNameDefault"
  echo ""
  echo "--region <azure-region>             The Azure region in which the cluster is."
  echo "                                    Can also be set by REGION"
  echo "                                    Default: $regionDefault"
  echo ""
  echo "-f|--force                          Restart node(s) without first draining."
  echo "                                    Useful if draining a node fails."
  echo ""
  echo "-d|--dry-run                        Just print what to do; don't actually do it"
  echo ""
  echo "-h|--help                           Print usage and exit."
}

while [[ $# -gt 0 ]]
do
  key="$1"

  case $key in
    -n|--node)
    node="$2"
    shift
    shift
    ;;
    --resource-group)
    resourceGroup="$2"
    shift
    shift
    ;;
    --cluster-name)
    clusterName="$2"
    shift
    shift
    ;;
    --region)
    region="$2"
    shift
    shift
    ;;
    -f|--force)
    force=true
    shift
    ;;
    --dry-run)
    dryrun=true
    shift
    ;;
    -h|--help)
    print_usage
    exit 0
    ;;
    *)
    print_usage
    exit 1
    ;;
  esac
done

group="MC_${resourceGroup}_${clusterName}_$region"

function wait_for_status() {
  node=$1
  reason=$2
  i=0
  while [[ $i -lt 30 ]]; do
    status=$(kubectl get node $node -o "jsonpath={.status.conditions[?(.reason==\"$reason\")].type}")
    if [[ "$status" == "Ready" ]]; then
      echo "$reason after $((i*2)) seconds"
      break;
    else
      sleep 2s
      i=$(($i+1))
    fi
  done
  if [[ $i == 30 ]]; then
    echo "Error: Did not reach $reason state within 1 minute"
    exit 1
  fi
}

if [ -z "$node" ]; then
  nodes=$(kubectl get nodes -o jsonpath={.items[*].metadata.name})
else
  nodes="$node"
fi

for node in $nodes; do
  if $force; then
    echo "WARNING: --force specified, restarting node $node without draining first"
    if $dryrun; then
      echo "kubectl cordon $node"
    else
      kubectl cordon "$node"
    fi
  else
    echo "Draining $node..."
    if $dryrun; then
      echo "kubectl drain $node --ignore-daemonsets --delete-local-data"
    else
      kubectl drain "$node" --ignore-daemonsets --delete-local-data
    fi
  fi

  echo "Initiating VM restart for $node..."
  if $dryrun; then
    echo "az vm restart --resource-group $group --name $node"
  else
    az vm restart --resource-group "$group" --name "$node"
  fi

  if ! $dryrun; then
    echo "Waiting for $node to start back up..."
    wait_for_status $node KubeletNotReady
    wait_for_status $node KubeletReady
  fi

  echo "Re-enabling $node for scheduling"

  if $dryrun; then
    echo "kubectl uncordon $node"
  else
    kubectl uncordon "$node"
  fi
done

@tomasaschan, you're correct that it would result in downtime. I just wanted anyone following this that hadn't noticed to know that AKS start/stop is now an option and supported by MS.