A failover script for dual WAN with dual interfaces, using a ping healthcheck and managing default routes appropriately, with antiflap and back to normal state availability

failover.sh

#!/bin/bash

# Set defaults if not provided by environment
CHECK_DELAY=${CHECK_DELAY:-5}
CHECK_LOOPS_FAIL=${CHECK_LOOPS_FAIL:-3}
CHECK_LOOPS_REVERT=${CHECK_LOOPS_REVERT:-5}
CHECK_IP=${CHECK_IP:-8.8.8.8}
PRIMARY_IF=${PRIMARY_IF:-enp0s17}
PRIMARY_GW=${PRIMARY_GW:-192.168.1.252}
BACKUP_IF=${BACKUP_IF:-enp0s18}
BACKUP_GW=${BACKUP_GW:-192.168.100.1}

# Compare arg with current default gateway interface for route to healthcheck IP
gateway_if() {
  [[ "$1" = "$(ip r g "$CHECK_IP" | sed -rn 's/^.*dev ([^ ]*).*$/\1/p')" ]]
}

ip route del ${CHECK_IP} via ${PRIMARY_GW}
LOOP_FAIL=0
LOOP_REVERT=0

# Cycle healthcheck continuously with specified delay
while sleep "$CHECK_DELAY"
do
  # If healthcheck succeeds from primary interface
  ip route add ${CHECK_IP} via ${PRIMARY_GW}
  if ping -I "$PRIMARY_IF" -c1 "$CHECK_IP" &>/dev/null
  then
    ip route del ${CHECK_IP} via ${PRIMARY_GW}
    # Are we using the backup?
    if gateway_if "$BACKUP_IF"
    then # anti-flap
      LOOP_REVERT=$(( $LOOP_REVERT + 1 ))
      if [[ $LOOP_REVERT -le $CHECK_LOOPS_REVERT ]] ; then echo $(date +'%Y-%m-%d %H:%M:%S') " : check successful ! (${LOOP_REVERT}/${CHECK_LOOPS_REVERT})" ; fi
      if [[ $LOOP_REVERT -ge $CHECK_LOOPS_REVERT ]]
      then # swith to primary
        echo $(date +'%Y-%m-%d %H:%M:%S') " : reverting to primary after ${LOOP_REVERT} checks successful"
        ip r d default via "$BACKUP_GW" dev "$BACKUP_IF"
        ip r a default via "$PRIMARY_GW" dev "$PRIMARY_IF"
        LOOP_FAIL=0
      fi
    else LOOP_FAIL=0
    fi
  else
    ip route del ${CHECK_IP} via ${PRIMARY_GW}
    LOOP_FAIL=$(( $LOOP_FAIL + 1 ))
    if [[ $LOOP_FAIL -le $CHECK_LOOPS_FAIL ]] ; then echo $(date +'%Y-%m-%d %H:%M:%S') " : check ${LOOP_FAIL}/${CHECK_LOOPS_FAIL} failed" ; fi
    if [[ $LOOP_FAIL -ge $CHECK_LOOPS_FAIL ]]
    then
      # Are we using the primary?
      if gateway_if "$PRIMARY_IF"
      then # Switch to backup
        echo $(date +'%Y-%m-%d %H:%M:%S') " : switching to backup"
        ip r d default via "$PRIMARY_GW" dev "$PRIMARY_IF"
        ip r a default via "$BACKUP_GW" dev "$BACKUP_IF"
        LOOP_REVERT=0
      else LOOP_REVERT=0
      fi
    fi
  fi
done