#!/bin/sh

# this script needs to be installed so that statd points to it with the -H 
# command line argument. The easiest way to do that is to put something like this in 
# /etc/sysconfig/nfs:
#   STATD_HOSTNAME="myhostname -H /etc/ctdb/statd-callout"

[ -z "$CTDB_BASE" ] && {
    export CTDB_BASE="/etc/ctdb"
}

[ -z "$CTDB_VARDIR" ] && {
    export CTDB_VARDIR="/var/lib/ctdb"
}

. $CTDB_BASE/functions
loadconfig ctdb
loadconfig nfs

[ -z $NFS_HOSTNAME ] && {
	echo NFS_HOSTNAME is not configured. statd-callout failed.
	exit 0
}

case "$1" in
  add-client)
	# the callout does not tell us to which ip the client connected
	# so we must add it to all the ips that we serve
	PNN=`ctdb xpnn | sed -e "s/.*://"`
	ctdb ip -Y | while read LINE; do
		NODE=`echo $LINE | cut -f3 -d:`
		[ "$NODE" = "$PNN" ] || {
			# not us
			continue
		} 
		IP=`echo $LINE | cut -f2 -d:`
		/bin/mkdir -p $CTDB_VARDIR/state/statd/ip/$IP
		touch $CTDB_VARDIR/state/statd/ip/$IP/$2
	done
	;;
  del-client)
	# the callout does not tell us to which ip the client disconnected
	# so we must remove it from all the ips that we serve
	PNN=`ctdb xpnn | sed -e "s/.*://"`
	ctdb ip -Y | while read LINE; do
		NODE=`echo $LINE | cut -f3 -d:`
		[ "$NODE" = "$PNN" ] || {
			# not us
			continue
		} 
		IP=`echo $LINE | cut -f2 -d:`
		mkdir -p $CTDB_VARDIR/state/statd/ip/$IP
		/bin/rm -f $CTDB_VARDIR/state/statd/ip/$IP/$2
	done
	;;
  updatelocal)
	# For all IPs we serve, collect info and push to the config database
	PNN=`ctdb xpnn | sed -e "s/.*://"`
	ctdb ip -Y | tail -n +2 | while read LINE; do
		NODE=`echo $LINE | cut -f3 -d:`
		[ "$NODE" = "$PNN" ] || {
			continue
		} 
		IP=`echo $LINE | cut -f2 -d:`

		mkdir -p $CTDB_VARDIR/state/statd/ip/$IP

		rm -f $CTDB_VARDIR/state/statd/ip/$IP.tar
		tar cfP $CTDB_VARDIR/state/statd/ip/$IP.tar $CTDB_VARDIR/state/statd/ip/$IP

		rm -f $CTDB_VARDIR/state/statd/ip/$IP.rec
		ctdb pfetch ctdb.tdb statd-state:$IP $CTDB_VARDIR/state/statd/ip/$IP.rec 2>/dev/null
		[ "$?" = "0" ] || {
			# something went wrong,  try storing this data
			echo No record. Store STATD state data for $IP
			ctdb pstore ctdb.tdb statd-state:$IP $CTDB_VARDIR/state/statd/ip/$IP.tar 2>/dev/null
			continue
		}

		cmp $CTDB_VARDIR/state/statd/ip/$IP.tar $CTDB_VARDIR/state/statd/ip/$IP.rec >/dev/null 2>/dev/null
		[ "$?" = "0" ] || {
			# something went wrong,  try storing this data
			echo Updated record. Store STATD state data for $IP
			ctdb pstore ctdb.tdb statd-state:$IP $CTDB_VARDIR/state/statd/ip/$IP.tar 2>/dev/null
			continue
		}
	done
	;;

  updateremote)
	# For all IPs we dont serve, pull the state from the database
	PNN=`ctdb xpnn | sed -e "s/.*://"`
	ctdb ip -Y | tail -n +2 | while read LINE; do
		NODE=`echo $LINE | cut -f3 -d:`
		[ "$NODE" = "$PNN" ] && {
			continue
		} 
		IP=`echo $LINE | cut -f2 -d:`

		mkdir -p $CTDB_VARDIR/state/statd/ip/$IP

		rm -f $CTDB_VARDIR/state/statd/ip/$IP.rec
		ctdb pfetch ctdb.tdb statd-state:$IP $CTDB_VARDIR/state/statd/ip/$IP.rec 2>/dev/null
		[ "$?" = "0" ] || {
			continue
		}

		rm -f $CTDB_VARDIR/state/statd/ip/$IP/*
		tar xfP $CTDB_VARDIR/state/statd/ip/$IP.rec
	done
	;;

  notify)
	# we must restart the lockmanager (on all nodes) so that we get
	# a clusterwide grace period (so other clients dont take out
	# conflicting locks through other nodes before all locks have been
	# reclaimed)

	# we need these settings to make sure that no tcp connections survive
	# across a very fast failover/failback
	#echo 10 > /proc/sys/net/ipv4/tcp_fin_timeout
	#echo 0 > /proc/sys/net/ipv4/tcp_max_tw_buckets
	#echo 0 > /proc/sys/net/ipv4/tcp_max_orphans

	# Delete the notification list for statd, we dont want it to 
	# ping any clients
	rm -f /var/lib/nfs/statd/sm/*
	rm -f /var/lib/nfs/statd/sm.bak/*

	# we must keep a monotonically increasing state variable for the entire
	# cluster  so state always increases when ip addresses fail from one
	# node to another
	# We use epoch and hope the nodes are close enough in clock.
	# Even numbers mean service is shut down, odd numbers mean
	# service is started.
	STATE=`date +"%s"`
	STATE=`expr "$STATE" "/" "2"`


	# we must also let some time pass between stopping and restarting the
	# lockmanager since othervise there is a window where the lockmanager
	# will respond "strangely" immediately after restarting it, which
	# causes clients to fail to reclaim the locks.
	# 
	startstop_nfslock stop > /dev/null 2>&1
	sleep 2

	# now start lockmanager again with the new state directory.
	startstop_nfslock start > /dev/null 2>&1

	# we now need to send out additional statd notifications to ensure
	# that clients understand that the lockmanager has restarted.
	# we have three cases:
	# 1, clients that ignore the ip address the stat notification came from
	#    and ONLY care about the 'name' in the notify packet.
	#    these clients ONLY work with lock failover IFF that name
	#    can be resolved into an ipaddress that matches the one used
	#    to mount the share.  (==linux clients)
	#    This is handled when starting lockmanager above,  but those
	#    packets are sent from the "wrong" ip address, something linux
	#    clients are ok with, buth other clients will barf at.
	# 2, Some clients only accept statd packets IFF they come from the
	#    'correct' ip address.
	# 2a,Send out the notification using the 'correct' ip address and also
	#    specify the 'correct' hostname in the statd packet.
	#    Some clients require both the correct source address and also the
	#    correct name. (these clients also ONLY work if the ip addresses
	#    used to map the share can be resolved into the name returned in
	#    the notify packet.)
	# 2b,Other clients require that the source ip address of the notify
	#    packet matches the ip address used to take out the lock.
	#    I.e. that the correct source address is used.
	#    These clients also require that the statd notify packet contains
	#    the name as the ip address used when the lock was taken out.
	#
	# Both 2a and 2b are commonly used in lockmanagers since they maximize
	# probability that the client will accept the statd notify packet and
	# not just ignore it.
	# For all IPs we serve, collect info and push to the config database
	PNN=`ctdb xpnn | sed -e "s/.*://"`
	ctdb ip -Y | tail -n +2 | while read LINE; do
		NODE=`echo $LINE | cut -f3 -d:`
		[ "$NODE" = "$PNN" ] || {
			continue
		} 
		IP=`echo $LINE | cut -f2 -d:`

		ls $CTDB_VARDIR/state/statd/ip/$IP | while read CLIENT; do
			rm $CTDB_VARDIR/state/statd/ip/$IP/$CLIENT
			/usr/bin/smnotify --client=$CLIENT --ip=$IP --server=$ip --stateval=$STATE
			/usr/bin/smnotify --client=$CLIENT --ip=$IP --server=$NFS_HOSTNAME --stateval=$STATE
			STATE=`expr "$STATE" "+" "1"`
			/usr/bin/smnotify --client=$CLIENT --ip=$IP --server=$ip --stateval=$STATE
			/usr/bin/smnotify --client=$CLIENT --ip=$IP --server=$NFS_HOSTNAME --stateval=$STATE
		done
	done
	;;
esac