#!/usr/bin/ksh
#
# Nagios check script for Sun Cluster.
# Written by Thomas Sluyter (nagios@kilala.nl)
# By request of KPN-IS, i-Provide SYS, the Netherlands
# Last Modified: 25-09-2006
#
# Usage: ./check_suncluster [-t, -q, -g, -G resource-group, -r, -R resource, -i]
#
# Description:
# This script is capable of performing a number of basic checks on a 
# system running Sun Cluster. Depending on the parameter you pass to 
# it, it will check:
# * Transport paths (-t).
# * Quorum (-q).
# * Resource groups (-g).
# * One selected resource group (-G).
# * Resources (-r).
# * One selected resource (-R).
# * IPMP groups (-i).
#
# Limitations:
# This script will only work with Korn shell, due to some funky while
# looping with pipe forking. Bash doesn't handle this very gracefully,
# due to its sub-shell variable scoping. Maybe I really should learn
# to program in Perl.   
#
# Output:
# * Transport paths return a WARN when one of the paths is down and a
#   CRIT when all paths are offline. 
# * Quorum returns a WARN when not all, but enough quorum devices are
#   available. It returns a CRIT when quorum cannot be reached.
# * Resource groups returns a CRIT when a group is offline on all nodes
#   and a WARN if a group is in an unstable state.
# * Resources returns a CRIT when a resource is offline on all nodes
#   and a WARN if a resource is in an unstable state.
# * IPMP groups returns a CRIT when a group is offline.
#
# Other notes:
# Aside from the debugging output that I've built into most of my recent
# scripts, this check script will also have a testing mode  hacked on, as
# a bag on the side. This testing mode is only engaged when the test_check_suncluster
# script is being run and will intentionally "break" a few things, to 
# verify the failure options of this check script.
#

# Enabling the following dumps information into DEBUGFILE at various
# stages during the execution of this script.
DEBUG=0
DEBUGFILE="/tmp/foobar"

if [ -f /tmp/neko-wa-baka ]
then
	if [ `cat /tmp/neko-wa-baka` == "Nyo!" ]
	then
	   TESTING="1"
	else
	   TESTING="0"
	fi
else
	TESTING="0"
fi


### REQUISITE NAGIOS USER INTERFACE STUFF ###

# You may have to change this, depending on where you installed your
# Nagios plugins
PATH="/usr/bin:/usr/sbin:/bin:/sbin:/usr/cluster/bin"
LIBEXEC="/usr/local/nagios/libexec"
PROGNAME="check_suncluster"
. $LIBEXEC/utils.sh

[ $DEBUG -gt 0 ] && rm $DEBUGFILE 

print_usage() {
        echo "Usage: $PROGNAME [-t, -q, -g, -G resource-group, -r, -R resource, -i]"
        echo "Usage: $PROGNAME --help"
}

print_help() {
        echo ""
        print_usage
        echo ""
        echo "Sun Cluster check plugin for Nagios"
        echo ""
        echo "-t: check transport paths"
        echo "-q: check quorum"
        echo "-g: check resource groups"
        echo "-G: check one individual resource group"
        echo "-r: check all resources"
        echo "-R: check one individual resources"
        echo "-i: check IPMP groups"
        echo ""
        echo "This plugin not developped by the Nagios Plugin group."
        echo "Please do not e-mail them for support on this plugin, since"
        echo "they won't know what you're talking about :P"
        echo ""
        echo "For contact info, read the plugin itself..."
}


### SUB-ROUTINE DEFINITIONS ### 

function check_transport_paths
{
[ $DEBUG -gt 0 ] && echo "Starting check_transport_path subroutine." >> $DEBUGFILE

	TOTAL=`scstat -W | grep "Transport path:" | wc -l`
	let COUNT=0

	scstat -W | grep "Transport path:" | awk '{print $3" "$6}' | while read PATH STATUS
	do
[ $DEBUG -gt 0 ] && echo "Before math, Count has the value of $COUNT." >> $DEBUGFILE
		if [ $STATUS == "online" ]
		then
		   let COUNT=$COUNT+1
		fi
[ $DEBUG -gt 0 ] && echo "Path: $PATH has status $STATUS" >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Count: $COUNT online transport paths." >> $DEBUGFILE
	done

[ $DEBUG -gt 0 ] && echo "Count: Outside the loop it has a value of $COUNT." >> $DEBUGFILE
[ $TESTING -gt 0 ] && COUNT="0"

	if [ $COUNT -lt 1 ]
	then
	   echo "NOK - No transport paths online."
	   exit $STATE_CRITICAL
	elif [ $COUNT -lt $TOTAL ]
	then
	   echo "NOK - One or more transport paths offline."
	   exit $STATE_WARNING
	fi
}

function check_quorum
{
[ $DEBUG -gt 0 ] && echo "Starting check_quorum subroutine." >> $DEBUGFILE
	NEED=`scstat -q | grep "votes needed:" | awk '{print $4}'`
	PRES=`scstat -q | grep "votes present:" | awk '{print $4}'`

[ $DEBUG -gt 0 ] && echo "Quorum needed: $NEED" >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Quorum present: $PRES" >> $DEBUGFILE

[ $TESTING -gt 0 ] && PRES="0"
	if [ $PRES -ge $NEED ]
	then
[ $DEBUG -gt 0 ] && echo "Enough quorum votes." >> $DEBUGFILE
		scstat -q | grep "votes:" | awk '{print $3" "$6}' | while read VOTE STATUS
		do
[ $DEBUG -gt 0 ] && echo "Vote: $VOTE has status $STATUS." >> $DEBUGFILE
			if [ $STATUS != "Online" ] 
			then
			   echo "NOK - Quorum vote $VOTE not available."
			   exit $STATE_WARNING
			fi
		done		
	else
[ $DEBUG -gt 0 ] && echo "Not enough quorum." >> $DEBUGFILE
		echo "NOK - Not enough quorum votes present."
		exit $STATE_CRITICAL
	fi
}

function check_resource_groups
{
[ $DEBUG -gt 0 ] && echo "Starting check_resource_groups subroutine." >> $DEBUGFILE
	scstat -g | grep "Group:" | awk '{print $2}' | sort -u | while read GROUP
	do
	ONLINE=`scstat -g | grep "Group: $GROUP" | grep "Online" | wc -l`
	WEIRD=`scstat -g | grep "Group: $GROUP" | grep -v "Resources" | grep -v "Online" | grep -v "Offline" | wc -l`
[ $DEBUG -gt 0 ] && echo "Resource Group $GROUP has $ONLINE instances online." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Resource Group $GROUP has $WEIRD instances in a weird state." >> $DEBUGFILE
[ $TESTING -gt 0 ] && ONLINE="0"
		if [ $ONLINE -lt 1 ] 
		then
		   echo "NOK - Resource group $GROUP not online."
		   exit $STATE_CRITICAL
		fi
                if [ $WEIRD -gt 1 ]
                then
                   echo "NOK - Resource group $GROUP is an unstable state."
                   exit $STATE_WARNING
                fi
	done
}

function check_resource_grp
{
[ $DEBUG -gt 0 ] && echo "Starting check_resource_grp subroutine." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Selected group: $RGROUP" >> $DEBUGFILE
	ONLINE=`scstat -g | grep $RGROUP | grep "Online" | wc -l`
	WEIRD=`scstat -g | grep $RGROUP | grep -v "Resources" | grep -v "Online" | grep -v "Offline" | wc -l`
[ $DEBUG -gt 0 ] && echo "Resource Group $GROUP has $ONLINE instances online." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Resource Group $GROUP has $WEIRD instances in a weird state." >> $DEBUGFILE
[ $TESTING -gt 0 ] && ONLINE="0"
	if [ $ONLINE -lt 1 ] 
	then
	   echo "NOK - Resource group $RGROUP not online."
	   exit $STATE_CRITICAL
	fi
	if [ $WEIRD -gt 1 ]
        then
           echo "NOK - Resource group $RGROUP is in an unstable state."
           exit $STATE_WARNING
        fi
}

function check_resources
{
[ $DEBUG -gt 0 ] && echo "Starting check_resources subroutine." >> $DEBUGFILE
	RESOURCES=`scstat -g | grep "Resource:" | awk '{print $2}' | sort -u`
[ $DEBUG -gt 0 ] && echo "List of resources to check: $RESOURCES" >> $DEBUGFILE
	for RESOURCE in `echo $RESOURCES`
	do
	ONLINE=`scstat -g | grep "Resource: $RESOURCE" | awk '{print $4}' | grep "Online" | wc -l` 
	WEIRD=`scstat -g | grep "Resource: $RESOURCE" | awk '{print $4}' | grep -v "Online" | grep -v "Offline" | wc -l`
[ $DEBUG -gt 0 ] && echo "Resource $RESOURCE has $ONLINE instances online." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Resource $RESOURCE has $WEIRD instances in a weird state." >> $DEBUGFILE
[ $TESTING -gt 0 ] && ONLINE="0"
		if [ $ONLINE -lt 1 ] 
		then
		   echo "NOK - Resource $RESOURCE not online."
		   exit $STATE_CRITICAL
		fi
                if [ $WEIRD -gt 1 ]
                then
                   echo "NOK - Resource $RESOURCE is in an unstable state."
                   exit $STATE_WARNING
                fi
	done
}

function check_rsrce
{
[ $DEBUG -gt 0 ] && echo "Starting check_rsrce subroutine." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Selected resource: $RSRCE" >> $DEBUGFILE
	ONLINE=`scstat -g | grep "Resource: $RSRCE" | awk '{print $4}' | grep "Online" | wc -l`
	WEIRD=`scstat -g | grep "Resource: $RSRCE" | awk '{print $4}' | grep -v "Online" | grep -v "Offline" | wc -l`
[ $DEBUG -gt 0 ] && echo "Resource $RESOURCE has $ONLINE instances online." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "Resource $RESOURCE has $WEIRD instances in a weird state." >> $DEBUGFILE
[ $TESTING -gt 0 ] && ONLINE="0"
	if [ $ONLINE -lt 1 ] 
	then
	   echo "NOK - Resource $RESOURCE not online."
	   exit $STATE_CRITICAL
	fi
	if [ $WEIRD -gt 1 ]
        then
           echo "NOK - Resource $RESOURCE is in an unstable state."
           exit $STATE_WARNING
        fi
}

function check_ipmp
{
[ $DEBUG -gt 0 ] && echo "Starting check_ipmp subroutine." >> $DEBUGFILE
	scstat -i | grep "IPMP Group:" | awk '{print $3" "$5}' | while read GROUP STATUS
	do
[ $DEBUG -gt 0 ] && echo "IPMP Group: $GROUP has status $STATUS" >> $DEBUGFILE
		if [ $STATUS != "Online" ] 
		then
		   echo "NOK - IPMP group $GROUP not online."
		   exit $STATE_CRITICAL
		fi
if [ $TESTING -gt 0 ]
then
   echo "NOK - IPMP group $GROUP not online."
   exit $STATE_CRITICAL
fi
	done
}

### THE MAIN ROUTINE FINALLY STARTS ###

[ $DEBUG -gt 0 ] && echo "Starting main routine." >> $DEBUGFILE

if [ $# -lt 1 ]
then
	print_usage
	exit $STATE_UNKNOWN
fi

[ $DEBUG -gt 0 ] && echo "More than one argument." >> $DEBUGFILE
[ $DEBUG -gt 0 ] && echo "" >> $DEBUGFILE

case "$1" in
	--help) print_help; exit $STATE_OK;;
	-h) print_help; exit $STATE_OK;;
	-t) check_transport_paths;;
	-q) check_quorum;;
	-g) check_resource_groups;;
	-G) RGROUP="$2"; check_resource_grp;;
	-r) check_resources;;
	-R) RSRCE="$2"; check_rsrce;;
	-i) check_ipmp;;
	*) print_usage; exit $STATE_UNKNOWN;;
esac

[ $DEBUG -gt 0 ] && echo "No problems. Exiting normally." >> $DEBUGFILE

# None of the other subroutines forced us to exit 1 before here, so let's quit with a 0.
echo "OK - Everything running like it should"
exit $STATE_OK