cd /usr/local/nagiosxi/scripts
./reconfigure_nagios.sh
Former Nagios employee
"It is turtles. All. The. Way. Down. . . .and maybe an elephant or two."
VI VI VI - The editor of the Beast!
Come to the Dark Side.
abrist wrote:What distro and version are you running on your XI box?
There have been some issues with sudo and the reconfigure script. What is the output of:
[nagios@nagiosprodxi1 debug]$ service nagios status
nagios is not running
[nagios@nagiosprodxi1 debug]$ service nagios restart
Running configuration check...done.
Stopping nagios: /etc/init.d/nagios: line 67: kill: (4330) - No such process
done.
Starting nagios: done.
[nagios@nagiosprodxi1 debug]$ service nagios status
nagios (pid 21003) is running...
[nagios@nagiosprodxi1 init.d]$ cat nagios
#!/bin/sh
#
# chkconfig: 345 99 01
# description: Nagios network monitor
#
# File : nagios
#
# Author : Jorge Sanchez Aymar ([email protected])
#
# Changelog :
#
# 1999-07-09 Karl DeBisschop <[email protected]>
# - setup for autoconf
# - add reload function
# 1999-08-06 Ethan Galstad <[email protected]>
# - Added configuration info for use with RedHat's chkconfig tool
# per Fran Boon's suggestion
# 1999-08-13 Jim Popovitch <[email protected]>
# - added variable for nagios/var directory
# - cd into nagios/var directory before creating tmp files on startup
# 1999-08-16 Ethan Galstad <[email protected]>
# - Added test for rc.d directory as suggested by Karl DeBisschop
# 2000-07-23 Karl DeBisschop <[email protected]>
# - Clean out redhat macros and other dependencies
# 2003-01-11 Ethan Galstad <[email protected]>
# - Updated su syntax (Gary Miller)
#
# Description: Starts and stops the Nagios monitor
# used to provide network services status.
#
status_nagios ()
{
if test -x $NagiosCGI/daemonchk.cgi; then
if $NagiosCGI/daemonchk.cgi -l $NagiosRunFile; then
return 0
else
return 1
fi
else
if ps -p $NagiosPID > /dev/null 2>&1; then
return 0
else
return 1
fi
fi
return 1
}
printstatus_nagios()
{
if status_nagios $1 $2; then
echo "nagios (pid $NagiosPID) is running..."
else
echo "nagios is not running"
fi
}
killproc_nagios ()
{
kill $2 $NagiosPID
}
pid_nagios ()
{
if test ! -f $NagiosRunFile; then
echo "No lock file found in $NagiosRunFile"
exit 1
fi
NagiosPID=`head -n 1 $NagiosRunFile`
}
# Source function library
# Solaris doesn't have an rc.d directory, so do a test first
if [ -f /etc/rc.d/init.d/functions ]; then
. /etc/rc.d/init.d/functions
elif [ -f /etc/init.d/functions ]; then
. /etc/init.d/functions
fi
prefix=/usr/local/nagios
exec_prefix=${prefix}
NagiosBin=${exec_prefix}/bin/nagios
NagiosCfgFile=${prefix}/etc/nagios.cfg
NagiosStatusFile=${prefix}/var/status.dat
NagiosRetentionFile=${prefix}/var/retention.dat
NagiosCommandFile=${prefix}/var/rw/nagios.cmd
NagiosVarDir=${prefix}/var
NagiosRunFile=${prefix}/var/nagios.lock
#NagiosLockDir=/var/lock/subsys
NagiosLockDir=/usr/local/nagiosxi/var/subsys
NagiosLockFile=nagios
NagiosCGIDir=${exec_prefix}/sbin
NagiosUser=nagios
NagiosGroup=nagios
# Check that nagios exists.
if [ ! -f $NagiosBin ]; then
echo "Executable file $NagiosBin not found. Exiting."
exit 1
fi
# Check that nagios.cfg exists.
if [ ! -f $NagiosCfgFile ]; then
echo "Configuration file $NagiosCfgFile not found. Exiting."
exit 1
fi
# See how we were called.
case "$1" in
start)
echo -n "Starting nagios:"
$NagiosBin -v $NagiosCfgFile > /dev/null 2>&1;
if [ $? -eq 0 ]; then
# THESE TWO LINES WERE ADDED TO WORK WITH SUDO
touch $NagiosVarDir/nagios.log $NagiosRetentionFile
chown $NagiosUser $NagiosVarDir/nagios.log $NagiosRetentionFile
# su - $NagiosUser -c "touch $NagiosVarDir/nagios.log $NagiosRetentionFile"
rm -f $NagiosCommandFile
touch $NagiosRunFile
chown $NagiosUser:$NagiosGroup $NagiosRunFile
$NagiosBin -d $NagiosCfgFile
if [ -d $NagiosLockDir ]; then
touch $NagiosLockDir/$NagiosLockFile;
chown $NagiosUser:$NagiosGroup $NagiosLockDir/$NagiosLockFile;
fi
echo " done."
exit 0
else
echo "CONFIG ERROR! Start aborted. Check your Nagios configuration."
exit 1
fi
;;
stop)
echo -n "Stopping nagios: "
pid_nagios
killproc_nagios nagios
# now we have to wait for nagios to exit and remove its
# own NagiosRunFile, otherwise a following "start" could
# happen, and then the exiting nagios will remove the
# new NagiosRunFile, allowing multiple nagios daemons
# to (sooner or later) run - John Sellens
#echo -n 'Waiting for nagios to exit .'
for i in 1 2 3 4 5 6 7 8 9 10 ; do
if status_nagios > /dev/null; then
echo -n '.'
sleep 1
else
break
fi
done
if status_nagios > /dev/null; then
echo ''
echo 'Warning - nagios did not exit in a timely manner'
else
# Forcefully kill all other nagios processes that might be running, so we don't end up with a wierd setup
# Get a list of PIDs for all running Nagios daemons
plist=`ps axuw | grep "/usr/local/nagios/bin/nagios -d" | awk '{print $2}'`
#echo "PIDS"
#echo $plist
for pid in $plist; do
#echo "KILL $pid"
kill -9 $pid > /dev/null 2>&1
done
echo 'done.'
fi
rm -f $NagiosStatusFile $NagiosRunFile $NagiosLockDir/$NagiosLockFile $NagiosCommandFile
;;
status)
pid_nagios
printstatus_nagios nagios
;;
checkconfig)
printf "Running configuration check..."
$NagiosBin -v $NagiosCfgFile > /dev/null 2>&1;
if [ $? -eq 0 ]; then
echo " OK."
else
echo " CONFIG ERROR! Check your Nagios configuration."
exit 1
fi
;;
restart)
printf "Running configuration check..."
$NagiosBin -v $NagiosCfgFile > /dev/null 2>&1;
if [ $? -eq 0 ]; then
echo "done."
$0 stop
$0 start
else
echo " CONFIG ERROR! Restart aborted. Check your Nagios configuration."
exit 1
fi
;;
reload|force-reload)
printf "Running configuration check..."
$NagiosBin -v $NagiosCfgFile > /dev/null 2>&1;
if [ $? -eq 0 ]; then
echo "done."
if test ! -f $NagiosRunFile; then
$0 start
else
pid_nagios
if status_nagios > /dev/null; then
printf "Reloading nagios configuration..."
killproc_nagios nagios -HUP
echo "done"
else
$0 stop
$0 start
fi
fi
else
echo " CONFIG ERROR! Reload aborted. Check your Nagios configuration."
exit 1
fi
;;
*)
echo "Usage: nagios {start|stop|restart|reload|force-reload|status|checkconfig}"
exit 1
;;
esac
# End of this script
FYI, I have resolved the Monitoring Event Queue and Monitoring Engine Statistics issue.
Removed the sed commands left over from version 1.2 and it is back to normal.
Fixed one problem and got another.
All the graphs are dead since I took out the sed command.
This is because of the \n in the perfdata.
I thought this was fixed already?