So I'm trying to fix the init script that comes with nagios. It
fundamentally relies upon a program which doesn't come with the RPM,
wouldn't work if it did, and that cannot be compiled from source. So...
When I start nagios, I want to capture the PID to sock away in a
runfile. This was a little problematic because ps likes to add spaces
to the beginning of the PID so the right edges will line up in the
output. "ps -C nagios", however, returns a line with the PID aligned to
the left, so I'm in like Flynn, right? Wrong!
>From the command line, sudo /usr/bin/nagios -d /etc/nagios/nagios.cfg &&
ps -C nagios returns one line of output. Inside of the init script,
though, I wind up with three lines, and I'll be damned if I know why. I
munged around that by redirecting the output to a temp file and tailing
that temp file into the runfile, and that seems to be working. But I
dislike kludges.
Does anyone else use nagios with an init script? How did you make it
work? Here's what I wound up with:
#!/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)
# 2008-04-03 John Oliver
# - Removed daemoncheck nonsense so script actually works
#
# Description: Starts and stops the Nagios monitor
# used to provide network services status.
#
status_nagios ()
{
if ps -p $NagiosPID > /dev/null 2>&1; then
return 0
else
return 1
fi
}
printstatus_nagios()
{
if status_nagios $1 ; then
echo "nagios (pid $NagiosPID) is running..."
else
echo "nagios is not running"
fi
}
killproc_nagios ()
{
kill $2 $NagiosPID
}
pid_nagios ()
{
if test ! -s $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
exec_prefix=/usr
NagiosBin=/usr/bin/nagios
NagiosCfgFile=/etc/nagios/nagios.cfg
NagiosStatusFile=/var/log/nagios/status.dat
NagiosTempFile=/var/log/nagios/nagios.tmp
NagiosRetentionFile=/var/log/nagios/retention.dat
NagiosCommandFile=/var/log/nagios/rw/nagios.cmd
NagiosVarDir=/var/log/nagios
NagiosRunFile=/var/run/nagios.pid
NagiosLockDir=/var/lock/subsys
NagiosLockFile=nagios
NagiosCGIDir=/usr/lib/nagios/cgi
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
su - $NagiosUser -c "touch
$NagiosVarDir/nagios.log $NagiosRetentionFile"
rm -f $NagiosCommandFile
# touch $NagiosRunFile
# chown $NagiosUser:$NagiosGroup $NagiosRunFile
$NagiosBin -d $NagiosCfgFile && ps -C nagios |
cut -d" " -f 1 > /tmp/nagios; tail -1 /tmp/nagios > $NagiosRunFile; rm
-f /tmp/nagios
if [ -d $NagiosLockDir ]; then touch
$NagiosLockDir/$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
echo 'done.'
fi
rm -f $NagiosStatusFile $NagiosTempFile $NagiosRunFile
$NagiosLockDir/$NagiosLockFile $NagiosCommandFile
;;
status)
pid_nagios
printstatus_nagios nagios
;;
restart)
printf "Running configuration check..."
$NagiosBin -v $NagiosCfgFile > /dev/null 2>&1;
if [ $? -eq 0 ]; then
echo "done"
$0 stop
$0 start
else
#$NagiosBin -v $NagiosCfgFile
echo " FAILED! 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
$0 start
fi
fi
else
#$NagiosBin -v $NagiosCfgFile
echo " FAILED! Reload aborted. Check your
Nagios configuration."
exit 1
fi
;;
*)
echo "Usage: nagios
{start|stop|restart|reload|force-reload|status}"
exit 1
;;
esac
# End of this script
--
***********************************************************************
* John Oliver http://www.john-oliver.net/ *
* *
***********************************************************************
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
