Nagios Support Forum

abrist wrote:No, it looks like you are doing everything right.

mlong: Can you post the init script you are currently using in code wraps?

Here it is. I have made no changes to it from the 3.5.1 installation.

Code: Select all

#!/bin/sh
#
# chkconfig: 345 99 01
# description: Nagios network monitor
#
# File : nagios
#
# Author : Jorge Sanchez Aymar (jsanchez@lanchile.cl)
#
# Changelog :
#
# 1999-07-09 Karl DeBisschop <kdebisschop@infoplease.com>
#  - setup for autoconf
#  - add reload function
# 1999-08-06 Ethan Galstad <egalstad@nagios.org>
#  - Added configuration info for use with RedHat's chkconfig tool
#    per Fran Boon's suggestion
# 1999-08-13 Jim Popovitch <jimpop@rocketship.com>
#  - added variable for nagios/var directory
#  - cd into nagios/var directory before creating tmp files on startup
# 1999-08-16 Ethan Galstad <egalstad@nagios.org>
#  - Added test for rc.d directory as suggested by Karl DeBisschop
# 2000-07-23 Karl DeBisschop <kdebisschop@users.sourceforge.net>
#  - Clean out redhat macros and other dependencies
# 2003-01-11 Ethan Galstad <egalstad@nagios.org>
#  - Updated su syntax (Gary Miller)
#
# Description: Starts and stops the Nagios monitor
#              used to provide network services status.
#

# Load any extra environment variables for Nagios and its plugins
if test -f /etc/sysconfig/nagios; then
   . /etc/sysconfig/nagios
fi

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
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
         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; 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 $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

magna.vis wrote:Looks like this guy may have some input as well: http://roger.steneteg.org/492/installing-nagios-from-source/

I'm also thinking about cloning my current setup, and upgrading without doing the make install-init command and seeing if it still works. If I get around to it in the next couple of days, I'll post my results.

And here it is in code brackets:

Code: Select all

#! /bin/sh
### BEGIN INIT INFO
# Provides:          nagios
# Required-Start:    $remote_fs $syslog
# Required-Stop:     $remote_fs $syslog
# Default-Start:     2 3 4 5
# Default-Stop:      0 1 6
# Short-Description: start and stop Nagios monitoring server
# Description:       Nagios is a service monitoring system
### END INIT INFO

# Author: Foo Bar <roger@steneteg.org>
#
# Please remove the "Author" lines above and replace them
# with your own name if you copy and modify this script.

# Do NOT "set -e"

# PATH should only include /usr/* if it runs after the mountnfs.sh script
PATH=/sbin:/usr/sbin:/bin:/usr/bin
DESC="Nagios monitoring system"
NAME=nagios
PREFIX=/srv/nagios
STATEDIR=/var/nagios
CONFIGDIR=/etc/nagios
CONFIGFILE="$CONFIGDIR/nagios.cfg"
DAEMON="${PREFIX}/bin/${NAME}"
DAEMON_ARGS="-d $CONFIGFILE"
SCRIPTNAME=/etc/init.d/$NAME
PIDFILE=/var/run/$NAME.pid
USER="nagios"
GROUP="nagios"

# Exit if the package is not installed
[ -x "$DAEMON" ] || exit 0

# Read configuration variable file if it is present
[ -r /etc/default/$NAME ] && . /etc/default/$NAME

# Load the VERBOSE setting and other rcS variables
. /lib/init/vars.sh

# Define LSB log_* functions.
# Depend on lsb-base (>= 3.2-14) to ensure that this file is present
# and status_of_proc is working.
. /lib/lsb/init-functions

check_config() {
   RESULTFILE="$STATEDIR/configcheck$$"
   CHECKRESULT=`$DAEMON -v $CONFIGFILE > $RESULTFILE`
   WARN=`grep ^"Total Warnings:" $RESULTFILE | awk -F: '{print $2}' |sed s/' '//g`
   ERR=`grep ^"Total Errors:" $RESULTFILE | awk -F: '{print $2}' |sed s/' '//g`

   if test "${WARN}" = "0" && test "${ERR}" = "0"; then
      echo "OK - Configuration check verified"
      return 0
   else
      cat $RESULTFILE
      exit 8
   fi
}

#
# Function that starts the daemon/service
#
do_start()
{
   # Return
   #   0 if daemon has been started
   #   1 if daemon was already running
   #   2 if daemon could not be started

   test -x $DAEMON || exit 2
   test -f $CONFIGGILE || exit 2
   if test "$1" = "checkconfig"; then
      check_config
   fi
   echo -n "Starting $NAME .."
   start-stop-daemon --start --quiet --pidfile $PIDFILE --exec $DAEMON --test > /dev/null || return 1
   start-stop-daemon --start --quiet --make-pidfile --pidfile $PIDFILE --exec $DAEMON -- $DAEMON_ARGS || return 2
   echo ". $NAME started"
}

#
# Function that stops the daemon/service
#
do_stop()
{
   # Return
   #   0 if daemon has been stopped
   #   1 if daemon was already stopped
   #   2 if daemon could not be stopped
   #   other if a failure occurred
   echo -n "Stopping $NAME .."
#   start-stop-daemon --stop --quiet --retry=5 --pidfile $PIDFILE --name $NAME
#   RETVAL="$?"
#   [ "$RETVAL" = 2 ] && return 2
   # Wait for children to finish too if this is a daemon that forks
   # and if the daemon is only ever run from this initscript.
   # If the above conditions are not satisfied then add some other code
   # that waits for the process to drop all resources that could be
   # needed by services started subsequently.  A last resort is to
   # sleep for some time.
   start-stop-daemon --stop --quiet --oknodo --retry=5 --exec $DAEMON
   RETVAL="$?"
   [ "$RETVAL" = 2 ] && return 2
   # Many daemons don't delete their pidfiles when they exit.
   rm -f $PIDFILE
   echo ". $NAME stopped"
   return "$RETVAL"
}

#
# Function that sends a SIGHUP to the daemon/service
#
do_reload() {
   #
   # If the daemon can reload its configuration without
   # restarting (for example, when it is sent a SIGHUP),
   # then implement that here.
   #
   check_config
   # This does not seem to be working
   #start-stop-daemon --stop --signal HUP --quiet --pidfile $PIDFILE --name $NAME
   echo "There is something wrong with the reload function, use restart instead"
   return 0
}

case "$1" in
  start)
   [ "$VERBOSE" != no ] && log_daemon_msg "Starting $DESC" "$NAME"
   do_start "checkconfig"
   case "$?" in
      0|1) [ "$VERBOSE" != no ] && log_end_msg 0 ;;
      2) [ "$VERBOSE" != no ] && log_end_msg 1 ;;
   esac
   ;;
  stop)
   [ "$VERBOSE" != no ] && log_daemon_msg "Stopping $DESC" "$NAME"
   do_stop
   case "$?" in
      0|1) [ "$VERBOSE" != no ] && log_end_msg 0 ;;
      2) [ "$VERBOSE" != no ] && log_end_msg 1 ;;
   esac
   ;;
  status)
   status_of_proc "$DAEMON" "$NAME" && exit 0 || exit $?
   ;;
  reload)
   #
   # If do_reload() is not implemented then leave this commented out
   # and leave 'force-reload' as an alias for 'restart'.
   #
   log_daemon_msg "Reloading $DESC" "$NAME"
   do_reload
   log_end_msg $?
   ;;
  restart)
   #
   # If the "reload" option is implemented then remove the
   # 'force-reload' alias
   #
   log_daemon_msg "Restarting $DESC" "$NAME"
   check_config
   do_stop
   case "$?" in
     0|1)
      do_start
      case "$?" in
         0) log_end_msg 0 ;;
         1) log_end_msg 1 ;; # Old process is still running
         *) log_end_msg 1 ;; # Failed to start
      esac
      ;;
     *)
      # Failed to stop
      log_end_msg 1
      ;;
   esac
   ;;
  *)
   echo "Usage: $SCRIPTNAME {start|stop|restart|reload|force-reload}" >&2
   exit 3
   ;;
esac

It does seem to work without running the make install-init command.

In ubuntu 12.04, installed from the repos (3.2.3)

my functions are at:
/lib/lsb/init-functions

it's worth editing /etc/init.d/nagios with that

Yeah, but you will run into other issues (status, runuser, etc). I will try to get Ludmil to post a copy of the init script we hacked out the other night. It is not perfect, but it does work.

Here you go... Let us know if it worked for you.

Code: Select all

#!/bin/sh

# Nagios   Startup script for the Nagios monitoring daemon
#
# chkconfig:   - 85 15
# description:   Nagios is a service monitoring system
# processname: nagios
# config: /etc/nagios/nagios.cfg
# pidfile: /var/nagios/nagios.pid
#
### BEGIN INIT INFO
# Provides:      nagios
# Required-Start:   $local_fs $syslog $network
# Required-Stop:   $local_fs $syslog $network
# Short-Description:   start and stop Nagios monitoring server
# Description:      Nagios is is a service monitoring system
### END INIT INFO

# Source function library.
# . /etc/rc.d/init.d/functions
. /lib/lsb/init-functions

prefix="/usr/local/nagios"
exec_prefix="${prefix}"
exec="${exec_prefix}/bin/nagios"
prog="nagios"
config="${prefix}/etc/nagios.cfg"
pidfile="${prefix}/var/nagios.lock"
user="nagios"
group="nagios"
checkconfig="false"
ramdiskdir="/var/nagios/ramcache"

test -e /etc/sysconfig/$prog && . /etc/sysconfig/$prog

lockfile=/var/lock/$prog
USE_RAMDISK=${USE_RAMDISK:-0}

if test "$USE_RAMDISK" -ne 0 && test "$RAMDISK_SIZE"X != "X"; then
   ramdisk=`mount |grep "$ramdiskdir type tmpfs"`
   if [ "$ramdisk"X == "X" ]; then
      mkdir -p -m 0755 $ramdiskdir
      mount -t tmpfs -o size=${RAMDISK_SIZE}m tmpfs $ramdiskdir
      mkdir -p -m 0755 $ramdiskdir/checkresults
      chown -R $user:$group $ramdiskdir
   fi
fi

check_config() {
   TMPFILE="/tmp/.configtest.$$"
   /usr/sbin/service nagios configtest > "$TMPFILE"
   WARN=`grep ^"Total Warnings:" "$TMPFILE" |awk -F: '{print \$2}' |sed s/' '//g`
   ERR=`grep ^"Total Errors:" "$TMPFILE" |awk -F: '{print \$2}' |sed s/' '//g`

   if test "$WARN" = "0" && test "${ERR}" = "0"; then
      echo "OK - Configuration check verified" > /var/run/nagios.configtest
      chmod 0644 /var/run/nagios.configtest
      /bin/rm "$TMPFILE"
   return 0
   else
      # We'll write out the errors to a file we can have a
      # script watching for
      echo "WARNING: Errors in config files - see log for details: $TMPFILE" > /var/run/nagios.configtest
      egrep -i "(^warning|^error)" "$TMPFILE" >> /var/run/nagios.configtest
      chmod 0644 /var/run/nagios.configtest
      cat "$TMPFILE"
   exit 8
   fi
}

start() {
   test -x $exec || exit 5
   test -f $config || exit 6
   if test "$checkconfig" = "false"; then
      check_config
   fi
   echo -n $"Starting $prog: "
   # We need to _make sure_ the precache is there and verified
   # Raise priority to make it run better
   daemon --user=$user -- $exec -d $config
   #touch $lockfile
   retval=$?
   echo
   test $retval -eq 0 && touch $lockfile
   return $retval
}

stop() {
   echo -n $"Stopping $prog: "
   killproc -p ${pidfile}  $exec
   retval=$?
   echo
   test $retval -eq 0 && rm -f $lockfile
   return $retval
}


restart() {
   check_config
   checkconfig="true"
   stop
   start
}

reload() {
   echo -n $"Reloading $prog: "
   killproc -p ${pidfile} $exec -HUP
   RETVAL=$?
   echo
}

force_reload() {
   restart
}

case "$1" in
   start)
      status_of_proc $prog && exit 0
      $1
      ;;
   stop)
      status_of_proc $prog|| exit 0
      $1
      ;;
   restart)
      $1
      ;;
   reload)
      status_of_proc $prog || exit 7
      $1
      ;;
   force-reload)
      force_reload
      ;;
   status)
      status_of_proc $prog
      ;;
   condrestart|try-restart)
      status_of_proc $prog|| exit 0
      restart
      ;;
   configtest)
      $nice su -s /bin/bash - nagios -c "$corelimit >/dev/null 2>&1 ; $exec -vp $config"
      RETVAL=$?
      ;;
   *)
      echo $"Usage: $0 {start|stop|status|restart|condrestart|try-restart|reload|force-reload|configtest}"
      exit 2
esac
exit $?


lmiltchev wrote:Here you go... Let us know if it worked for you.

Code: Select all

#!/bin/sh

# Nagios   Startup script for the Nagios monitoring daemon
#
# chkconfig:   - 85 15
# description:   Nagios is a service monitoring system
# processname: nagios
# config: /etc/nagios/nagios.cfg
# pidfile: /var/nagios/nagios.pid
#
### BEGIN INIT INFO
# Provides:      nagios
# Required-Start:   $local_fs $syslog $network
# Required-Stop:   $local_fs $syslog $network
# Short-Description:   start and stop Nagios monitoring server
# Description:      Nagios is is a service monitoring system
### END INIT INFO

# Source function library.
# . /etc/rc.d/init.d/functions
. /lib/lsb/init-functions

prefix="/usr/local/nagios"
exec_prefix="${prefix}"
exec="${exec_prefix}/bin/nagios"
prog="nagios"
config="${prefix}/etc/nagios.cfg"
pidfile="${prefix}/var/nagios.lock"
user="nagios"
group="nagios"
checkconfig="false"
ramdiskdir="/var/nagios/ramcache"

test -e /etc/sysconfig/$prog && . /etc/sysconfig/$prog

lockfile=/var/lock/$prog
USE_RAMDISK=${USE_RAMDISK:-0}

if test "$USE_RAMDISK" -ne 0 && test "$RAMDISK_SIZE"X != "X"; then
   ramdisk=`mount |grep "$ramdiskdir type tmpfs"`
   if [ "$ramdisk"X == "X" ]; then
      mkdir -p -m 0755 $ramdiskdir
      mount -t tmpfs -o size=${RAMDISK_SIZE}m tmpfs $ramdiskdir
      mkdir -p -m 0755 $ramdiskdir/checkresults
      chown -R $user:$group $ramdiskdir
   fi
fi

check_config() {
   TMPFILE="/tmp/.configtest.$$"
   /usr/sbin/service nagios configtest > "$TMPFILE"
   WARN=`grep ^"Total Warnings:" "$TMPFILE" |awk -F: '{print \$2}' |sed s/' '//g`
   ERR=`grep ^"Total Errors:" "$TMPFILE" |awk -F: '{print \$2}' |sed s/' '//g`

   if test "$WARN" = "0" && test "${ERR}" = "0"; then
      echo "OK - Configuration check verified" > /var/run/nagios.configtest
      chmod 0644 /var/run/nagios.configtest
      /bin/rm "$TMPFILE"
   return 0
   else
      # We'll write out the errors to a file we can have a
      # script watching for
      echo "WARNING: Errors in config files - see log for details: $TMPFILE" > /var/run/nagios.configtest
      egrep -i "(^warning|^error)" "$TMPFILE" >> /var/run/nagios.configtest
      chmod 0644 /var/run/nagios.configtest
      cat "$TMPFILE"
   exit 8
   fi
}

start() {
   test -x $exec || exit 5
   test -f $config || exit 6
   if test "$checkconfig" = "false"; then
      check_config
   fi
   echo -n $"Starting $prog: "
   # We need to _make sure_ the precache is there and verified
   # Raise priority to make it run better
   daemon --user=$user -- $exec -d $config
   #touch $lockfile
   retval=$?
   echo
   test $retval -eq 0 && touch $lockfile
   return $retval
}

stop() {
   echo -n $"Stopping $prog: "
   killproc -p ${pidfile}  $exec
   retval=$?
   echo
   test $retval -eq 0 && rm -f $lockfile
   return $retval
}


restart() {
   check_config
   checkconfig="true"
   stop
   start
}

reload() {
   echo -n $"Reloading $prog: "
   killproc -p ${pidfile} $exec -HUP
   RETVAL=$?
   echo
}

force_reload() {
   restart
}

case "$1" in
   start)
      status_of_proc $prog && exit 0
      $1
      ;;
   stop)
      status_of_proc $prog|| exit 0
      $1
      ;;
   restart)
      $1
      ;;
   reload)
      status_of_proc $prog || exit 7
      $1
      ;;
   force-reload)
      force_reload
      ;;
   status)
      status_of_proc $prog
      ;;
   condrestart|try-restart)
      status_of_proc $prog|| exit 0
      restart
      ;;
   configtest)
      $nice su -s /bin/bash - nagios -c "$corelimit >/dev/null 2>&1 ; $exec -vp $config"
      RETVAL=$?
      ;;
   *)
      echo $"Usage: $0 {start|stop|status|restart|condrestart|try-restart|reload|force-reload|configtest}"
      exit 2
esac
exit $?


I replaced the /etc/init.d/nagios file with the reccomeded updated and when I attempted to restart nagios I received this

Code: Select all

root@nagios downloads/nagios# /etc/init.d/nagios restart                                                                     
$Stopping nagios:                                                                                                             
$Starting nagios: /etc/init.d/nagios: 149: daemon: not found

And this is on the debian squeeze box?

abrist wrote:And this is on the debian squeeze box?

Yep
and I have to say Turnkey Restore points are awesome

Try running:

Code: Select all

apt-get install daemon

lmiltchev wrote:Try running:

Code: Select all

apt-get install daemon

so after using the recommended init script and installing daemon (apt-get install daemon), I restarted the nagios process an everything looked good.

Code: Select all

root@nagios downloads/nagios# /etc/init.d/nagios restart                                                                                                                                     
$Stopping nagios:                                                                                                                                                                             
$Starting nagios: 

Until I went to look at the Nagios web interface. it looked like the Nagios service was not running (see attachmet whoops.png)
I checked the status and got this

Code: Select all

root@nagios downloads/nagios# service nagios status                                                                                                                                           
is not running ... failed!

THis time I manually stopped an started the service using

Code: Select all

root@nagios downloads/nagios# /etc/init.d/nagios stop                                                                                                                                         
is not running ... failed!
root@nagios downloads/nagios# /etc/init.d/nagios start                                                                                                                                       
is not running ... failed!
$Starting nagios:


This time nagios was actually running and I could see my Service status

When I rebooted I saw this:

Code: Select all

is not running ... failed!
$Starting nagios:

but when it was back up and running. Nagios seems to be working as expected.

Its kind of ugly, but it seems to have solved my issues.