nagios plugin to monitor dfs

check_dfs.sh

#!/usr/bin/env bash

# ---
# => Nagios plugin to monitor hadoop dfs
#    This script serves as base line for nagios plugins for hadoop
# Author: Ashrith
# ---

PROGNAME=`basename $0`
VERSION="Version 1.0"
 
ST_OK=0
ST_WR=1
ST_CR=2
ST_UK=3
 
print_help() {
  echo "$PROGNAME $VERSION"
  echo ""
  echo "$PROGNAME is a Nagios plugin to check the status of HDFS, Hadoop's"
  echo "underlying, redundant, distributed file system."
  echo ""
  echo "Options:"
  echo "  -w|--warning)"
	echo "     Defines the warning level for available datanodes. Default"
	echo "     is: off"
	echo "  -c|--critical)"
	echo "     Defines the critical level for available datanodes. Default"
	echo "     is: off"
  exit $ST_UK
}
#validate input arguments
while [ -n "$1" ]; do
    case "$1" in
        --help|-h)
            print_help
            exit $ST_UK
            ;;
        --version|-v)
            print_version $PROGNAME $VERSION
            exit $ST_UK
            ;;
        --warning|-w)
            warning=$2
            shift
            ;;
        --critical|-c)
            critical=$2
            shift
            ;;
        *)
            echo "Unknown argument: $1"
            print_help
            exit $ST_UK
            ;;
        esac
    shift
done
 
get_wcdiff() {
    if [ ! -z "$warning" -a ! -z "$critical" ]
    then
        wclvls=1
 
        if [ ${warning} -lt ${critical} ]
        then
            wcdiff=1
        fi
    elif [ ! -z "$warning" -a -z "$critical" ]
    then
        wcdiff=2
    elif [ -z "$warning" -a ! -z "$critical" ]
    then
        wcdiff=3
    fi
}
 
val_wcdiff() {
    if [ "$wcdiff" = 1 ]
    then
        echo "Please adjust your warning/critical thresholds. The warning \
must be higher than the critical level!"
        exit $ST_UK
    elif [ "$wcdiff" = 2 ]
    then
        echo "Please also set a critical value when you want to use \
warning/critical thresholds!"
        exit $ST_UK
    elif [ "$wcdiff" = 3 ]
    then
        echo "Please also set a warning value when you want to use \
warning/critical thresholds!"
        exit $ST_UK
    fi
}
 
get_vals() {
    tmp_vals=`sudo -u hdfs hdfs dfsadmin -report`
    dn_avail=`echo -e "$tmp_vals" | grep -m1 "Datanodes available:" | awk '{print $3}'`
    dfs_used=`echo -e "$tmp_vals" | grep -m1 "DFS Used:" | awk '{print $3}'`
    dfs_used=`expr ${dfs_used} / 1024 / 1024`
    dfs_used_p=`echo -e "$tmp_vals" | grep -m1 "DFS Used%:" | awk '{print $3}'`
    dfs_total=`echo -e "$tmp_vals" | grep -m1 "Configured Capacity:" | awk '{print $3}'`
    dfs_total=`expr ${dfs_total} / 1024 / 1024`
}
 
do_output() {
	output="Datanodes up and running: ${dn_avail}, DFS total: \
${dfs_total} MB, DFS used: ${dfs_used} MB (${dfs_used_p})"
}
 
do_perfdata() {
	perfdata="'datanodes_available'=${dn_avail} 'dfs_total'=${dfs_total} \
'dfs_used'=${dfs_used}"
}
 
#Call the Functions
get_wcdiff
val_wcdiff
 
get_vals	#collects the actual values
 
do_output
do_perfdata
 
if [ -n "$warning" -a -n "$critical" ]
then
    if [ "$dn_avail" -le "$warning" -a "$dn_avail" -gt "$critical" ]
    then
        echo "WARNING - ${output} | ${perfdata}"
	exit $ST_WR
    elif [ "$dn_avail" -le "$critical" ]
    then
        echo "CRITICAL - ${output} | ${perfdata}"
	exit $ST_CR
    else
        echo "OK - ${output} | ${perfdata} "
	exit $ST_OK
    fi
else
    echo "OK - ${output} | ${perfdata}"
    exit $ST_OK
fi