#!/bin/sh
# Copyright (C) 2008-2010  Equinox Software, Inc.
# Written by Don McMorris <dmcmorris@esilibrary.com>
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
#
# Author       : Don McMorris, Sys Admin, ESI
# Purpose      : Look for excessive NULLS in the gateway logs
# Usage        : check_null <# mins to check> <WARNLIMIT> <CRITLIMIT>


WARNLIMIT=$2
CRITLIMIT=$3
PERIOD=$1
# Note: These should really be checked to ensure they are defined and within range...

PREVTOT=0
LOGFILE="/var/log/evergreen/prod/$(date +%Y/%m/%d)/gateway.$(date +%H).log"

if [ $(date +%H | cut -b1) = 0 ]; then
	CURRHOUR=$(date +%H | cut -b2)
else
	CURRHOUR=$(date +%H)
fi

if [ $(date +%M | cut -b1) = 0 ]; then
        CURRMIN=$(date +%M | cut -b2 )
else
        CURRMIN=$(date +%M)
fi

if [ $CURRMIN -lt $PERIOD ]; then
	# How many minutes of the last hour do we need to check?
        TMPDIFFM2=$((60 - $(($PERIOD - $CURRMIN))))

	# This logic will mean that "Returning NULL"'s logged at the late 2300 hour will not be counted during the early Midnight hour check.
	# This is acceptable for now.
        if [ $CURRHOUR -gt 0 ]; then
		# define LOGFILE2 (last hours' log)
		if [ $CURRHOUR -gt 11 ]; then
			LOGFILE2="/var/log/evergreen/prod/$(date +%Y/%m/%d)/gateway.$(($CURRHOUR - 1)).log"
		else
			LOGFILE2="/var/log/evergreen/prod/$(date +%Y/%m/%d)/gateway.0$(($CURRHOUR - 1)).log"
		fi

		while [ $TMPDIFFM2 -lt 60 ]; do
			PREVTOT=$(($PREVTOT + $(grep "Returning NULL" $LOGFILE2 | cut -d":" -f2 | grep -c $TMPDIFFM2)))
			TMPDIFFM2=$(($TMPDIFFM2 + 1))
		done
        fi
	while [ $TMPDIFF1 -le $CURRMIN ]; do
		PREVTOT=$(($PREVTOT + $(grep "Returning NULL" $LOGFILE | cut -d":" -f2 | grep -c $TMPDIFF1)))
	        TMPDIFF1=$(($TMPDIFF1 + 1))
	done
else
	TMPDIFF1=$(($CURRMIN-$PERIOD))
	while [ $TMPDIFF1 -le $CURRMIN ]; do
		PREVTOT=$(($PREVTOT + $(grep "Returning NULL" $LOGFILE | cut -d":" -f2 | grep -c $TMPDIFF1)))
	        TMPDIFF1=$(($TMPDIFF1 + 1))
	done

fi


TOPSERVER=$(grep "Returning NULL" $LOGFILE | cut -d" " -f3 | sort | uniq -c | sort -nr | head -1)

if [ "$TOPSERVER" != null ]; then
	SVRMSG=" (Top server this hour: $TOPSERVER)"
else
	SVRMSG="."
fi

if [ $PREVTOT -ge $CRITLIMIT ]; then
        echo "CRIT: $PREVTOT NULLs returned in past $PERIOD minutes$SVRMSG"
        exit 2
elif [ $PREVTOT -ge $WARNLIMIT ]; then
        echo "WARN: $PREVTOT NULLs returned in the past $PERIOD minutes$SVRMSG"
        exit 1
elif [ $PREVTOT -lt $WARNLIMIT ]; then
        echo "OK: $PREVTOT NULLs returned in the past $PERIOD minutes$SVRMSG"
        exit 0
else
        echo "WARN: An error has occurred $PREVTOT $PERIOD"
        exit 1
fi