Monitoring
/
nagios-plugins
mirror of https://github.com/opinkerfi/nagios-plugins.git
1
0
Fork 0
Code Issues Releases Wiki Activity

rewritten to also detect predictive failures

This commit is contained in:
Páll Guðjón Sigurðsson 2010-07-28 13:26:14 +00:00
parent c5c02a0b73
commit a94dec1228
1 changed files with 22 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
check_hparray/trunk/check_hparray
View File

@ -43,6 +43,9 @@ STATE_CRITICAL=2
STATE_UNKNOWN=3 STATE_UNKNOWN=3
STATE_DEPENDENT=4 STATE_DEPENDENT=4
TEMPFILE=`mktemp`
print_usage() { print_usage() {
echo "" echo ""
echo "Usage: $PROGNAME -s <slot-number>" echo "Usage: $PROGNAME -s <slot-number>"
@ -76,43 +79,39 @@ fi
check_raid() check_raid()
{ {
raid_ok=`echo $check|grep -i ok|wc -l` raid_ok=`cat $TEMPFILE |grep -i ok|wc -l`
raid_warning=`echo $check|grep -i rebuild|wc -l` raid_warning=`cat $TEMPFILE|grep -i -E 'rebuild|predictive' |wc -l`
raid_critical_1=`echo $check|grep -i failed|wc -l` raid_critical_1=`cat $TEMPFILE|grep -i 'failed|recovery' | wc -l`
raid_critical_2=`echo $check|grep -i recovery|wc -l`
err_check=`expr $raid_ok + $raid_warning + $raid_critical_1 + $raid_critical_2` err_check=`expr $raid_ok + $raid_warning + $raid_critical_1 `
if [ $err_check -eq "0" ]; then if [ $err_check -eq "0" ]; then
checkm=`echo $check|sed -e '/^$/ d'` checkm=`cat $TEMPFILE|sed -e '/^$/ d'`
echo "$PROGNAME Error. $checkm" echo "$PROGNAME Error. $checkm"
exit 2 exit 2
fi fi
if [ $raid_ok -ge "1" ]; then if [ $raid_ok -ge "1" ]; then
exit_status=$STATE_OK exit_status=$STATE_OK
elif [ $raid_warning -ge "1" ]; then fi
if [ $raid_warning -ge "1" ]; then
exit_status=$STATE_WARNING exit_status=$STATE_WARNING
elif [ $raid_critical_1 -ge "1" ]; then fi
if [ $raid_critical_1 -ge "1" ]; then
exit_status=$STATE_CRITICAL exit_status=$STATE_CRITICAL
elif [ $raid_critical_2 -ge "1" ]; then fi
exit_status=$STATE_CRITICAL
fi
if [ $exit_status -eq "0" ]; then if [ $exit_status -eq "0" ]; then
msg_ok=`echo $check|grep -i ok` echo "RAID OK - ($raid_ok disks ok)"
echo "RAID OK - ($msg_ok)"
exit $exit_status
elif [ $exit_status -eq "1" ]; then elif [ $exit_status -eq "1" ]; then
msg_warning=`echo $check|grep -i rebuild` echo "RAID WARNING - ($raid_ok OK; $raid_warning warnings)"
echo "RAID WARNING - ($msg_warning)"
exit $exit_status
elif [ $exit_status -eq "2" ]; then elif [ $exit_status -eq "2" ]; then
msg_critical1=`echo $check|grep -i failed` echo "RAID CRITICAL - ($raid_ok OK; $raid_warning warnings; $raid_critical_1 crit)"
msg_critical2=`echo $check|grep -i recovery`
echo "RAID CRITICAL - ($msg_critical1 $msg_critical2)"
exit $exit_status
fi fi
cat $TEMPFILE
rm -f "$TEMPFILE"
exit $exit_status
} }
@ -135,11 +134,11 @@ case "$1" in
;; ;;
--all) --all)
controllers=`sudo -u root hpacucli controller all show | sed 's/.*Slot \([0-9]*\).*/\1/'` controllers=`sudo -u root hpacucli controller all show | sed 's/.*Slot \([0-9]*\).*/\1/'`
check=`for i in $controllers ; do sudo -u root $HPACUCLI controller slot=$i ld all show;done` for i in $controllers ; do sudo -u root $HPACUCLI controller slot=$i pd all show status;done > $TEMPFILE
check_raid check_raid
;; ;;
-s) -s)
check=`sudo -u root $HPACUCLI controller slot=$2 ld all show` sudo -u root $HPACUCLI controller slot=$2 pd all show status > $TEMPFILE
check_raid check_raid
;; ;;
*) *)