ZFS JBOD Monitoring

If using ZFS software raid (RAIDZ2 for example) to provide Lustre OST's, monitoring disk and enclosure health can be a challenge. This is because typically vendor disk array monitoring is included as part of a package with RAID controllers.

If you are aware of any vendor-supported monitoring solutions for this or have your own solution, please add to this page.

Disk Failure: zpool status
To detect disk failure, simply check the zpool status.

This is useful for any zfs filesystem, even those built on traditional RAID.

Standalone Example
To perform checks standalone scripts can be written to use the zpool status command. An example is as follows, which uses the ldev.conf file to know pool names associated with lustre, and mutt to send the email:


 * 1) !/bin/bash
 * 2) zfs monitoring script for lustre with zfs backend
 * 3) uses /etc/ldev.conf to locate zpools, then zpool status to find degraded pools.
 * 1) uses /etc/ldev.conf to locate zpools, then zpool status to find degraded pools.

HELP=" This script uses /etc/ldev.conf and zpool status to identify mounted pools, then sends an email if a pool returns a status other then ONLINE "

LDEV_FILE="/etc/ldev.conf" EMAIL="admin@place.org"

send_email { /usr/bin/mutt -s "zpool status warning on $HOSTNAME" $EMAIL<< EOF "$1" EOF }

if [ ! -f $LDEV_FILE ] then /usr/bin/mutt -s "WARNING, no ldev file found on $HOSTNAME" $EMAIL exit fi

for POOL in `cat $LDEV_FILE` do if grep ost` then POOL_NAME=`echo $POOL | cut -f2 -d":" | cut -f1 -d"/"` POOL_STATUS=`/sbin/zpool status $POOL_NAME`

#check for errors running zpool if [ ! $? ]		then send_email "$POOL_STATUS" fi

#get pool state POOL_STATE=`echo "$POOL_STATUS" | grep state` if $POOL_STATE != *ONLINE* then send_email "$POOL_STATUS" fi fi done

The script above can then be run as a cron job, with the below as an example of that cron job.

SHELL=/bin/bash PATH=/sbin:/bin:/usr/sbin:/usr/bin HOME=/tmp 50 06 * * * root /usr/local/zfs_monitor/zfs_mon.sh 2>&1 /dev/null; exit 0
 * 1) zpool monitoring crontab for oss systems

Check_mk Example
This is an example check_mk script, nagios or other agent-based monitoring systems will be similar.

currentDate=$(date +"%y%m%d") zfsVols=$(/sbin/zpool list -H -o name)
 * 1) !/bin/bash

if [ "$zfsVols" == "" ]; then exit fi

for volume in ${zfsVols} do               if [ $(/sbin/zpool status $volume | egrep -c "none requested") -ge 1 ]; then status=1 statustxt="$volume needs to initial scrub; $statustxt" fi               if [ $(/sbin/zpool status $volume | egrep -c "scrub in progress|resilver") -ge 1 ]; then status=0 statustxt="$volume scrub in progress; $statustxt" fi

scrubReportedDate=$(/sbin/zpool status $volume | grep scrub | cut -d' ' -f13-) scrubDate=$(date -d "$scrubReportedDate + 35 days" +"%y%m%d") if [ $currentDate -ge $scrubDate ]; then status=2 statustxt="$volume scrub out of date; $statustxt" fi               if [ $scrubDate -ge $currentDate ]; then if $status != 1 &&  $status != 2 ; then status=0 statustxt="$volume up to date; $statustxt" fi               fi        done

echo "$status ZPOOL_SCRUB_STATUS - $statustxt"

Predictive Failure: smartctl
To monitor predictive drive failure, you can use 'smartctl' provided by the 'smartmontools' package for centos.

Example check_mk script:
 * 1) !/bin/bash

DISKS="$(/bin/ls /dev/disk/by-vdev| /bin/grep -v part)" UNHEALTHY_COUNT=0

for DISK in ${DISKS} do HEALTH=`smartctl -H /dev/disk/by-vdev/${DISK} | grep SMART` HEALTHSTATUS=`echo ${HEALTH} | cut -d ' ' -f 4` if $HEALTHSTATUS != "OK" ; then status=2 else status=0 fi echo "$status SMART_Status_${DISK} - ${DISK} ${HEALTH}"

done

Enclosure Monitoring
This information is used for linux systems and monitoring Dell MD1200 disk arrays directly attached via SAS, with no RAID card. While the above techniques tell you if you have a disk problem, you still need to monitor the status of the arrays themselves. For our particular problem this is MD1200 disk arrays via SAS. For us, sg3_utils and SCSI Enclosure Services sg_ses is the best answer so far.

At SSEC to monitor our enclosures we use this script: http://www.ssec.wisc.edu/~scottn/Lustre_ZFS_notes/script/check_md1200.pl