ZFS Health Check Script

zfs_health.sh

#!/usr/local/bin/bash
#
# MODIFIED VERSION OF:
#
# Calomel.org
#     https://calomel.org/zfs_health_check_script.html
#     FreeBSD 9.1 ZFS Health Check script
#     zfs_health.sh @ Version 0.15

emailReceiver="[email protected]"
emailSender="[email protected]"
emailSubject="ZFS pool - HEALTH check"
emailMessage=""
maxCapacity=80
scrubExpire=691200 # 8 Days
problems=0


# Health - Check if all zfs volumes are in good condition. We are looking for
# any keyword signifying a degraded or broken array.

condition=$(/sbin/zpool status | egrep -i '(DEGRADED|FAULTED|OFFLINE|UNAVAIL|REMOVED|FAIL|DESTROYED|corrupt|cannot|unrecover)')
if [ "${condition}" ]; then
  emailSubject="$emailSubject - fault"
  problems=1
fi


# Capacity - Make sure pool capacities are below 80% for best performance.

if [ ${problems} -eq 0 ]; then
  capacity=$(/sbin/zpool list -H -o capacity)
  for line in ${capacity//%/}
  do  
    if [ $line -ge $maxCapacity ]; then
      emailSubject="$emailSubject - Capacity Exceeded"
      problems=1
    fi
  done
fi


# Errors - Check the columns for READ, WRITE and CKSUM (checksum) drive errors
# on all volumes and all drives using "zpool status". If any non-zero errors
# are reported an email will be sent out.

if [ ${problems} -eq 0 ]; then
  errors=$(/sbin/zpool status | grep ONLINE | grep -v state | awk '{print $3 $4 $5}' | grep -v 000)
  if [ "${errors}" ]; then
    emailSubject="$emailSubject - Drive Errors"
    problems=1
  fi
fi


# Scrub Expired - Check if all volumes have been scrubbed in at least the last 8 days.

if [ ${problems} -eq 0 ]; then
  currentDate=$(date +%s)
  zfsVolumes=$(/sbin/zpool list -H -o name)

  for volume in ${zfsVolumes}
  do
    if [ $(/sbin/zpool status $volume | egrep -c "none requested") -ge 1 ]; then 
      echo "ERROR: You need to run \"zpool scrub $volume\" before this script can monitor the scrub expiration time."
      break
    fi
    if [ $(/sbin/zpool status $volume | egrep -c "scrub in progress|resilver") -ge 1 ]; then
      break
    fi

    ### FreeBSD 11.2 with *nix supported date format
    scrubRawDate=$(/sbin/zpool status $volume | grep scrub | awk '{print $15 $12 $13}')
    scrubDate=$(date -j -f '%Y%b%e-%H%M%S' $scrubRawDate'-000000' +%s)

    ### FreeBSD 12.0 with *nix supported date format
    #scrubRawDate=$(/sbin/zpool status $volume | grep scrub | awk '{print $17 $14 $15}')
    #scrubDate=$(date -j -f '%Y%b%e-%H%M%S' $scrubRawDate'-000000' +%s)

    if [ $(($currentDate - $scrubDate)) -ge $scrubExpire ]; then
      if [ ${problems} -eq 0 ]; then
        emailSubject="$emailSubject - Scrub Time Expired. Scrub Needed on Volume(s)"
      fi
      problems=1
      emailMessage="${emailMessage}Pool: $volume needs scrub \n"
    fi
  done
fi


# Notifications - On any problems send email with drive status information and
# capacities including a helpful subject line. Also use logger to write
# the email subject to the local logs.

if [ "$problems" -ne 0 ]; then
  echo -e "To: $emailReceiver\nFrom: $emailSender\nSubject: $emailSubject\n\n
               $emailMessage\n\n\n `/sbin/zpool list` \n\n\n `/sbin/zpool status`" | ssmtp $emailReceiver

  logger $emailSubject
fi

### EOF ###