#!/bin/bash

################################################################################
# ZFS_HEALTH_CHECK.SH
# -------------------
# This script checks the ZFS health and reports any problems on stdout
#
# Inspired by https://gist.github.com/petervanderdoes/bd6660302404ed5b094d
#
# Author: Robin Meier - robin@meier.si
################################################################################

script_dir=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )

# Load configuration
set -o allexport
source ${script_dir}/config/zfs_health_check
set +o allexport

# Import logging functionality
logfile=${script_dir}/log/zfs_health_check.log
log_identifier="ZFS"
source ${script_dir}/functions/logging.sh

problems=0

log "Starting ZFS Health Check"

# Pool Status
zpool_status=$(/sbin/zpool status | egrep -i '(DEGRADED|FAULTED|OFFLINE|UNAVAIL|REMOVED|FAIL|DESTROYED|corrupt|cannot|unrecover)')
if [ "${zpool_status}" ]; then
  log_echo "[ERROR] !!! BAD ZFS HEALTH !!!"
  /sbin/zpool status | ts "[%Y-%m-%d %H:%M:%S] $log_identifier" | tee -a $logfile
  problems=1
fi

# Capacity
maxCapacity=50
if [ ${problems} -eq 0 ]; then
  capacity=$(/sbin/zpool list -H -o capacity)
  for line in ${capacity//%/}
  do
    if [ $line -ge $maxCapacity ]; then
      problems=1
    fi
  done
  if [ ${problems} -eq 1 ]; then
    log_echo "[ERROR] !!! BAD ZFS CAPACITY !!!"
    /sbin/zpool list -o name,cap,free | ts "[%Y-%m-%d %H:%M:%S] $log_identifier" | tee -a $logfile
  fi
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. You should then look to replace the
# faulty drive and run "zpool scrub" on the affected volume after resilvering.
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
    log_echo "[ERROR] !!! ZFS ERRORS FOUND !!!"
    /sbin/zpool status | ts "[%Y-%m-%d %H:%M:%S] $log_identifier" | tee -a $logfile
    log_echo "[ERROR] You shoud replace the faulty drive and run \"zpool scrub\" after resilvering"
    problems=1
  fi
fi

# Scrub Expired - Check if all volumes have been scrubbed in at least the last
# 8 days. The general guide is to scrub volumes on desktop quality drives once
# a week and volumes on enterprise class drives once a month. You can always
# use cron to schedule "zpool scrub" in off hours. We scrub our volumes every
# Sunday morning for example.
#
# Scrubbing traverses all the data in the pool once and verifies all blocks can
# be read. Scrubbing proceeds as fast as the devices allows, though the
# priority of any I/O remains below that of normal calls. This operation might
# negatively impact performance, but the file system will remain usable and
# responsive while scrubbing occurs. To initiate an explicit scrub, use the
# "zpool scrub" command.
#
# The scrubExpire variable is in seconds. So for 8 days we calculate 8 days
# times 24 hours times 3600 seconds to equal 691200 seconds.
# scrubExpire=691200
# SCRUB_EXPIRE=1382400 # This was moved to config file
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
      log_echo "ERROR: You need to run \"zpool scrub $volume\" before this script can monitor the scrub expiration time."
      break
    fi
    if [ $(/sbin/zpool status $volume | egrep -c "scrub in progress|resilver") -ge 1 ]; then
      break
    fi
    scrubRawDate=$(/sbin/zpool status $volume | grep scrub | awk '{print $11" "$12" " $13" " $14" "$15}')
    scrubDate=$(date -d "$scrubRawDate" +%s)
    if [ $(($currentDate - $scrubDate)) -ge $scrubExpire ]; then
      problems=1
      log_echo "[ERROR] Pool: $volume needs scrub!"
    fi
  done
fi

# Unmounted datasets
unmounted=$(/sbin/zfs list -o mounted | grep no)
if [ "${unmounted}" ]; then
  log "[WARN] THERE ARE UNMOUNTED DATASETS"
fi

# Warnable unmounted datasets
for dataset in $MONITORED_DATASETS
do
  unmounted=$(/sbin/zfs list $dataset -o mounted | grep no)
  if [ "${unmounted}" ]; then
    log_echo "[MON] Monitored dataset $dataset is not mounted"
    problems=1
  fi
done

# Finish
if [ ${problems} -eq 0 ]; then
  log "ZFS Health Check Successful"
else
  log "ZFS Health Check Found Problems"
fi