mirror_zfs/tests/zfs-tests/include/libtest.shlib

#
# CDDL HEADER START
#
# The contents of this file are subject to the terms of the
# Common Development and Distribution License (the "License").
# You may not use this file except in compliance with the License.
#
# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
# or http://www.opensolaris.org/os/licensing.
# See the License for the specific language governing permissions
# and limitations under the License.
#
# When distributing Covered Code, include this CDDL HEADER in each
# file and include the License file at usr/src/OPENSOLARIS.LICENSE.
# If applicable, add the following below this CDDL HEADER, with the
# fields enclosed by brackets "[]" replaced with your own identifying
# information: Portions Copyright [yyyy] [name of copyright owner]
#
# CDDL HEADER END
#

#
# Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
# Use is subject to license terms.
# Copyright (c) 2012, 2017 by Delphix. All rights reserved.
# Copyright 2016 Nexenta Systems, Inc.
# Copyright (c) 2017 Lawrence Livermore National Security, LLC.
# Copyright (c) 2017 Datto Inc.
# Copyright (c) 2017 Open-E, Inc. All Rights Reserved.
#

. ${STF_TOOLS}/include/logapi.shlib
. ${STF_SUITE}/include/math.shlib
. ${STF_SUITE}/include/blkdev.shlib

#
# Apply constrained path when available.  This is required since the
# PATH may have been modified by sudo's secure_path behavior.
#
if [ -n "$STF_PATH" ]; then
	PATH="$STF_PATH"
fi

#
# Generic dot version comparison function
#
# Returns success when version $1 is greater than or equal to $2.
#
function compare_version_gte
{
	if [[ "$(printf "$1\n$2" | sort -V | tail -n1)" == "$1" ]]; then
		return 0
	else
		return 1
	fi
}

# Linux kernel version comparison function
#
# $1 Linux version ("4.10", "2.6.32") or blank for installed Linux version
#
# Used for comparison: if [ $(linux_version) -ge $(linux_version "2.6.32") ]
#
function linux_version
{
	typeset ver="$1"

	[[ -z "$ver" ]] && ver=$(uname -r | grep -Eo "^[0-9]+\.[0-9]+\.[0-9]+")

	typeset version=$(echo $ver | cut -d '.' -f 1)
	typeset major=$(echo $ver | cut -d '.' -f 2)
	typeset minor=$(echo $ver | cut -d '.' -f 3)

	[[ -z "$version" ]] && version=0
	[[ -z "$major" ]] && major=0
	[[ -z "$minor" ]] && minor=0

	echo $((version * 10000 + major * 100 + minor))
}

# Determine if this is a Linux test system
#
# Return 0 if platform Linux, 1 if otherwise

function is_linux
{
	if [[ $(uname -o) == "GNU/Linux" ]]; then
		return 0
	else
		return 1
	fi
}

# Determine if this is a 32-bit system
#
# Return 0 if platform is 32-bit, 1 if otherwise

function is_32bit
{
	if [[ $(getconf LONG_BIT) == "32" ]]; then
		return 0
	else
		return 1
	fi
}

# Determine if kmemleak is enabled
#
# Return 0 if kmemleak is enabled, 1 if otherwise

function is_kmemleak
{
	if is_linux && [[ -e /sys/kernel/debug/kmemleak ]]; then
		return 0
	else
		return 1
	fi
}

# Determine whether a dataset is mounted
#
# $1 dataset name
# $2 filesystem type; optional - defaulted to zfs
#
# Return 0 if dataset is mounted; 1 if unmounted; 2 on error

function ismounted
{
	typeset fstype=$2
	[[ -z $fstype ]] && fstype=zfs
	typeset out dir name ret

	case $fstype in
		zfs)
			if [[ "$1" == "/"* ]] ; then
				for out in $(zfs mount | awk '{print $2}'); do
					[[ $1 == $out ]] && return 0
				done
			else
				for out in $(zfs mount | awk '{print $1}'); do
					[[ $1 == $out ]] && return 0
				done
			fi
		;;
		ufs|nfs)
			out=$(df -F $fstype $1 2>/dev/null)
			ret=$?
			(($ret != 0)) && return $ret

			dir=${out%%\(*}
			dir=${dir%% *}
			name=${out##*\(}
			name=${name%%\)*}
			name=${name%% *}

			[[ "$1" == "$dir" || "$1" == "$name" ]] && return 0
		;;
		ext*)
			out=$(df -t $fstype $1 2>/dev/null)
			return $?
		;;
		zvol)
			if [[ -L "$ZVOL_DEVDIR/$1" ]]; then
				link=$(readlink -f $ZVOL_DEVDIR/$1)
				[[ -n "$link" ]] && \
					mount | grep -q "^$link" && \
						return 0
			fi
		;;
	esac

	return 1
}

# Return 0 if a dataset is mounted; 1 otherwise
#
# $1 dataset name
# $2 filesystem type; optional - defaulted to zfs

function mounted
{
	ismounted $1 $2
	(($? == 0)) && return 0
	return 1
}

# Return 0 if a dataset is unmounted; 1 otherwise
#
# $1 dataset name
# $2 filesystem type; optional - defaulted to zfs

function unmounted
{
	ismounted $1 $2
	(($? == 1)) && return 0
	return 1
}

# split line on ","
#
# $1 - line to split

function splitline
{
	echo $1 | sed "s/,/ /g"
}

function default_setup
{
	default_setup_noexit "$@"

	log_pass
}

#
# Given a list of disks, setup storage pools and datasets.
#
function default_setup_noexit
{
	typeset disklist=$1
	typeset container=$2
	typeset volume=$3
	log_note begin default_setup_noexit

	if is_global_zone; then
		if poolexists $TESTPOOL ; then
			destroy_pool $TESTPOOL
		fi
		[[ -d /$TESTPOOL ]] && rm -rf /$TESTPOOL
		log_must zpool create -f $TESTPOOL $disklist
	else
		reexport_pool
	fi

	rm -rf $TESTDIR  || log_unresolved Could not remove $TESTDIR
	mkdir -p $TESTDIR || log_unresolved Could not create $TESTDIR

	log_must zfs create $TESTPOOL/$TESTFS
	log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS

	if [[ -n $container ]]; then
		rm -rf $TESTDIR1  || \
			log_unresolved Could not remove $TESTDIR1
		mkdir -p $TESTDIR1 || \
			log_unresolved Could not create $TESTDIR1

		log_must zfs create $TESTPOOL/$TESTCTR
		log_must zfs set canmount=off $TESTPOOL/$TESTCTR
		log_must zfs create $TESTPOOL/$TESTCTR/$TESTFS1
		log_must zfs set mountpoint=$TESTDIR1 \
		    $TESTPOOL/$TESTCTR/$TESTFS1
	fi

	if [[ -n $volume ]]; then
		if is_global_zone ; then
			log_must zfs create -V $VOLSIZE $TESTPOOL/$TESTVOL
			block_device_wait
		else
			log_must zfs create $TESTPOOL/$TESTVOL
		fi
	fi
}

#
# Given a list of disks, setup a storage pool, file system and
# a container.
#
function default_container_setup
{
	typeset disklist=$1

	default_setup "$disklist" "true"
}

#
# Given a list of disks, setup a storage pool,file system
# and a volume.
#
function default_volume_setup
{
	typeset disklist=$1

	default_setup "$disklist" "" "true"
}

#
# Given a list of disks, setup a storage pool,file system,
# a container and a volume.
#
function default_container_volume_setup
{
	typeset disklist=$1

	default_setup "$disklist" "true" "true"
}

#
# Create a snapshot on a filesystem or volume. Defaultly create a snapshot on
# filesystem
#
# $1 Existing filesystem or volume name. Default, $TESTPOOL/$TESTFS
# $2 snapshot name. Default, $TESTSNAP
#
function create_snapshot
{
	typeset fs_vol=${1:-$TESTPOOL/$TESTFS}
	typeset snap=${2:-$TESTSNAP}

	[[ -z $fs_vol ]] && log_fail "Filesystem or volume's name is undefined."
	[[ -z $snap ]] && log_fail "Snapshot's name is undefined."

	if snapexists $fs_vol@$snap; then
		log_fail "$fs_vol@$snap already exists."
	fi
	datasetexists $fs_vol || \
		log_fail "$fs_vol must exist."

	log_must zfs snapshot $fs_vol@$snap
}

#
# Create a clone from a snapshot, default clone name is $TESTCLONE.
#
# $1 Existing snapshot, $TESTPOOL/$TESTFS@$TESTSNAP is default.
# $2 Clone name, $TESTPOOL/$TESTCLONE is default.
#
function create_clone   # snapshot clone
{
	typeset snap=${1:-$TESTPOOL/$TESTFS@$TESTSNAP}
	typeset clone=${2:-$TESTPOOL/$TESTCLONE}

	[[ -z $snap ]] && \
		log_fail "Snapshot name is undefined."
	[[ -z $clone ]] && \
		log_fail "Clone name is undefined."

	log_must zfs clone $snap $clone
}

#
# Create a bookmark of the given snapshot.  Defaultly create a bookmark on
# filesystem.
#
# $1 Existing filesystem or volume name. Default, $TESTFS
# $2 Existing snapshot name. Default, $TESTSNAP
# $3 bookmark name. Default, $TESTBKMARK
#
function create_bookmark
{
	typeset fs_vol=${1:-$TESTFS}
	typeset snap=${2:-$TESTSNAP}
	typeset bkmark=${3:-$TESTBKMARK}

	[[ -z $fs_vol ]] && log_fail "Filesystem or volume's name is undefined."
	[[ -z $snap ]] && log_fail "Snapshot's name is undefined."
	[[ -z $bkmark ]] && log_fail "Bookmark's name is undefined."

	if bkmarkexists $fs_vol#$bkmark; then
		log_fail "$fs_vol#$bkmark already exists."
	fi
	datasetexists $fs_vol || \
		log_fail "$fs_vol must exist."
	snapexists $fs_vol@$snap || \
		log_fail "$fs_vol@$snap must exist."

	log_must zfs bookmark $fs_vol@$snap $fs_vol#$bkmark
}

#
# Create a temporary clone result of an interrupted resumable 'zfs receive'
# $1 Destination filesystem name. Must not exist, will be created as the result
#    of this function along with its %recv temporary clone
# $2 Source filesystem name. Must not exist, will be created and destroyed
#
function create_recv_clone
{
	typeset recvfs="$1"
	typeset sendfs="${2:-$TESTPOOL/create_recv_clone}"
	typeset snap="$sendfs@snap1"
	typeset incr="$sendfs@snap2"
	typeset mountpoint="$TESTDIR/create_recv_clone"
	typeset sendfile="$TESTDIR/create_recv_clone.zsnap"

	[[ -z $recvfs ]] && log_fail "Recv filesystem's name is undefined."

	datasetexists $recvfs && log_fail "Recv filesystem must not exist."
	datasetexists $sendfs && log_fail "Send filesystem must not exist."

	log_must zfs create -o mountpoint="$mountpoint" $sendfs
	log_must zfs snapshot $snap
	log_must eval "zfs send $snap | zfs recv -u $recvfs"
	log_must mkfile 1m "$mountpoint/data"
	log_must zfs snapshot $incr
	log_must eval "zfs send -i $snap $incr | dd bs=10K count=1 > $sendfile"
	log_mustnot eval "zfs recv -su $recvfs < $sendfile"
	destroy_dataset "$sendfs" "-r"
	log_must rm -f "$sendfile"

	if [[ $(get_prop 'inconsistent' "$recvfs/%recv") -ne 1 ]]; then
		log_fail "Error creating temporary $recvfs/%recv clone"
	fi
}

function default_mirror_setup
{
	default_mirror_setup_noexit $1 $2 $3

	log_pass
}

#
# Given a pair of disks, set up a storage pool and dataset for the mirror
# @parameters: $1 the primary side of the mirror
#   $2 the secondary side of the mirror
# @uses: ZPOOL ZFS TESTPOOL TESTFS
function default_mirror_setup_noexit
{
	readonly func="default_mirror_setup_noexit"
	typeset primary=$1
	typeset secondary=$2

	[[ -z $primary ]] && \
		log_fail "$func: No parameters passed"
	[[ -z $secondary ]] && \
		log_fail "$func: No secondary partition passed"
	[[ -d /$TESTPOOL ]] && rm -rf /$TESTPOOL
	log_must zpool create -f $TESTPOOL mirror $@
	log_must zfs create $TESTPOOL/$TESTFS
	log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS
}

#
# create a number of mirrors.
# We create a number($1) of 2 way mirrors using the pairs of disks named
# on the command line. These mirrors are *not* mounted
# @parameters: $1 the number of mirrors to create
#  $... the devices to use to create the mirrors on
# @uses: ZPOOL ZFS TESTPOOL
function setup_mirrors
{
	typeset -i nmirrors=$1

	shift
	while ((nmirrors > 0)); do
		log_must test -n "$1" -a -n "$2"
		[[ -d /$TESTPOOL$nmirrors ]] && rm -rf /$TESTPOOL$nmirrors
		log_must zpool create -f $TESTPOOL$nmirrors mirror $1 $2
		shift 2
		((nmirrors = nmirrors - 1))
	done
}

#
# create a number of raidz pools.
# We create a number($1) of 2 raidz pools  using the pairs of disks named
# on the command line. These pools are *not* mounted
# @parameters: $1 the number of pools to create
#  $... the devices to use to create the pools on
# @uses: ZPOOL ZFS TESTPOOL
function setup_raidzs
{
	typeset -i nraidzs=$1

	shift
	while ((nraidzs > 0)); do
		log_must test -n "$1" -a -n "$2"
		[[ -d /$TESTPOOL$nraidzs ]] && rm -rf /$TESTPOOL$nraidzs
		log_must zpool create -f $TESTPOOL$nraidzs raidz $1 $2
		shift 2
		((nraidzs = nraidzs - 1))
	done
}

#
# Destroy the configured testpool mirrors.
# the mirrors are of the form ${TESTPOOL}{number}
# @uses: ZPOOL ZFS TESTPOOL
function destroy_mirrors
{
	default_cleanup_noexit

	log_pass
}

#
# Given a minimum of two disks, set up a storage pool and dataset for the raid-z
# $1 the list of disks
#
function default_raidz_setup
{
	typeset disklist="$*"
	disks=(${disklist[*]})

	if [[ ${#disks[*]} -lt 2 ]]; then
		log_fail "A raid-z requires a minimum of two disks."
	fi

	[[ -d /$TESTPOOL ]] && rm -rf /$TESTPOOL
	log_must zpool create -f $TESTPOOL raidz $disklist
	log_must zfs create $TESTPOOL/$TESTFS
	log_must zfs set mountpoint=$TESTDIR $TESTPOOL/$TESTFS

	log_pass
}

#
# Common function used to cleanup storage pools and datasets.
#
# Invoked at the start of the test suite to ensure the system
# is in a known state, and also at the end of each set of
# sub-tests to ensure errors from one set of tests doesn't
# impact the execution of the next set.

function default_cleanup
{
	default_cleanup_noexit

	log_pass
}

#
# Utility function used to list all available pool names.
#
# NOTE: $KEEP is a variable containing pool names, separated by a newline
# character, that must be excluded from the returned list.
#
function get_all_pools
{
	zpool list -H -o name | grep -Fvx "$KEEP" | grep -v "$NO_POOLS"
}

function default_cleanup_noexit
{
	typeset pool=""
	#
	# Destroying the pool will also destroy any
	# filesystems it contains.
	#
	if is_global_zone; then
		zfs unmount -a > /dev/null 2>&1
		ALL_POOLS=$(get_all_pools)
		# Here, we loop through the pools we're allowed to
		# destroy, only destroying them if it's safe to do
		# so.
		while [ ! -z ${ALL_POOLS} ]
		do
			for pool in ${ALL_POOLS}
			do
				if safe_to_destroy_pool $pool ;
				then
					destroy_pool $pool
				fi
				ALL_POOLS=$(get_all_pools)
			done
		done

		zfs mount -a
	else
		typeset fs=""
		for fs in $(zfs list -H -o name \
		    | grep "^$ZONE_POOL/$ZONE_CTR[01234]/"); do
			destroy_dataset "$fs" "-Rf"
		done

		# Need cleanup here to avoid garbage dir left.
		for fs in $(zfs list -H -o name); do
			[[ $fs == /$ZONE_POOL ]] && continue
			[[ -d $fs ]] && log_must rm -rf $fs/*
		done

		#
		# Reset the $ZONE_POOL/$ZONE_CTR[01234] file systems property to
		# the default value
		#
		for fs in $(zfs list -H -o name); do
			if [[ $fs == $ZONE_POOL/$ZONE_CTR[01234] ]]; then
				log_must zfs set reservation=none $fs
				log_must zfs set recordsize=128K $fs
				log_must zfs set mountpoint=/$fs $fs
				typeset enc=""
				enc=$(get_prop encryption $fs)
				if [[ $? -ne 0 ]] || [[ -z "$enc" ]] || \
					[[ "$enc" == "off" ]]; then
					log_must zfs set checksum=on $fs
				fi
				log_must zfs set compression=off $fs
				log_must zfs set atime=on $fs
				log_must zfs set devices=off $fs
				log_must zfs set exec=on $fs
				log_must zfs set setuid=on $fs
				log_must zfs set readonly=off $fs
				log_must zfs set snapdir=hidden $fs
				log_must zfs set aclmode=groupmask $fs
				log_must zfs set aclinherit=secure $fs
			fi
		done
	fi

	[[ -d $TESTDIR ]] && \
		log_must rm -rf $TESTDIR

	disk1=${DISKS%% *}
	if is_mpath_device $disk1; then
		delete_partitions
	fi

	rm -f $TEST_BASE_DIR/{err,out}
}


#
# Common function used to cleanup storage pools, file systems
# and containers.
#
function default_container_cleanup
{
	if ! is_global_zone; then
		reexport_pool
	fi

	ismounted $TESTPOOL/$TESTCTR/$TESTFS1
	[[ $? -eq 0 ]] && \
	    log_must zfs unmount $TESTPOOL/$TESTCTR/$TESTFS1

	destroy_dataset "$TESTPOOL/$TESTCTR/$TESTFS1" "-R"
	destroy_dataset "$TESTPOOL/$TESTCTR" "-Rf"

	[[ -e $TESTDIR1 ]] && \
	    log_must rm -rf $TESTDIR1 > /dev/null 2>&1

	default_cleanup
}

#
# Common function used to cleanup snapshot of file system or volume. Default to
# delete the file system's snapshot
#
# $1 snapshot name
#
function destroy_snapshot
{
	typeset snap=${1:-$TESTPOOL/$TESTFS@$TESTSNAP}

	if ! snapexists $snap; then
		log_fail "'$snap' does not exist."
	fi

	#
	# For the sake of the value which come from 'get_prop' is not equal
	# to the really mountpoint when the snapshot is unmounted. So, firstly
	# check and make sure this snapshot's been mounted in current system.
	#
	typeset mtpt=""
	if ismounted $snap; then
		mtpt=$(get_prop mountpoint $snap)
		(($? != 0)) && \
			log_fail "get_prop mountpoint $snap failed."
	fi

	destroy_dataset "$snap"
	[[ $mtpt != "" && -d $mtpt ]] && \
		log_must rm -rf $mtpt
}

#
# Common function used to cleanup clone.
#
# $1 clone name
#
function destroy_clone
{
	typeset clone=${1:-$TESTPOOL/$TESTCLONE}

	if ! datasetexists $clone; then
		log_fail "'$clone' does not existed."
	fi

	# With the same reason in destroy_snapshot
	typeset mtpt=""
	if ismounted $clone; then
		mtpt=$(get_prop mountpoint $clone)
		(($? != 0)) && \
			log_fail "get_prop mountpoint $clone failed."
	fi

	destroy_dataset "$clone"
	[[ $mtpt != "" && -d $mtpt ]] && \
		log_must rm -rf $mtpt
}

#
# Common function used to cleanup bookmark of file system or volume.  Default
# to delete the file system's bookmark.
#
# $1 bookmark name
#
function destroy_bookmark
{
	typeset bkmark=${1:-$TESTPOOL/$TESTFS#$TESTBKMARK}

	if ! bkmarkexists $bkmark; then
		log_fail "'$bkmarkp' does not existed."
	fi

	destroy_dataset "$bkmark"
}

# Return 0 if a snapshot exists; $? otherwise
#
# $1 - snapshot name

function snapexists
{
	zfs list -H -t snapshot "$1" > /dev/null 2>&1
	return $?
}

#
# Return 0 if a bookmark exists; $? otherwise
#
# $1 - bookmark name
#
function bkmarkexists
{
	zfs list -H -t bookmark "$1" > /dev/null 2>&1
	return $?
}

#
# Set a property to a certain value on a dataset.
# Sets a property of the dataset to the value as passed in.
# @param:
#	$1 dataset who's property is being set
#	$2 property to set
#	$3 value to set property to
# @return:
#	0 if the property could be set.
#	non-zero otherwise.
# @use: ZFS
#
function dataset_setprop
{
	typeset fn=dataset_setprop

	if (($# < 3)); then
		log_note "$fn: Insufficient parameters (need 3, had $#)"
		return 1
	fi
	typeset output=
	output=$(zfs set $2=$3 $1 2>&1)
	typeset rv=$?
	if ((rv != 0)); then
		log_note "Setting property on $1 failed."
		log_note "property $2=$3"
		log_note "Return Code: $rv"
		log_note "Output: $output"
		return $rv
	fi
	return 0
}

#
# Assign suite defined dataset properties.
# This function is used to apply the suite's defined default set of
# properties to a dataset.
# @parameters: $1 dataset to use
# @uses: ZFS COMPRESSION_PROP CHECKSUM_PROP
# @returns:
#   0 if the dataset has been altered.
#   1 if no pool name was passed in.
#   2 if the dataset could not be found.
#   3 if the dataset could not have it's properties set.
#
function dataset_set_defaultproperties
{
	typeset dataset="$1"

	[[ -z $dataset ]] && return 1

	typeset confset=
	typeset -i found=0
	for confset in $(zfs list); do
		if [[ $dataset = $confset ]]; then
			found=1
			break
		fi
	done
	[[ $found -eq 0 ]] && return 2
	if [[ -n $COMPRESSION_PROP ]]; then
		dataset_setprop $dataset compression $COMPRESSION_PROP || \
			return 3
		log_note "Compression set to '$COMPRESSION_PROP' on $dataset"
	fi
	if [[ -n $CHECKSUM_PROP ]]; then
		dataset_setprop $dataset checksum $CHECKSUM_PROP || \
			return 3
		log_note "Checksum set to '$CHECKSUM_PROP' on $dataset"
	fi
	return 0
}

#
# Check a numeric assertion
# @parameter: $@ the assertion to check
# @output: big loud notice if assertion failed
# @use: log_fail
#
function assert
{
	(($@)) || log_fail "$@"
}

#
# Function to format partition size of a disk
# Given a disk cxtxdx reduces all partitions
# to 0 size
#
function zero_partitions #<whole_disk_name>
{
	typeset diskname=$1
	typeset i

	if is_linux; then
		DSK=$DEV_DSKDIR/$diskname
		DSK=$(echo $DSK | sed -e "s|//|/|g")
		log_must parted $DSK -s -- mklabel gpt
		blockdev --rereadpt $DSK 2>/dev/null
		block_device_wait
	else
		for i in 0 1 3 4 5 6 7
		do
			log_must set_partition $i "" 0mb $diskname
		done
	fi

	return 0
}

#
# Given a slice, size and disk, this function
# formats the slice to the specified size.
# Size should be specified with units as per
# the `format` command requirements eg. 100mb 3gb
#
# NOTE: This entire interface is problematic for the Linux parted utilty
# which requires the end of the partition to be specified.  It would be
# best to retire this interface and replace it with something more flexible.
# At the moment a best effort is made.
#
function set_partition #<slice_num> <slice_start> <size_plus_units>  <whole_disk_name>
{
	typeset -i slicenum=$1
	typeset start=$2
	typeset size=$3
	typeset disk=$4

	if is_linux; then
		if [[ -z $size || -z $disk ]]; then
			log_fail "The size or disk name is unspecified."
		fi
		typeset size_mb=${size%%[mMgG]}

		size_mb=${size_mb%%[mMgG][bB]}
		if [[ ${size:1:1} == 'g' ]]; then
			((size_mb = size_mb * 1024))
		fi

		# Create GPT partition table when setting slice 0 or
		# when the device doesn't already contain a GPT label.
		parted $DEV_DSKDIR/$disk -s -- print 1 >/dev/null
		typeset ret_val=$?
		if [[ $slicenum -eq 0 || $ret_val -ne 0 ]]; then
			parted $DEV_DSKDIR/$disk -s -- mklabel gpt
			if [[ $? -ne 0 ]]; then
				log_note "Failed to create GPT partition table on $disk"
				return 1
			fi
		fi

		# When no start is given align on the first cylinder.
		if [[ -z "$start" ]]; then
			start=1
		fi

		# Determine the cylinder size for the device and using
		# that calculate the end offset in cylinders.
		typeset -i cly_size_kb=0
		cly_size_kb=$(parted -m $DEV_DSKDIR/$disk -s -- \
			unit cyl print | head -3 | tail -1 | \
			awk -F '[:k.]' '{print $4}')
		((end = (size_mb * 1024 / cly_size_kb) + start))

		parted $DEV_DSKDIR/$disk -s -- \
		    mkpart part$slicenum ${start}cyl ${end}cyl
		if [[ $? -ne 0 ]]; then
			log_note "Failed to create partition $slicenum on $disk"
			return 1
		fi

		blockdev --rereadpt $DEV_DSKDIR/$disk 2>/dev/null
		block_device_wait
	else
		if [[ -z $slicenum || -z $size || -z $disk ]]; then
			log_fail "The slice, size or disk name is unspecified."
		fi

		typeset format_file=/var/tmp/format_in.$$

		echo "partition" >$format_file
		echo "$slicenum" >> $format_file
		echo "" >> $format_file
		echo "" >> $format_file
		echo "$start" >> $format_file
		echo "$size" >> $format_file
		echo "label" >> $format_file
		echo "" >> $format_file
		echo "q" >> $format_file
		echo "q" >> $format_file

		format -e -s -d $disk -f $format_file
	fi

	typeset ret_val=$?
	rm -f $format_file
	if [[ $ret_val -ne 0 ]]; then
		log_note "Unable to format $disk slice $slicenum to $size"
		return 1
	fi
	return 0
}

#
# Delete all partitions on all disks - this is specifically for the use of multipath
# devices which currently can only be used in the test suite as raw/un-partitioned
# devices (ie a zpool cannot be created on a whole mpath device that has partitions)
#
function delete_partitions
{
	typeset -i j=1

	if [[ -z $DISK_ARRAY_NUM ]]; then
		DISK_ARRAY_NUM=$(echo ${DISKS} | nawk '{print NF}')
	fi
	if [[ -z $DISKSARRAY ]]; then
		DISKSARRAY=$DISKS
	fi

	if is_linux; then
		if (( $DISK_ARRAY_NUM == 1 )); then
			while ((j < MAX_PARTITIONS)); do
				parted $DEV_DSKDIR/$DISK -s rm $j \
				    > /dev/null 2>&1
				if (( $? == 1 )); then
					lsblk | egrep ${DISK}${SLICE_PREFIX}${j} > /dev/null
						if (( $? == 1 )); then
							log_note "Partitions for $DISK should be deleted"
						else
							log_fail "Partition for ${DISK}${SLICE_PREFIX}${j} not deleted"
						fi
						return 0
				else
					lsblk | egrep ${DISK}${SLICE_PREFIX}${j} > /dev/null
						if (( $? == 0 )); then
							log_fail "Partition for ${DISK}${SLICE_PREFIX}${j} not deleted"
						fi
				fi
				((j = j+1))
			done
		else
			for disk in `echo $DISKSARRAY`; do
				while ((j < MAX_PARTITIONS)); do
					parted $DEV_DSKDIR/$disk -s rm $j > /dev/null 2>&1
					if (( $? == 1 )); then
						lsblk | egrep ${disk}${SLICE_PREFIX}${j} > /dev/null
						if (( $? == 1 )); then
							log_note "Partitions for $disk should be deleted"
						else
							log_fail "Partition for ${disk}${SLICE_PREFIX}${j} not deleted"
						fi
						j=7
					else
						lsblk | egrep ${disk}${SLICE_PREFIX}${j} > /dev/null
						if (( $? == 0 )); then
							log_fail "Partition for ${disk}${SLICE_PREFIX}${j} not deleted"
						fi
					fi
					((j = j+1))
				done
				j=1
			done
		fi
	fi
	return 0
}

#
# Get the end cyl of the given slice
#
function get_endslice #<disk> <slice>
{
	typeset disk=$1
	typeset slice=$2
	if [[ -z $disk || -z $slice ]] ; then
		log_fail "The disk name or slice number is unspecified."
	fi

	if is_linux; then
		endcyl=$(parted -s $DEV_DSKDIR/$disk -- unit cyl print | \
			grep "part${slice}" | \
			awk '{print $3}' | \
			sed 's,cyl,,')
		((endcyl = (endcyl + 1)))
	else
		disk=${disk#/dev/dsk/}
		disk=${disk#/dev/rdsk/}
		disk=${disk%s*}

		typeset -i ratio=0
		ratio=$(prtvtoc /dev/rdsk/${disk}s2 | \
		    grep "sectors\/cylinder" | \
		    awk '{print $2}')

		if ((ratio == 0)); then
			return
		fi

		typeset -i endcyl=$(prtvtoc -h /dev/rdsk/${disk}s2 |
		    nawk -v token="$slice" '{if ($1==token) print $6}')

		((endcyl = (endcyl + 1) / ratio))
	fi

	echo $endcyl
}


#
# Given a size,disk and total slice number,  this function formats the
# disk slices from 0 to the total slice number with the same specified
# size.
#
function partition_disk	#<slice_size> <whole_disk_name>	<total_slices>
{
	typeset -i i=0
	typeset slice_size=$1
	typeset disk_name=$2
	typeset total_slices=$3
	typeset cyl

	zero_partitions $disk_name
	while ((i < $total_slices)); do
		if ! is_linux; then
			if ((i == 2)); then
				((i = i + 1))
				continue
			fi
		fi
		log_must set_partition $i "$cyl" $slice_size $disk_name
		cyl=$(get_endslice $disk_name $i)
		((i = i+1))
	done
}

#
# This function continues to write to a filenum number of files into dirnum
# number of directories until either file_write returns an error or the
# maximum number of files per directory have been written.
#
# Usage:
# fill_fs [destdir] [dirnum] [filenum] [bytes] [num_writes] [data]
#
# Return value: 0 on success
#		non 0 on error
#
# Where :
#	destdir:    is the directory where everything is to be created under
#	dirnum:	    the maximum number of subdirectories to use, -1 no limit
#	filenum:    the maximum number of files per subdirectory
#	bytes:	    number of bytes to write
#	num_writes: numer of types to write out bytes
#	data:	    the data that will be written
#
#	E.g.
#	file_fs /testdir 20 25 1024 256 0
#
# Note: bytes * num_writes equals the size of the testfile
#
function fill_fs # destdir dirnum filenum bytes num_writes data
{
	typeset destdir=${1:-$TESTDIR}
	typeset -i dirnum=${2:-50}
	typeset -i filenum=${3:-50}
	typeset -i bytes=${4:-8192}
	typeset -i num_writes=${5:-10240}
	typeset -i data=${6:-0}

	typeset -i odirnum=1
	typeset -i idirnum=0
	typeset -i fn=0
	typeset -i retval=0

	log_must mkdir -p $destdir/$idirnum
	while (($odirnum > 0)); do
		if ((dirnum >= 0 && idirnum >= dirnum)); then
			odirnum=0
			break
		fi
		file_write -o create -f $destdir/$idirnum/$TESTFILE.$fn \
		    -b $bytes -c $num_writes -d $data
		retval=$?
		if (($retval != 0)); then
			odirnum=0
			break
		fi
		if (($fn >= $filenum)); then
			fn=0
			((idirnum = idirnum + 1))
			log_must mkdir -p $destdir/$idirnum
		else
			((fn = fn + 1))
		fi
	done
	return $retval
}

#
# Simple function to get the specified property. If unable to
# get the property then exits.
#
# Note property is in 'parsable' format (-p)
#
function get_prop # property dataset
{
	typeset prop_val
	typeset prop=$1
	typeset dataset=$2

	prop_val=$(zfs get -pH -o value $prop $dataset 2>/dev/null)
	if [[ $? -ne 0 ]]; then
		log_note "Unable to get $prop property for dataset " \
		"$dataset"
		return 1
	fi

	echo "$prop_val"
	return 0
}

#
# Simple function to get the specified property of pool. If unable to
# get the property then exits.
#
# Note property is in 'parsable' format (-p)
#
function get_pool_prop # property pool
{
	typeset prop_val
	typeset prop=$1
	typeset pool=$2

	if poolexists $pool ; then
		prop_val=$(zpool get -pH $prop $pool 2>/dev/null | tail -1 | \
			awk '{print $3}')
		if [[ $? -ne 0 ]]; then
			log_note "Unable to get $prop property for pool " \
			"$pool"
			return 1
		fi
	else
		log_note "Pool $pool not exists."
		return 1
	fi

	echo "$prop_val"
	return 0
}

# Return 0 if a pool exists; $? otherwise
#
# $1 - pool name

function poolexists
{
	typeset pool=$1

	if [[ -z $pool ]]; then
		log_note "No pool name given."
		return 1
	fi

	zpool get name "$pool" > /dev/null 2>&1
	return $?
}

# Return 0 if all the specified datasets exist; $? otherwise
#
# $1-n  dataset name
function datasetexists
{
	if (($# == 0)); then
		log_note "No dataset name given."
		return 1
	fi

	while (($# > 0)); do
		zfs get name $1 > /dev/null 2>&1 || \
			return $?
		shift
	done

	return 0
}

# return 0 if none of the specified datasets exists, otherwise return 1.
#
# $1-n  dataset name
function datasetnonexists
{
	if (($# == 0)); then
		log_note "No dataset name given."
		return 1
	fi

	while (($# > 0)); do
		zfs list -H -t filesystem,snapshot,volume $1 > /dev/null 2>&1 \
		    && return 1
		shift
	done

	return 0
}

function is_shared_impl
{
	typeset fs=$1
	typeset mtpt

	if is_linux; then
		for mtpt in `share | awk '{print $1}'` ; do
			if [[ $mtpt == $fs ]] ; then
				return 0
			fi
		done
		return 1
	fi

	for mtpt in `share | awk '{print $2}'` ; do
		if [[ $mtpt == $fs ]] ; then
			return 0
		fi
	done

	typeset stat=$(svcs -H -o STA nfs/server:default)
	if [[ $stat != "ON" ]]; then
		log_note "Current nfs/server status: $stat"
	fi

	return 1
}

#
# Given a mountpoint, or a dataset name, determine if it is shared via NFS.
#
# Returns 0 if shared, 1 otherwise.
#
function is_shared
{
	typeset fs=$1
	typeset mtpt

	if [[ $fs != "/"* ]] ; then
		if datasetnonexists "$fs" ; then
			return 1
		else
			mtpt=$(get_prop mountpoint "$fs")
			case $mtpt in
				none|legacy|-) return 1
					;;
				*)	fs=$mtpt
					;;
			esac
		fi
	fi

	is_shared_impl "$fs"
}

#
# Given a dataset name determine if it is shared via SMB.
#
# Returns 0 if shared, 1 otherwise.
#
function is_shared_smb
{
	typeset fs=$1
	typeset mtpt

	if datasetnonexists "$fs" ; then
		return 1
	else
		fs=$(echo $fs | sed 's@/@_@g')
	fi

	if is_linux; then
		for mtpt in `net usershare list | awk '{print $1}'` ; do
			if [[ $mtpt == $fs ]] ; then
				return 0
			fi
		done
		return 1
	else
		log_unsupported "Currently unsupported by the test framework"
		return 1
	fi
}

#
# Given a mountpoint, determine if it is not shared via NFS.
#
# Returns 0 if not shared, 1 otherwise.
#
function not_shared
{
	typeset fs=$1

	is_shared $fs
	if (($? == 0)); then
		return 1
	fi

	return 0
}

#
# Given a dataset determine if it is not shared via SMB.
#
# Returns 0 if not shared, 1 otherwise.
#
function not_shared_smb
{
	typeset fs=$1

	is_shared_smb $fs
	if (($? == 0)); then
		return 1
	fi

	return 0
}

#
# Helper function to unshare a mountpoint.
#
function unshare_fs #fs
{
	typeset fs=$1

	is_shared $fs || is_shared_smb $fs
	if (($? == 0)); then
		log_must zfs unshare $fs
	fi

	return 0
}

#
# Helper function to share a NFS mountpoint.
#
function share_nfs #fs
{
	typeset fs=$1

	if is_linux; then
		is_shared $fs
		if (($? != 0)); then
			log_must share "*:$fs"
		fi
	else
		is_shared $fs
		if (($? != 0)); then
			log_must share -F nfs $fs
		fi
	fi

	return 0
}

#
# Helper function to unshare a NFS mountpoint.
#
function unshare_nfs #fs
{
	typeset fs=$1

	if is_linux; then
		is_shared $fs
		if (($? == 0)); then
			log_must unshare -u "*:$fs"
		fi
	else
		is_shared $fs
		if (($? == 0)); then
			log_must unshare -F nfs $fs
		fi
	fi

	return 0
}

#
# Helper function to show NFS shares.
#
function showshares_nfs
{
	if is_linux; then
		share -v
	else
		share -F nfs
	fi

	return 0
}

#
# Helper function to show SMB shares.
#
function showshares_smb
{
	if is_linux; then
		net usershare list
	else
		share -F smb
	fi

	return 0
}

#
# Check NFS server status and trigger it online.
#
function setup_nfs_server
{
	# Cannot share directory in non-global zone.
	#
	if ! is_global_zone; then
		log_note "Cannot trigger NFS server by sharing in LZ."
		return
	fi

	if is_linux; then
		#
		# Re-synchronize /var/lib/nfs/etab with /etc/exports and
		# /etc/exports.d./* to provide a clean test environment.
		#
		log_must share -r

		log_note "NFS server must be started prior to running ZTS."
		return
	fi

	typeset nfs_fmri="svc:/network/nfs/server:default"
	if [[ $(svcs -Ho STA $nfs_fmri) != "ON" ]]; then
		#
		# Only really sharing operation can enable NFS server
		# to online permanently.
		#
		typeset dummy=/tmp/dummy

		if [[ -d $dummy ]]; then
			log_must rm -rf $dummy
		fi

		log_must mkdir $dummy
		log_must share $dummy

		#
		# Waiting for fmri's status to be the final status.
		# Otherwise, in transition, an asterisk (*) is appended for
		# instances, unshare will reverse status to 'DIS' again.
		#
		# Waiting for 1's at least.
		#
		log_must sleep 1
		timeout=10
		while [[ timeout -ne 0 && $(svcs -Ho STA $nfs_fmri) == *'*' ]]
		do
			log_must sleep 1

			((timeout -= 1))
		done

		log_must unshare $dummy
		log_must rm -rf $dummy
	fi

	log_note "Current NFS status: '$(svcs -Ho STA,FMRI $nfs_fmri)'"
}

#
# To verify whether calling process is in global zone
#
# Return 0 if in global zone, 1 in non-global zone
#
function is_global_zone
{
	if is_linux; then
		return 0
	else
		typeset cur_zone=$(zonename 2>/dev/null)
		if [[ $cur_zone != "global" ]]; then
			return 1
		fi
		return 0
	fi
}

#
# Verify whether test is permitted to run from
# global zone, local zone, or both
#
# $1 zone limit, could be "global", "local", or "both"(no limit)
#
# Return 0 if permitted, otherwise exit with log_unsupported
#
function verify_runnable # zone limit
{
	typeset limit=$1

	[[ -z $limit ]] && return 0

	if is_global_zone ; then
		case $limit in
			global|both)
				;;
			local)	log_unsupported "Test is unable to run from "\
					"global zone."
				;;
			*)	log_note "Warning: unknown limit $limit - " \
					"use both."
				;;
		esac
	else
		case $limit in
			local|both)
				;;
			global)	log_unsupported "Test is unable to run from "\
					"local zone."
				;;
			*)	log_note "Warning: unknown limit $limit - " \
					"use both."
				;;
		esac

		reexport_pool
	fi

	return 0
}

# Return 0 if create successfully or the pool exists; $? otherwise
# Note: In local zones, this function should return 0 silently.
#
# $1 - pool name
# $2-n - [keyword] devs_list

function create_pool #pool devs_list
{
	typeset pool=${1%%/*}

	shift

	if [[ -z $pool ]]; then
		log_note "Missing pool name."
		return 1
	fi

	if poolexists $pool ; then
		destroy_pool $pool
	fi

	if is_global_zone ; then
		[[ -d /$pool ]] && rm -rf /$pool
		log_must zpool create -f $pool $@
	fi

	return 0
}

# Return 0 if destroy successfully or the pool exists; $? otherwise
# Note: In local zones, this function should return 0 silently.
#
# $1 - pool name
# Destroy pool with the given parameters.

function destroy_pool #pool
{
	typeset pool=${1%%/*}
	typeset mtpt

	if [[ -z $pool ]]; then
		log_note "No pool name given."
		return 1
	fi

	if is_global_zone ; then
		if poolexists "$pool" ; then
			mtpt=$(get_prop mountpoint "$pool")

			# At times, syseventd/udev activity can cause attempts
			# to destroy a pool to fail with EBUSY. We retry a few
			# times allowing failures before requiring the destroy
			# to succeed.
			log_must_busy zpool destroy -f $pool

			[[ -d $mtpt ]] && \
				log_must rm -rf $mtpt
		else
			log_note "Pool does not exist. ($pool)"
			return 1
		fi
	fi

	return 0
}

# Return 0 if created successfully; $? otherwise
#
# $1 - dataset name
# $2-n - dataset options

function create_dataset #dataset dataset_options
{
	typeset dataset=$1

	shift

	if [[ -z $dataset ]]; then
		log_note "Missing dataset name."
		return 1
	fi

	if datasetexists $dataset ; then
		destroy_dataset $dataset
	fi

	log_must zfs create $@ $dataset

	return 0
}

# Return 0 if destroy successfully or the dataset exists; $? otherwise
# Note: In local zones, this function should return 0 silently.
#
# $1 - dataset name
# $2 - custom arguments for zfs destroy
# Destroy dataset with the given parameters.

function destroy_dataset #dataset #args
{
	typeset dataset=$1
	typeset mtpt
	typeset args=${2:-""}

	if [[ -z $dataset ]]; then
		log_note "No dataset name given."
		return 1
	fi

	if is_global_zone ; then
		if datasetexists "$dataset" ; then
			mtpt=$(get_prop mountpoint "$dataset")
			log_must_busy zfs destroy $args $dataset

			[[ -d $mtpt ]] && \
				log_must rm -rf $mtpt
		else
			log_note "Dataset does not exist. ($dataset)"
			return 1
		fi
	fi

	return 0
}

#
# Firstly, create a pool with 5 datasets. Then, create a single zone and
# export the 5 datasets to it. In addition, we also add a ZFS filesystem
# and a zvol device to the zone.
#
# $1 zone name
# $2 zone root directory prefix
# $3 zone ip
#
function zfs_zones_setup #zone_name zone_root zone_ip
{
	typeset zone_name=${1:-$(hostname)-z}
	typeset zone_root=${2:-"/zone_root"}
	typeset zone_ip=${3:-"10.1.1.10"}
	typeset prefix_ctr=$ZONE_CTR
	typeset pool_name=$ZONE_POOL
	typeset -i cntctr=5
	typeset -i i=0

	# Create pool and 5 container within it
	#
	[[ -d /$pool_name ]] && rm -rf /$pool_name
	log_must zpool create -f $pool_name $DISKS
	while ((i < cntctr)); do
		log_must zfs create $pool_name/$prefix_ctr$i
		((i += 1))
	done

	# create a zvol
	log_must zfs create -V 1g $pool_name/zone_zvol
	block_device_wait

	#
	# If current system support slog, add slog device for pool
	#
	if verify_slog_support ; then
		typeset sdevs="$TEST_BASE_DIR/sdev1 $TEST_BASE_DIR/sdev2"
		log_must mkfile $MINVDEVSIZE $sdevs
		log_must zpool add $pool_name log mirror $sdevs
	fi

	# this isn't supported just yet.
	# Create a filesystem. In order to add this to
	# the zone, it must have it's mountpoint set to 'legacy'
	# log_must zfs create $pool_name/zfs_filesystem
	# log_must zfs set mountpoint=legacy $pool_name/zfs_filesystem

	[[ -d $zone_root ]] && \
		log_must rm -rf $zone_root/$zone_name
	[[ ! -d $zone_root ]] && \
		log_must mkdir -p -m 0700 $zone_root/$zone_name

	# Create zone configure file and configure the zone
	#
	typeset zone_conf=/tmp/zone_conf.$$
	echo "create" > $zone_conf
	echo "set zonepath=$zone_root/$zone_name" >> $zone_conf
	echo "set autoboot=true" >> $zone_conf
	i=0
	while ((i < cntctr)); do
		echo "add dataset" >> $zone_conf
		echo "set name=$pool_name/$prefix_ctr$i" >> \
			$zone_conf
		echo "end" >> $zone_conf
		((i += 1))
	done

	# add our zvol to the zone
	echo "add device" >> $zone_conf
	echo "set match=/dev/zvol/dsk/$pool_name/zone_zvol" >> $zone_conf
	echo "end" >> $zone_conf

	# add a corresponding zvol rdsk to the zone
	echo "add device" >> $zone_conf
	echo "set match=$ZVOL_RDEVDIR/$pool_name/zone_zvol" >> $zone_conf
	echo "end" >> $zone_conf

	# once it's supported, we'll add our filesystem to the zone
	# echo "add fs" >> $zone_conf
	# echo "set type=zfs" >> $zone_conf
	# echo "set special=$pool_name/zfs_filesystem" >> $zone_conf
	# echo "set dir=/export/zfs_filesystem" >> $zone_conf
	# echo "end" >> $zone_conf

	echo "verify" >> $zone_conf
	echo "commit" >> $zone_conf
	log_must zonecfg -z $zone_name -f $zone_conf
	log_must rm -f $zone_conf

	# Install the zone
	zoneadm -z $zone_name install
	if (($? == 0)); then
		log_note "SUCCESS: zoneadm -z $zone_name install"
	else
		log_fail "FAIL: zoneadm -z $zone_name install"
	fi

	# Install sysidcfg file
	#
	typeset sysidcfg=$zone_root/$zone_name/root/etc/sysidcfg
	echo "system_locale=C" > $sysidcfg
	echo  "terminal=dtterm" >> $sysidcfg
	echo  "network_interface=primary {" >> $sysidcfg
	echo  "hostname=$zone_name" >> $sysidcfg
	echo  "}" >> $sysidcfg
	echo  "name_service=NONE" >> $sysidcfg
	echo  "root_password=mo791xfZ/SFiw" >> $sysidcfg
	echo  "security_policy=NONE" >> $sysidcfg
	echo  "timezone=US/Eastern" >> $sysidcfg

	# Boot this zone
	log_must zoneadm -z $zone_name boot
}

#
# Reexport TESTPOOL & TESTPOOL(1-4)
#
function reexport_pool
{
	typeset -i cntctr=5
	typeset -i i=0

	while ((i < cntctr)); do
		if ((i == 0)); then
			TESTPOOL=$ZONE_POOL/$ZONE_CTR$i
			if ! ismounted $TESTPOOL; then
				log_must zfs mount $TESTPOOL
			fi
		else
			eval TESTPOOL$i=$ZONE_POOL/$ZONE_CTR$i
			if eval ! ismounted \$TESTPOOL$i; then
				log_must eval zfs mount \$TESTPOOL$i
			fi
		fi
		((i += 1))
	done
}

#
# Verify a given disk or pool state
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_state # pool disk state{online,offline,degraded}
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset state=$3

	[[ -z $pool ]] || [[ -z $state ]] \
	    && log_fail "Arguments invalid or missing"

	if [[ -z $disk ]]; then
		#check pool state only
		zpool get -H -o value health $pool \
		    | grep -i "$state" > /dev/null 2>&1
	else
		zpool status -v $pool | grep "$disk"  \
		    | grep -i "$state" > /dev/null 2>&1
	fi

	return $?
}

#
# Get the mountpoint of snapshot
# For the snapshot use <mp_filesystem>/.zfs/snapshot/<snap>
# as its mountpoint
#
function snapshot_mountpoint
{
	typeset dataset=${1:-$TESTPOOL/$TESTFS@$TESTSNAP}

	if [[ $dataset != *@* ]]; then
		log_fail "Error name of snapshot '$dataset'."
	fi

	typeset fs=${dataset%@*}
	typeset snap=${dataset#*@}

	if [[ -z $fs || -z $snap ]]; then
		log_fail "Error name of snapshot '$dataset'."
	fi

	echo $(get_prop mountpoint $fs)/.zfs/snapshot/$snap
}

#
# Given a device and 'ashift' value verify it's correctly set on every label
#
function verify_ashift # device ashift
{
	typeset device="$1"
	typeset ashift="$2"

	zdb -e -lll $device | awk -v ashift=$ashift '/ashift: / {
	    if (ashift != $2)
	        exit 1;
	    else
	        count++;
	    } END {
	    if (count != 4)
	        exit 1;
	    else
	        exit 0;
	    }'

	return $?
}

#
# Given a pool and file system, this function will verify the file system
# using the zdb internal tool. Note that the pool is exported and imported
# to ensure it has consistent state.
#
function verify_filesys # pool filesystem dir
{
	typeset pool="$1"
	typeset filesys="$2"
	typeset zdbout="/tmp/zdbout.$$"

	shift
	shift
	typeset dirs=$@
	typeset search_path=""

	log_note "Calling zdb to verify filesystem '$filesys'"
	zfs unmount -a > /dev/null 2>&1
	log_must zpool export $pool

	if [[ -n $dirs ]] ; then
		for dir in $dirs ; do
			search_path="$search_path -d $dir"
		done
	fi

	log_must zpool import $search_path $pool

	zdb -cudi $filesys > $zdbout 2>&1
	if [[ $? != 0 ]]; then
		log_note "Output: zdb -cudi $filesys"
		cat $zdbout
		log_fail "zdb detected errors with: '$filesys'"
	fi

	log_must zfs mount -a
	log_must rm -rf $zdbout
}

#
# Given a pool issue a scrub and verify that no checksum errors are reported.
#
function verify_pool
{
	typeset pool=${1:-$TESTPOOL}

	log_must zpool scrub $pool
	log_must wait_scrubbed $pool

	cksum=$(zpool status $pool | awk 'L{print $NF;L=0} /CKSUM$/{L=1}')
	if [[ $cksum != 0 ]]; then
		log_must zpool status -v
	        log_fail "Unexpected CKSUM errors found on $pool ($cksum)"
	fi
}

#
# Given a pool, and this function list all disks in the pool
#
function get_disklist # pool
{
	typeset disklist=""

	disklist=$(zpool iostat -v $1 | nawk '(NR >4) {print $1}' | \
	    grep -v "\-\-\-\-\-" | \
	    egrep -v -e "^(mirror|raidz1|raidz2|spare|log|cache)$")

	echo $disklist
}

#
# Given a pool, and this function list all disks in the pool with their full
# path (like "/dev/sda" instead of "sda").
#
function get_disklist_fullpath # pool
{
	args="-P $1"
	get_disklist $args
}



# /**
#  This function kills a given list of processes after a time period. We use
#  this in the stress tests instead of STF_TIMEOUT so that we can have processes
#  run for a fixed amount of time, yet still pass. Tests that hit STF_TIMEOUT
#  would be listed as FAIL, which we don't want : we're happy with stress tests
#  running for a certain amount of time, then finishing.
#
# @param $1 the time in seconds after which we should terminate these processes
# @param $2..$n the processes we wish to terminate.
# */
function stress_timeout
{
	typeset -i TIMEOUT=$1
	shift
	typeset cpids="$@"

	log_note "Waiting for child processes($cpids). " \
		"It could last dozens of minutes, please be patient ..."
	log_must sleep $TIMEOUT

	log_note "Killing child processes after ${TIMEOUT} stress timeout."
	typeset pid
	for pid in $cpids; do
		ps -p $pid > /dev/null 2>&1
		if (($? == 0)); then
			log_must kill -USR1 $pid
		fi
	done
}

#
# Verify a given hotspare disk is inuse or avail
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_hotspare_state # pool disk state{inuse,avail}
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset state=$3

	cur_state=$(get_device_state $pool $disk "spares")

	if [[ $state != ${cur_state} ]]; then
		return 1
	fi
	return 0
}

#
# Wait until a hotspare transitions to a given state or times out.
#
# Return 0 when  pool/disk matches expected state, 1 on timeout.
#
function wait_hotspare_state # pool disk state timeout
{
	typeset pool=$1
	typeset disk=${2#*$DEV_DSKDIR/}
	typeset state=$3
	typeset timeout=${4:-60}
	typeset -i i=0

	while [[ $i -lt $timeout ]]; do
		if check_hotspare_state $pool $disk $state; then
			return 0
		fi

		i=$((i+1))
		sleep 1
	done

	return 1
}

#
# Verify a given slog disk is inuse or avail
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_slog_state # pool disk state{online,offline,unavail}
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset state=$3

	cur_state=$(get_device_state $pool $disk "logs")

	if [[ $state != ${cur_state} ]]; then
		return 1
	fi
	return 0
}

#
# Verify a given vdev disk is inuse or avail
#
# Return 0 is pool/disk matches expected state, 1 otherwise
#
function check_vdev_state # pool disk state{online,offline,unavail}
{
	typeset pool=$1
	typeset disk=${2#*$DEV_DSKDIR/}
	typeset state=$3

	cur_state=$(get_device_state $pool $disk)

	if [[ $state != ${cur_state} ]]; then
		return 1
	fi
	return 0
}

#
# Wait until a vdev transitions to a given state or times out.
#
# Return 0 when  pool/disk matches expected state, 1 on timeout.
#
function wait_vdev_state # pool disk state timeout
{
	typeset pool=$1
	typeset disk=${2#*$DEV_DSKDIR/}
	typeset state=$3
	typeset timeout=${4:-60}
	typeset -i i=0

	while [[ $i -lt $timeout ]]; do
		if check_vdev_state $pool $disk $state; then
			return 0
		fi

		i=$((i+1))
		sleep 1
	done

	return 1
}

#
# Check the output of 'zpool status -v <pool>',
# and to see if the content of <token> contain the <keyword> specified.
#
# Return 0 is contain, 1 otherwise
#
function check_pool_status # pool token keyword <verbose>
{
	typeset pool=$1
	typeset token=$2
	typeset keyword=$3
	typeset verbose=${4:-false}

	scan=$(zpool status -v "$pool" 2>/dev/null | nawk -v token="$token:" '
		($1==token) {print $0}')
	if [[ $verbose == true ]]; then
		log_note $scan
	fi
	echo $scan | grep -i "$keyword" > /dev/null 2>&1

	return $?
}

#
# These 6 following functions are instance of check_pool_status()
#	is_pool_resilvering - to check if the pool is resilver in progress
#	is_pool_resilvered - to check if the pool is resilver completed
#	is_pool_scrubbing - to check if the pool is scrub in progress
#	is_pool_scrubbed - to check if the pool is scrub completed
#	is_pool_scrub_stopped - to check if the pool is scrub stopped
#	is_pool_scrub_paused - to check if the pool has scrub paused
#	is_pool_removing - to check if the pool is removing a vdev
#	is_pool_removed - to check if the pool is remove completed
#
function is_pool_resilvering #pool <verbose>
{
	check_pool_status "$1" "scan" "resilver in progress since " $2
	return $?
}

function is_pool_resilvered #pool <verbose>
{
	check_pool_status "$1" "scan" "resilvered " $2
	return $?
}

function is_pool_scrubbing #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub in progress since " $2
	return $?
}

function is_pool_scrubbed #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub repaired" $2
	return $?
}

function is_pool_scrub_stopped #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub canceled" $2
	return $?
}

function is_pool_scrub_paused #pool <verbose>
{
	check_pool_status "$1" "scan" "scrub paused since " $2
	return $?
}

function is_pool_removing #pool
{
	check_pool_status "$1" "remove" "in progress since "
	return $?
}

function is_pool_removed #pool
{
	check_pool_status "$1" "remove" "completed on"
	return $?
}

function wait_for_degraded
{
	typeset pool=$1
	typeset timeout=${2:-30}
	typeset t0=$SECONDS

	while :; do
		[[ $(get_pool_prop health $pool) == "DEGRADED" ]] && break
		log_note "$pool is not yet degraded."
		sleep 1
		if ((SECONDS - t0 > $timeout)); then
			log_note "$pool not degraded after $timeout seconds."
			return 1
		fi
	done

	return 0
}

#
# Use create_pool()/destroy_pool() to clean up the information in
# in the given disk to avoid slice overlapping.
#
function cleanup_devices #vdevs
{
	typeset pool="foopool$$"

	if poolexists $pool ; then
		destroy_pool $pool
	fi

	create_pool $pool $@
	destroy_pool $pool

	return 0
}

#/**
# A function to find and locate free disks on a system or from given
# disks as the parameter. It works by locating disks that are in use
# as swap devices and dump devices, and also disks listed in /etc/vfstab
#
# $@ given disks to find which are free, default is all disks in
# the test system
#
# @return a string containing the list of available disks
#*/
function find_disks
{
	# Trust provided list, no attempt is made to locate unused devices.
	if is_linux; then
		echo "$@"
		return
	fi


	sfi=/tmp/swaplist.$$
	dmpi=/tmp/dumpdev.$$
	max_finddisksnum=${MAX_FINDDISKSNUM:-6}

	swap -l > $sfi
	dumpadm > $dmpi 2>/dev/null

# write an awk script that can process the output of format
# to produce a list of disks we know about. Note that we have
# to escape "$2" so that the shell doesn't interpret it while
# we're creating the awk script.
# -------------------
	cat > /tmp/find_disks.awk <<EOF
#!/bin/nawk -f
	BEGIN { FS="."; }

	/^Specify disk/{
		searchdisks=0;
	}

	{
		if (searchdisks && \$2 !~ "^$"){
			split(\$2,arr," ");
			print arr[1];
		}
	}

	/^AVAILABLE DISK SELECTIONS:/{
		searchdisks=1;
	}
EOF
#---------------------

	chmod 755 /tmp/find_disks.awk
	disks=${@:-$(echo "" | format -e 2>/dev/null | /tmp/find_disks.awk)}
	rm /tmp/find_disks.awk

	unused=""
	for disk in $disks; do
	# Check for mounted
		grep "${disk}[sp]" /etc/mnttab >/dev/null
		(($? == 0)) && continue
	# Check for swap
		grep "${disk}[sp]" $sfi >/dev/null
		(($? == 0)) && continue
	# check for dump device
		grep "${disk}[sp]" $dmpi >/dev/null
		(($? == 0)) && continue
	# check to see if this disk hasn't been explicitly excluded
	# by a user-set environment variable
		echo "${ZFS_HOST_DEVICES_IGNORE}" | grep "${disk}" > /dev/null
		(($? == 0)) && continue
		unused_candidates="$unused_candidates $disk"
	done
	rm $sfi
	rm $dmpi

# now just check to see if those disks do actually exist
# by looking for a device pointing to the first slice in
# each case. limit the number to max_finddisksnum
	count=0
	for disk in $unused_candidates; do
		if [ -b $DEV_DSKDIR/${disk}s0 ]; then
		if [ $count -lt $max_finddisksnum ]; then
			unused="$unused $disk"
			# do not impose limit if $@ is provided
			[[ -z $@ ]] && ((count = count + 1))
		fi
		fi
	done

# finally, return our disk list
	echo $unused
}

#
# Add specified user to specified group
#
# $1 group name
# $2 user name
# $3 base of the homedir (optional)
#
function add_user #<group_name> <user_name> <basedir>
{
	typeset gname=$1
	typeset uname=$2
	typeset basedir=${3:-"/var/tmp"}

	if ((${#gname} == 0 || ${#uname} == 0)); then
		log_fail "group name or user name are not defined."
	fi

	log_must useradd -g $gname -d $basedir/$uname -m $uname
	echo "export PATH=\"$STF_PATH\"" >>$basedir/$uname/.profile
	echo "export PATH=\"$STF_PATH\"" >>$basedir/$uname/.bash_profile
	echo "export PATH=\"$STF_PATH\"" >>$basedir/$uname/.login

	# Add new users to the same group and the command line utils.
	# This allows them to be run out of the original users home
	# directory as long as it permissioned to be group readable.
	if is_linux; then
		cmd_group=$(stat --format="%G" $(which zfs))
		log_must usermod -a -G $cmd_group $uname
	fi

	return 0
}

#
# Delete the specified user.
#
# $1 login name
# $2 base of the homedir (optional)
#
function del_user #<logname> <basedir>
{
	typeset user=$1
	typeset basedir=${2:-"/var/tmp"}

	if ((${#user} == 0)); then
		log_fail "login name is necessary."
	fi

	if id $user > /dev/null 2>&1; then
		log_must_retry "currently used" 5 userdel $user
	fi

	[[ -d $basedir/$user ]] && rm -fr $basedir/$user

	return 0
}

#
# Select valid gid and create specified group.
#
# $1 group name
#
function add_group #<group_name>
{
	typeset group=$1

	if ((${#group} == 0)); then
		log_fail "group name is necessary."
	fi

	# Assign 100 as the base gid, a larger value is selected for
	# Linux because for many distributions 1000 and under are reserved.
	if is_linux; then
		while true; do
			groupadd $group > /dev/null 2>&1
			typeset -i ret=$?
			case $ret in
				0) return 0 ;;
				*) return 1 ;;
			esac
		done
	else
		typeset -i gid=100
		while true; do
			groupadd -g $gid $group > /dev/null 2>&1
			typeset -i ret=$?
			case $ret in
				0) return 0 ;;
				# The gid is not  unique
				4) ((gid += 1)) ;;
				*) return 1 ;;
			esac
		done
	fi
}

#
# Delete the specified group.
#
# $1 group name
#
function del_group #<group_name>
{
	typeset grp=$1
	if ((${#grp} == 0)); then
		log_fail "group name is necessary."
	fi

	if is_linux; then
		getent group $grp > /dev/null 2>&1
		typeset -i ret=$?
		case $ret in
			# Group does not exist.
			2) return 0 ;;
			# Name already exists as a group name
			0) log_must groupdel $grp ;;
			*) return 1 ;;
		esac
	else
		groupmod -n $grp $grp > /dev/null 2>&1
		typeset -i ret=$?
		case $ret in
			# Group does not exist.
			6) return 0 ;;
			# Name already exists as a group name
			9) log_must groupdel $grp ;;
			*) return 1 ;;
		esac
	fi

	return 0
}

#
# This function will return true if it's safe to destroy the pool passed
# as argument 1. It checks for pools based on zvols and files, and also
# files contained in a pool that may have a different mountpoint.
#
function safe_to_destroy_pool { # $1 the pool name

	typeset pool=""
	typeset DONT_DESTROY=""

	# We check that by deleting the $1 pool, we're not
	# going to pull the rug out from other pools. Do this
	# by looking at all other pools, ensuring that they
	# aren't built from files or zvols contained in this pool.

	for pool in $(zpool list -H -o name)
	do
		ALTMOUNTPOOL=""

		# this is a list of the top-level directories in each of the
		# files that make up the path to the files the pool is based on
		FILEPOOL=$(zpool status -v $pool | grep /$1/ | \
			awk '{print $1}')

		# this is a list of the zvols that make up the pool
		ZVOLPOOL=$(zpool status -v $pool | grep "$ZVOL_DEVDIR/$1$" \
		    | awk '{print $1}')

		# also want to determine if it's a file-based pool using an
		# alternate mountpoint...
		POOL_FILE_DIRS=$(zpool status -v $pool | \
					grep / | awk '{print $1}' | \
					awk -F/ '{print $2}' | grep -v "dev")

		for pooldir in $POOL_FILE_DIRS
		do
			OUTPUT=$(zfs list -H -r -o mountpoint $1 | \
					grep "${pooldir}$" | awk '{print $1}')

			ALTMOUNTPOOL="${ALTMOUNTPOOL}${OUTPUT}"
		done


		if [ ! -z "$ZVOLPOOL" ]
		then
			DONT_DESTROY="true"
			log_note "Pool $pool is built from $ZVOLPOOL on $1"
		fi

		if [ ! -z "$FILEPOOL" ]
		then
			DONT_DESTROY="true"
			log_note "Pool $pool is built from $FILEPOOL on $1"
		fi

		if [ ! -z "$ALTMOUNTPOOL" ]
		then
			DONT_DESTROY="true"
			log_note "Pool $pool is built from $ALTMOUNTPOOL on $1"
		fi
	done

	if [ -z "${DONT_DESTROY}" ]
	then
		return 0
	else
		log_note "Warning: it is not safe to destroy $1!"
		return 1
	fi
}

#
# Get the available ZFS compression options
# $1 option type zfs_set|zfs_compress
#
function get_compress_opts
{
	typeset COMPRESS_OPTS
	typeset GZIP_OPTS="gzip gzip-1 gzip-2 gzip-3 gzip-4 gzip-5 \
			gzip-6 gzip-7 gzip-8 gzip-9"

	if [[ $1 == "zfs_compress" ]] ; then
		COMPRESS_OPTS="on lzjb"
	elif [[ $1 == "zfs_set" ]] ; then
		COMPRESS_OPTS="on off lzjb"
	fi
	typeset valid_opts="$COMPRESS_OPTS"
	zfs get 2>&1 | grep gzip >/dev/null 2>&1
	if [[ $? -eq 0 ]]; then
		valid_opts="$valid_opts $GZIP_OPTS"
	fi
	echo "$valid_opts"
}

#
# Verify zfs operation with -p option work as expected
# $1 operation, value could be create, clone or rename
# $2 dataset type, value could be fs or vol
# $3 dataset name
# $4 new dataset name
#
function verify_opt_p_ops
{
	typeset ops=$1
	typeset datatype=$2
	typeset dataset=$3
	typeset newdataset=$4

	if [[ $datatype != "fs" && $datatype != "vol" ]]; then
		log_fail "$datatype is not supported."
	fi

	# check parameters accordingly
	case $ops in
		create)
			newdataset=$dataset
			dataset=""
			if [[ $datatype == "vol" ]]; then
				ops="create -V $VOLSIZE"
			fi
			;;
		clone)
			if [[ -z $newdataset ]]; then
				log_fail "newdataset should not be empty" \
					"when ops is $ops."
			fi
			log_must datasetexists $dataset
			log_must snapexists $dataset
			;;
		rename)
			if [[ -z $newdataset ]]; then
				log_fail "newdataset should not be empty" \
					"when ops is $ops."
			fi
			log_must datasetexists $dataset
			log_mustnot snapexists $dataset
			;;
		*)
			log_fail "$ops is not supported."
			;;
	esac

	# make sure the upper level filesystem does not exist
	destroy_dataset "${newdataset%/*}" "-rRf"

	# without -p option, operation will fail
	log_mustnot zfs $ops $dataset $newdataset
	log_mustnot datasetexists $newdataset ${newdataset%/*}

	# with -p option, operation should succeed
	log_must zfs $ops -p $dataset $newdataset
	block_device_wait

	if ! datasetexists $newdataset ; then
		log_fail "-p option does not work for $ops"
	fi

	# when $ops is create or clone, redo the operation still return zero
	if [[ $ops != "rename" ]]; then
		log_must zfs $ops -p $dataset $newdataset
	fi

	return 0
}

#
# Get configuration of pool
# $1 pool name
# $2 config name
#
function get_config
{
	typeset pool=$1
	typeset config=$2
	typeset alt_root

	if ! poolexists "$pool" ; then
		return 1
	fi
	alt_root=$(zpool list -H $pool | awk '{print $NF}')
	if [[ $alt_root == "-" ]]; then
		value=$(zdb -C $pool | grep "$config:" | awk -F: \
		    '{print $2}')
	else
		value=$(zdb -e $pool | grep "$config:" | awk -F: \
		    '{print $2}')
	fi
	if [[ -n $value ]] ; then
		value=${value#'}
		value=${value%'}
	fi
	echo $value

	return 0
}

#
# Privated function. Random select one of items from arguments.
#
# $1 count
# $2-n string
#
function _random_get
{
	typeset cnt=$1
	shift

	typeset str="$@"
	typeset -i ind
	((ind = RANDOM % cnt + 1))

	typeset ret=$(echo "$str" | cut -f $ind -d ' ')
	echo $ret
}

#
# Random select one of item from arguments which include NONE string
#
function random_get_with_non
{
	typeset -i cnt=$#
	((cnt =+ 1))

	_random_get "$cnt" "$@"
}

#
# Random select one of item from arguments which doesn't include NONE string
#
function random_get
{
	_random_get "$#" "$@"
}

#
# Detect if the current system support slog
#
function verify_slog_support
{
	typeset dir=$TEST_BASE_DIR/disk.$$
	typeset pool=foo.$$
	typeset vdev=$dir/a
	typeset sdev=$dir/b

	mkdir -p $dir
	mkfile $MINVDEVSIZE $vdev $sdev

	typeset -i ret=0
	if ! zpool create -n $pool $vdev log $sdev > /dev/null 2>&1; then
		ret=1
	fi
	rm -r $dir

	return $ret
}

#
# The function will generate a dataset name with specific length
# $1, the length of the name
# $2, the base string to construct the name
#
function gen_dataset_name
{
	typeset -i len=$1
	typeset basestr="$2"
	typeset -i baselen=${#basestr}
	typeset -i iter=0
	typeset l_name=""

	if ((len % baselen == 0)); then
		((iter = len / baselen))
	else
		((iter = len / baselen + 1))
	fi
	while ((iter > 0)); do
		l_name="${l_name}$basestr"

		((iter -= 1))
	done

	echo $l_name
}

#
# Get cksum tuple of dataset
# $1 dataset name
#
# sample zdb output:
# Dataset data/test [ZPL], ID 355, cr_txg 2413856, 31.0K, 7 objects, rootbp
# DVA[0]=<0:803046400:200> DVA[1]=<0:81199000:200> [L0 DMU objset] fletcher4
# lzjb LE contiguous unique double size=800L/200P birth=2413856L/2413856P
# fill=7 cksum=11ce125712:643a9c18ee2:125e25238fca0:254a3f74b59744
function datasetcksum
{
	typeset cksum
	sync
	cksum=$(zdb -vvv $1 | grep "^Dataset $1 \[" | grep "cksum" \
		| awk -F= '{print $7}')
	echo $cksum
}

#
# Get cksum of file
# #1 file path
#
function checksum
{
	typeset cksum
	cksum=$(cksum $1 | awk '{print $1}')
	echo $cksum
}

#
# Get the given disk/slice state from the specific field of the pool
#
function get_device_state #pool disk field("", "spares","logs")
{
	typeset pool=$1
	typeset disk=${2#$DEV_DSKDIR/}
	typeset field=${3:-$pool}

	state=$(zpool status -v "$pool" 2>/dev/null | \
		nawk -v device=$disk -v pool=$pool -v field=$field \
		'BEGIN {startconfig=0; startfield=0; }
		/config:/ {startconfig=1}
		(startconfig==1) && ($1==field) {startfield=1; next;}
		(startfield==1) && ($1==device) {print $2; exit;}
		(startfield==1) &&
		($1==field || $1 ~ "^spares$" || $1 ~ "^logs$") {startfield=0}')
	echo $state
}


#
# print the given directory filesystem type
#
# $1 directory name
#
function get_fstype
{
	typeset dir=$1

	if [[ -z $dir ]]; then
		log_fail "Usage: get_fstype <directory>"
	fi

	#
	#  $ df -n /
	#  /		  : ufs
	#
	df -n $dir | awk '{print $3}'
}

#
# Given a disk, label it to VTOC regardless what label was on the disk
# $1 disk
#
function labelvtoc
{
	typeset disk=$1
	if [[ -z $disk ]]; then
		log_fail "The disk name is unspecified."
	fi
	typeset label_file=/var/tmp/labelvtoc.$$
	typeset arch=$(uname -p)

	if is_linux; then
		log_note "Currently unsupported by the test framework"
		return 1
	fi

	if [[ $arch == "i386" ]]; then
		echo "label" > $label_file
		echo "0" >> $label_file
		echo "" >> $label_file
		echo "q" >> $label_file
		echo "q" >> $label_file

		fdisk -B $disk >/dev/null 2>&1
		# wait a while for fdisk finishes
		sleep 60
	elif [[ $arch == "sparc" ]]; then
		echo "label" > $label_file
		echo "0" >> $label_file
		echo "" >> $label_file
		echo "" >> $label_file
		echo "" >> $label_file
		echo "q" >> $label_file
	else
		log_fail "unknown arch type"
	fi

	format -e -s -d $disk -f $label_file
	typeset -i ret_val=$?
	rm -f $label_file
	#
	# wait the format to finish
	#
	sleep 60
	if ((ret_val != 0)); then
		log_fail "unable to label $disk as VTOC."
	fi

	return 0
}

#
# check if the system was installed as zfsroot or not
# return: 0 ture, otherwise false
#
function is_zfsroot
{
	df -n / | grep zfs > /dev/null 2>&1
	return $?
}

#
# get the root filesystem name if it's zfsroot system.
#
# return: root filesystem name
function get_rootfs
{
	typeset rootfs=""

	if ! is_linux; then
		rootfs=$(awk '{if ($2 == "/" && $3 == "zfs") print $1}' \
			/etc/mnttab)
	fi
	if [[ -z "$rootfs" ]]; then
		log_fail "Can not get rootfs"
	fi
	zfs list $rootfs > /dev/null 2>&1
	if (($? == 0)); then
		echo $rootfs
	else
		log_fail "This is not a zfsroot system."
	fi
}

#
# get the rootfs's pool name
# return:
#       rootpool name
#
function get_rootpool
{
	typeset rootfs=""
	typeset rootpool=""

	if ! is_linux; then
		rootfs=$(awk '{if ($2 == "/" && $3 =="zfs") print $1}' \
			 /etc/mnttab)
	fi
	if [[ -z "$rootfs" ]]; then
		log_fail "Can not get rootpool"
	fi
	zfs list $rootfs > /dev/null 2>&1
	if (($? == 0)); then
		rootpool=`echo $rootfs | awk -F\/ '{print $1}'`
		echo $rootpool
	else
		log_fail "This is not a zfsroot system."
	fi
}

#
# Get the package name
#
function get_package_name
{
	typeset dirpath=${1:-$STC_NAME}

	echo "SUNWstc-${dirpath}" | /usr/bin/sed -e "s/\//-/g"
}

#
# Get the word numbers from a string separated by white space
#
function get_word_count
{
	echo $1 | wc -w
}

#
# To verify if the require numbers of disks is given
#
function verify_disk_count
{
	typeset -i min=${2:-1}

	typeset -i count=$(get_word_count "$1")

	if ((count < min)); then
		log_untested "A minimum of $min disks is required to run." \
			" You specified $count disk(s)"
	fi
}

function ds_is_volume
{
	typeset type=$(get_prop type $1)
	[[ $type = "volume" ]] && return 0
	return 1
}

function ds_is_filesystem
{
	typeset type=$(get_prop type $1)
	[[ $type = "filesystem" ]] && return 0
	return 1
}

function ds_is_snapshot
{
	typeset type=$(get_prop type $1)
	[[ $type = "snapshot" ]] && return 0
	return 1
}

#
# Check if Trusted Extensions are installed and enabled
#
function is_te_enabled
{
	svcs -H -o state labeld 2>/dev/null | grep "enabled"
	if (($? != 0)); then
		return 1
	else
		return 0
	fi
}

# Utility function to determine if a system has multiple cpus.
function is_mp
{
	if is_linux; then
		(($(nproc) > 1))
	else
		(($(psrinfo | wc -l) > 1))
	fi

	return $?
}

function get_cpu_freq
{
	if is_linux; then
		lscpu | awk '/CPU MHz/ { print $3 }'
	else
		psrinfo -v 0 | awk '/processor operates at/ {print $6}'
	fi
}

# Run the given command as the user provided.
function user_run
{
	typeset user=$1
	shift

	log_note "user:$user $@"
	eval su - \$user -c \"$@\" > $TEST_BASE_DIR/out 2>$TEST_BASE_DIR/err
	return $?
}

#
# Check if the pool contains the specified vdevs
#
# $1 pool
# $2..n <vdev> ...
#
# Return 0 if the vdevs are contained in the pool, 1 if any of the specified
# vdevs is not in the pool, and 2 if pool name is missing.
#
function vdevs_in_pool
{
	typeset pool=$1
	typeset vdev

	if [[ -z $pool ]]; then
		log_note "Missing pool name."
		return 2
	fi

	shift

	# We could use 'zpool list' to only get the vdevs of the pool but we
	# can't reference a mirror/raidz vdev using its ID (i.e mirror-0),
	# therefore we use the 'zpool status' output.
	typeset tmpfile=$(mktemp)
	zpool status -v "$pool" | grep -A 1000 "config:" >$tmpfile
	for vdev in $@; do
		grep -w ${vdev##*/} $tmpfile >/dev/null 2>&1
		[[ $? -ne 0 ]] && return 1
	done

	rm -f $tmpfile

	return 0;
}

function get_max
{
	typeset -l i max=$1
	shift

	for i in "$@"; do
		max=$(echo $((max > i ? max : i)))
	done

	echo $max
}

function get_min
{
	typeset -l i min=$1
	shift

	for i in "$@"; do
		min=$(echo $((min < i ? min : i)))
	done

	echo $min
}

#
# Generate a random number between 1 and the argument.
#
function random
{
        typeset max=$1
        echo $(( ($RANDOM % $max) + 1 ))
}

# Write data that can be compressed into a directory
function write_compressible
{
	typeset dir=$1
	typeset megs=$2
	typeset nfiles=${3:-1}
	typeset bs=${4:-1024k}
	typeset fname=${5:-file}

	[[ -d $dir ]] || log_fail "No directory: $dir"

	# Under Linux fio is not currently used since its behavior can
	# differ significantly across versions.  This includes missing
	# command line options and cases where the --buffer_compress_*
	# options fail to behave as expected.
	if is_linux; then
		typeset file_bytes=$(to_bytes $megs)
		typeset bs_bytes=4096
		typeset blocks=$(($file_bytes / $bs_bytes))

		for (( i = 0; i < $nfiles; i++ )); do
			truncate -s $file_bytes $dir/$fname.$i

			# Write every third block to get 66% compression.
			for (( j = 0; j < $blocks; j += 3 )); do
				dd if=/dev/urandom of=$dir/$fname.$i \
				    seek=$j bs=$bs_bytes count=1 \
				    conv=notrunc >/dev/null 2>&1
			done
		done
	else
		log_must eval "fio \
		    --name=job \
		    --fallocate=0 \
		    --minimal \
		    --randrepeat=0 \
		    --buffer_compress_percentage=66 \
		    --buffer_compress_chunk=4096 \
		    --directory=$dir \
		    --numjobs=$nfiles \
		    --nrfiles=$nfiles \
		    --rw=write \
		    --bs=$bs \
		    --filesize=$megs \
		    --filename_format='$fname.\$jobnum' >/dev/null"
	fi
}

function get_objnum
{
	typeset pathname=$1
	typeset objnum

	[[ -e $pathname ]] || log_fail "No such file or directory: $pathname"
	objnum=$(stat -c %i $pathname)
	echo $objnum
}

#
# Sync data to the pool
#
# $1 pool name
# $2 boolean to force uberblock (and config including zpool cache file) update
#
function sync_pool #pool <force>
{
	typeset pool=${1:-$TESTPOOL}
	typeset force=${2:-false}

	if [[ $force == true ]]; then
		log_must zpool sync -f $pool
	else
		log_must zpool sync $pool
	fi

	return 0
}

#
# Wait for zpool 'freeing' property drops to zero.
#
# $1 pool name
#
function wait_freeing #pool
{
	typeset pool=${1:-$TESTPOOL}
	while true; do
		[[ "0" == "$(zpool list -Ho freeing $pool)" ]] && break
		log_must sleep 1
	done
}

#
# Wait for every device replace operation to complete
#
# $1 pool name
#
function wait_replacing #pool
{
	typeset pool=${1:-$TESTPOOL}
	while true; do
		[[ "" == "$(zpool status $pool |
		    awk '/replacing-[0-9]+/ {print $1}')" ]] && break
		log_must sleep 1
	done
}

#
# Wait for a pool to be scrubbed
#
# $1 pool name
# $2 number of seconds to wait (optional)
#
# Returns true when pool has been scrubbed, or false if there's a timeout or if
# no scrub was done.
#
function wait_scrubbed
{
	typeset pool=${1:-$TESTPOOL}
	while true ; do
		is_pool_scrubbed $pool && break
		log_must sleep 1
	done
}

# Backup the zed.rc in our test directory so that we can edit it for our test.
#
# Returns: Backup file name.  You will need to pass this to zed_rc_restore().
function zed_rc_backup
{
	zedrc_backup="$(mktemp)"
	cp $ZEDLET_DIR/zed.rc $zedrc_backup
	echo $zedrc_backup
}

function zed_rc_restore
{
	mv $1 $ZEDLET_DIR/zed.rc
}

#
# Setup custom environment for the ZED.
#
# $@ Optional list of zedlets to run under zed.
function zed_setup
{
	if ! is_linux; then
		return
	fi

	if [[ ! -d $ZEDLET_DIR ]]; then
		log_must mkdir $ZEDLET_DIR
	fi

	if [[ ! -e $VDEVID_CONF ]]; then
		log_must touch $VDEVID_CONF
	fi

	if [[ -e $VDEVID_CONF_ETC ]]; then
		log_fail "Must not have $VDEVID_CONF_ETC file present on system"
	fi
	EXTRA_ZEDLETS=$@

	# Create a symlink for /etc/zfs/vdev_id.conf file.
	log_must ln -s $VDEVID_CONF $VDEVID_CONF_ETC

	# Setup minimal ZED configuration.  Individual test cases should
	# add additional ZEDLETs as needed for their specific test.
	log_must cp ${ZEDLET_ETC_DIR}/zed.rc $ZEDLET_DIR
	log_must cp ${ZEDLET_ETC_DIR}/zed-functions.sh $ZEDLET_DIR

	# Scripts must only be user writable.
	if [[ -n "$EXTRA_ZEDLETS" ]] ; then
		saved_umask=$(umask)
		log_must umask 0022
		for i in $EXTRA_ZEDLETS ; do
			log_must cp ${ZEDLET_LIBEXEC_DIR}/$i $ZEDLET_DIR
		done
		log_must umask $saved_umask
	fi

	# Customize the zed.rc file to enable the full debug log.
	log_must sed -i '/\#ZED_DEBUG_LOG=.*/d' $ZEDLET_DIR/zed.rc
	echo "ZED_DEBUG_LOG=$ZED_DEBUG_LOG" >>$ZEDLET_DIR/zed.rc

}

#
# Cleanup custom ZED environment.
#
# $@ Optional list of zedlets to remove from our test zed.d directory.
function zed_cleanup
{
	if ! is_linux; then
		return
	fi
	EXTRA_ZEDLETS=$@

	log_must rm -f ${ZEDLET_DIR}/zed.rc
	log_must rm -f ${ZEDLET_DIR}/zed-functions.sh
	log_must rm -f ${ZEDLET_DIR}/all-syslog.sh
	log_must rm -f ${ZEDLET_DIR}/all-debug.sh
	log_must rm -f ${ZEDLET_DIR}/state

	if [[ -n "$EXTRA_ZEDLETS" ]] ; then
		for i in $EXTRA_ZEDLETS ; do
			log_must rm -f ${ZEDLET_DIR}/$i
		done
	fi
	log_must rm -f $ZED_LOG
	log_must rm -f $ZED_DEBUG_LOG
	log_must rm -f $VDEVID_CONF_ETC
	log_must rm -f $VDEVID_CONF
	rmdir $ZEDLET_DIR
}

#
# Check if ZED is currently running, if not start ZED.
#
function zed_start
{
	if ! is_linux; then
		return
	fi

	# ZEDLET_DIR=/var/tmp/zed
	if [[ ! -d $ZEDLET_DIR ]]; then
		log_must mkdir $ZEDLET_DIR
	fi

	# Verify the ZED is not already running.
	pgrep -x zed > /dev/null
	if (($? == 0)); then
		log_fail "ZED already running"
	fi

	log_note "Starting ZED"
	# run ZED in the background and redirect foreground logging
	# output to $ZED_LOG.
	log_must truncate -s 0 $ZED_DEBUG_LOG
	log_must eval "zed -vF -d $ZEDLET_DIR -p $ZEDLET_DIR/zed.pid -P $PATH" \
	    "-s $ZEDLET_DIR/state 2>$ZED_LOG &"

	return 0
}

#
# Kill ZED process
#
function zed_stop
{
	if ! is_linux; then
		return
	fi

	log_note "Stopping ZED"
	if [[ -f ${ZEDLET_DIR}/zed.pid ]]; then
		zedpid=$(<${ZEDLET_DIR}/zed.pid)
		kill $zedpid
		while ps -p $zedpid > /dev/null; do
			sleep 1
		done
		rm -f ${ZEDLET_DIR}/zed.pid
	fi
	return 0
}

#
# Drain all zevents
#
function zed_events_drain
{
	while [ $(zpool events -H | wc -l) -ne 0 ]; do
		sleep 1
		zpool events -c >/dev/null
	done
}

# Set a variable in zed.rc to something, un-commenting it in the process.
#
# $1 variable
# $2 value
function zed_rc_set
{
	var="$1"
	val="$2"
	# Remove the line
	cmd="'/$var/d'"
	eval sed -i $cmd $ZEDLET_DIR/zed.rc

	# Add it at the end
	echo "$var=$val" >> $ZEDLET_DIR/zed.rc
}


#
# Check is provided device is being active used as a swap device.
#
function is_swap_inuse
{
	typeset device=$1

	if [[ -z $device ]] ; then
		log_note "No device specified."
		return 1
	fi

	if is_linux; then
		swapon -s | grep -w $(readlink -f $device) > /dev/null 2>&1
	else
		swap -l | grep -w $device > /dev/null 2>&1
	fi

	return $?
}

#
# Setup a swap device using the provided device.
#
function swap_setup
{
	typeset swapdev=$1

	if is_linux; then
		log_must eval "mkswap $swapdev > /dev/null 2>&1"
		log_must swapon $swapdev
	else
	        log_must swap -a $swapdev
	fi

	return 0
}

#
# Cleanup a swap device on the provided device.
#
function swap_cleanup
{
	typeset swapdev=$1

	if is_swap_inuse $swapdev; then
		if is_linux; then
			log_must swapoff $swapdev
		else
			log_must swap -d $swapdev
		fi
	fi

	return 0
}

#
# Set a global system tunable (64-bit value)
#
# $1 tunable name
# $2 tunable values
#
function set_tunable64
{
	set_tunable_impl "$1" "$2" Z
}

#
# Set a global system tunable (32-bit value)
#
# $1 tunable name
# $2 tunable values
#
function set_tunable32
{
	set_tunable_impl "$1" "$2" W
}

function set_tunable_impl
{
	typeset tunable="$1"
	typeset value="$2"
	typeset mdb_cmd="$3"
	typeset module="${4:-zfs}"

	[[ -z "$tunable" ]] && return 1
	[[ -z "$value" ]] && return 1
	[[ -z "$mdb_cmd" ]] && return 1

	case "$(uname)" in
	Linux)
		typeset zfs_tunables="/sys/module/$module/parameters"
		[[ -w "$zfs_tunables/$tunable" ]] || return 1
		echo -n "$value" > "$zfs_tunables/$tunable"
		return "$?"
		;;
	SunOS)
		[[ "$module" -eq "zfs" ]] || return 1
		echo "${tunable}/${mdb_cmd}0t${value}" | mdb -kw
		return "$?"
		;;
	esac
}

#
# Get a global system tunable
#
# $1 tunable name
#
function get_tunable
{
	get_tunable_impl "$1"
}

function get_tunable_impl
{
	typeset tunable="$1"
	typeset module="${2:-zfs}"

	[[ -z "$tunable" ]] && return 1

	case "$(uname)" in
	Linux)
		typeset zfs_tunables="/sys/module/$module/parameters"
		[[ -f "$zfs_tunables/$tunable" ]] || return 1
		cat $zfs_tunables/$tunable
		return "$?"
		;;
	SunOS)
		[[ "$module" -eq "zfs" ]] || return 1
		;;
	esac

	return 1
}

#
# Prints the current time in seconds since UNIX Epoch.
#
function current_epoch
{
	printf '%(%s)T'
}

#
# Get decimal value of global uint32_t variable using mdb.
#
function mdb_get_uint32
{
	typeset variable=$1
	typeset value

	value=$(mdb -k -e "$variable/X | ::eval .=U")
	if [[ $? -ne 0 ]]; then
		log_fail "Failed to get value of '$variable' from mdb."
		return 1
	fi

	echo $value
	return 0
}

#
# Set global uint32_t variable to a decimal value using mdb.
#
function mdb_set_uint32
{
	typeset variable=$1
	typeset value=$2

	mdb -kw -e "$variable/W 0t$value" > /dev/null
	if [[ $? -ne 0 ]]; then
		echo "Failed to set '$variable' to '$value' in mdb."
		return 1
	fi

	return 0
}

#
# Set global scalar integer variable to a hex value using mdb.
# Note: Target should have CTF data loaded.
#
function mdb_ctf_set_int
{
	typeset variable=$1
	typeset value=$2

	mdb -kw -e "$variable/z $value" > /dev/null
	if [[ $? -ne 0 ]]; then
		echo "Failed to set '$variable' to '$value' in mdb."
		return 1
	fi

	return 0
}