[fio.git] / t / zbd / test-zbd-support

#!/bin/bash
#
# Copyright (C) 2018 Western Digital Corporation or its affiliates.
#
# This file is released under the GPL.

usage() {
	echo "Usage: $(basename "$0") [OPTIONS] <test target device file>"
	echo "Options:"
	echo -e "\t-d Run fio with valgrind using DRD tool"
	echo -e "\t-e Run fio with valgrind using helgrind tool"
	echo -e "\t-v Run fio with valgrind --read-var-info option"
	echo -e "\t-l Test with libzbc ioengine"
	echo -e "\t-r Reset all zones before test start"
	echo -e "\t-o <max_open_zones> Run fio with max_open_zones limit"
	echo -e "\t-t <test #> Run only a single test case with specified number"
	echo -e "\t-q Quit the test run after any failed test"
	echo -e "\t-z Run fio with debug=zbd option"
}

max() {
    if [ "$1" -gt "$2" ]; then
	echo "$1"
    else
	echo "$2"
    fi
}

min() {
    if [ "$1" -lt "$2" ]; then
	echo "$1"
    else
	echo "$2"
    fi
}

ioengine() {
	if [ -n "$use_libzbc" ]; then
		echo -n "--ioengine=libzbc"
	else
		echo -n "--ioengine=$1"
	fi
}

set_io_scheduler() {
    local dev=$1 sched=$2

    [ -e "/sys/block/$dev" ] || return $?
    if [ -e "/sys/block/$dev/mq" ]; then
	case "$sched" in
	    noop)        sched=none;;
	    deadline)    sched=mq-deadline;;
	esac
    else
	case "$sched" in
	    none)        sched=noop;;
	    mq-deadline) sched=deadline;;
	esac
    fi

    echo "$sched" >"/sys/block/$dev/queue/scheduler"
}

check_read() {
    local read

    read=$(fio_read <"${logfile}.${test_number}")
    echo "read: $read <> $1" >> "${logfile}.${test_number}"
    [ "$read" = "$1" ]
}

check_written() {
    local written

    written=$(fio_written <"${logfile}.${test_number}")
    echo "written: $written <> $1" >> "${logfile}.${test_number}"
    [ "$written" = "$1" ]
}

# Compare the reset count from the log file with reset count $2 using operator
# $1 (=, -ge, -gt, -le, -lt).
check_reset_count() {
    local reset_count

    reset_count=$(fio_reset_count <"${logfile}.${test_number}")
    echo "reset_count: test $reset_count $1 $2" >> "${logfile}.${test_number}"
    eval "[ '$reset_count' '$1' '$2' ]"
}

# Check log for failed assertions and crashes. Without these checks,
# a test can succeed even when these events happen, but it must fail.
check_log() {
     [ ! -f "${logfile}.${1}" ] && return 0
     ! grep -q -e "Assertion " -e "Aborted " "${logfile}.${1}"
}

# Whether or not $1 (/dev/...) is a SCSI device.
is_scsi_device() {
    local d f

    d=$(basename "$dev")
    for f in /sys/class/scsi_device/*/device/block/"$d"; do
	[ -e "$f" ] && return 0
    done
    return 1
}

job_var_opts_exclude() {
	local o
	local ex_key="${1}"

	for o in "${job_var_opts[@]}"; do
		if [[ ${o} =~ "${ex_key}" ]]; then
			continue
		fi
		echo -n "${o}"
	done
}

has_max_open_zones() {
	while (($# > 1)); do
		if [[ ${1} =~ "--max_open_zones" ]]; then
			return 0
		fi
		shift
	done
	return 1
}

run_fio() {
    local fio opts

    fio=$(dirname "$0")/../../fio

    opts=(${global_var_opts[@]})
    opts+=("--max-jobs=16" "--aux-path=/tmp" "--allow_file_create=0" \
			   "--significant_figures=10" "$@")
    # When max_open_zones option is specified to this test script, add
    # max_open_zones option to fio command unless the test case already add it.
    if [[ -n ${max_open_zones_opt} ]] && ! has_max_open_zones "${opts[@]}"; then
	    opts+=("--max_open_zones=${max_open_zones_opt}")
    fi
    { echo; echo "fio ${opts[*]}"; echo; } >>"${logfile}.${test_number}"

    "${dynamic_analyzer[@]}" "$fio" "${opts[@]}"
}

run_one_fio_job() {
    local r

    r=$(((RANDOM << 16) | RANDOM))
    run_fio --name="$dev" --filename="$dev" "$@" --randseed="$r"	\
	    --thread=1 --direct=1
}

write_and_run_one_fio_job() {
    local r
    local write_offset="${1}"
    local write_size="${2}"
    local -a write_opts

    shift 2
    r=$(((RANDOM << 16) | RANDOM))
    write_opts=(--name="write_job" --rw=write "$(ioengine "psync")" \
		      --bs="${logical_block_size}" --zonemode=zbd \
		      --zonesize="${zone_size}" --thread=1 --direct=1 \
		      --offset="${write_offset}" --size="${write_size}")
    write_opts+=("${job_var_opts[@]}")
    run_fio --filename="$dev" --randseed="$r" "${write_opts[@]}" \
	    --name="$dev" --wait_for="write_job" "$@" --thread=1 --direct=1
}

# Run fio on the first four sequential zones of the disk.
run_fio_on_seq() {
    local opts=()

    opts+=("--offset=$((first_sequential_zone_sector * 512))")
    opts+=("--size=$((4 * zone_size))" "--zonemode=zbd")
    if [ -z "$is_zbd" ]; then
	opts+=("--zonesize=${zone_size}")
    fi
    run_one_fio_job "${opts[@]}" "$@"
}

# Prepare for write test by resetting zones. When max_open_zones option is
# specified, reset all zones of the test target to ensure that zones out of the
# test target range do not have open zones. This allows the write test to the
# target range to be able to open zones up to max_open_zones.
prep_write() {
	[[ -n "${max_open_zones_opt}" && -n "${is_zbd}" ]] &&
		reset_zone "${dev}" -1
}

SKIP_TESTCASE=255

require_scsi_dev() {
	if ! is_scsi_device "$dev"; then
		SKIP_REASON="$dev is not a SCSI device"
		return 1
	fi
	return 0
}

require_conv_zone_bytes() {
	local req_bytes=${1}

	if ((req_bytes > first_sequential_zone_sector * 512)); then
		SKIP_REASON="$dev does not have enough conventional zones"
		return 1
	fi
	return 0
}

require_zbd() {
	if [[ -z ${is_zbd} ]]; then
		SKIP_REASON="$dev is not a zoned block device"
		return 1
	fi
	return 0
}

require_regular_block_dev() {
	if [[ -n ${is_zbd} ]]; then
		SKIP_REASON="$dev is not a regular block device"
		return 1
	fi
	return 0
}

require_seq_zones() {
	local req_seq_zones=${1}
	local seq_bytes=$((disk_size - first_sequential_zone_sector * 512))

	if ((req_seq_zones > seq_bytes / zone_size)); then
		SKIP_REASON="$dev does not have $req_seq_zones sequential zones"
		return 1
	fi
	return 0
}

require_conv_zones() {
	local req_c_zones=${1}
	local conv_bytes=$((first_sequential_zone_sector * 512))

	if ((req_c_zones > conv_bytes / zone_size)); then
		SKIP_REASON="$dev does not have $req_c_zones conventional zones"
		return 1
	fi
	return 0
}

# Check whether buffered writes are refused.
test1() {
    run_fio --name=job1 --filename="$dev" --rw=write --direct=0 --bs=4K	\
	    "$(ioengine "psync")" --size="${zone_size}" --thread=1	\
	    --zonemode=zbd --zonesize="${zone_size}" 2>&1 |
	tee -a "${logfile}.${test_number}" |
	grep -q 'Using direct I/O is mandatory for writing to ZBD drives'
    local fio_rc=${PIPESTATUS[0]} grep_rc=${PIPESTATUS[2]}
    case "$fio_rc" in
	0|1) ;;
	*)   return "$fio_rc"
    esac
    if [ -n "$is_zbd" ]; then
	[ "$grep_rc" = 0 ]
    else
	[ "$grep_rc" != 0 ]
    fi
}

# Block size exceeds zone size.
test2() {
    local bs off opts=() rc

    off=$(((first_sequential_zone_sector + 2 * sectors_per_zone) * 512))
    bs=$((2 * zone_size))
    opts+=("$(ioengine "psync")")
    opts+=("--name=job1" "--filename=$dev" "--rw=write" "--direct=1")
    opts+=("--zonemode=zbd" "--offset=$off" "--bs=$bs" "--size=$bs")
    if [ -z "$is_zbd" ]; then
	opts+=("--zonesize=${zone_size}")
    fi
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 && return 1
    grep -q 'buflen exceeds zone size' "${logfile}.${test_number}"
}

# Run fio against an empty zone. This causes fio to report "No I/O performed".
test3() {
    local off opts=() rc

    require_seq_zones 129 || return $SKIP_TESTCASE
    off=$((first_sequential_zone_sector * 512 + 128 * zone_size))
    size=$((zone_size))
    [ -n "$is_zbd" ] && reset_zone "$dev" $((off / 512))
    opts+=("--name=$dev" "--filename=$dev" "--offset=$off" "--bs=4K")
    opts+=("--size=$size" "--zonemode=zbd")
    opts+=("$(ioengine "psync")" "--rw=read" "--direct=1" "--thread=1")
    if [ -z "$is_zbd" ]; then
	opts+=("--zonesize=${zone_size}")
    fi
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
    ! grep -q 'READ:' "${logfile}.${test_number}"
}

# Run fio with --read_beyond_wp=1 against an empty zone.
test4() {
    local off opts=()

    require_seq_zones 130 || return $SKIP_TESTCASE
    off=$((first_sequential_zone_sector * 512 + 129 * zone_size))
    size=$((zone_size))
    [ -n "$is_zbd" ] && reset_zone "$dev" $((off / 512))
    opts+=("--name=$dev" "--filename=$dev" "--offset=$off" "--bs=$size")
    opts+=("--size=$size" "--thread=1" "--read_beyond_wp=1")
    opts+=("$(ioengine "psync")" "--rw=read" "--direct=1" "--disable_lat=1")
    opts+=("--zonemode=zbd" "--zonesize=${zone_size}")
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
    check_read $size || return $?
}

# Sequential write to sequential zones.
test5() {
    local size off capacity

    prep_write
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 4 $off $dev)
    size=$((4 * zone_size))
    run_fio_on_seq "$(ioengine "psync")" --iodepth=1 --rw=write	\
		   --bs="$(max $((zone_size / 64)) "$logical_block_size")"\
		   --do_verify=1 --verify=md5				\
		   >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $capacity || return $?
    check_read $capacity || return $?
}

# Sequential read from sequential zones.
test6() {
    local size off capacity

    prep_write
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 4 $off $dev)
    size=$((4 * zone_size))
    write_and_run_one_fio_job \
	    $((first_sequential_zone_sector * 512)) "${size}" \
	    --offset="${off}" \
	    --size="${size}" --zonemode=zbd --zonesize="${zone_size}" \
	    "$(ioengine "psync")" --iodepth=1 --rw=read \
	    --bs="$(max $((zone_size / 64)) "$logical_block_size")" \
	    >>"${logfile}.${test_number}" 2>&1 || return $?
    check_read $capacity || return $?
}

# Random write to sequential zones, libaio, queue depth 1.
test7() {
    local size=$((zone_size))
    local off capacity

    prep_write
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 1 $off $dev)
    run_fio_on_seq "$(ioengine "libaio")" --iodepth=1 --rw=randwrite	\
		   --bs="$(min 16384 "${zone_size}")"			\
		   --do_verify=1 --verify=md5 --size="$size"		\
		   >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $capacity || return $?
    check_read $capacity || return $?
}

# Random write to sequential zones, libaio, queue depth 64.
test8() {
    local size off capacity

    prep_write
    size=$((4 * zone_size))
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 4 $off $dev)
    run_fio_on_seq "$(ioengine "libaio")" --iodepth=64 --rw=randwrite	\
		   --bs="$(min 16384 "${zone_size}")"			\
		   --do_verify=1 --verify=md5				\
		   >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $capacity || return $?
    check_read $capacity || return $?
}

# Random write to sequential zones, sg, queue depth 1.
test9() {
    local size

    require_scsi_dev || return $SKIP_TESTCASE

    prep_write
    size=$((4 * zone_size))
    run_fio_on_seq --ioengine=sg					\
		   --iodepth=1 --rw=randwrite --bs=16K			\
		   --do_verify=1 --verify=md5				\
		   >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $size || return $?
    check_read $size || return $?
}

# Random write to sequential zones, sg, queue depth 64.
test10() {
    local size

    require_scsi_dev || return $SKIP_TESTCASE

    prep_write
    size=$((4 * zone_size))
    run_fio_on_seq --ioengine=sg 					\
		   --iodepth=64 --rw=randwrite --bs=16K			\
		   --do_verify=1 --verify=md5				\
		   >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $size || return $?
    check_read $size || return $?
}

# Random write to sequential zones, libaio, queue depth 64, random block size.
test11() {
    local size off capacity

    prep_write
    size=$((4 * zone_size))
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 4 $off $dev)
    run_fio_on_seq "$(ioengine "libaio")" --iodepth=64 --rw=randwrite	\
		   --bsrange=4K-64K --do_verify=1 --verify=md5		\
		   --debug=zbd >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $capacity || return $?
    check_read $capacity || return $?
}

# Random write to sequential zones, libaio, queue depth 64, max 1 open zone.
test12() {
    local size off capacity

    prep_write
    size=$((8 * zone_size))
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 8 $off $dev)
    run_fio_on_seq "$(ioengine "libaio")" --iodepth=64 --rw=randwrite --bs=16K \
		   --max_open_zones=1 --size=$size --do_verify=1 --verify=md5 \
		   --debug=zbd >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $capacity || return $?
    check_read $capacity || return $?
}

# Random write to sequential zones, libaio, queue depth 64, max 4 open zones.
test13() {
    local size off capacity

    prep_write
    size=$((8 * zone_size))
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 8 $off $dev)
    run_fio_on_seq "$(ioengine "libaio")" --iodepth=64 --rw=randwrite --bs=16K \
		   --max_open_zones=4 --size=$size --do_verify=1 --verify=md5 \
		   --debug=zbd						      \
		   >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $capacity || return $?
    check_read $capacity || return $?
}

# Random write to conventional zones.
test14() {
    local size

    prep_write
    size=$((16 * 2**20)) # 20 MB
    require_conv_zone_bytes "${size}" || return $SKIP_TESTCASE

    run_one_fio_job "$(ioengine "libaio")" --iodepth=64 --rw=randwrite --bs=16K \
		    --zonemode=zbd --zonesize="${zone_size}" --do_verify=1 \
		    --verify=md5 --size=$size				   \
		    >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $((size)) || return $?
    check_read $((size)) || return $?
}

# Sequential read on a mix of empty and full zones.
test15() {
    local i off size
    local w_off w_size w_capacity

    for ((i=0;i<4;i++)); do
	[ -n "$is_zbd" ] &&
	    reset_zone "$dev" $((first_sequential_zone_sector +
				 i*sectors_per_zone))
    done
    prep_write
    w_off=$(((first_sequential_zone_sector + 2 * sectors_per_zone) * 512))
    w_size=$((2 * zone_size))
    w_capacity=$(total_zone_capacity 2 $w_off $dev)
    off=$((first_sequential_zone_sector * 512))
    size=$((4 * zone_size))
    write_and_run_one_fio_job "${w_off}" "${w_size}" \
		    "$(ioengine "psync")" --rw=read --bs=$((zone_size / 16)) \
		    --zonemode=zbd --zonesize="${zone_size}" --offset=$off \
		    --size=$((size)) >>"${logfile}.${test_number}" 2>&1 ||
	return $?
    check_written $((w_capacity)) || return $?
    check_read $((w_capacity))
}

# Random read on a mix of empty and full zones.
test16() {
    local off size
    local i w_off w_size w_capacity

    for ((i=0;i<4;i++)); do
	[ -n "$is_zbd" ] &&
	    reset_zone "$dev" $((first_sequential_zone_sector +
				 i*sectors_per_zone))
    done
    prep_write
    w_off=$(((first_sequential_zone_sector + 2 * sectors_per_zone) * 512))
    w_size=$((2 * zone_size))
    w_capacity=$(total_zone_capacity 2 $w_off $dev)
    off=$((first_sequential_zone_sector * 512))
    size=$((4 * zone_size))
    write_and_run_one_fio_job "${w_off}" "${w_size}" \
		    "$(ioengine "libaio")" --iodepth=64 --rw=randread --bs=16K \
		    --zonemode=zbd --zonesize="${zone_size}" --offset=$off \
		    --size=$size >>"${logfile}.${test_number}" 2>&1 || return $?
    check_written $w_capacity || return $?
    check_read $size || return $?
}

# Random reads and writes in the last zone.
test17() {
    local io off read size written

    off=$(((disk_size / zone_size - 1) * zone_size))
    size=$((disk_size - off))
    if [ -n "$is_zbd" ]; then
	reset_zone "$dev" $((off / 512)) || return $?
    fi
    prep_write
    run_one_fio_job "$(ioengine "libaio")" --iodepth=8 --rw=randrw --bs=4K \
		    --zonemode=zbd --zonesize="${zone_size}"		\
		    --offset=$off --loops=2 --norandommap=1\
		    >>"${logfile}.${test_number}" 2>&1 || return $?
    written=$(fio_written <"${logfile}.${test_number}")
    read=$(fio_read <"${logfile}.${test_number}")
    io=$((written + read))
    echo "Total number of bytes read and written: $io <> $size" \
	 >>"${logfile}.${test_number}"
    [ $io = $((size * 2)) ];
}

# Out-of-range zone reset threshold and frequency parameters.
test18() {
    run_fio_on_seq --zone_reset_threshold=-1 |&
	tee -a "${logfile}.${test_number}"   |
	    grep -q 'value out of range' || return $?
}

test19() {
    run_fio_on_seq --zone_reset_threshold=2  |&
	tee -a "${logfile}.${test_number}"   |
	grep -q 'value out of range' || return $?
}

test20() {
    run_fio_on_seq --zone_reset_threshold=.4:.6 |&
	tee -a "${logfile}.${test_number}"   |
	grep -q 'the list exceeding max length' || return $?
}

test21() {
    run_fio_on_seq --zone_reset_frequency=-1 |&
	tee -a "${logfile}.${test_number}"   |
	grep -q 'value out of range' || return $?
}

test22() {
    run_fio_on_seq --zone_reset_frequency=2  |&
	tee -a "${logfile}.${test_number}"   |
	grep -q 'value out of range' || return $?
}

test23() {
    run_fio_on_seq --zone_reset_frequency=.4:.6  |&
	tee -a "${logfile}.${test_number}"   |
	grep -q 'the list exceeding max length' || return $?
}

test24() {
    local bs loops=9 size=$((zone_size))
    local off capacity

    prep_write
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 1 $off $dev)

    bs=$(min $((256*1024)) "$zone_size")
    run_fio_on_seq "$(ioengine "psync")" --rw=write --bs="$bs"		\
		   --size=$size --loops=$loops				\
		   --zone_reset_frequency=.01 --zone_reset_threshold=.90 \
		   >> "${logfile}.${test_number}" 2>&1 || return $?
    check_written $((capacity * loops)) || return $?
    check_reset_count -eq 8 ||
	check_reset_count -eq 9 ||
	check_reset_count -eq 10 || return $?
}

# Multiple non-overlapping sequential write jobs for the same drive.
test25() {
    local i opts=()

    for ((i=0;i<16;i++)); do
        [ -n "$is_zbd" ] &&
	    reset_zone "$dev" $((first_sequential_zone_sector + i*sectors_per_zone))
    done
    prep_write
    for ((i=0;i<16;i++)); do
	opts+=("--name=job$i" "--filename=$dev" "--thread=1" "--direct=1")
	opts+=("--offset=$((first_sequential_zone_sector*512 + zone_size*i))")
	opts+=("--size=$zone_size" "$(ioengine "psync")" "--rw=write" "--bs=16K")
	opts+=("--zonemode=zbd" "--zonesize=${zone_size}" "--group_reporting=1")
	opts+=(${job_var_opts[@]})
    done
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
}

write_to_first_seq_zone() {
    local loops=4 r
    local off capacity

    prep_write
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 1 $off $dev)

    r=$(((RANDOM << 16) | RANDOM))
    run_fio --name="$dev" --filename="$dev" "$(ioengine "psync")" --rw="$1" \
	    --thread=1 --do_verify=1 --verify=md5 --direct=1 --bs=4K	\
	    --offset=$off						\
	    --size=$zone_size --loops=$loops --randseed="$r"		\
	    --zonemode=zbd --zonesize="${zone_size}" --group_reporting=1	\
	    --gtod_reduce=1 >> "${logfile}.${test_number}" 2>&1 || return $?
    check_written $((loops * capacity)) || return $?
}

# Overwrite the first sequential zone four times sequentially.
test26() {
    write_to_first_seq_zone write
}

# Overwrite the first sequential zone four times using random writes.
test27() {
    write_to_first_seq_zone randwrite
}

# Multiple overlapping random write jobs for the same drive.
test28() {
    local i jobs=16 off opts

    require_seq_zones 65 || return $SKIP_TESTCASE
    off=$((first_sequential_zone_sector * 512 + 64 * zone_size))
    [ -n "$is_zbd" ] && reset_zone "$dev" $((off / 512))
    prep_write
    opts=("--debug=zbd")
    capacity=$(total_zone_capacity 1 $off $dev)
    for ((i=0;i<jobs;i++)); do
	opts+=("--name=job$i" "--filename=$dev" "--offset=$off" "--bs=16K")
	opts+=("--size=$zone_size" "--io_size=$capacity" "$(ioengine "psync")" "--rw=randwrite")
	opts+=("--thread=1" "--direct=1" "--zonemode=zbd")
	opts+=("--zonesize=${zone_size}" "--group_reporting=1")
	opts+=(${job_var_opts[@]})
    done
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
    check_written $((jobs * $capacity)) || return $?
    check_reset_count -eq $jobs ||
	check_reset_count -eq $((jobs - 1)) ||
	return $?
}

# Multiple overlapping random write jobs for the same drive and with a limited
# number of open zones.
test29() {
    local i jobs=16 off opts=()

    require_seq_zones 80 || return $SKIP_TESTCASE
    off=$((first_sequential_zone_sector * 512 + 64 * zone_size))
    size=$((16*zone_size))
    prep_write
    opts=("--debug=zbd")
    for ((i=0;i<jobs;i++)); do
	opts+=("--name=job$i" "--filename=$dev" "--offset=$off" "--bs=16K")
	opts+=("--size=$size" "--io_size=$zone_size" "--thread=1")
	opts+=("$(ioengine "psync")" "--rw=randwrite" "--direct=1")
	opts+=("--max_open_zones=4" "--group_reporting=1")
	opts+=("--zonemode=zbd" "--zonesize=${zone_size}")
	# max_open_zones is already specified
	opts+=($(job_var_opts_exclude "--max_open_zones"))
    done
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
    check_written $((jobs * zone_size)) || return $?
}

# Random reads and writes across the entire disk for 30s.
test30() {
    local off

    prep_write
    off=$((first_sequential_zone_sector * 512))
    run_one_fio_job "$(ioengine "libaio")" --iodepth=8 --rw=randrw	\
		    --bs="$(max $((zone_size / 128)) "$logical_block_size")"\
		    --zonemode=zbd --zonesize="${zone_size}" --offset=$off\
		    --loops=2 --time_based --runtime=30s --norandommap=1\
		    >>"${logfile}.${test_number}" 2>&1
}

# Random reads across all sequential zones for 30s. This is not only a fio
# test but also allows to verify the performance of a drive.
test31() {
    local bs inc nz off opts size

    prep_write
    # Start with writing 128 KB to 128 sequential zones.
    bs=128K
    nz=128
    # shellcheck disable=SC2017
    inc=$(((disk_size - (first_sequential_zone_sector * 512)) / (nz * zone_size)
	   * zone_size))
    opts=()
    for ((off = first_sequential_zone_sector * 512; off < disk_size;
	  off += inc)); do
	opts+=("--name=$dev" "--filename=$dev" "--offset=$off" "--io_size=$bs")
	opts+=("--bs=$bs" "--size=$zone_size" "$(ioengine "libaio")")
	opts+=("--rw=write" "--direct=1" "--thread=1" "--stats=0")
	opts+=("--zonemode=zbd" "--zonesize=${zone_size}")
	opts+=(${job_var_opts[@]})
    done
    "$(dirname "$0")/../../fio" "${opts[@]}" >> "${logfile}.${test_number}" 2>&1
    # Next, run the test.
    off=$((first_sequential_zone_sector * 512))
    size=$((disk_size - off))
    opts=("--name=$dev" "--filename=$dev" "--offset=$off" "--size=$size")
    opts+=("--bs=$bs" "$(ioengine "psync")" "--rw=randread" "--direct=1")
    opts+=("--thread=1" "--time_based" "--runtime=30" "--zonemode=zbd")
    opts+=("--zonesize=${zone_size}")
    opts+=(${job_var_opts[@]})
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
}

# Random writes across all sequential zones. This is not only a fio test but
# also allows to verify the performance of a drive.
test32() {
    local off opts=() size

    require_zbd || return $SKIP_TESTCASE

    prep_write
    off=$((first_sequential_zone_sector * 512))
    size=$((disk_size - off))
    opts+=("--name=$dev" "--filename=$dev" "--offset=$off" "--size=$size")
    opts+=("--bs=128K" "$(ioengine "psync")" "--rw=randwrite" "--direct=1")
    opts+=("--thread=1" "--time_based" "--runtime=30")
    opts+=("--max_open_zones=$max_open_zones" "--zonemode=zbd")
    opts+=("--zonesize=${zone_size}")
    run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
}

# Write to sequential zones with a block size that is not a divisor of the
# zone size.
test33() {
    local bs io_size size
    local off capacity=0;

    prep_write
    off=$((first_sequential_zone_sector * 512))
    capacity=$(total_zone_capacity 1 $off $dev)
    size=$((2 * zone_size))
    io_size=$((5 * capacity))
    bs=$((3 * capacity / 4))
    run_fio_on_seq "$(ioengine "psync")" --iodepth=1 --rw=write	\
		   --size=$size --io_size=$io_size --bs=$bs	\
		   >> "${logfile}.${test_number}" 2>&1 || return $?
    check_written $(((io_size + bs - 1) / bs * bs)) || return $?
}

# Write to sequential zones with a block size that is not a divisor of the
# zone size and with data verification enabled.
test34() {
    local size

    prep_write
    size=$((2 * zone_size))
    run_fio_on_seq "$(ioengine "psync")" --iodepth=1 --rw=write --size=$size \
		   --do_verify=1 --verify=md5 --bs=$((3 * zone_size / 4)) \
		   >> "${logfile}.${test_number}" 2>&1 && return 1
    grep -q 'not a divisor of' "${logfile}.${test_number}"
}

# Test 1/4 for the I/O boundary rounding code: $size < $zone_size.
test35() {
    local bs off io_size size

    prep_write
    off=$(((first_sequential_zone_sector + 1) * 512))
    size=$((zone_size - 2 * 512))
    bs=$((zone_size / 4))
    run_one_fio_job --offset=$off --size=$size "$(ioengine "psync")"	\
		    --iodepth=1 --rw=write --do_verify=1 --verify=md5	\
		    --bs=$bs --zonemode=zbd --zonesize="${zone_size}"	\
		    >> "${logfile}.${test_number}" 2>&1 && return 1
    grep -q 'io_size must be at least one zone' "${logfile}.${test_number}"
}

# Test 2/4 for the I/O boundary rounding code: $size < $zone_size.
test36() {
    local bs off io_size size

    prep_write
    off=$(((first_sequential_zone_sector) * 512))
    size=$((zone_size - 512))
    bs=$((zone_size / 4))
    run_one_fio_job --offset=$off --size=$size "$(ioengine "psync")"	\
		    --iodepth=1 --rw=write --do_verify=1 --verify=md5	\
		    --bs=$bs --zonemode=zbd --zonesize="${zone_size}"	\
		    >> "${logfile}.${test_number}" 2>&1 && return 1
    grep -q 'io_size must be at least one zone' "${logfile}.${test_number}"
}

# Test 3/4 for the I/O boundary rounding code: $size > $zone_size.
test37() {
    local bs off size capacity

    prep_write
    capacity=$(total_zone_capacity 1 $((first_sequential_zone_sector*512)) $dev)
    if [ "$first_sequential_zone_sector" = 0 ]; then
	off=0
    else
	off=$(((first_sequential_zone_sector - 1) * 512))
    fi
    size=$((zone_size + 2 * 512))
    bs=$((zone_size / 4))
    run_one_fio_job --offset=$off --size=$size "$(ioengine "psync")"	\
		    --iodepth=1 --rw=write --do_verify=1 --verify=md5	\
		    --bs=$bs --zonemode=zbd --zonesize="${zone_size}"	\
		    >> "${logfile}.${test_number}" 2>&1
    check_written $capacity || return $?
}

# Test 4/4 for the I/O boundary rounding code: $offset > $disk_size - $zone_size
test38() {
    local bs off size

    prep_write
    size=$((logical_block_size))
    off=$((disk_size - logical_block_size))
    bs=$((logical_block_size))
    run_one_fio_job --offset=$off --size=$size "$(ioengine "psync")"	\
		    --iodepth=1 --rw=write --do_verify=1 --verify=md5	\
		    --bs=$bs --zonemode=zbd --zonesize="${zone_size}"	\
		    >> "${logfile}.${test_number}" 2>&1 && return 1
    grep -q 'io_size must be at least one zone' "${logfile}.${test_number}"
}

# Read one block from a block device.
read_one_block() {
    local bs

    bs=$((logical_block_size))
    run_one_fio_job --rw=read "$(ioengine "psync")" --bs=$bs --size=$bs "$@" 2>&1 |
	tee -a "${logfile}.${test_number}"
}

# Check whether fio accepts --zonemode=none for zoned block devices.
test39() {
    require_zbd || return $SKIP_TESTCASE
    read_one_block --zonemode=none >/dev/null || return $?
    check_read $((logical_block_size)) || return $?
}

# Check whether fio accepts --zonemode=strided for zoned block devices.
test40() {
    local bs

    bs=$((logical_block_size))
    require_zbd || return $SKIP_TESTCASE
    read_one_block --zonemode=strided |
	grep -q 'fio: --zonesize must be specified when using --zonemode=strided' ||
	return $?
    read_one_block --zonemode=strided --zonesize=$bs >/dev/null || return $?
    check_read $bs || return $?
}

# Check whether fio checks the zone size for zoned block devices.
test41() {
    require_zbd || return $SKIP_TESTCASE
    read_one_block --zonemode=zbd --zonesize=$((2 * zone_size)) |
	grep -q 'job parameter zonesize.*does not match disk zone size'
}

# Check whether fio handles --zonesize=0 correctly for regular block devices.
test42() {
    require_regular_block_dev || return $SKIP_TESTCASE
    read_one_block --zonemode=zbd --zonesize=0 |
	grep -q 'Specifying the zone size is mandatory for regular block devices with --zonemode=zbd'
}

# Check whether fio handles --zonesize=1 correctly for regular block devices.
test43() {
    require_regular_block_dev || return $SKIP_TESTCASE
    read_one_block --zonemode=zbd --zonesize=1 |
	grep -q 'zone size must be at least 512 bytes for --zonemode=zbd'
}

# Check whether fio handles --zonemode=none --zonesize=1 correctly.
test44() {
    read_one_block --zonemode=none --zonesize=1 |
	grep -q 'fio: --zonemode=none and --zonesize are not compatible'
}

test45() {
    local bs i

    require_zbd || return $SKIP_TESTCASE
    prep_write
    bs=$((logical_block_size))
    run_one_fio_job "$(ioengine "psync")" --iodepth=1 --rw=randwrite --bs=$bs\
		    --offset=$((first_sequential_zone_sector * 512)) \
		    --size="$zone_size" --do_verify=1 --verify=md5 2>&1 |
	tee -a "${logfile}.${test_number}" |
	grep -q "fio: first I/O failed. If .* is a zoned block device, consider --zonemode=zbd"
}

# Random write to sequential zones, libaio, 8 jobs, queue depth 64 per job
test46() {
    local size

    prep_write
    size=$((4 * zone_size))
    run_fio_on_seq "$(ioengine "libaio")" --iodepth=64 --rw=randwrite --bs=4K \
		   --group_reporting=1 --numjobs=8 \
		   >> "${logfile}.${test_number}" 2>&1 || return $?
    check_written $((size * 8)) || return $?
}

# Check whether fio handles --zonemode=zbd --zoneskip=1 correctly.
test47() {
    local bs

    prep_write
    bs=$((logical_block_size))
    run_fio_on_seq "$(ioengine "psync")" --rw=write --bs=$bs --zoneskip=1 \
		    >> "${logfile}.${test_number}" 2>&1 && return 1
    grep -q 'zoneskip 1 is not a multiple of the device zone size' "${logfile}.${test_number}"
}

# Multiple overlapping random write jobs for the same drive and with a
# limited number of open zones. This is similar to test29, but uses libaio
# to stress test zone locking.
test48() {
    local i jobs=16 off opts=()

    require_zbd || return $SKIP_TESTCASE
    require_seq_zones 80 || return $SKIP_TESTCASE

    off=$((first_sequential_zone_sector * 512 + 64 * zone_size))
    size=$((16*zone_size))
    prep_write
    opts=("--aux-path=/tmp" "--allow_file_create=0" "--significant_figures=10")
    opts+=("--debug=zbd")
    opts+=("$(ioengine "libaio")" "--rw=randwrite" "--direct=1")
    opts+=("--time_based" "--runtime=30")
    opts+=("--zonemode=zbd" "--zonesize=${zone_size}")
    opts+=("--max_open_zones=4")
    for ((i=0;i<jobs;i++)); do
	opts+=("--name=job$i" "--filename=$dev" "--offset=$off" "--bs=16K")
	opts+=("--io_size=$zone_size" "--iodepth=256" "--thread=1")
	opts+=("--size=$size" "--group_reporting=1")
	# max_open_zones is already specified
	opts+=($(job_var_opts_exclude "--max_open_zones"))
    done

    fio=$(dirname "$0")/../../fio

    { echo; echo "fio ${opts[*]}"; echo; } >>"${logfile}.${test_number}"

    timeout -v -s KILL 45s \
	    "${dynamic_analyzer[@]}" "$fio" "${opts[@]}" \
	    >> "${logfile}.${test_number}" 2>&1 || return $?
}

# Check if fio handles --zonecapacity on a normal block device correctly
test49() {

    require_regular_block_dev || return $SKIP_TESTCASE

    size=$((2 * zone_size))
    capacity=$((zone_size * 3 / 4))

    run_one_fio_job "$(ioengine "psync")" --rw=write \
		    --zonemode=zbd --zonesize="${zone_size}" \
		    --zonecapacity=${capacity} \
		    --verify=md5  --size=${size} >>"${logfile}.${test_number}" 2>&1 ||
	return $?
    check_written $((capacity * 2)) || return $?
    check_read $((capacity * 2)) || return $?
}

# Verify that conv zones are not locked and only seq zones are locked during
# random read on conv-seq mixed zones.
test50() {
	local off

	require_zbd || return $SKIP_TESTCASE
	require_conv_zones 8 || return $SKIP_TESTCASE
	require_seq_zones 8 || return $SKIP_TESTCASE

	reset_zone "${dev}" -1

	off=$((first_sequential_zone_sector * 512 - 8 * zone_size))
	run_fio --name=job --filename=${dev} --offset=${off} --bs=64K \
		--size=$((16 * zone_size)) "$(ioengine "libaio")" --rw=randread\
		--time_based --runtime=3 --zonemode=zbd --zonesize=${zone_size}\
		--direct=1 --group_reporting=1 ${job_var_opts[@]} \
		>> "${logfile}.${test_number}" 2>&1 || return $?
}

# Verify that conv zones are neither locked nor opened during random write on
# conv-seq mixed zones. Zone lock and zone open shall happen only on seq zones.
test51() {
	local off jobs=16
	local -a opts

	require_zbd || return $SKIP_TESTCASE
	require_conv_zones 8 || return $SKIP_TESTCASE
	require_seq_zones 8 || return $SKIP_TESTCASE

	prep_write

	off=$((first_sequential_zone_sector * 512 - 8 * zone_size))
	opts+=("--size=$((16 * zone_size))" "$(ioengine "libaio")")
	opts+=("--zonemode=zbd" "--direct=1" "--zonesize=${zone_size}")
	opts+=("--max_open_zones=2" "--offset=$off")
	opts+=("--thread=1" "--group_reporting=1")
	opts+=("--time_based" "--runtime=30" "--rw=randwrite")
	for ((i=0;i<jobs;i++)); do
		opts+=("--name=job${i}" "--filename=$dev")
		opts+=("--bs=$(((i+1)*16))K")
		opts+=($(job_var_opts_exclude "--max_open_zones"))
	done
	run_fio "${opts[@]}" >> "${logfile}.${test_number}" 2>&1 || return $?
}

# Verify that zone_reset_threshold only takes logical blocks from seq
# zones into account, and logical blocks of conv zones are not counted.
test52() {
	local off io_size

	require_zbd || return $SKIP_TESTCASE
	require_conv_zones 8 || return $SKIP_TESTCASE
	require_seq_zones 8 || return $SKIP_TESTCASE

	reset_zone "${dev}" -1

	# Total I/O size is 1/8 = 0.125 of the I/O range of cont + seq zones.
	# Set zone_reset_threshold as 0.1. The threshold size is less than
	# 0.125, then, reset count zero is expected.
	# On the other hand, half of the I/O range is covered by conv zones.
	# If fio would count the conv zones for zone_reset_threshold, the ratio
	# were more than 0.5 and would trigger zone resets.

	off=$((first_sequential_zone_sector * 512 - 8 * zone_size))
	io_size=$((zone_size * 16 / 8))
	run_fio --name=job --filename=$dev --rw=randwrite --bs=$((zone_size/16))\
		--size=$((zone_size * 16)) --softrandommap=1 \
		--io_size=$((io_size)) "$(ioengine "psync")" --offset=$off \
		--zonemode=zbd --direct=1 --zonesize=${zone_size} \
		--zone_reset_threshold=.1 --zone_reset_frequency=1.0 \
		${job_var_opts[@]} --debug=zbd \
		>> "${logfile}.${test_number}" 2>&1 || return $?

	check_written ${io_size} || return $?
	check_reset_count -eq 0 || return $?
}

# Check both reads and writes are executed by random I/O to conventional zones.
test53() {
	local off capacity io read_b=0 written_b=0

	require_zbd || return $SKIP_TESTCASE
	require_conv_zones 4 || return $SKIP_TESTCASE

	off=$((first_sequential_zone_sector * 512 - 4 * zone_size))
	capacity=$(total_zone_capacity 4 $off $dev)
	run_fio --name=job --filename=${dev} --rw=randrw --bs=64K \
		--size=$((4 * zone_size)) "$(ioengine "psync")" --offset=${off}\
		--zonemode=zbd --direct=1 --zonesize=${zone_size} \
		${job_var_opts[@]} \
		>> "${logfile}.${test_number}" 2>&1 || return $?

	written_b=$(fio_written <"${logfile}.${test_number}")
	read_b=$(fio_read <"${logfile}.${test_number}")
	io=$((written_b + read_b))
	echo "Number of bytes read: $read_b" >>"${logfile}.${test_number}"
	echo "Number of bytes written: $written_b" >>"${logfile}.${test_number}"
	echo "Total number of bytes read and written: $io <> $capacity" \
	     >>"${logfile}.${test_number}"
	if ((io==capacity && written_b != 0 && read_b != 0)); then
		return 0
	fi
	return 1
}

tests=()
dynamic_analyzer=()
reset_all_zones=
use_libzbc=
zbd_debug=
max_open_zones_opt=
quit_on_err=

while [ "${1#-}" != "$1" ]; do
  case "$1" in
    -d) dynamic_analyzer=(valgrind "--read-var-info=yes" "--tool=drd"
			  "--show-confl-seg=no");
	shift;;
    -e) dynamic_analyzer=(valgrind "--read-var-info=yes" "--tool=helgrind");
	shift;;
    -l) use_libzbc=1; shift;;
    -r) reset_all_zones=1; shift;;
    -t) tests+=("$2"); shift; shift;;
    -o) max_open_zones_opt="${2}"; shift; shift;;
    -v) dynamic_analyzer=(valgrind "--read-var-info=yes");
	shift;;
    -q) quit_on_err=1; shift;;
    -z) zbd_debug=1; shift;;
    --) shift; break;;
  esac
done

if [ $# != 1 ]; then
    usage
    exit 1
fi

# shellcheck source=functions
source "$(dirname "$0")/functions" || exit $?

global_var_opts=()
job_var_opts=()
if [ -n "$zbd_debug" ]; then
    global_var_opts+=("--debug=zbd")
fi
dev=$1
realdev=$(readlink -f "$dev")
basename=$(basename "$realdev")

if [[ -b "$realdev" ]]; then
	major=$((0x$(stat -L -c '%t' "$realdev"))) || exit $?
	minor=$((0x$(stat -L -c '%T' "$realdev"))) || exit $?
	disk_size=$(($(<"/sys/dev/block/$major:$minor/size")*512))

	# When the target is a partition device, get basename of its
	# holder device to access sysfs path of the holder device
	if [[ -r "/sys/dev/block/$major:$minor/partition" ]]; then
		realsysfs=$(readlink "/sys/dev/block/$major:$minor")
		basename=$(basename "${realsysfs%/*}")
	fi
	logical_block_size=$(<"/sys/block/$basename/queue/logical_block_size")
	case "$(<"/sys/class/block/$basename/queue/zoned")" in
	host-managed|host-aware)
		is_zbd=true
		if ! check_blkzone "${dev}"; then
			exit 1
		fi
		if ! result=($(first_sequential_zone "$dev")); then
			echo "Failed to determine first sequential zone"
			exit 1
		fi
		first_sequential_zone_sector=${result[0]}
		sectors_per_zone=${result[1]}
		zone_size=$((sectors_per_zone * 512))
		if ! max_open_zones=$(max_open_zones "$dev"); then
			echo "Failed to determine maximum number of open zones"
			exit 1
		fi
		set_io_scheduler "$basename" deadline || exit $?
		if [ -n "$reset_all_zones" ]; then
			reset_zone "$dev" -1
		fi
		;;
	*)
		first_sequential_zone_sector=$(((disk_size / 2) &
						(logical_block_size - 1)))
		zone_size=$(max 65536 "$logical_block_size")
		sectors_per_zone=$((zone_size / 512))
		max_open_zones=128
		set_io_scheduler "$basename" none || exit $?
		;;
	esac
elif [[ -c "$realdev" ]]; then
	# For an SG node, we must have libzbc option specified
	if [[ ! -n "$use_libzbc" ]]; then
		echo "Character device files can only be used with -l (libzbc) option"
		exit 1
	fi

	if ! $(is_zbc "$dev"); then
		echo "Device is not a ZBC disk"
		exit 1
	fi
	is_zbd=true

	if ! disk_size=($(( $(zbc_disk_sectors "$dev") * 512))); then
		echo "Failed to determine disk size"
		exit 1
	fi
	if ! logical_block_size=($(zbc_logical_block_size "$dev")); then
		echo "Failed to determine logical block size"
		exit 1
	fi
	if ! result=($(first_sequential_zone "$dev")); then
		echo "Failed to determine first sequential zone"
		exit 1
	fi
	first_sequential_zone_sector=${result[0]}
	sectors_per_zone=${result[1]}
	zone_size=$((sectors_per_zone * 512))
	if ! max_open_zones=$(max_open_zones "$dev"); then
		echo "Failed to determine maximum number of open zones"
		exit 1
	fi
	if [ -n "$reset_all_zones" ]; then
		reset_zone "$dev" -1
	fi
fi

if [[ -n ${max_open_zones_opt} ]]; then
	# Override max_open_zones with the script option value
	max_open_zones="${max_open_zones_opt}"
	job_var_opts+=("--max_open_zones=${max_open_zones_opt}")
fi

echo -n "First sequential zone starts at sector $first_sequential_zone_sector;"
echo " zone size: $((zone_size >> 20)) MB"

if [ "${#tests[@]}" = 0 ]; then
    readarray -t tests < <(declare -F | grep "test[0-9]*" | \
				   tr -c -d "[:digit:]\n" | sort -n)
fi

logfile=$0.log

passed=0
skipped=0
failed=0
if [ -t 1 ]; then
    red="\e[1;31m"
    green="\e[1;32m"
    cyan="\e[1;36m"
    end="\e[m"
else
    red=""
    green=""
    end=""
fi
rc=0

intr=0
trap 'intr=1' SIGINT
ret=0

for test_number in "${tests[@]}"; do
    rm -f "${logfile}.${test_number}"
    unset SKIP_REASON
    echo -n "Running test $(printf "%02d" $test_number) ... "
    eval "test$test_number"
    ret=$?
    if ((!ret)) && check_log $test_number; then
	status="PASS"
	cc_status="${green}${status}${end}"
	((passed++))
    elif ((ret==SKIP_TESTCASE)); then
	status="SKIP"
	echo "${SKIP_REASON}" >> "${logfile}.${test_number}"
	cc_status="${cyan}${status}${end}    ${SKIP_REASON}"
	((skipped++))
    else
	status="FAIL"
	cc_status="${red}${status}${end}"
	((failed++))
	rc=1
    fi
    echo -e "$cc_status"
    echo "$status" >> "${logfile}.${test_number}"
    [ $intr -ne 0 ] && exit 1
    [ -n "$quit_on_err" -a "$rc" -ne 0 ] && exit 1
done

echo "$passed tests passed"
if [ $skipped -gt 0 ]; then
    echo " $skipped tests skipped"
fi
if [ $failed -gt 0 ]; then
    echo " $failed tests failed"
fi
exit $rc