t/zbd: get max_open_zones from sysfs

[fio.git] / t / zbd / functions

#!/bin/bash

blkzone=$(type -p blkzone 2>/dev/null)
sg_inq=$(type -p sg_inq 2>/dev/null)
zbc_report_zones=$(type -p zbc_report_zones 2>/dev/null)
zbc_reset_zone=$(type -p zbc_reset_zone 2>/dev/null)
zbc_close_zone=$(type -p zbc_close_zone 2>/dev/null)
zbc_info=$(type -p zbc_info 2>/dev/null)
if [ -z "${blkzone}" ] &&
       { [ -z "${zbc_report_zones}" ] || [ -z "${zbc_reset_zone}" ]; }; then
    echo "Error: neither blkzone nor zbc_report_zones is available"
    exit 1
fi

if [ -n "${use_libzbc}" ] &&
       { [ -z "${zbc_report_zones}" ] || [ -z "${zbc_reset_zone}" ] ||
         [ -z "${zbc_info}" ]; }; then
    echo "Error: zbc_report_zones, or zbc_reset_zone or zbc_info is not available"
    echo "Error: reinstall libzbc tools"
    exit 1
fi

blkzone_reports_capacity() {
	local dev="${1}"

	[[ -n "${blkzone}" ]] &&
		"${blkzone}" report -c 1 -o 0 "${dev}" | grep -q 'cap '
}

# Whether or not $1 (/dev/...) is a NVME ZNS device.
is_nvme_zns() {
	local s

	s=/sys/block/$(basename "${1}")/device/subsystem

	if [[ ! -h "${s}" || $(realpath "${s}") != /sys/class/nvme ]]; then
		return 1
	fi

	[[ $(</sys/block/$(basename "${1}")/queue/zoned) == host-managed ]]
}

# Whether or not $1 (/dev/...) is a null_blk device with zone capacity smaller
# than zone size.
is_nullb_with_zone_cap() {
	local f

	f=/sys/kernel/config/nullb/$(basename "${1}")
	[[ -r "${f}/zone_capacity" &&
		   $(<"${f}/zone_capacity") -lt $(<"${f}/zone_size") ]]
}

# Check if blkzone is available and suitable for the test target device. If not
# available, print error message and return 1. Otherwise return 0.
check_blkzone() {
	local dev="${1}"

	# If the device supports zone capacity, mandate zone capacity report by
	# blkzone.
	if (is_nvme_zns "${dev}" || is_nullb_with_zone_cap "${dev}") &&
				! blkzone_reports_capacity "${dev}"; then
		echo "Error: blkzone does not report zone capacity"
		echo "Error: install latest util-linux with blkzone"
		return 1
	fi
}

# Check zone capacity of each zone and report block size aligned to the zone
# capacities. If zone capacity is same as zone size for zones, report zone size.
zone_cap_bs() {
	local dev="${1}"
	local zone_size="${2}"
	local sed_str='s/.*len \([0-9A-Za-z]*\), cap \([0-9A-Za-z]*\).*/\1 \2/p'
	local cap bs="$zone_size"

	# When blkzone command is neither available nor relevant to the
	# test device, or when blkzone command does not report capacity,
	# assume that zone capacity is same as zone size for all zones.
	if [ -z "${blkzone}" ] || [ -z "$is_zbd" ] || [ -c "$dev" ] ||
		   ! blkzone_reports_capacity "${dev}"; then
		echo "$zone_size"
		return
	fi

	while read -r -a line; do
		((line[0] == line[1])) && continue
		cap=$((line[1] * 512))
		while ((bs > 512 && cap % bs)); do
			bs=$((bs / 2))
		done
	done < <(blkzone report "${dev}" | sed -n "${sed_str}")

	echo "$bs"
}

# Reports the starting sector and length of the first sequential zone of device
# $1.
first_sequential_zone() {
    local dev=$1

    if [ -n "${blkzone}" ] && [ ! -n "${use_libzbc}" ]; then
	${blkzone} report "$dev" |
	    sed -n 's/^[[:blank:]]*start:[[:blank:]]\([0-9a-zA-Z]*\),[[:blank:]]len[[:blank:]]\([0-9a-zA-Z]*\),.*zcond:\(14\|[[:blank:]][0-4]\)(.*type:[[:blank:]]\([2]\)(.*/\1 \2/p' |
	    {
		read -r starting_sector length &&
		    # Convert from hex to decimal
		    echo $((starting_sector)) $((length))
	    }
    else
	${zbc_report_zones} "$dev" |
	    sed -n 's/^Zone [0-9]*: type 0x2 .*,[[:blank:]]cond[[:blank:]]0x[0-4e][[:blank:]].*, sector \([0-9]*\), \([0-9]*\) sectors.*$/\1 \2/p' |
	    head -n1
    fi
}

# Reports the summed zone capacity of $1 number of zones starting from offset $2
# on device $3.
total_zone_capacity() {
	local nr_zones=$1
	local sector=$(($2 / 512))
	local dev=$3
	local capacity=0 num
	local grep_str

	if [ -z "$is_zbd" ]; then
		# For regular block devices, handle zone size as zone capacity.
		echo $((zone_size * nr_zones))
		return
	fi

	if [ -n "${blkzone}" ] && [ ! -n "${use_libzbc}" ]; then
		if blkzone_reports_capacity "${dev}"; then
			grep_str='cap \K[0-9a-zA-Z]*'
		else
			# If zone capacity is not reported, refer zone length.
			grep_str='len \K[0-9a-zA-Z]*'
		fi
		while read num; do
			capacity=$((capacity + num))
		done < <(${blkzone} report -c "$nr_zones" -o "$sector" "$dev" |
				grep -Po "${grep_str}")
	else
		# ZBC devices do not have zone capacity. Use zone size.
		while read num; do
			capacity=$((capacity + num))
		done < <(${zbc_report_zones} -nz "$nr_zones" -start "$sector" \
				"$dev" | grep -Po 'sector [0-9]*, \K[0-9]*')
	fi

	echo $((capacity * 512))
}

# Reports the starting sector and length of the first zone of device $1
# that is not in offline (or similar) condition.
first_online_zone() {
    local dev=$1

    if [ -z "$is_zbd" ]; then
	echo 0
	return
    fi

    if [ -n "${blkzone}" ] && [ ! -n "${use_libzbc}" ]; then
	${blkzone} report "$dev" |
	    sed -n 's/^[[:blank:]]*start:[[:blank:]]\([0-9a-zA-Z]*\),[[:blank:]]len[[:blank:]]\([0-9a-zA-Z]*\),.*zcond:\(14\|[[:blank:]][0-4]\)(.*type:[[:blank:]][12](.*/\1/p' |
	    head -n1 |
	    {
		read -r starting_sector &&
		    # Convert from hex to decimal
		    echo $((starting_sector))
	    }
    else
	${zbc_report_zones} "$dev" |
	    sed -n 's/^Zone[[:blank:]][0-9]*:[[:blank:]]type[[:blank:]]0x[12][[:blank:]].*,[[:blank:]]cond[[:blank:]]0x[0-4e][[:blank:]].*,[[:blank:]]sector[[:blank:]]\([0-9]*\),.*$/\1/p' |
	    head -n1
    fi
}

# Reports the starting sector and length of the last zone of device $1
# that is not in offline (or similar) condition.
last_online_zone() {
    local dev=$1

    if [ -z "$is_zbd" ]; then
	echo 0
	return
    fi

    if [ -n "${blkzone}" ] && [ ! -n "${use_libzbc}" ]; then
	${blkzone} report "$dev" |
	    sed -n 's/^[[:blank:]]*start:[[:blank:]]\([0-9a-zA-Z]*\),[[:blank:]]len[[:blank:]]\([0-9a-zA-Z]*\),.*zcond:\(14\|[[:blank:]][0-4]\)(.*type:[[:blank:]][12](.*/\1/p' |
	    tail -1 |
	    {
		read -r starting_sector &&
		    # Convert from hex to decimal
		    echo $((starting_sector))
	    }
    else
	${zbc_report_zones} "$dev" |
	    sed -n 's/^Zone[[:blank:]][0-9]*:[[:blank:]]type[[:blank:]]0x[12][[:blank:]].*,[[:blank:]]cond[[:blank:]]0x[0-4e][[:blank:]].*,[[:blank:]]sector[[:blank:]]\([0-9]*\),.*$/\1/p' |
	    tail -1
    fi
}

# Get max_open_zones of SMR drives using sg_inq or libzbc tools. Two test cases
# 31 and 32 use this max_open_zones value. The test case 31 uses max_open_zones
# to decide number of write target zones. The test case 32 passes max_open_zones
# value to fio with --max_open_zones option. Of note is that fio itself has the
# feature to get max_open_zones from the device through sysfs or ioengine
# specific implementation. This max_open_zones fetch by test script is required
# in case fio is running on an old Linux kernel version which lacks
# max_open_zones in sysfs, or which lacks zoned block device support completely.
max_open_zones() {
    local dev=$1
    local realdev syspath

    realdev=$(readlink -f "$dev")
    syspath=/sys/block/${realdev##*/}/queue/max_open_zones

    if [ -b "${realdev}" ] && [ -r "${syspath}" ]; then
	cat ${syspath}
    elif [ -n "${sg_inq}" ] && [ ! -n "${use_libzbc}" ]; then
	if ! ${sg_inq} -e --page=0xB6 --len=20 --hex "$dev" \
		 > /dev/null 2>&1; then
	    # When sg_inq can not get max open zones, specify 0 which indicates
	    # fio to get max open zones limit from the device.
	    echo 0
	else
	    ${sg_inq} -e --page=0xB6 --len=20 --hex "$dev" | tail -1 |
		{
		    read -r offset b0 b1 b2 b3 trailer || return $?
		    # Convert from hex to decimal
		    max_nr_open_zones=$((0x${b0}))
		    max_nr_open_zones=$((max_nr_open_zones * 256 + 0x${b1}))
		    max_nr_open_zones=$((max_nr_open_zones * 256 + 0x${b2}))
		    max_nr_open_zones=$((max_nr_open_zones * 256 + 0x${b3}))
		    echo ${max_nr_open_zones}
		}
	fi
    elif [ -n "${use_libzbc}" ]; then
	${zbc_report_zones} "$dev" |
	    sed -n 's/^[[:blank:]]*Maximum number of open sequential write required zones:[[:blank:]]*//p'
    else
	echo 0
    fi
}

# If sysfs provides, get max_active_zones limit of the zoned block device.
max_active_zones() {
	local dev=$1
	local sys_queue="/sys/block/${dev##*/}/queue/"

	if [[ -e "$sys_queue/max_active_zones" ]]; then
		cat "$sys_queue/max_active_zones"
		return
	fi
	echo 0
}

# Get minimum block size to write to seq zones. Refer the sysfs attribute
# zone_write_granularity which shows the valid minimum size regardless of zoned
# block device type. If the sysfs attribute is not available, refer physical
# block size for rotational SMR drives. For non-rotational devices such as ZNS
# devices, refer logical block size.
min_seq_write_size() {
	local sys_path="/sys/block/$1/queue"
	local -i size=0

	if [[ -r "$sys_path/zone_write_granularity" ]]; then
		size=$(<"$sys_path/zone_write_granularity")
	fi

	if ((size)); then
		echo "$size"
	elif (($(<"$sys_path/rotational"))); then
		cat "$sys_path/physical_block_size"
	else
		cat "$sys_path/logical_block_size"
	fi
}

is_zbc() {
	local dev=$1

	[[ -z "$(${zbc_info} "$dev" | grep "is not a zoned block device")" ]]
}

zbc_physical_block_size() {
	local dev=$1

	${zbc_info} "$dev" |
		grep "physical blocks" |
		sed -n 's/^[[:blank:]]*[0-9]* physical blocks of[[:blank:]]*//p' |
		sed 's/ B//'
}

zbc_disk_sectors() {
        local dev=$1

	zbc_info "$dev" |
		grep "512-bytes sectors" |
		sed -e 's/[[:blank:]]*\([0-9]*\)512-bytes sectors.*/\1/'
}

# Reset the write pointer of one zone on device $1 at offset $2. The offset
# must be specified in units of 512 byte sectors. Offset -1 means reset all
# zones.
reset_zone() {
    local dev=$1 offset=$2 sectors

    if [ -n "${blkzone}" ] && [ ! -n "${use_libzbc}" ]; then
	if [ "$offset" -lt 0 ]; then
	    ${blkzone} reset "$dev"
	else
	    ${blkzone} reset -o "${offset}" -c 1 "$dev"
	fi
    else
	if [ "$offset" -lt 0 ]; then
	    ${zbc_reset_zone} -all "$dev" >/dev/null
	else
	    ${zbc_reset_zone} -sector "$dev" "${offset}" >/dev/null
	fi
    fi
}

# Close the zone on device $1 at offset $2. The offset must be specified in
# units of 512 byte sectors.
close_zone() {
	local dev=$1 offset=$2

	if [ -n "${blkzone}" ] && [ -z "${use_libzbc}" ]; then
		${blkzone} close -o "${offset}" -c 1 "$dev"
	else
		${zbc_close_zone} -sector "$dev" "${offset}" >/dev/null
	fi
}

# Extract the number of bytes that have been transferred from a line like
# READ: bw=6847KiB/s (7011kB/s), 6847KiB/s-6847KiB/s (7011kB/s-7011kB/s), io=257MiB (269MB), run=38406-38406msec
fio_io() {
    sed -n 's/^[[:blank:]]*'"$1"'.*, io=\([^[:blank:]]*\).*/\1/p' |
	tail -n 1 |
	(
	    read -r io;
	    # Parse <number>.<number><suffix> into n1, n2 and s. See also
	    # num2str().
	    shopt -s extglob
	    n1=${io%${io##*([0-9])}}
	    s=${io#${io%%*([a-zA-Z])}}
	    n2=${io#${n1}}
	    n2=${n2#.}
	    n2=${n2%$s}000
	    n2=${n2:0:3}
	    case "$s" in
		KiB) m=10;;
		MiB) m=20;;
		GiB) m=30;;
		B)   m=0;;
		*)   return 1;;
	    esac
	    [ -n "$n1" ] || return 1
	    echo $(((n1 << m) + (n2 << m) / 1000))
	)
}

fio_read() {
    fio_io 'READ:'
}

fio_written() {
    fio_io 'WRITE:'
}

fio_reset_count() {
    local count

    count=$(sed -n 's/^.*write:[^;]*; \([0-9]*\) zone resets$/\1/p')
    echo "${count:-0}"
}