mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-17 18:11:00 +03:00
d441e85dd7
While the autoexpand property may seem like a small feature it depends on a significant amount of system infrastructure. Enough of that infrastructure is now in place that with a few modifications for Linux it can be supported. Auto-expand works as follows; when a block device is modified (re-sized, closed after being open r/w, etc) a change uevent is generated for udev. The ZED, which is monitoring udev events, passes the change event along to zfs_deliver_dle() if the disk or partition contains a zfs_member as identified by blkid. From here the device is matched against all imported pool vdevs using the vdev_guid which was read from the label by blkid. If a match is found the ZED reopens the pool vdev. This re-opening is important because it allows the vdev to be briefly closed so the disk partition table can be re-read. Otherwise, it wouldn't be possible to report the maximum possible expansion size. Finally, if the property autoexpand=on a vdev expansion will be attempted. After performing some sanity checks on the disk to verify that it is safe to expand, the primary partition (-part1) will be expanded and the partition table updated. The partition is then re-opened (again) to detect the updated size which allows the new capacity to be used. In order to make all of the above possible the following changes were required: * Updated the zpool_expand_001_pos and zpool_expand_003_pos tests. These tests now create a pool which is layered on a loopback, scsi_debug, and file vdev. This allows for testing of non- partitioned block device (loopback), a partition block device (scsi_debug), and a file which does not receive udev change events. This provided for better test coverage, and by removing the layering on ZFS volumes there issues surrounding layering one pool on another are avoided. * zpool_find_vdev_by_physpath() updated to accept a vdev guid. This allows for matching by guid rather than path which is a more reliable way for the ZED to reference a vdev. * Fixed zfs_zevent_wait() signal handling which could result in the ZED spinning when a signal was not handled. * Removed vdev_disk_rrpart() functionality which can be abandoned in favor of kernel provided blkdev_reread_part() function. * Added a rwlock which is held as a writer while a disk is being reopened. This is important to prevent errors from occurring for any configuration related IOs which bypass the SCL_ZIO lock. The zpool_reopen_007_pos.ksh test case was added to verify IO error are never observed when reopening. This is not expected to impact IO performance. Additional fixes which aren't critical but were discovered and resolved in the course of developing this functionality. * Added PHYS_PATH="/dev/zvol/dataset" to the vdev configuration for ZFS volumes. This is as good as a unique physical path, while the volumes are not used in the test cases anymore for other reasons this improvement was included. Reviewed by: Richard Elling <Richard.Elling@RichardElling.com> Signed-off-by: Sara Hartse <sara.hartse@delphix.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #120 Closes #2437 Closes #5771 Closes #7366 Closes #7582 Closes #7629
450 lines
10 KiB
Plaintext
450 lines
10 KiB
Plaintext
#
|
|
# This file and its contents are supplied under the terms of the
|
|
# Common Development and Distribution License ("CDDL"), version 1.0.
|
|
# You may only use this file in accordance with the terms of version
|
|
# 1.0 of the CDDL.
|
|
#
|
|
# A full copy of the text of the CDDL should have accompanied this
|
|
# source. A copy of the CDDL is also available via the Internet at
|
|
# http://www.illumos.org/license/CDDL.
|
|
#
|
|
|
|
#
|
|
# Copyright 2009 Sun Microsystems, Inc. All rights reserved.
|
|
# Use is subject to license terms.
|
|
# Copyright (c) 2012, 2016 by Delphix. All rights reserved.
|
|
# Copyright 2016 Nexenta Systems, Inc.
|
|
# Copyright (c) 2016, 2017 by Intel Corporation. All rights reserved.
|
|
# Copyright (c) 2017 Lawrence Livermore National Security, LLC.
|
|
# Copyright (c) 2017 Datto Inc.
|
|
# Copyright (c) 2017 Open-E, Inc. All Rights Reserved.
|
|
#
|
|
|
|
#
|
|
# Returns SCSI host number for the given disk
|
|
#
|
|
function get_scsi_host #disk
|
|
{
|
|
typeset disk=$1
|
|
ls /sys/block/${disk}/device/scsi_device | cut -d : -f 1
|
|
}
|
|
|
|
#
|
|
# Cause a scan of all scsi host adapters by default
|
|
#
|
|
# $1 optional host number
|
|
#
|
|
function scan_scsi_hosts
|
|
{
|
|
typeset hostnum=${1}
|
|
|
|
if is_linux; then
|
|
if [[ -z $hostnum ]]; then
|
|
for host in /sys/class/scsi_host/host*; do
|
|
log_must eval "echo '- - -' > $host/scan"
|
|
done
|
|
else
|
|
log_must eval \
|
|
"echo /sys/class/scsi_host/host$hostnum/scan" \
|
|
> /dev/null
|
|
log_must eval \
|
|
"echo '- - -' > /sys/class/scsi_host/host$hostnum/scan"
|
|
fi
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Wait for newly created block devices to have their minors created.
|
|
#
|
|
function block_device_wait
|
|
{
|
|
if is_linux; then
|
|
udevadm trigger
|
|
udevadm settle
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Check if the given device is physical device
|
|
#
|
|
function is_physical_device #device
|
|
{
|
|
typeset device=${1#$DEV_DSKDIR}
|
|
device=${device#$DEV_RDSKDIR}
|
|
|
|
if is_linux; then
|
|
[[ -b "$DEV_DSKDIR/$device" ]] && \
|
|
[[ -f /sys/module/loop/parameters/max_part ]]
|
|
return $?
|
|
else
|
|
echo $device | egrep "^c[0-F]+([td][0-F]+)+$" > /dev/null 2>&1
|
|
return $?
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Check if the given device is a real device (ie SCSI device)
|
|
#
|
|
function is_real_device #disk
|
|
{
|
|
typeset disk=$1
|
|
[[ -z $disk ]] && log_fail "No argument for disk given."
|
|
|
|
if is_linux; then
|
|
lsblk $DEV_RDSKDIR/$disk -o TYPE 2>/dev/null | \
|
|
egrep disk >/dev/null
|
|
return $?
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Check if the given device is a loop device
|
|
#
|
|
function is_loop_device #disk
|
|
{
|
|
typeset disk=$1
|
|
[[ -z $disk ]] && log_fail "No argument for disk given."
|
|
|
|
if is_linux; then
|
|
lsblk $DEV_RDSKDIR/$disk -o TYPE 2>/dev/null | \
|
|
egrep loop >/dev/null
|
|
return $?
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Check if the given device is a multipath device and if there is a sybolic
|
|
# link to a device mapper and to a disk
|
|
# Currently no support for dm devices alone without multipath
|
|
#
|
|
function is_mpath_device #disk
|
|
{
|
|
typeset disk=$1
|
|
[[ -z $disk ]] && log_fail "No argument for disk given."
|
|
|
|
if is_linux; then
|
|
lsblk $DEV_MPATHDIR/$disk -o TYPE 2>/dev/null | \
|
|
egrep mpath >/dev/null
|
|
if (($? == 0)); then
|
|
readlink $DEV_MPATHDIR/$disk > /dev/null 2>&1
|
|
return $?
|
|
else
|
|
return $?
|
|
fi
|
|
fi
|
|
}
|
|
|
|
# Set the slice prefix for disk partitioning depending
|
|
# on whether the device is a real, multipath, or loop device.
|
|
# Currently all disks have to be of the same type, so only
|
|
# checks first disk to determine slice prefix.
|
|
#
|
|
function set_slice_prefix
|
|
{
|
|
typeset disk
|
|
typeset -i i=0
|
|
|
|
if is_linux; then
|
|
while (( i < $DISK_ARRAY_NUM )); do
|
|
disk="$(echo $DISKS | nawk '{print $(i + 1)}')"
|
|
if ( is_mpath_device $disk ) && [[ -z $(echo $disk | awk 'substr($1,18,1)\
|
|
~ /^[[:digit:]]+$/') ]] || ( is_real_device $disk ); then
|
|
export SLICE_PREFIX=""
|
|
return 0
|
|
elif ( is_mpath_device $disk || is_loop_device \
|
|
$disk ); then
|
|
export SLICE_PREFIX="p"
|
|
return 0
|
|
else
|
|
log_fail "$disk not supported for partitioning."
|
|
fi
|
|
(( i = i + 1))
|
|
done
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Set the directory path of the listed devices in $DISK_ARRAY_NUM
|
|
# Currently all disks have to be of the same type, so only
|
|
# checks first disk to determine device directory
|
|
# default = /dev (linux)
|
|
# real disk = /dev (linux)
|
|
# multipath device = /dev/mapper (linux)
|
|
#
|
|
function set_device_dir
|
|
{
|
|
typeset disk
|
|
typeset -i i=0
|
|
|
|
if is_linux; then
|
|
while (( i < $DISK_ARRAY_NUM )); do
|
|
disk="$(echo $DISKS | nawk '{print $(i + 1)}')"
|
|
if is_mpath_device $disk; then
|
|
export DEV_DSKDIR=$DEV_MPATHDIR
|
|
return 0
|
|
else
|
|
export DEV_DSKDIR=$DEV_RDSKDIR
|
|
return 0
|
|
fi
|
|
(( i = i + 1))
|
|
done
|
|
else
|
|
export DEV_DSKDIR=$DEV_RDSKDIR
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Get the directory path of given device
|
|
#
|
|
function get_device_dir #device
|
|
{
|
|
typeset device=$1
|
|
|
|
if ! $(is_physical_device $device) ; then
|
|
if [[ $device != "/" ]]; then
|
|
device=${device%/*}
|
|
fi
|
|
if [[ -b "$DEV_DSKDIR/$device" ]]; then
|
|
device="$DEV_DSKDIR"
|
|
fi
|
|
echo $device
|
|
else
|
|
echo "$DEV_DSKDIR"
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Get persistent name for given disk
|
|
#
|
|
function get_persistent_disk_name #device
|
|
{
|
|
typeset device=$1
|
|
typeset dev_id
|
|
|
|
if is_linux; then
|
|
if is_real_device $device; then
|
|
dev_id="$(udevadm info -q all -n $DEV_DSKDIR/$device \
|
|
| egrep disk/by-id | nawk '{print $2; exit}' \
|
|
| nawk -F / '{print $3}')"
|
|
echo $dev_id
|
|
elif is_mpath_device $device; then
|
|
dev_id="$(udevadm info -q all -n $DEV_DSKDIR/$device \
|
|
| egrep disk/by-id/dm-uuid \
|
|
| nawk '{print $2; exit}' \
|
|
| nawk -F / '{print $3}')"
|
|
echo $dev_id
|
|
else
|
|
echo $device
|
|
fi
|
|
else
|
|
echo $device
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Online or offline a disk on the system
|
|
#
|
|
# First checks state of disk. Test will fail if disk is not properly onlined
|
|
# or offlined. Online is a full rescan of SCSI disks by echoing to every
|
|
# host entry.
|
|
#
|
|
function on_off_disk # disk state{online,offline} host
|
|
{
|
|
typeset disk=$1
|
|
typeset state=$2
|
|
typeset host=$3
|
|
|
|
[[ -z $disk ]] || [[ -z $state ]] && \
|
|
log_fail "Arguments invalid or missing"
|
|
|
|
if is_linux; then
|
|
if [[ $state == "offline" ]] && ( is_mpath_device $disk ); then
|
|
dm_name="$(readlink $DEV_DSKDIR/$disk \
|
|
| nawk -F / '{print $2}')"
|
|
slave="$(ls /sys/block/${dm_name}/slaves \
|
|
| nawk '{print $1}')"
|
|
while [[ -n $slave ]]; do
|
|
#check if disk is online
|
|
lsscsi | egrep $slave > /dev/null
|
|
if (($? == 0)); then
|
|
slave_dir="/sys/block/${dm_name}"
|
|
slave_dir+="/slaves/${slave}/device"
|
|
ss="${slave_dir}/state"
|
|
sd="${slave_dir}/delete"
|
|
log_must eval "echo 'offline' > ${ss}"
|
|
log_must eval "echo '1' > ${sd}"
|
|
lsscsi | egrep $slave > /dev/null
|
|
if (($? == 0)); then
|
|
log_fail "Offlining" \
|
|
"$disk failed"
|
|
fi
|
|
fi
|
|
slave="$(ls /sys/block/$dm_name/slaves \
|
|
2>/dev/null | nawk '{print $1}')"
|
|
done
|
|
elif [[ $state == "offline" ]] && ( is_real_device $disk ); then
|
|
#check if disk is online
|
|
lsscsi | egrep $disk > /dev/null
|
|
if (($? == 0)); then
|
|
dev_state="/sys/block/$disk/device/state"
|
|
dev_delete="/sys/block/$disk/device/delete"
|
|
log_must eval "echo 'offline' > ${dev_state}"
|
|
log_must eval "echo '1' > ${dev_delete}"
|
|
lsscsi | egrep $disk > /dev/null
|
|
if (($? == 0)); then
|
|
log_fail "Offlining $disk" \
|
|
"failed"
|
|
fi
|
|
else
|
|
log_note "$disk is already offline"
|
|
fi
|
|
elif [[ $state == "online" ]]; then
|
|
#force a full rescan
|
|
scan_scsi_hosts $host
|
|
block_device_wait
|
|
if is_mpath_device $disk; then
|
|
dm_name="$(readlink $DEV_DSKDIR/$disk \
|
|
| nawk -F / '{print $2}')"
|
|
slave="$(ls /sys/block/$dm_name/slaves \
|
|
| nawk '{print $1}')"
|
|
lsscsi | egrep $slave > /dev/null
|
|
if (($? != 0)); then
|
|
log_fail "Onlining $disk failed"
|
|
fi
|
|
elif is_real_device $disk; then
|
|
block_device_wait
|
|
typeset -i retries=0
|
|
while ! lsscsi | egrep -q $disk; do
|
|
if (( $retries > 2 )); then
|
|
log_fail "Onlining $disk failed"
|
|
break
|
|
fi
|
|
(( ++retries ))
|
|
sleep 1
|
|
done
|
|
else
|
|
log_fail "$disk is not a real dev"
|
|
fi
|
|
else
|
|
log_fail "$disk failed to $state"
|
|
fi
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Simulate disk removal
|
|
#
|
|
function remove_disk #disk
|
|
{
|
|
typeset disk=$1
|
|
on_off_disk $disk "offline"
|
|
block_device_wait
|
|
}
|
|
|
|
#
|
|
# Simulate disk insertion for the given SCSI host
|
|
#
|
|
function insert_disk #disk scsi_host
|
|
{
|
|
typeset disk=$1
|
|
typeset scsi_host=$2
|
|
on_off_disk $disk "online" $scsi_host
|
|
block_device_wait
|
|
}
|
|
|
|
#
|
|
# Load scsi_debug module with specified parameters
|
|
# $blksz can be either one of: < 512b | 512e | 4Kn >
|
|
#
|
|
function load_scsi_debug # dev_size_mb add_host num_tgts max_luns blksz
|
|
{
|
|
typeset devsize=$1
|
|
typeset hosts=$2
|
|
typeset tgts=$3
|
|
typeset luns=$4
|
|
typeset blksz=$5
|
|
|
|
[[ -z $devsize ]] || [[ -z $hosts ]] || [[ -z $tgts ]] || \
|
|
[[ -z $luns ]] || [[ -z $blksz ]] && \
|
|
log_fail "Arguments invalid or missing"
|
|
|
|
case "$5" in
|
|
'512b')
|
|
typeset sector=512
|
|
typeset blkexp=0
|
|
;;
|
|
'512e')
|
|
typeset sector=512
|
|
typeset blkexp=3
|
|
;;
|
|
'4Kn')
|
|
typeset sector=4096
|
|
typeset blkexp=0
|
|
;;
|
|
*) log_fail "Unsupported blksz value: $5" ;;
|
|
esac
|
|
|
|
if is_linux; then
|
|
modprobe -n scsi_debug
|
|
if (($? != 0)); then
|
|
log_unsupported "Platform does not have scsi_debug"
|
|
"module"
|
|
fi
|
|
lsmod | egrep scsi_debug > /dev/null
|
|
if (($? == 0)); then
|
|
log_fail "scsi_debug module already installed"
|
|
else
|
|
log_must modprobe scsi_debug dev_size_mb=$devsize \
|
|
add_host=$hosts num_tgts=$tgts max_luns=$luns \
|
|
sector_size=$sector physblk_exp=$blkexp
|
|
block_device_wait
|
|
lsscsi | egrep scsi_debug > /dev/null
|
|
if (($? == 1)); then
|
|
log_fail "scsi_debug module install failed"
|
|
fi
|
|
fi
|
|
fi
|
|
}
|
|
|
|
#
|
|
# Unload scsi_debug module, if needed.
|
|
#
|
|
function unload_scsi_debug
|
|
{
|
|
log_must_retry "in use" 5 modprobe -r scsi_debug
|
|
}
|
|
|
|
#
|
|
# Get scsi_debug device name.
|
|
# Returns basename of scsi_debug device (for example "sdb").
|
|
#
|
|
function get_debug_device
|
|
{
|
|
for i in {1..10} ; do
|
|
val=$(lsscsi | nawk '/scsi_debug/ {print $6; exit}' | cut -d / -f3)
|
|
|
|
# lsscsi can take time to settle
|
|
if [ "$val" != "-" ] ; then
|
|
break
|
|
fi
|
|
sleep 1
|
|
done
|
|
echo "$val"
|
|
}
|
|
|
|
#
|
|
# Get actual devices used by the pool (i.e. linux sdb1 not sdb).
|
|
#
|
|
function get_pool_devices #testpool #devdir
|
|
{
|
|
typeset testpool=$1
|
|
typeset devdir=$2
|
|
typeset out=""
|
|
|
|
if is_linux; then
|
|
out=$(zpool status -P $testpool |grep ${devdir} | awk '{print $1}')
|
|
out=$(echo $out | sed -e "s|${devdir}/||g" | tr '\n' ' ')
|
|
fi
|
|
echo $out
|
|
}
|