mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2026-05-22 10:37:35 +03:00
Distributed Spare (dRAID) Feature
This patch adds a new top-level vdev type called dRAID, which stands
for Distributed parity RAID. This pool configuration allows all dRAID
vdevs to participate when rebuilding to a distributed hot spare device.
This can substantially reduce the total time required to restore full
parity to pool with a failed device.
A dRAID pool can be created using the new top-level `draid` type.
Like `raidz`, the desired redundancy is specified after the type:
`draid[1,2,3]`. No additional information is required to create the
pool and reasonable default values will be chosen based on the number
of child vdevs in the dRAID vdev.
zpool create <pool> draid[1,2,3] <vdevs...>
Unlike raidz, additional optional dRAID configuration values can be
provided as part of the draid type as colon separated values. This
allows administrators to fully specify a layout for either performance
or capacity reasons. The supported options include:
zpool create <pool> \
draid[<parity>][:<data>d][:<children>c][:<spares>s] \
<vdevs...>
- draid[parity] - Parity level (default 1)
- draid[:<data>d] - Data devices per group (default 8)
- draid[:<children>c] - Expected number of child vdevs
- draid[:<spares>s] - Distributed hot spares (default 0)
Abbreviated example `zpool status` output for a 68 disk dRAID pool
with two distributed spares using special allocation classes.
```
pool: tank
state: ONLINE
config:
NAME STATE READ WRITE CKSUM
slag7 ONLINE 0 0 0
draid2:8d:68c:2s-0 ONLINE 0 0 0
L0 ONLINE 0 0 0
L1 ONLINE 0 0 0
...
U25 ONLINE 0 0 0
U26 ONLINE 0 0 0
spare-53 ONLINE 0 0 0
U27 ONLINE 0 0 0
draid2-0-0 ONLINE 0 0 0
U28 ONLINE 0 0 0
U29 ONLINE 0 0 0
...
U42 ONLINE 0 0 0
U43 ONLINE 0 0 0
special
mirror-1 ONLINE 0 0 0
L5 ONLINE 0 0 0
U5 ONLINE 0 0 0
mirror-2 ONLINE 0 0 0
L6 ONLINE 0 0 0
U6 ONLINE 0 0 0
spares
draid2-0-0 INUSE currently in use
draid2-0-1 AVAIL
```
When adding test coverage for the new dRAID vdev type the following
options were added to the ztest command. These options are leverages
by zloop.sh to test a wide range of dRAID configurations.
-K draid|raidz|random - kind of RAID to test
-D <value> - dRAID data drives per group
-S <value> - dRAID distributed hot spares
-R <value> - RAID parity (raidz or dRAID)
The zpool_create, zpool_import, redundancy, replacement and fault
test groups have all been updated provide test coverage for the
dRAID feature.
Co-authored-by: Isaac Huang <he.huang@intel.com>
Co-authored-by: Mark Maybee <mmaybee@cray.com>
Co-authored-by: Don Brady <don.brady@delphix.com>
Co-authored-by: Matthew Ahrens <mahrens@delphix.com>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mmaybee@cray.com>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10102
This commit is contained in:
Brian Behlendorf
@@ -36,6 +36,7 @@ export ZPOOL_SCRIPT_DIR=$$CMD_DIR/zpool/zpool.d
|
||||
export ZPOOL_SCRIPTS_PATH=$$CMD_DIR/zpool/zpool.d
|
||||
export CONTRIB_DIR=@abs_top_builddir@/contrib
|
||||
export LIB_DIR=@abs_top_builddir@/lib
|
||||
export SYSCONF_DIR=@abs_top_builddir@/etc
|
||||
|
||||
export INSTALL_UDEV_DIR=@udevdir@
|
||||
export INSTALL_UDEV_RULE_DIR=@udevruledir@
|
||||
|
||||
@@ -166,6 +166,8 @@ if [ "${INSTALL}" = "yes" ]; then
|
||||
"$INSTALL_UDEV_RULE_DIR/90-zfs.rules"
|
||||
install "$CMD_DIR/zpool/zpool.d" \
|
||||
"$INSTALL_SYSCONF_DIR/zfs/zpool.d"
|
||||
install "$SYSCONF_DIR/zfs/draid.d" \
|
||||
"$INSTALL_SYSCONF_DIR/zfs/draid.d"
|
||||
install "$CONTRIB_DIR/pyzfs/libzfs_core" \
|
||||
"$INSTALL_PYTHON_DIR/libzfs_core"
|
||||
# Ideally we would install these in the configured ${libdir}, which is
|
||||
@@ -185,6 +187,7 @@ else
|
||||
remove "$INSTALL_UDEV_RULE_DIR/69-vdev.rules"
|
||||
remove "$INSTALL_UDEV_RULE_DIR/90-zfs.rules"
|
||||
remove "$INSTALL_SYSCONF_DIR/zfs/zpool.d"
|
||||
remove "$INSTALL_SYSCONF_DIR/zfs/draid.d"
|
||||
remove "$INSTALL_PYTHON_DIR/libzfs_core"
|
||||
remove "/lib/libzfs_core.so"
|
||||
remove "/lib/libnvpair.so"
|
||||
|
||||
+48
-14
@@ -18,6 +18,7 @@
|
||||
#
|
||||
# Copyright (c) 2015 by Delphix. All rights reserved.
|
||||
# Copyright (C) 2016 Lawrence Livermore National Security, LLC.
|
||||
# Copyright (c) 2017, Intel Corporation.
|
||||
#
|
||||
|
||||
BASE_DIR=$(dirname "$0")
|
||||
@@ -246,27 +247,60 @@ while [[ $timeout -eq 0 ]] || [[ $curtime -le $((starttime + timeout)) ]]; do
|
||||
or_die rm -rf "$workdir"
|
||||
or_die mkdir "$workdir"
|
||||
|
||||
# switch between common arrangements & fully randomized
|
||||
if [[ $((RANDOM % 2)) -eq 0 ]]; then
|
||||
mirrors=2
|
||||
raidz=0
|
||||
parity=1
|
||||
vdevs=2
|
||||
else
|
||||
mirrors=$(((RANDOM % 3) * 1))
|
||||
parity=$(((RANDOM % 3) + 1))
|
||||
raidz=$((((RANDOM % 9) + parity + 1) * (RANDOM % 2)))
|
||||
vdevs=$(((RANDOM % 3) + 3))
|
||||
fi
|
||||
# switch between three types of configs
|
||||
# 1/3 basic, 1/3 raidz mix, and 1/3 draid mix
|
||||
choice=$((RANDOM % 3))
|
||||
|
||||
# ashift range 9 - 15
|
||||
align=$(((RANDOM % 2) * 3 + 9))
|
||||
runtime=$((RANDOM % 100))
|
||||
|
||||
# randomly use special classes
|
||||
class="special=random"
|
||||
|
||||
if [[ $choice -eq 0 ]]; then
|
||||
# basic mirror only
|
||||
parity=1
|
||||
mirrors=2
|
||||
draid_data=0
|
||||
draid_spares=0
|
||||
raid_children=0
|
||||
vdevs=2
|
||||
raid_type="raidz"
|
||||
elif [[ $choice -eq 1 ]]; then
|
||||
# fully randomized mirror/raidz (sans dRAID)
|
||||
parity=$(((RANDOM % 3) + 1))
|
||||
mirrors=$(((RANDOM % 3) * 1))
|
||||
draid_data=0
|
||||
draid_spares=0
|
||||
raid_children=$((((RANDOM % 9) + parity + 1) * (RANDOM % 2)))
|
||||
vdevs=$(((RANDOM % 3) + 3))
|
||||
raid_type="raidz"
|
||||
else
|
||||
# fully randomized dRAID (sans mirror/raidz)
|
||||
parity=$(((RANDOM % 3) + 1))
|
||||
mirrors=0
|
||||
draid_data=$(((RANDOM % 8) + 3))
|
||||
draid_spares=$(((RANDOM % 2) + parity))
|
||||
stripe=$((draid_data + parity))
|
||||
extra=$((draid_spares + (RANDOM % 4)))
|
||||
raid_children=$(((((RANDOM % 4) + 1) * stripe) + extra))
|
||||
vdevs=$((RANDOM % 3))
|
||||
raid_type="draid"
|
||||
fi
|
||||
|
||||
# run from 30 to 120 seconds
|
||||
runtime=$(((RANDOM % 90) + 30))
|
||||
passtime=$((RANDOM % (runtime / 3 + 1) + 10))
|
||||
|
||||
zopt="$zopt -K $raid_type"
|
||||
zopt="$zopt -m $mirrors"
|
||||
zopt="$zopt -r $raidz"
|
||||
zopt="$zopt -r $raid_children"
|
||||
zopt="$zopt -D $draid_data"
|
||||
zopt="$zopt -S $draid_spares"
|
||||
zopt="$zopt -R $parity"
|
||||
zopt="$zopt -v $vdevs"
|
||||
zopt="$zopt -a $align"
|
||||
zopt="$zopt -C $class"
|
||||
zopt="$zopt -T $runtime"
|
||||
zopt="$zopt -P $passtime"
|
||||
zopt="$zopt -s $size"
|
||||
|
||||
Reference in New Issue
Block a user