From b2255edcc0099e62ad46a3dd9d64537663c6aee3 Mon Sep 17 00:00:00 2001 From: Brian Behlendorf Date: Fri, 13 Nov 2020 13:51:51 -0800 Subject: 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 draid[1,2,3] 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 \ draid[][:d][:c][:s] \ - draid[parity] - Parity level (default 1) - draid[:d] - Data devices per group (default 8) - draid[:c] - Expected number of child vdevs - draid[: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 - dRAID data drives per group -S - dRAID distributed hot spares -R - 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 Co-authored-by: Mark Maybee Co-authored-by: Don Brady Co-authored-by: Matthew Ahrens Co-authored-by: Brian Behlendorf Reviewed-by: Mark Maybee Reviewed-by: Matt Ahrens Reviewed-by: Tony Hutter Signed-off-by: Brian Behlendorf Closes #10102 --- module/zfs/metaslab.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'module/zfs/metaslab.c') diff --git a/module/zfs/metaslab.c b/module/zfs/metaslab.c index 325f505b7..fcf1285f6 100644 --- a/module/zfs/metaslab.c +++ b/module/zfs/metaslab.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -1563,6 +1564,7 @@ metaslab_block_find(zfs_btree_t *t, range_tree_t *rt, uint64_t start, #if defined(WITH_DF_BLOCK_ALLOCATOR) || \ defined(WITH_CF_BLOCK_ALLOCATOR) + /* * This is a helper function that can be used by the allocator to find a * suitable block to allocate. This will search the specified B-tree looking @@ -1654,6 +1656,7 @@ metaslab_df_alloc(metaslab_t *msp, uint64_t size) range_seg_t *rs; if (zfs_btree_numnodes(&msp->ms_allocatable_by_size) == 0) metaslab_size_tree_full_load(msp->ms_allocatable); + if (metaslab_df_use_largest_segment) { /* use largest free segment */ rs = zfs_btree_last(&msp->ms_allocatable_by_size, NULL); @@ -2616,6 +2619,10 @@ metaslab_init(metaslab_group_t *mg, uint64_t id, uint64_t object, ms->ms_allocator = -1; ms->ms_new = B_TRUE; + vdev_ops_t *ops = vd->vdev_ops; + if (ops->vdev_op_metaslab_init != NULL) + ops->vdev_op_metaslab_init(vd, &ms->ms_start, &ms->ms_size); + /* * We only open space map objects that already exist. All others * will be opened when we finally allocate an object for it. @@ -5813,7 +5820,6 @@ metaslab_alloc(spa_t *spa, metaslab_class_t *mc, uint64_t psize, blkptr_t *bp, metaslab_group_alloc_increment(spa, DVA_GET_VDEV(&dva[d]), zio, flags, allocator); } - } ASSERT(error == 0); ASSERT(BP_GET_NDVAS(bp) == ndvas); -- cgit v1.2.3