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
2020-11-13 13:51:51 -08:00
committed by GitHub
parent a724db0374
commit b2255edcc0
153 changed files with 10203 additions and 1882 deletions
+44 -26
View File
@@ -292,19 +292,28 @@ vdev_file_io_done(zio_t *zio)
}
vdev_ops_t vdev_file_ops = {
vdev_file_open,
vdev_file_close,
vdev_default_asize,
vdev_file_io_start,
vdev_file_io_done,
NULL,
NULL,
vdev_file_hold,
vdev_file_rele,
NULL,
vdev_default_xlate,
VDEV_TYPE_FILE, /* name of this vdev type */
B_TRUE /* leaf vdev */
.vdev_op_init = NULL,
.vdev_op_fini = NULL,
.vdev_op_open = vdev_file_open,
.vdev_op_close = vdev_file_close,
.vdev_op_asize = vdev_default_asize,
.vdev_op_min_asize = vdev_default_min_asize,
.vdev_op_min_alloc = NULL,
.vdev_op_io_start = vdev_file_io_start,
.vdev_op_io_done = vdev_file_io_done,
.vdev_op_state_change = NULL,
.vdev_op_need_resilver = NULL,
.vdev_op_hold = vdev_file_hold,
.vdev_op_rele = vdev_file_rele,
.vdev_op_remap = NULL,
.vdev_op_xlate = vdev_default_xlate,
.vdev_op_rebuild_asize = NULL,
.vdev_op_metaslab_init = NULL,
.vdev_op_config_generate = NULL,
.vdev_op_nparity = NULL,
.vdev_op_ndisks = NULL,
.vdev_op_type = VDEV_TYPE_FILE, /* name of this vdev type */
.vdev_op_leaf = B_TRUE /* leaf vdev */
};
/*
@@ -313,19 +322,28 @@ vdev_ops_t vdev_file_ops = {
#ifndef _KERNEL
vdev_ops_t vdev_disk_ops = {
vdev_file_open,
vdev_file_close,
vdev_default_asize,
vdev_file_io_start,
vdev_file_io_done,
NULL,
NULL,
vdev_file_hold,
vdev_file_rele,
NULL,
vdev_default_xlate,
VDEV_TYPE_DISK, /* name of this vdev type */
B_TRUE /* leaf vdev */
.vdev_op_init = NULL,
.vdev_op_fini = NULL,
.vdev_op_open = vdev_file_open,
.vdev_op_close = vdev_file_close,
.vdev_op_asize = vdev_default_asize,
.vdev_op_min_asize = vdev_default_min_asize,
.vdev_op_min_alloc = NULL,
.vdev_op_io_start = vdev_file_io_start,
.vdev_op_io_done = vdev_file_io_done,
.vdev_op_state_change = NULL,
.vdev_op_need_resilver = NULL,
.vdev_op_hold = vdev_file_hold,
.vdev_op_rele = vdev_file_rele,
.vdev_op_remap = NULL,
.vdev_op_xlate = vdev_default_xlate,
.vdev_op_rebuild_asize = NULL,
.vdev_op_metaslab_init = NULL,
.vdev_op_config_generate = NULL,
.vdev_op_nparity = NULL,
.vdev_op_ndisks = NULL,
.vdev_op_type = VDEV_TYPE_DISK, /* name of this vdev type */
.vdev_op_leaf = B_TRUE /* leaf vdev */
};
#endif
+22 -13
View File
@@ -1189,17 +1189,26 @@ vdev_geom_rele(vdev_t *vd)
}
vdev_ops_t vdev_disk_ops = {
vdev_geom_open,
vdev_geom_close,
vdev_default_asize,
vdev_geom_io_start,
vdev_geom_io_done,
NULL,
NULL,
vdev_geom_hold,
vdev_geom_rele,
NULL,
vdev_default_xlate,
VDEV_TYPE_DISK, /* name of this vdev type */
B_TRUE /* leaf vdev */
.vdev_op_init = NULL,
.vdev_op_fini = NULL,
.vdev_op_open = vdev_geom_open,
.vdev_op_close = vdev_geom_close,
.vdev_op_asize = vdev_default_asize,
.vdev_op_min_asize = vdev_default_min_asize,
.vdev_op_min_alloc = NULL,
.vdev_op_io_start = vdev_geom_io_start,
.vdev_op_io_done = vdev_geom_io_done,
.vdev_op_state_change = NULL,
.vdev_op_need_resilver = NULL,
.vdev_op_hold = vdev_geom_hold,
.vdev_op_rele = vdev_geom_rele,
.vdev_op_remap = NULL,
.vdev_op_xlate = vdev_default_xlate,
.vdev_op_rebuild_asize = NULL,
.vdev_op_metaslab_init = NULL,
.vdev_op_config_generate = NULL,
.vdev_op_nparity = NULL,
.vdev_op_ndisks = NULL,
.vdev_op_type = VDEV_TYPE_DISK, /* name of this vdev type */
.vdev_op_leaf = B_TRUE /* leaf vdev */
};