c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-26 12:12:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Distributed Spare (dRAID) Feature

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/zio.c
+30 -12
View File
@@ -1702,16 +1702,16 @@ zio_write_compress(zio_t *zio)
return (zio);
} else {
/*
* Round up compressed size up to the ashift
* of the smallest-ashift device, and zero the tail.
* This ensures that the compressed size of the BP
* (and thus compressratio property) are correct,
* Round compressed size up to the minimum allocation
* size of the smallest-ashift device, and zero the
* tail. This ensures that the compressed size of the
* BP (and thus compressratio property) are correct,
* in that we charge for the padding used to fill out
* the last sector.
*/
ASSERT3U(spa->spa_min_ashift, >=, SPA_MINBLOCKSHIFT);
size_t rounded = (size_t)P2ROUNDUP(psize,
1ULL << spa->spa_min_ashift);
ASSERT3U(spa->spa_min_alloc, >=, SPA_MINBLOCKSHIFT);
size_t rounded = (size_t)roundup(psize,
spa->spa_min_alloc);
if (rounded >= lsize) {
compress = ZIO_COMPRESS_OFF;
zio_buf_free(cbuf, lsize);
@@ -3754,19 +3754,37 @@ zio_vdev_io_start(zio_t *zio)
* However, indirect vdevs point off to other vdevs which may have
* DTL's, so we never bypass them. The child i/os on concrete vdevs
* will be properly bypassed instead.
*
* Leaf DTL_PARTIAL can be empty when a legitimate write comes from
* a dRAID spare vdev. For example, when a dRAID spare is first
* used, its spare blocks need to be written to but the leaf vdev's
* of such blocks can have empty DTL_PARTIAL.
*
* There seemed no clean way to allow such writes while bypassing
* spurious ones. At this point, just avoid all bypassing for dRAID
* for correctness.
*/
if ((zio->io_flags & ZIO_FLAG_IO_REPAIR) &&
!(zio->io_flags & ZIO_FLAG_SELF_HEAL) &&
zio->io_txg != 0 && /* not a delegated i/o */
vd->vdev_ops != &vdev_indirect_ops &&
vd->vdev_top->vdev_ops != &vdev_draid_ops &&
!vdev_dtl_contains(vd, DTL_PARTIAL, zio->io_txg, 1)) {
ASSERT(zio->io_type == ZIO_TYPE_WRITE);
zio_vdev_io_bypass(zio);
return (zio);
}
if (vd->vdev_ops->vdev_op_leaf && (zio->io_type == ZIO_TYPE_READ ||
zio->io_type == ZIO_TYPE_WRITE || zio->io_type == ZIO_TYPE_TRIM)) {
/*
* Select the next best leaf I/O to process. Distributed spares are
* excluded since they dispatch the I/O directly to a leaf vdev after
* applying the dRAID mapping.
*/
if (vd->vdev_ops->vdev_op_leaf &&
vd->vdev_ops != &vdev_draid_spare_ops &&
(zio->io_type == ZIO_TYPE_READ ||
zio->io_type == ZIO_TYPE_WRITE ||
zio->io_type == ZIO_TYPE_TRIM)) {
if (zio->io_type == ZIO_TYPE_READ && vdev_cache_read(zio))
return (zio);
@@ -3803,8 +3821,8 @@ zio_vdev_io_done(zio_t *zio)
if (zio->io_delay)
zio->io_delay = gethrtime() - zio->io_delay;
if (vd != NULL && vd->vdev_ops->vdev_op_leaf) {
if (vd != NULL && vd->vdev_ops->vdev_op_leaf &&
vd->vdev_ops != &vdev_draid_spare_ops) {
vdev_queue_io_done(zio);
if (zio->io_type == ZIO_TYPE_WRITE)
@@ -4206,7 +4224,7 @@ zio_checksum_verify(zio_t *zio)
if (zio->io_prop.zp_checksum == ZIO_CHECKSUM_OFF)
return (zio);
ASSERT(zio->io_prop.zp_checksum == ZIO_CHECKSUM_LABEL);
ASSERT3U(zio->io_prop.zp_checksum, ==, ZIO_CHECKSUM_LABEL);
}
if ((error = zio_checksum_error(zio, &info)) != 0) {