c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 10:37:35 +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/vdev_label.c
+39 -23
View File
@@ -142,6 +142,7 @@
#include <sys/zap.h>
#include <sys/vdev.h>
#include <sys/vdev_impl.h>
#include <sys/vdev_draid.h>
#include <sys/uberblock_impl.h>
#include <sys/metaslab.h>
#include <sys/metaslab_impl.h>
@@ -453,31 +454,13 @@ vdev_config_generate(spa_t *spa, vdev_t *vd, boolean_t getstats,
if (vd->vdev_fru != NULL)
fnvlist_add_string(nv, ZPOOL_CONFIG_FRU, vd->vdev_fru);
if (vd->vdev_nparity != 0) {
ASSERT(strcmp(vd->vdev_ops->vdev_op_type,
VDEV_TYPE_RAIDZ) == 0);
if (vd->vdev_ops->vdev_op_config_generate != NULL)
vd->vdev_ops->vdev_op_config_generate(vd, nv);
/*
* Make sure someone hasn't managed to sneak a fancy new vdev
* into a crufty old storage pool.
*/
ASSERT(vd->vdev_nparity == 1 ||
(vd->vdev_nparity <= 2 &&
spa_version(spa) >= SPA_VERSION_RAIDZ2) ||
(vd->vdev_nparity <= 3 &&
spa_version(spa) >= SPA_VERSION_RAIDZ3));
/*
* Note that we'll add the nparity tag even on storage pools
* that only support a single parity device -- older software
* will just ignore it.
*/
fnvlist_add_uint64(nv, ZPOOL_CONFIG_NPARITY, vd->vdev_nparity);
}
if (vd->vdev_wholedisk != -1ULL)
if (vd->vdev_wholedisk != -1ULL) {
fnvlist_add_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
vd->vdev_wholedisk);
}
if (vd->vdev_not_present && !(flags & VDEV_CONFIG_MISSING))
fnvlist_add_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT, 1);
@@ -785,6 +768,14 @@ vdev_label_read_config(vdev_t *vd, uint64_t txg)
if (!vdev_readable(vd))
return (NULL);
/*
* The label for a dRAID distributed spare is not stored on disk.
* Instead it is generated when needed which allows us to bypass
* the pipeline when reading the config from the label.
*/
if (vd->vdev_ops == &vdev_draid_spare_ops)
return (vdev_draid_read_config_spare(vd));
vp_abd = abd_alloc_linear(sizeof (vdev_phys_t), B_TRUE);
vp = abd_to_buf(vp_abd);
@@ -1497,7 +1488,8 @@ vdev_uberblock_load_impl(zio_t *zio, vdev_t *vd, int flags,
for (int c = 0; c < vd->vdev_children; c++)
vdev_uberblock_load_impl(zio, vd->vdev_child[c], flags, cbp);
if (vd->vdev_ops->vdev_op_leaf && vdev_readable(vd)) {
if (vd->vdev_ops->vdev_op_leaf && vdev_readable(vd) &&
vd->vdev_ops != &vdev_draid_spare_ops) {
for (int l = 0; l < VDEV_LABELS; l++) {
for (int n = 0; n < VDEV_UBERBLOCK_COUNT(vd); n++) {
vdev_label_read(zio, vd, l,
@@ -1586,6 +1578,13 @@ vdev_copy_uberblocks(vdev_t *vd)
SCL_STATE);
ASSERT(vd->vdev_ops->vdev_op_leaf);
/*
* No uberblocks are stored on distributed spares, they may be
* safely skipped when expanding a leaf vdev.
*/
if (vd->vdev_ops == &vdev_draid_spare_ops)
return;
spa_config_enter(vd->vdev_spa, locks, FTAG, RW_READER);
ub_abd = abd_alloc_linear(VDEV_UBERBLOCK_SIZE(vd), B_TRUE);
@@ -1647,6 +1646,15 @@ vdev_uberblock_sync(zio_t *zio, uint64_t *good_writes,
if (!vdev_writeable(vd))
return;
/*
* There's no need to write uberblocks to a distributed spare, they
* are already stored on all the leaves of the parent dRAID. For
* this same reason vdev_uberblock_load_impl() skips distributed
* spares when reading uberblocks.
*/
if (vd->vdev_ops == &vdev_draid_spare_ops)
return;
/* If the vdev was expanded, need to copy uberblock rings. */
if (vd->vdev_state == VDEV_STATE_HEALTHY &&
vd->vdev_copy_uberblocks == B_TRUE) {
@@ -1763,6 +1771,14 @@ vdev_label_sync(zio_t *zio, uint64_t *good_writes,
if (!vdev_writeable(vd))
return;
/*
* The top-level config never needs to be written to a distributed
* spare. When read vdev_dspare_label_read_config() will generate
* the config for the vdev_label_read_config().
*/
if (vd->vdev_ops == &vdev_draid_spare_ops)
return;
/*
* Generate a label describing the top-level config to which we belong.
*/