If unsure, say Y.
- config MULTICORE_RAID456
- bool "RAID-4/RAID-5/RAID-6 Multicore processing (EXPERIMENTAL)"
- depends on MD_RAID456
- depends on SMP
- depends on EXPERIMENTAL
- ---help---
- Enable the raid456 module to dispatch per-stripe raid operations to a
- thread pool.
-
- If unsure, say N.
-
config MD_MULTIPATH
tristate "Multipath I/O support"
depends on BLK_DEV_MD
config DM_BUFIO
tristate
- depends on BLK_DEV_DM && EXPERIMENTAL
+ depends on BLK_DEV_DM
---help---
This interface allows you to do buffered I/O on a device and acts
as a cache, holding recently-read blocks in memory and performing
config DM_BIO_PRISON
tristate
- depends on BLK_DEV_DM && EXPERIMENTAL
+ depends on BLK_DEV_DM
---help---
Some bio locking schemes used by other device-mapper targets
including thin provisioning.
Allow volume managers to take writable snapshots of a device.
config DM_THIN_PROVISIONING
- tristate "Thin provisioning target (EXPERIMENTAL)"
- depends on BLK_DEV_DM && EXPERIMENTAL
+ tristate "Thin provisioning target"
+ depends on BLK_DEV_DM
select DM_PERSISTENT_DATA
select DM_BIO_PRISON
---help---
If unsure, say N.
+config DM_CACHE
+ tristate "Cache target (EXPERIMENTAL)"
+ depends on BLK_DEV_DM
+ default n
+ select DM_PERSISTENT_DATA
+ select DM_BIO_PRISON
+ ---help---
+ dm-cache attempts to improve performance of a block device by
+ moving frequently used data to a smaller, higher performance
+ device. Different 'policy' plugins can be used to change the
+ algorithms used to select which blocks are promoted, demoted,
+ cleaned etc. It supports writeback and writethrough modes.
+
+config DM_CACHE_MQ
+ tristate "MQ Cache Policy (EXPERIMENTAL)"
+ depends on DM_CACHE
+ default y
+ ---help---
+ A cache policy that uses a multiqueue ordered by recent hit
+ count to select which blocks should be promoted and demoted.
+ This is meant to be a general purpose policy. It prioritises
+ reads over writes.
+
+config DM_CACHE_CLEANER
+ tristate "Cleaner Cache Policy (EXPERIMENTAL)"
+ depends on DM_CACHE
+ default y
+ ---help---
+ A simple cache policy that writes back all data to the
+ origin. Used when decommissioning a dm-cache.
+
config DM_MIRROR
tristate "Mirror target"
depends on BLK_DEV_DM
in one of the available parity distribution methods.
config DM_LOG_USERSPACE
- tristate "Mirror userspace logging (EXPERIMENTAL)"
- depends on DM_MIRROR && EXPERIMENTAL && NET
+ tristate "Mirror userspace logging"
+ depends on DM_MIRROR && NET
select CONNECTOR
---help---
The userspace logging module provides a mechanism for
If unsure, say N.
config DM_DELAY
- tristate "I/O delaying target (EXPERIMENTAL)"
- depends on BLK_DEV_DM && EXPERIMENTAL
+ tristate "I/O delaying target"
+ depends on BLK_DEV_DM
---help---
A target that delays reads and/or writes and can send
them to different devices. Useful for testing.
Generate udev events for DM events.
config DM_FLAKEY
- tristate "Flakey target (EXPERIMENTAL)"
- depends on BLK_DEV_DM && EXPERIMENTAL
+ tristate "Flakey target"
+ depends on BLK_DEV_DM
---help---
A target that intermittently fails I/O for debugging purposes.
config DM_VERITY
- tristate "Verity target support (EXPERIMENTAL)"
- depends on BLK_DEV_DM && EXPERIMENTAL
+ tristate "Verity target support"
+ depends on BLK_DEV_DM
select CRYPTO
select CRYPTO_HASH
select DM_BUFIO
{"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}
};
+ static char *raid10_md_layout_to_format(int layout)
+ {
+ /*
+ * Bit 16 and 17 stand for "offset" and "use_far_sets"
+ * Refer to MD's raid10.c for details
+ */
+ if ((layout & 0x10000) && (layout & 0x20000))
+ return "offset";
+
+ if ((layout & 0xFF) > 1)
+ return "near";
+
+ return "far";
+ }
+
static unsigned raid10_md_layout_to_copies(int layout)
{
- return layout & 0xFF;
+ if ((layout & 0xFF) > 1)
+ return layout & 0xFF;
+ return (layout >> 8) & 0xFF;
}
static int raid10_format_to_md_layout(char *format, unsigned copies)
{
- /* 1 "far" copy, and 'copies' "near" copies */
- return (1 << 8) | (copies & 0xFF);
+ unsigned n = 1, f = 1;
+
+ if (!strcmp("near", format))
+ n = copies;
+ else
+ f = copies;
+
+ if (!strcmp("offset", format))
+ return 0x30000 | (f << 8) | n;
+
+ if (!strcmp("far", format))
+ return 0x20000 | (f << 8) | n;
+
+ return (f << 8) | n;
}
static struct raid_type *get_raid_type(char *name)
{
unsigned i, rebuild_cnt = 0;
unsigned rebuilds_per_group, copies, d;
+ unsigned group_size, last_group_start;
for (i = 0; i < rs->md.raid_disks; i++)
if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
* as long as the failed devices occur in different mirror
* groups (i.e. different stripes).
*
- * Right now, we only allow for "near" copies. When other
- * formats are added, we will have to check those too.
- *
* When checking "near" format, make sure no adjacent devices
* have failed beyond what can be handled. In addition to the
* simple case where the number of devices is a multiple of the
* A A B B C
* C D D E E
*/
- for (i = 0; i < rs->md.raid_disks * copies; i++) {
- if (!(i % copies))
+ if (!strcmp("near", raid10_md_layout_to_format(rs->md.layout))) {
+ for (i = 0; i < rs->md.raid_disks * copies; i++) {
+ if (!(i % copies))
+ rebuilds_per_group = 0;
+ d = i % rs->md.raid_disks;
+ if ((!rs->dev[d].rdev.sb_page ||
+ !test_bit(In_sync, &rs->dev[d].rdev.flags)) &&
+ (++rebuilds_per_group >= copies))
+ goto too_many;
+ }
+ break;
+ }
+
+ /*
+ * When checking "far" and "offset" formats, we need to ensure
+ * that the device that holds its copy is not also dead or
+ * being rebuilt. (Note that "far" and "offset" formats only
+ * support two copies right now. These formats also only ever
+ * use the 'use_far_sets' variant.)
+ *
+ * This check is somewhat complicated by the need to account
+ * for arrays that are not a multiple of (far) copies. This
+ * results in the need to treat the last (potentially larger)
+ * set differently.
+ */
+ group_size = (rs->md.raid_disks / copies);
+ last_group_start = (rs->md.raid_disks / group_size) - 1;
+ last_group_start *= group_size;
+ for (i = 0; i < rs->md.raid_disks; i++) {
+ if (!(i % copies) && !(i > last_group_start))
rebuilds_per_group = 0;
- d = i % rs->md.raid_disks;
- if ((!rs->dev[d].rdev.sb_page ||
- !test_bit(In_sync, &rs->dev[d].rdev.flags)) &&
+ if ((!rs->dev[i].rdev.sb_page ||
+ !test_bit(In_sync, &rs->dev[i].rdev.flags)) &&
(++rebuilds_per_group >= copies))
- goto too_many;
+ goto too_many;
}
break;
default:
*
* RAID10-only options:
* [raid10_copies <# copies>] Number of copies. (Default: 2)
- * [raid10_format <near>] Layout algorithm. (Default: near)
+ * [raid10_format <near|far|offset>] Layout algorithm. (Default: near)
*/
static int parse_raid_params(struct raid_set *rs, char **argv,
unsigned num_raid_params)
rs->ti->error = "'raid10_format' is an invalid parameter for this RAID type";
return -EINVAL;
}
- if (strcmp("near", argv[i])) {
+ if (strcmp("near", argv[i]) &&
+ strcmp("far", argv[i]) &&
+ strcmp("offset", argv[i])) {
rs->ti->error = "Invalid 'raid10_format' value given";
return -EINVAL;
}
return -EINVAL;
}
+ /*
+ * If the format is not "near", we only support
+ * two copies at the moment.
+ */
+ if (strcmp("near", raid10_format) && (raid10_copies > 2)) {
+ rs->ti->error = "Too many copies for given RAID10 format.";
+ return -EINVAL;
+ }
+
/* (Len * #mirrors) / #devices */
sectors_per_dev = rs->ti->len * raid10_copies;
sector_div(sectors_per_dev, rs->md.raid_disks);
/*
* Reshaping is not currently allowed
*/
- if ((le32_to_cpu(sb->level) != mddev->level) ||
- (le32_to_cpu(sb->layout) != mddev->layout) ||
- (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors)) {
- DMERR("Reshaping arrays not yet supported.");
+ if (le32_to_cpu(sb->level) != mddev->level) {
+ DMERR("Reshaping arrays not yet supported. (RAID level change)");
+ return -EINVAL;
+ }
+ if (le32_to_cpu(sb->layout) != mddev->layout) {
+ DMERR("Reshaping arrays not yet supported. (RAID layout change)");
+ DMERR(" 0x%X vs 0x%X", le32_to_cpu(sb->layout), mddev->layout);
+ DMERR(" Old layout: %s w/ %d copies",
+ raid10_md_layout_to_format(le32_to_cpu(sb->layout)),
+ raid10_md_layout_to_copies(le32_to_cpu(sb->layout)));
+ DMERR(" New layout: %s w/ %d copies",
+ raid10_md_layout_to_format(mddev->layout),
+ raid10_md_layout_to_copies(mddev->layout));
+ return -EINVAL;
+ }
+ if (le32_to_cpu(sb->stripe_sectors) != mddev->chunk_sectors) {
+ DMERR("Reshaping arrays not yet supported. (stripe sectors change)");
return -EINVAL;
}
/* We can only change the number of devices in RAID1 right now */
if ((rs->raid_type->level != 1) &&
(le32_to_cpu(sb->num_devices) != mddev->raid_disks)) {
- DMERR("Reshaping arrays not yet supported.");
+ DMERR("Reshaping arrays not yet supported. (device count change)");
return -EINVAL;
}
INIT_WORK(&rs->md.event_work, do_table_event);
ti->private = rs;
- ti->num_flush_requests = 1;
+ ti->num_flush_bios = 1;
mutex_lock(&rs->md.reconfig_mutex);
ret = md_run(&rs->md);
return DM_MAPIO_SUBMITTED;
}
-static int raid_status(struct dm_target *ti, status_type_t type,
- unsigned status_flags, char *result, unsigned maxlen)
+static void raid_status(struct dm_target *ti, status_type_t type,
+ unsigned status_flags, char *result, unsigned maxlen)
{
struct raid_set *rs = ti->private;
unsigned raid_param_cnt = 1; /* at least 1 for chunksize */
raid10_md_layout_to_copies(rs->md.layout));
if (rs->print_flags & DMPF_RAID10_FORMAT)
- DMEMIT(" raid10_format near");
+ DMEMIT(" raid10_format %s",
+ raid10_md_layout_to_format(rs->md.layout));
DMEMIT(" %d", rs->md.raid_disks);
for (i = 0; i < rs->md.raid_disks; i++) {
DMEMIT(" -");
}
}
-
- return 0;
}
static int raid_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
static struct target_type raid_target = {
.name = "raid",
- .version = {1, 4, 1},
+ .version = {1, 4, 2},
.module = THIS_MODULE,
.ctr = raid_ctr,
.dtr = raid_dtr,
static int __init dm_raid_init(void)
{
+ DMINFO("Loading target version %u.%u.%u",
+ raid_target.version[0],
+ raid_target.version[1],
+ raid_target.version[2]);
return dm_register_target(&raid_target);
}
return_bi = bi->bi_next;
bi->bi_next = NULL;
bi->bi_size = 0;
- trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
- bi, 0);
bio_endio(bi, 0);
bi = return_bi;
}
short generation)
{
struct stripe_head *sh;
- struct hlist_node *hn;
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
- hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
+ hlist_for_each_entry(sh, stripe_hash(conf, sector), hash)
if (sh->sector == sector && sh->generation == generation)
return sh;
pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
&sh->ops.zero_sum_result, percpu->spare_page, &submit);
}
- static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
put_cpu();
}
- #ifdef CONFIG_MULTICORE_RAID456
- static void async_run_ops(void *param, async_cookie_t cookie)
- {
- struct stripe_head *sh = param;
- unsigned long ops_request = sh->ops.request;
-
- clear_bit_unlock(STRIPE_OPS_REQ_PENDING, &sh->state);
- wake_up(&sh->ops.wait_for_ops);
-
- __raid_run_ops(sh, ops_request);
- release_stripe(sh);
- }
-
- static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
- {
- /* since handle_stripe can be called outside of raid5d context
- * we need to ensure sh->ops.request is de-staged before another
- * request arrives
- */
- wait_event(sh->ops.wait_for_ops,
- !test_and_set_bit_lock(STRIPE_OPS_REQ_PENDING, &sh->state));
- sh->ops.request = ops_request;
-
- atomic_inc(&sh->count);
- async_schedule(async_run_ops, sh);
- }
- #else
- #define raid_run_ops __raid_run_ops
- #endif
-
static int grow_one_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
return 0;
sh->raid_conf = conf;
- #ifdef CONFIG_MULTICORE_RAID456
- init_waitqueue_head(&sh->ops.wait_for_ops);
- #endif
spin_lock_init(&sh->stripe_lock);
break;
nsh->raid_conf = conf;
- #ifdef CONFIG_MULTICORE_RAID456
- init_waitqueue_head(&nsh->ops.wait_for_ops);
- #endif
spin_lock_init(&nsh->stripe_lock);
list_add(&nsh->lru, &newstripes);
rdev_dec_pending(rdev, conf->mddev);
if (!error && uptodate) {
- trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
- raid_bi, 0);
bio_endio(raid_bi, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
if ( rw == WRITE )
md_write_end(mddev);
- trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
- bi, 0);
bio_endio(bi, 0);
}
}
handled++;
}
remaining = raid5_dec_bi_active_stripes(raid_bio);
- if (remaining == 0) {
- trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
- raid_bio, 0);
+ if (remaining == 0)
bio_endio(raid_bio, 0);
- }
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
return handled;