#include <linux/cpu.h>
#include "md.h"
#include "raid5.h"
+#include "raid0.h"
#include "bitmap.h"
/*
static void error(mddev_t *mddev, mdk_rdev_t *rdev)
{
char b[BDEVNAME_SIZE];
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
pr_debug("raid5: error called\n");
if (!test_bit(Faulty, &rdev->flags)) {
struct r5dev *dev;
mdk_rdev_t *blocked_rdev = NULL;
int prexor;
+ int dec_preread_active = 0;
memset(&s, 0, sizeof(s));
pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
set_bit(STRIPE_INSYNC, &sh->state);
}
}
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) <
- IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ dec_preread_active = 1;
}
/* Now to consider new write requests and what else, if anything
ops_run_io(sh, &s);
+ if (dec_preread_active) {
+ /* We delay this until after ops_run_io so that if make_request
+ * is waiting on a barrier, it won't continue until the writes
+ * have actually been submitted.
+ */
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ }
return_io(return_bi);
}
struct r6_state r6s;
struct r5dev *dev, *pdev, *qdev;
mdk_rdev_t *blocked_rdev = NULL;
+ int dec_preread_active = 0;
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
* completed
*/
if (sh->reconstruct_state == reconstruct_state_drain_result) {
- int qd_idx = sh->qd_idx;
sh->reconstruct_state = reconstruct_state_idle;
/* All the 'written' buffers and the parity blocks are ready to
set_bit(STRIPE_INSYNC, &sh->state);
}
}
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) <
- IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ dec_preread_active = 1;
}
/* Now to consider new write requests and what else, if anything
ops_run_io(sh, &s);
+
+ if (dec_preread_active) {
+ /* We delay this until after ops_run_io so that if make_request
+ * is waiting on a barrier, it won't continue until the writes
+ * have actually been submitted.
+ */
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ }
+
return_io(return_bi);
}
if ((bi->bi_size>>9) > queue_max_sectors(q))
return 0;
blk_recount_segments(q, bi);
- if (bi->bi_phys_segments > queue_max_phys_segments(q))
+ if (bi->bi_phys_segments > queue_max_segments(q))
return 0;
if (q->merge_bvec_fn)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev->private;
- unsigned int dd_idx;
+ int dd_idx;
struct bio* align_bi;
mdk_rdev_t *rdev;
int cpu, remaining;
if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
- bio_endio(bi, -EOPNOTSUPP);
+ /* Drain all pending writes. We only really need
+ * to ensure they have been submitted, but this is
+ * easier.
+ */
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ md_barrier_request(mddev, bi);
return 0;
}
finish_wait(&conf->wait_for_overlap, &w);
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
+ if (mddev->barrier &&
+ !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ atomic_inc(&conf->preread_active_stripes);
release_stripe(sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
bio_endio(bi, 0);
}
+
+ if (mddev->barrier) {
+ /* We need to wait for the stripes to all be handled.
+ * So: wait for preread_active_stripes to drop to 0.
+ */
+ wait_event(mddev->thread->wqueue,
+ atomic_read(&conf->preread_active_stripes) == 0);
+ }
return 0;
}
* As the reads complete, handle_stripe will copy the data
* into the destination stripe and release that stripe.
*/
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
struct stripe_head *sh;
sector_t first_sector, last_sector;
int raid_disks = conf->previous_raid_disks;
/* FIXME go_faster isn't used */
static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
struct stripe_head *sh;
sector_t max_sector = mddev->dev_sectors;
int sync_blocks;
{
unsigned long cpu;
struct page *spare_page;
- struct raid5_percpu *allcpus;
+ struct raid5_percpu __percpu *allcpus;
void *scribble;
int err;
return ERR_PTR(-ENOMEM);
}
+
+static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
+{
+ switch (algo) {
+ case ALGORITHM_PARITY_0:
+ if (raid_disk < max_degraded)
+ return 1;
+ break;
+ case ALGORITHM_PARITY_N:
+ if (raid_disk >= raid_disks - max_degraded)
+ return 1;
+ break;
+ case ALGORITHM_PARITY_0_6:
+ if (raid_disk == 0 ||
+ raid_disk == raid_disks - 1)
+ return 1;
+ break;
+ case ALGORITHM_LEFT_ASYMMETRIC_6:
+ case ALGORITHM_RIGHT_ASYMMETRIC_6:
+ case ALGORITHM_LEFT_SYMMETRIC_6:
+ case ALGORITHM_RIGHT_SYMMETRIC_6:
+ if (raid_disk == raid_disks - 1)
+ return 1;
+ }
+ return 0;
+}
+
static int run(mddev_t *mddev)
{
raid5_conf_t *conf;
int working_disks = 0, chunk_size;
+ int dirty_parity_disks = 0;
mdk_rdev_t *rdev;
+ sector_t reshape_offset = 0;
if (mddev->recovery_cp != MaxSector)
printk(KERN_NOTICE "raid5: %s is not clean"
"on a stripe boundary\n");
return -EINVAL;
}
+ reshape_offset = here_new * mddev->new_chunk_sectors;
/* here_new is the stripe we will write to */
here_old = mddev->reshape_position;
sector_div(here_old, mddev->chunk_sectors *
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= 0 &&
- test_bit(In_sync, &rdev->flags))
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ if (rdev->raid_disk < 0)
+ continue;
+ if (test_bit(In_sync, &rdev->flags))
working_disks++;
+ /* This disc is not fully in-sync. However if it
+ * just stored parity (beyond the recovery_offset),
+ * when we don't need to be concerned about the
+ * array being dirty.
+ * When reshape goes 'backwards', we never have
+ * partially completed devices, so we only need
+ * to worry about reshape going forwards.
+ */
+ /* Hack because v0.91 doesn't store recovery_offset properly. */
+ if (mddev->major_version == 0 &&
+ mddev->minor_version > 90)
+ rdev->recovery_offset = reshape_offset;
+
+ printk("%d: w=%d pa=%d pr=%d m=%d a=%d r=%d op1=%d op2=%d\n",
+ rdev->raid_disk, working_disks, conf->prev_algo,
+ conf->previous_raid_disks, conf->max_degraded,
+ conf->algorithm, conf->raid_disks,
+ only_parity(rdev->raid_disk,
+ conf->prev_algo,
+ conf->previous_raid_disks,
+ conf->max_degraded),
+ only_parity(rdev->raid_disk,
+ conf->algorithm,
+ conf->raid_disks,
+ conf->max_degraded));
+ if (rdev->recovery_offset < reshape_offset) {
+ /* We need to check old and new layout */
+ if (!only_parity(rdev->raid_disk,
+ conf->algorithm,
+ conf->raid_disks,
+ conf->max_degraded))
+ continue;
+ }
+ if (!only_parity(rdev->raid_disk,
+ conf->prev_algo,
+ conf->previous_raid_disks,
+ conf->max_degraded))
+ continue;
+ dirty_parity_disks++;
+ }
mddev->degraded = (max(conf->raid_disks, conf->previous_raid_disks)
- working_disks);
mddev->dev_sectors &= ~(mddev->chunk_sectors - 1);
mddev->resync_max_sectors = mddev->dev_sectors;
- if (mddev->degraded > 0 &&
+ if (mddev->degraded > dirty_parity_disks &&
mddev->recovery_cp != MaxSector) {
if (mddev->ok_start_degraded)
printk(KERN_WARNING
}
/* Ok, everything is just fine now */
- if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+ if (mddev->to_remove == &raid5_attrs_group)
+ mddev->to_remove = NULL;
+ else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
printk(KERN_WARNING
"raid5: failed to create sysfs attributes for %s\n",
mdname(mddev));
static int stop(mddev_t *mddev)
{
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
mddev->queue->backing_dev_info.congested_fn = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
- sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
free_conf(conf);
mddev->private = NULL;
+ mddev->to_remove = &raid5_attrs_group;
return 0;
}
static void status(struct seq_file *seq, mddev_t *mddev)
{
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
int i;
seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev) == 0) {
char nm[20];
- set_bit(In_sync, &rdev->flags);
- added_devices++;
- rdev->recovery_offset = 0;
+ if (rdev->raid_disk >= conf->previous_raid_disks) {
+ set_bit(In_sync, &rdev->flags);
+ added_devices++;
+ } else
+ rdev->recovery_offset = 0;
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
break;
}
+ /* When a reshape changes the number of devices, ->degraded
+ * is measured against the large of the pre and post number of
+ * devices.*/
if (mddev->delta_disks > 0) {
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+ mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
- added_devices;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
}
+static void *raid5_takeover_raid0(mddev_t *mddev)
+{
+
+ mddev->new_level = 5;
+ mddev->new_layout = ALGORITHM_PARITY_N;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
+ mddev->raid_disks += 1;
+ mddev->delta_disks = 1;
+ /* make sure it will be not marked as dirty */
+ mddev->recovery_cp = MaxSector;
+
+ return setup_conf(mddev);
+}
+
+
static void *raid5_takeover_raid1(mddev_t *mddev)
{
int chunksect;
* raid4 - trivial - just use a raid4 layout.
* raid6 - Providing it is a *_6 layout
*/
+ if (mddev->level == 0) {
+ /* for raid0 takeover only one zone is supported */
+ struct raid0_private_data *raid0_priv
+ = mddev->private;
+ if (raid0_priv->nr_strip_zones > 1) {
+ printk(KERN_ERR "md: cannot takeover raid 0 with more than one zone.\n");
+ return ERR_PTR(-EINVAL);
+ }
+ return raid5_takeover_raid0(mddev);
+ }
if (mddev->level == 1)
return raid5_takeover_raid1(mddev);
module_init(raid5_init);
module_exit(raid5_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID4/5/6 (striping with parity) personality for MD");
MODULE_ALIAS("md-personality-4"); /* RAID5 */
MODULE_ALIAS("md-raid5");
MODULE_ALIAS("md-raid4");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff