* raid5.c : Multiple Devices driver for Linux
* Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman
* Copyright (C) 1999, 2000 Ingo Molnar
+ * Copyright (C) 2002, 2003 H. Peter Anvin
*
- * RAID-5 management functions.
+ * RAID-4/5/6 management functions.
+ * Thanks to Penguin Computing for making the RAID-6 development possible
+ * by donating a test server!
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
#include <linux/config.h>
#include <linux/module.h>
#include <linux/slab.h>
-#include <linux/raid/raid5.h>
#include <linux/highmem.h>
#include <linux/bitops.h>
+#include <linux/kthread.h>
#include <asm/atomic.h>
+#include "raid6.h"
#include <linux/raid/bitmap.h>
#define __inline__
#endif
+#if !RAID6_USE_EMPTY_ZERO_PAGE
+/* In .bss so it's zeroed */
+const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
+#endif
+
+static inline int raid6_next_disk(int disk, int raid_disks)
+{
+ disk++;
+ return (disk < raid_disks) ? disk : 0;
+}
static void print_raid5_conf (raid5_conf_t *conf);
static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
- if (!list_empty(&sh->lru))
- BUG();
- if (atomic_read(&conf->active_stripes)==0)
- BUG();
+ BUG_ON(!list_empty(&sh->lru));
+ BUG_ON(atomic_read(&conf->active_stripes)==0);
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state))
list_add_tail(&sh->lru, &conf->delayed_list);
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
}
- list_add_tail(&sh->lru, &conf->inactive_list);
atomic_dec(&conf->active_stripes);
- if (!conf->inactive_blocked ||
- atomic_read(&conf->active_stripes) < (conf->max_nr_stripes*3/4))
+ if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
+ list_add_tail(&sh->lru, &conf->inactive_list);
wake_up(&conf->wait_for_stripe);
+ }
}
}
}
{
raid5_conf_t *conf = sh->raid_conf;
unsigned long flags;
-
+
spin_lock_irqsave(&conf->device_lock, flags);
__release_stripe(conf, sh);
spin_unlock_irqrestore(&conf->device_lock, flags);
hlist_del_init(&sh->hash);
}
-static void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
+static inline void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
{
struct hlist_head *hp = stripe_hash(conf, sh->sector);
static void raid5_build_block (struct stripe_head *sh, int i);
-static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks)
{
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks, i;
+ int i;
- if (atomic_read(&sh->count) != 0)
- BUG();
- if (test_bit(STRIPE_HANDLE, &sh->state))
- BUG();
+ BUG_ON(atomic_read(&sh->count) != 0);
+ BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
CHECK_DEVLOCK();
PRINTK("init_stripe called, stripe %llu\n",
(unsigned long long)sh->sector);
remove_hash(sh);
-
+
sh->sector = sector;
sh->pd_idx = pd_idx;
sh->state = 0;
- for (i=disks; i--; ) {
+ sh->disks = disks;
+
+ for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->toread || dev->towrite || dev->written ||
insert_hash(conf, sh);
}
-static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector)
+static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, int disks)
{
struct stripe_head *sh;
struct hlist_node *hn;
CHECK_DEVLOCK();
PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
- if (sh->sector == sector)
+ if (sh->sector == sector && sh->disks == disks)
return sh;
PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
static void unplug_slaves(mddev_t *mddev);
static void raid5_unplug_device(request_queue_t *q);
-static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector,
- int pd_idx, int noblock)
+static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
+ int pd_idx, int noblock)
{
struct stripe_head *sh;
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0,
conf->device_lock, /* nothing */);
- sh = __find_stripe(conf, sector);
+ sh = __find_stripe(conf, sector, disks);
if (!sh) {
if (!conf->inactive_blocked)
sh = get_free_stripe(conf);
< (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
- unplug_slaves(conf->mddev);
+ unplug_slaves(conf->mddev)
);
conf->inactive_blocked = 0;
} else
- init_stripe(sh, sector, pd_idx);
+ init_stripe(sh, sector, pd_idx, disks);
} else {
if (atomic_read(&sh->count)) {
- if (!list_empty(&sh->lru))
- BUG();
+ BUG_ON(!list_empty(&sh->lru));
} else {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
kmem_cache_free(conf->slab_cache, sh);
return 0;
}
+ sh->disks = conf->raid_disks;
/* we just created an active stripe so... */
atomic_set(&sh->count, 1);
atomic_inc(&conf->active_stripes);
kmem_cache_t *sc;
int devs = conf->raid_disks;
- sprintf(conf->cache_name, "raid5/%s", mdname(conf->mddev));
-
- sc = kmem_cache_create(conf->cache_name,
+ sprintf(conf->cache_name[0], "raid5/%s", mdname(conf->mddev));
+ sprintf(conf->cache_name[1], "raid5/%s-alt", mdname(conf->mddev));
+ conf->active_name = 0;
+ sc = kmem_cache_create(conf->cache_name[conf->active_name],
sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
0, 0, NULL, NULL);
if (!sc)
return 1;
conf->slab_cache = sc;
- while (num--) {
+ conf->pool_size = devs;
+ while (num--)
if (!grow_one_stripe(conf))
return 1;
- }
return 0;
}
+#ifdef CONFIG_MD_RAID5_RESHAPE
+static int resize_stripes(raid5_conf_t *conf, int newsize)
+{
+ /* Make all the stripes able to hold 'newsize' devices.
+ * New slots in each stripe get 'page' set to a new page.
+ *
+ * This happens in stages:
+ * 1/ create a new kmem_cache and allocate the required number of
+ * stripe_heads.
+ * 2/ gather all the old stripe_heads and tranfer the pages across
+ * to the new stripe_heads. This will have the side effect of
+ * freezing the array as once all stripe_heads have been collected,
+ * no IO will be possible. Old stripe heads are freed once their
+ * pages have been transferred over, and the old kmem_cache is
+ * freed when all stripes are done.
+ * 3/ reallocate conf->disks to be suitable bigger. If this fails,
+ * we simple return a failre status - no need to clean anything up.
+ * 4/ allocate new pages for the new slots in the new stripe_heads.
+ * If this fails, we don't bother trying the shrink the
+ * stripe_heads down again, we just leave them as they are.
+ * As each stripe_head is processed the new one is released into
+ * active service.
+ *
+ * Once step2 is started, we cannot afford to wait for a write,
+ * so we use GFP_NOIO allocations.
+ */
+ struct stripe_head *osh, *nsh;
+ LIST_HEAD(newstripes);
+ struct disk_info *ndisks;
+ int err = 0;
+ kmem_cache_t *sc;
+ int i;
+
+ if (newsize <= conf->pool_size)
+ return 0; /* never bother to shrink */
+
+ /* Step 1 */
+ sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
+ sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev),
+ 0, 0, NULL, NULL);
+ if (!sc)
+ return -ENOMEM;
+
+ for (i = conf->max_nr_stripes; i; i--) {
+ nsh = kmem_cache_alloc(sc, GFP_KERNEL);
+ if (!nsh)
+ break;
+
+ memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev));
+
+ nsh->raid_conf = conf;
+ spin_lock_init(&nsh->lock);
+
+ list_add(&nsh->lru, &newstripes);
+ }
+ if (i) {
+ /* didn't get enough, give up */
+ while (!list_empty(&newstripes)) {
+ nsh = list_entry(newstripes.next, struct stripe_head, lru);
+ list_del(&nsh->lru);
+ kmem_cache_free(sc, nsh);
+ }
+ kmem_cache_destroy(sc);
+ return -ENOMEM;
+ }
+ /* Step 2 - Must use GFP_NOIO now.
+ * OK, we have enough stripes, start collecting inactive
+ * stripes and copying them over
+ */
+ list_for_each_entry(nsh, &newstripes, lru) {
+ spin_lock_irq(&conf->device_lock);
+ wait_event_lock_irq(conf->wait_for_stripe,
+ !list_empty(&conf->inactive_list),
+ conf->device_lock,
+ unplug_slaves(conf->mddev)
+ );
+ osh = get_free_stripe(conf);
+ spin_unlock_irq(&conf->device_lock);
+ atomic_set(&nsh->count, 1);
+ for(i=0; i<conf->pool_size; i++)
+ nsh->dev[i].page = osh->dev[i].page;
+ for( ; i<newsize; i++)
+ nsh->dev[i].page = NULL;
+ kmem_cache_free(conf->slab_cache, osh);
+ }
+ kmem_cache_destroy(conf->slab_cache);
+
+ /* Step 3.
+ * At this point, we are holding all the stripes so the array
+ * is completely stalled, so now is a good time to resize
+ * conf->disks.
+ */
+ ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO);
+ if (ndisks) {
+ for (i=0; i<conf->raid_disks; i++)
+ ndisks[i] = conf->disks[i];
+ kfree(conf->disks);
+ conf->disks = ndisks;
+ } else
+ err = -ENOMEM;
+
+ /* Step 4, return new stripes to service */
+ while(!list_empty(&newstripes)) {
+ nsh = list_entry(newstripes.next, struct stripe_head, lru);
+ list_del_init(&nsh->lru);
+ for (i=conf->raid_disks; i < newsize; i++)
+ if (nsh->dev[i].page == NULL) {
+ struct page *p = alloc_page(GFP_NOIO);
+ nsh->dev[i].page = p;
+ if (!p)
+ err = -ENOMEM;
+ }
+ release_stripe(nsh);
+ }
+ /* critical section pass, GFP_NOIO no longer needed */
+
+ conf->slab_cache = sc;
+ conf->active_name = 1-conf->active_name;
+ conf->pool_size = newsize;
+ return err;
+}
+#endif
+
static int drop_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
spin_unlock_irq(&conf->device_lock);
if (!sh)
return 0;
- if (atomic_read(&sh->count))
- BUG();
- shrink_buffers(sh, conf->raid_disks);
+ BUG_ON(atomic_read(&sh->count));
+ shrink_buffers(sh, conf->pool_size);
kmem_cache_free(conf->slab_cache, sh);
atomic_dec(&conf->active_stripes);
return 1;
{
struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks, i;
+ int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
if (bi->bi_size)
{
struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks, i;
+ int disks = sh->disks, i;
unsigned long flags;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
dev->req.bi_private = sh;
dev->flags = 0;
- if (i != sh->pd_idx)
- dev->sector = compute_blocknr(sh, i);
+ dev->sector = compute_blocknr(sh, i);
}
static void error(mddev_t *mddev, mdk_rdev_t *rdev)
" Operation continuing on %d devices\n",
bdevname(rdev->bdev,b), conf->working_disks);
}
-}
+}
/*
* Input: a 'big' sector number,
/*
* Select the parity disk based on the user selected algorithm.
*/
- if (conf->level == 4)
+ switch(conf->level) {
+ case 4:
*pd_idx = data_disks;
- else switch (conf->algorithm) {
+ break;
+ case 5:
+ switch (conf->algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
*pd_idx = data_disks - stripe % raid_disks;
if (*dd_idx >= *pd_idx)
default:
printk(KERN_ERR "raid5: unsupported algorithm %d\n",
conf->algorithm);
+ }
+ break;
+ case 6:
+
+ /**** FIX THIS ****/
+ switch (conf->algorithm) {
+ case ALGORITHM_LEFT_ASYMMETRIC:
+ *pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ if (*pd_idx == raid_disks-1)
+ (*dd_idx)++; /* Q D D D P */
+ else if (*dd_idx >= *pd_idx)
+ (*dd_idx) += 2; /* D D P Q D */
+ break;
+ case ALGORITHM_RIGHT_ASYMMETRIC:
+ *pd_idx = stripe % raid_disks;
+ if (*pd_idx == raid_disks-1)
+ (*dd_idx)++; /* Q D D D P */
+ else if (*dd_idx >= *pd_idx)
+ (*dd_idx) += 2; /* D D P Q D */
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC:
+ *pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+ break;
+ case ALGORITHM_RIGHT_SYMMETRIC:
+ *pd_idx = stripe % raid_disks;
+ *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+ break;
+ default:
+ printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
+ conf->algorithm);
+ }
+ break;
}
/*
static sector_t compute_blocknr(struct stripe_head *sh, int i)
{
raid5_conf_t *conf = sh->raid_conf;
- int raid_disks = conf->raid_disks, data_disks = raid_disks - 1;
+ int raid_disks = sh->disks, data_disks = raid_disks - 1;
sector_t new_sector = sh->sector, check;
int sectors_per_chunk = conf->chunk_size >> 9;
sector_t stripe;
int chunk_number, dummy1, dummy2, dd_idx = i;
sector_t r_sector;
+
chunk_offset = sector_div(new_sector, sectors_per_chunk);
stripe = new_sector;
BUG_ON(new_sector != stripe);
-
- switch (conf->algorithm) {
+ if (i == sh->pd_idx)
+ return 0;
+ switch(conf->level) {
+ case 4: break;
+ case 5:
+ switch (conf->algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
case ALGORITHM_RIGHT_ASYMMETRIC:
if (i > sh->pd_idx)
break;
default:
printk(KERN_ERR "raid5: unsupported algorithm %d\n",
+ conf->algorithm);
+ }
+ break;
+ case 6:
+ data_disks = raid_disks - 2;
+ if (i == raid6_next_disk(sh->pd_idx, raid_disks))
+ return 0; /* It is the Q disk */
+ switch (conf->algorithm) {
+ case ALGORITHM_LEFT_ASYMMETRIC:
+ case ALGORITHM_RIGHT_ASYMMETRIC:
+ if (sh->pd_idx == raid_disks-1)
+ i--; /* Q D D D P */
+ else if (i > sh->pd_idx)
+ i -= 2; /* D D P Q D */
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC:
+ case ALGORITHM_RIGHT_SYMMETRIC:
+ if (sh->pd_idx == raid_disks-1)
+ i--; /* Q D D D P */
+ else {
+ /* D D P Q D */
+ if (i < sh->pd_idx)
+ i += raid_disks;
+ i -= (sh->pd_idx + 2);
+ }
+ break;
+ default:
+ printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
conf->algorithm);
+ }
+ break;
}
chunk_number = stripe * data_disks + i;
/*
- * Copy data between a page in the stripe cache, and a bio.
- * There are no alignment or size guarantees between the page or the
- * bio except that there is some overlap.
- * All iovecs in the bio must be considered.
+ * Copy data between a page in the stripe cache, and one or more bion
+ * The page could align with the middle of the bio, or there could be
+ * several bion, each with several bio_vecs, which cover part of the page
+ * Multiple bion are linked together on bi_next. There may be extras
+ * at the end of this list. We ignore them.
*/
static void copy_data(int frombio, struct bio *bio,
struct page *page,
if (len > 0 && page_offset + len > STRIPE_SIZE)
clen = STRIPE_SIZE - page_offset;
else clen = len;
-
+
if (clen > 0) {
char *ba = __bio_kmap_atomic(bio, i, KM_USER0);
if (frombio)
static void compute_block(struct stripe_head *sh, int dd_idx)
{
- raid5_conf_t *conf = sh->raid_conf;
- int i, count, disks = conf->raid_disks;
+ int i, count, disks = sh->disks;
void *ptr[MAX_XOR_BLOCKS], *p;
PRINTK("compute_block, stripe %llu, idx %d\n",
set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
}
-static void compute_parity(struct stripe_head *sh, int method)
+static void compute_parity5(struct stripe_head *sh, int method)
{
raid5_conf_t *conf = sh->raid_conf;
- int i, pd_idx = sh->pd_idx, disks = conf->raid_disks, count;
+ int i, pd_idx = sh->pd_idx, disks = sh->disks, count;
void *ptr[MAX_XOR_BLOCKS];
struct bio *chosen;
- PRINTK("compute_parity, stripe %llu, method %d\n",
+ PRINTK("compute_parity5, stripe %llu, method %d\n",
(unsigned long long)sh->sector, method);
count = 1;
ptr[0] = page_address(sh->dev[pd_idx].page);
switch(method) {
case READ_MODIFY_WRITE:
- if (!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags))
- BUG();
+ BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags));
for (i=disks ; i-- ;) {
if (i==pd_idx)
continue;
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
- if (sh->dev[i].written) BUG();
+ BUG_ON(sh->dev[i].written);
sh->dev[i].written = chosen;
check_xor();
}
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
- if (sh->dev[i].written) BUG();
+ BUG_ON(sh->dev[i].written);
sh->dev[i].written = chosen;
}
break;
clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
}
+static void compute_parity6(struct stripe_head *sh, int method)
+{
+ raid6_conf_t *conf = sh->raid_conf;
+ int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = conf->raid_disks, count;
+ struct bio *chosen;
+ /**** FIX THIS: This could be very bad if disks is close to 256 ****/
+ void *ptrs[disks];
+
+ qd_idx = raid6_next_disk(pd_idx, disks);
+ d0_idx = raid6_next_disk(qd_idx, disks);
+
+ PRINTK("compute_parity, stripe %llu, method %d\n",
+ (unsigned long long)sh->sector, method);
+
+ switch(method) {
+ case READ_MODIFY_WRITE:
+ BUG(); /* READ_MODIFY_WRITE N/A for RAID-6 */
+ case RECONSTRUCT_WRITE:
+ for (i= disks; i-- ;)
+ if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) {
+ chosen = sh->dev[i].towrite;
+ sh->dev[i].towrite = NULL;
+
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ wake_up(&conf->wait_for_overlap);
+
+ if (sh->dev[i].written) BUG();
+ sh->dev[i].written = chosen;
+ }
+ break;
+ case CHECK_PARITY:
+ BUG(); /* Not implemented yet */
+ }
+
+ for (i = disks; i--;)
+ if (sh->dev[i].written) {
+ sector_t sector = sh->dev[i].sector;
+ struct bio *wbi = sh->dev[i].written;
+ while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
+ copy_data(1, wbi, sh->dev[i].page, sector);
+ wbi = r5_next_bio(wbi, sector);
+ }
+
+ set_bit(R5_LOCKED, &sh->dev[i].flags);
+ set_bit(R5_UPTODATE, &sh->dev[i].flags);
+ }
+
+// switch(method) {
+// case RECONSTRUCT_WRITE:
+// case CHECK_PARITY:
+// case UPDATE_PARITY:
+ /* Note that unlike RAID-5, the ordering of the disks matters greatly. */
+ /* FIX: Is this ordering of drives even remotely optimal? */
+ count = 0;
+ i = d0_idx;
+ do {
+ ptrs[count++] = page_address(sh->dev[i].page);
+ if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags))
+ printk("block %d/%d not uptodate on parity calc\n", i,count);
+ i = raid6_next_disk(i, disks);
+ } while ( i != d0_idx );
+// break;
+// }
+
+ raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs);
+
+ switch(method) {
+ case RECONSTRUCT_WRITE:
+ set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
+ set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
+ set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
+ set_bit(R5_LOCKED, &sh->dev[qd_idx].flags);
+ break;
+ case UPDATE_PARITY:
+ set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
+ set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags);
+ break;
+ }
+}
+
+
+/* Compute one missing block */
+static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
+{
+ raid6_conf_t *conf = sh->raid_conf;
+ int i, count, disks = conf->raid_disks;
+ void *ptr[MAX_XOR_BLOCKS], *p;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = raid6_next_disk(pd_idx, disks);
+
+ PRINTK("compute_block_1, stripe %llu, idx %d\n",
+ (unsigned long long)sh->sector, dd_idx);
+
+ if ( dd_idx == qd_idx ) {
+ /* We're actually computing the Q drive */
+ compute_parity6(sh, UPDATE_PARITY);
+ } else {
+ ptr[0] = page_address(sh->dev[dd_idx].page);
+ if (!nozero) memset(ptr[0], 0, STRIPE_SIZE);
+ count = 1;
+ for (i = disks ; i--; ) {
+ if (i == dd_idx || i == qd_idx)
+ continue;
+ p = page_address(sh->dev[i].page);
+ if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
+ ptr[count++] = p;
+ else
+ printk("compute_block() %d, stripe %llu, %d"
+ " not present\n", dd_idx,
+ (unsigned long long)sh->sector, i);
+
+ check_xor();
+ }
+ if (count != 1)
+ xor_block(count, STRIPE_SIZE, ptr);
+ if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ }
+}
+
+/* Compute two missing blocks */
+static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
+{
+ raid6_conf_t *conf = sh->raid_conf;
+ int i, count, disks = conf->raid_disks;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = raid6_next_disk(pd_idx, disks);
+ int d0_idx = raid6_next_disk(qd_idx, disks);
+ int faila, failb;
+
+ /* faila and failb are disk numbers relative to d0_idx */
+ /* pd_idx become disks-2 and qd_idx become disks-1 */
+ faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx;
+ failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx;
+
+ BUG_ON(faila == failb);
+ if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
+
+ PRINTK("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
+ (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb);
+
+ if ( failb == disks-1 ) {
+ /* Q disk is one of the missing disks */
+ if ( faila == disks-2 ) {
+ /* Missing P+Q, just recompute */
+ compute_parity6(sh, UPDATE_PARITY);
+ return;
+ } else {
+ /* We're missing D+Q; recompute D from P */
+ compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
+ compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
+ return;
+ }
+ }
+
+ /* We're missing D+P or D+D; build pointer table */
+ {
+ /**** FIX THIS: This could be very bad if disks is close to 256 ****/
+ void *ptrs[disks];
+
+ count = 0;
+ i = d0_idx;
+ do {
+ ptrs[count++] = page_address(sh->dev[i].page);
+ i = raid6_next_disk(i, disks);
+ if (i != dd_idx1 && i != dd_idx2 &&
+ !test_bit(R5_UPTODATE, &sh->dev[i].flags))
+ printk("compute_2 with missing block %d/%d\n", count, i);
+ } while ( i != d0_idx );
+
+ if ( failb == disks-2 ) {
+ /* We're missing D+P. */
+ raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs);
+ } else {
+ /* We're missing D+D. */
+ raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs);
+ }
+
+ /* Both the above update both missing blocks */
+ set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
+ set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
+ }
+}
+
+
+
/*
* Each stripe/dev can have one or more bion attached.
- * toread/towrite point to the first in a chain.
+ * toread/towrite point to the first in a chain.
* The bi_next chain must be in order.
*/
static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite)
if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
goto overlap;
- if (*bip && bi->bi_next && (*bip) != bi->bi_next)
- BUG();
+ BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
if (*bip)
bi->bi_next = *bip;
*bip = bi;
return 0;
}
+static void end_reshape(raid5_conf_t *conf);
+
+static int page_is_zero(struct page *p)
+{
+ char *a = page_address(p);
+ return ((*(u32*)a) == 0 &&
+ memcmp(a, a+4, STRIPE_SIZE-4)==0);
+}
+
+static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
+{
+ int sectors_per_chunk = conf->chunk_size >> 9;
+ sector_t x = stripe;
+ int pd_idx, dd_idx;
+ int chunk_offset = sector_div(x, sectors_per_chunk);
+ stripe = x;
+ raid5_compute_sector(stripe*(disks-1)*sectors_per_chunk
+ + chunk_offset, disks, disks-1, &dd_idx, &pd_idx, conf);
+ return pd_idx;
+}
+
/*
* handle_stripe - do things to a stripe.
*
*/
-static void handle_stripe(struct stripe_head *sh)
+static void handle_stripe5(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks;
+ int disks = sh->disks;
struct bio *return_bi= NULL;
struct bio *bi;
int i;
- int syncing;
+ int syncing, expanding, expanded;
int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
int non_overwrite = 0;
int failed_num=0;
clear_bit(STRIPE_DELAYED, &sh->state);
syncing = test_bit(STRIPE_SYNCING, &sh->state);
+ expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
/* Now to look around and see what can be done */
rcu_read_lock();
* parity, or to satisfy requests
* or to load a block that is being partially written.
*/
- if (to_read || non_overwrite || (syncing && (uptodate < disks))) {
+ if (to_read || non_overwrite || (syncing && (uptodate < disks)) || expanding) {
for (i=disks; i--;) {
dev = &sh->dev[i];
if (!test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) &&
(dev->toread ||
(dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
syncing ||
+ expanding ||
(failed && (sh->dev[failed_num].toread ||
(sh->dev[failed_num].towrite && !test_bit(R5_OVERWRITE, &sh->dev[failed_num].flags))))
)
if (locked == 0 && (rcw == 0 ||rmw == 0) &&
!test_bit(STRIPE_BIT_DELAY, &sh->state)) {
PRINTK("Computing parity...\n");
- compute_parity(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE);
+ compute_parity5(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE);
/* now every locked buffer is ready to be written */
for (i=disks; i--;)
if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
!test_bit(STRIPE_INSYNC, &sh->state)) {
set_bit(STRIPE_HANDLE, &sh->state);
if (failed == 0) {
- char *pagea;
- if (uptodate != disks)
- BUG();
- compute_parity(sh, CHECK_PARITY);
+ BUG_ON(uptodate != disks);
+ compute_parity5(sh, CHECK_PARITY);
uptodate--;
- pagea = page_address(sh->dev[sh->pd_idx].page);
- if ((*(u32*)pagea) == 0 &&
- !memcmp(pagea, pagea+4, STRIPE_SIZE-4)) {
+ if (page_is_zero(sh->dev[sh->pd_idx].page)) {
/* parity is correct (on disc, not in buffer any more) */
set_bit(STRIPE_INSYNC, &sh->state);
} else {
set_bit(R5_Wantwrite, &dev->flags);
set_bit(R5_ReWrite, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
+ locked++;
} else {
/* let's read it back */
set_bit(R5_Wantread, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
+ locked++;
+ }
+ }
+
+ if (expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+ /* Need to write out all blocks after computing parity */
+ sh->disks = conf->raid_disks;
+ sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks);
+ compute_parity5(sh, RECONSTRUCT_WRITE);
+ for (i= conf->raid_disks; i--;) {
+ set_bit(R5_LOCKED, &sh->dev[i].flags);
+ locked++;
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
}
+ clear_bit(STRIPE_EXPANDING, &sh->state);
+ } else if (expanded) {
+ clear_bit(STRIPE_EXPAND_READY, &sh->state);
+ atomic_dec(&conf->reshape_stripes);
+ wake_up(&conf->wait_for_overlap);
+ md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
+ }
+
+ if (expanding && locked == 0) {
+ /* We have read all the blocks in this stripe and now we need to
+ * copy some of them into a target stripe for expand.
+ */
+ clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ for (i=0; i< sh->disks; i++)
+ if (i != sh->pd_idx) {
+ int dd_idx, pd_idx, j;
+ struct stripe_head *sh2;
+
+ sector_t bn = compute_blocknr(sh, i);
+ sector_t s = raid5_compute_sector(bn, conf->raid_disks,
+ conf->raid_disks-1,
+ &dd_idx, &pd_idx, conf);
+ sh2 = get_active_stripe(conf, s, conf->raid_disks, pd_idx, 1);
+ if (sh2 == NULL)
+ /* so far only the early blocks of this stripe
+ * have been requested. When later blocks
+ * get requested, we will try again
+ */
+ continue;
+ if(!test_bit(STRIPE_EXPANDING, &sh2->state) ||
+ test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
+ /* must have already done this block */
+ release_stripe(sh2);
+ continue;
+ }
+ memcpy(page_address(sh2->dev[dd_idx].page),
+ page_address(sh->dev[i].page),
+ STRIPE_SIZE);
+ set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
+ set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
+ for (j=0; j<conf->raid_disks; j++)
+ if (j != sh2->pd_idx &&
+ !test_bit(R5_Expanded, &sh2->dev[j].flags))
+ break;
+ if (j == conf->raid_disks) {
+ set_bit(STRIPE_EXPAND_READY, &sh2->state);
+ set_bit(STRIPE_HANDLE, &sh2->state);
+ }
+ release_stripe(sh2);
+ }
}
spin_unlock(&sh->lock);
rcu_read_unlock();
if (rdev) {
- if (syncing)
+ if (syncing || expanding || expanded)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
bi->bi_bdev = rdev->bdev;
}
}
-static void raid5_activate_delayed(raid5_conf_t *conf)
-{
- if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
- while (!list_empty(&conf->delayed_list)) {
- struct list_head *l = conf->delayed_list.next;
- struct stripe_head *sh;
- sh = list_entry(l, struct stripe_head, lru);
- list_del_init(l);
- clear_bit(STRIPE_DELAYED, &sh->state);
- if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- atomic_inc(&conf->preread_active_stripes);
- list_add_tail(&sh->lru, &conf->handle_list);
- }
- }
-}
-
-static void activate_bit_delay(raid5_conf_t *conf)
-{
- /* device_lock is held */
- struct list_head head;
- list_add(&head, &conf->bitmap_list);
- list_del_init(&conf->bitmap_list);
- while (!list_empty(&head)) {
- struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
- list_del_init(&sh->lru);
- atomic_inc(&sh->count);
- __release_stripe(conf, sh);
- }
-}
-
-static void unplug_slaves(mddev_t *mddev)
+static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
{
- raid5_conf_t *conf = mddev_to_conf(mddev);
+ raid6_conf_t *conf = sh->raid_conf;
+ int disks = conf->raid_disks;
+ struct bio *return_bi= NULL;
+ struct bio *bi;
int i;
+ int syncing;
+ int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
+ int non_overwrite = 0;
+ int failed_num[2] = {0, 0};
+ struct r5dev *dev, *pdev, *qdev;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = raid6_next_disk(pd_idx, disks);
+ int p_failed, q_failed;
- rcu_read_lock();
- for (i=0; i<mddev->raid_disks; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
+ PRINTK("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d, qd_idx=%d\n",
+ (unsigned long long)sh->sector, sh->state, atomic_read(&sh->count),
+ pd_idx, qd_idx);
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
+ spin_lock(&sh->lock);
+ clear_bit(STRIPE_HANDLE, &sh->state);
+ clear_bit(STRIPE_DELAYED, &sh->state);
- if (r_queue->unplug_fn)
- r_queue->unplug_fn(r_queue);
+ syncing = test_bit(STRIPE_SYNCING, &sh->state);
+ /* Now to look around and see what can be done */
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
- }
+ rcu_read_lock();
+ for (i=disks; i--; ) {
+ mdk_rdev_t *rdev;
+ dev = &sh->dev[i];
+ clear_bit(R5_Insync, &dev->flags);
+
+ PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
+ i, dev->flags, dev->toread, dev->towrite, dev->written);
+ /* maybe we can reply to a read */
+ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
+ struct bio *rbi, *rbi2;
+ PRINTK("Return read for disc %d\n", i);
+ spin_lock_irq(&conf->device_lock);
+ rbi = dev->toread;
+ dev->toread = NULL;
+ if (test_and_clear_bit(R5_Overlap, &dev->flags))
+ wake_up(&conf->wait_for_overlap);
+ spin_unlock_irq(&conf->device_lock);
+ while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
+ copy_data(0, rbi, dev->page, dev->sector);
+ rbi2 = r5_next_bio(rbi, dev->sector);
+ spin_lock_irq(&conf->device_lock);
+ if (--rbi->bi_phys_segments == 0) {
+ rbi->bi_next = return_bi;
+ return_bi = rbi;
+ }
+ spin_unlock_irq(&conf->device_lock);
+ rbi = rbi2;
+ }
+ }
+
+ /* now count some things */
+ if (test_bit(R5_LOCKED, &dev->flags)) locked++;
+ if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++;
+
+
+ if (dev->toread) to_read++;
+ if (dev->towrite) {
+ to_write++;
+ if (!test_bit(R5_OVERWRITE, &dev->flags))
+ non_overwrite++;
+ }
+ if (dev->written) written++;
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (!rdev || !test_bit(In_sync, &rdev->flags)) {
+ /* The ReadError flag will just be confusing now */
+ clear_bit(R5_ReadError, &dev->flags);
+ clear_bit(R5_ReWrite, &dev->flags);
+ }
+ if (!rdev || !test_bit(In_sync, &rdev->flags)
+ || test_bit(R5_ReadError, &dev->flags)) {
+ if ( failed < 2 )
+ failed_num[failed] = i;
+ failed++;
+ } else
+ set_bit(R5_Insync, &dev->flags);
+ }
+ rcu_read_unlock();
+ PRINTK("locked=%d uptodate=%d to_read=%d"
+ " to_write=%d failed=%d failed_num=%d,%d\n",
+ locked, uptodate, to_read, to_write, failed,
+ failed_num[0], failed_num[1]);
+ /* check if the array has lost >2 devices and, if so, some requests might
+ * need to be failed
+ */
+ if (failed > 2 && to_read+to_write+written) {
+ for (i=disks; i--; ) {
+ int bitmap_end = 0;
+
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ mdk_rdev_t *rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(In_sync, &rdev->flags))
+ /* multiple read failures in one stripe */
+ md_error(conf->mddev, rdev);
+ rcu_read_unlock();
+ }
+
+ spin_lock_irq(&conf->device_lock);
+ /* fail all writes first */
+ bi = sh->dev[i].towrite;
+ sh->dev[i].towrite = NULL;
+ if (bi) { to_write--; bitmap_end = 1; }
+
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ wake_up(&conf->wait_for_overlap);
+
+ while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
+ struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
+ clear_bit(BIO_UPTODATE, &bi->bi_flags);
+ if (--bi->bi_phys_segments == 0) {
+ md_write_end(conf->mddev);
+ bi->bi_next = return_bi;
+ return_bi = bi;
+ }
+ bi = nextbi;
+ }
+ /* and fail all 'written' */
+ bi = sh->dev[i].written;
+ sh->dev[i].written = NULL;
+ if (bi) bitmap_end = 1;
+ while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS) {
+ struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
+ clear_bit(BIO_UPTODATE, &bi->bi_flags);
+ if (--bi->bi_phys_segments == 0) {
+ md_write_end(conf->mddev);
+ bi->bi_next = return_bi;
+ return_bi = bi;
+ }
+ bi = bi2;
+ }
+
+ /* fail any reads if this device is non-operational */
+ if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+ test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ bi = sh->dev[i].toread;
+ sh->dev[i].toread = NULL;
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ wake_up(&conf->wait_for_overlap);
+ if (bi) to_read--;
+ while (bi && bi->bi_sector < sh->dev[i].sector + STRIPE_SECTORS){
+ struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
+ clear_bit(BIO_UPTODATE, &bi->bi_flags);
+ if (--bi->bi_phys_segments == 0) {
+ bi->bi_next = return_bi;
+ return_bi = bi;
+ }
+ bi = nextbi;
+ }
+ }
+ spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0, 0);
+ }
+ }
+ if (failed > 2 && syncing) {
+ md_done_sync(conf->mddev, STRIPE_SECTORS,0);
+ clear_bit(STRIPE_SYNCING, &sh->state);
+ syncing = 0;
+ }
+
+ /*
+ * might be able to return some write requests if the parity blocks
+ * are safe, or on a failed drive
+ */
+ pdev = &sh->dev[pd_idx];
+ p_failed = (failed >= 1 && failed_num[0] == pd_idx)
+ || (failed >= 2 && failed_num[1] == pd_idx);
+ qdev = &sh->dev[qd_idx];
+ q_failed = (failed >= 1 && failed_num[0] == qd_idx)
+ || (failed >= 2 && failed_num[1] == qd_idx);
+
+ if ( written &&
+ ( p_failed || ((test_bit(R5_Insync, &pdev->flags)
+ && !test_bit(R5_LOCKED, &pdev->flags)
+ && test_bit(R5_UPTODATE, &pdev->flags))) ) &&
+ ( q_failed || ((test_bit(R5_Insync, &qdev->flags)
+ && !test_bit(R5_LOCKED, &qdev->flags)
+ && test_bit(R5_UPTODATE, &qdev->flags))) ) ) {
+ /* any written block on an uptodate or failed drive can be
+ * returned. Note that if we 'wrote' to a failed drive,
+ * it will be UPTODATE, but never LOCKED, so we don't need
+ * to test 'failed' directly.
+ */
+ for (i=disks; i--; )
+ if (sh->dev[i].written) {
+ dev = &sh->dev[i];
+ if (!test_bit(R5_LOCKED, &dev->flags) &&
+ test_bit(R5_UPTODATE, &dev->flags) ) {
+ /* We can return any write requests */
+ int bitmap_end = 0;
+ struct bio *wbi, *wbi2;
+ PRINTK("Return write for stripe %llu disc %d\n",
+ (unsigned long long)sh->sector, i);
+ spin_lock_irq(&conf->device_lock);
+ wbi = dev->written;
+ dev->written = NULL;
+ while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) {
+ wbi2 = r5_next_bio(wbi, dev->sector);
+ if (--wbi->bi_phys_segments == 0) {
+ md_write_end(conf->mddev);
+ wbi->bi_next = return_bi;
+ return_bi = wbi;
+ }
+ wbi = wbi2;
+ }
+ if (dev->towrite == NULL)
+ bitmap_end = 1;
+ spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS,
+ !test_bit(STRIPE_DEGRADED, &sh->state), 0);
+ }
+ }
+ }
+
+ /* Now we might consider reading some blocks, either to check/generate
+ * parity, or to satisfy requests
+ * or to load a block that is being partially written.
+ */
+ if (to_read || non_overwrite || (to_write && failed) || (syncing && (uptodate < disks))) {
+ for (i=disks; i--;) {
+ dev = &sh->dev[i];
+ if (!test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) &&
+ (dev->toread ||
+ (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
+ syncing ||
+ (failed >= 1 && (sh->dev[failed_num[0]].toread || to_write)) ||
+ (failed >= 2 && (sh->dev[failed_num[1]].toread || to_write))
+ )
+ ) {
+ /* we would like to get this block, possibly
+ * by computing it, but we might not be able to
+ */
+ if (uptodate == disks-1) {
+ PRINTK("Computing stripe %llu block %d\n",
+ (unsigned long long)sh->sector, i);
+ compute_block_1(sh, i, 0);
+ uptodate++;
+ } else if ( uptodate == disks-2 && failed >= 2 ) {
+ /* Computing 2-failure is *very* expensive; only do it if failed >= 2 */
+ int other;
+ for (other=disks; other--;) {
+ if ( other == i )
+ continue;
+ if ( !test_bit(R5_UPTODATE, &sh->dev[other].flags) )
+ break;
+ }
+ BUG_ON(other < 0);
+ PRINTK("Computing stripe %llu blocks %d,%d\n",
+ (unsigned long long)sh->sector, i, other);
+ compute_block_2(sh, i, other);
+ uptodate += 2;
+ } else if (test_bit(R5_Insync, &dev->flags)) {
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantread, &dev->flags);
+#if 0
+ /* if I am just reading this block and we don't have
+ a failed drive, or any pending writes then sidestep the cache */
+ if (sh->bh_read[i] && !sh->bh_read[i]->b_reqnext &&
+ ! syncing && !failed && !to_write) {
+ sh->bh_cache[i]->b_page = sh->bh_read[i]->b_page;
+ sh->bh_cache[i]->b_data = sh->bh_read[i]->b_data;
+ }
+#endif
+ locked++;
+ PRINTK("Reading block %d (sync=%d)\n",
+ i, syncing);
+ }
+ }
+ }
+ set_bit(STRIPE_HANDLE, &sh->state);
+ }
+
+ /* now to consider writing and what else, if anything should be read */
+ if (to_write) {
+ int rcw=0, must_compute=0;
+ for (i=disks ; i--;) {
+ dev = &sh->dev[i];
+ /* Would I have to read this buffer for reconstruct_write */
+ if (!test_bit(R5_OVERWRITE, &dev->flags)
+ && i != pd_idx && i != qd_idx
+ && (!test_bit(R5_LOCKED, &dev->flags)
+#if 0
+ || sh->bh_page[i] != bh->b_page
+#endif
+ ) &&
+ !test_bit(R5_UPTODATE, &dev->flags)) {
+ if (test_bit(R5_Insync, &dev->flags)) rcw++;
+ else {
+ PRINTK("raid6: must_compute: disk %d flags=%#lx\n", i, dev->flags);
+ must_compute++;
+ }
+ }
+ }
+ PRINTK("for sector %llu, rcw=%d, must_compute=%d\n",
+ (unsigned long long)sh->sector, rcw, must_compute);
+ set_bit(STRIPE_HANDLE, &sh->state);
+
+ if (rcw > 0)
+ /* want reconstruct write, but need to get some data */
+ for (i=disks; i--;) {
+ dev = &sh->dev[i];
+ if (!test_bit(R5_OVERWRITE, &dev->flags)
+ && !(failed == 0 && (i == pd_idx || i == qd_idx))
+ && !test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) &&
+ test_bit(R5_Insync, &dev->flags)) {
+ if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ {
+ PRINTK("Read_old stripe %llu block %d for Reconstruct\n",
+ (unsigned long long)sh->sector, i);
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantread, &dev->flags);
+ locked++;
+ } else {
+ PRINTK("Request delayed stripe %llu block %d for Reconstruct\n",
+ (unsigned long long)sh->sector, i);
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ }
+ }
+ }
+ /* now if nothing is locked, and if we have enough data, we can start a write request */
+ if (locked == 0 && rcw == 0 &&
+ !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
+ if ( must_compute > 0 ) {
+ /* We have failed blocks and need to compute them */
+ switch ( failed ) {
+ case 0: BUG();
+ case 1: compute_block_1(sh, failed_num[0], 0); break;
+ case 2: compute_block_2(sh, failed_num[0], failed_num[1]); break;
+ default: BUG(); /* This request should have been failed? */
+ }
+ }
+
+ PRINTK("Computing parity for stripe %llu\n", (unsigned long long)sh->sector);
+ compute_parity6(sh, RECONSTRUCT_WRITE);
+ /* now every locked buffer is ready to be written */
+ for (i=disks; i--;)
+ if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
+ PRINTK("Writing stripe %llu block %d\n",
+ (unsigned long long)sh->sector, i);
+ locked++;
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
+ }
+ /* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
+ 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);
+ }
+ }
+ }
+
+ /* maybe we need to check and possibly fix the parity for this stripe
+ * Any reads will already have been scheduled, so we just see if enough data
+ * is available
+ */
+ if (syncing && locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state)) {
+ int update_p = 0, update_q = 0;
+ struct r5dev *dev;
+
+ set_bit(STRIPE_HANDLE, &sh->state);
+
+ BUG_ON(failed>2);
+ BUG_ON(uptodate < disks);
+ /* Want to check and possibly repair P and Q.
+ * However there could be one 'failed' device, in which
+ * case we can only check one of them, possibly using the
+ * other to generate missing data
+ */
+
+ /* If !tmp_page, we cannot do the calculations,
+ * but as we have set STRIPE_HANDLE, we will soon be called
+ * by stripe_handle with a tmp_page - just wait until then.
+ */
+ if (tmp_page) {
+ if (failed == q_failed) {
+ /* The only possible failed device holds 'Q', so it makes
+ * sense to check P (If anything else were failed, we would
+ * have used P to recreate it).
+ */
+ compute_block_1(sh, pd_idx, 1);
+ if (!page_is_zero(sh->dev[pd_idx].page)) {
+ compute_block_1(sh,pd_idx,0);
+ update_p = 1;
+ }
+ }
+ if (!q_failed && failed < 2) {
+ /* q is not failed, and we didn't use it to generate
+ * anything, so it makes sense to check it
+ */
+ memcpy(page_address(tmp_page),
+ page_address(sh->dev[qd_idx].page),
+ STRIPE_SIZE);
+ compute_parity6(sh, UPDATE_PARITY);
+ if (memcmp(page_address(tmp_page),
+ page_address(sh->dev[qd_idx].page),
+ STRIPE_SIZE)!= 0) {
+ clear_bit(STRIPE_INSYNC, &sh->state);
+ update_q = 1;
+ }
+ }
+ if (update_p || update_q) {
+ conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ /* don't try to repair!! */
+ update_p = update_q = 0;
+ }
+
+ /* now write out any block on a failed drive,
+ * or P or Q if they need it
+ */
+
+ if (failed == 2) {
+ dev = &sh->dev[failed_num[1]];
+ locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
+ if (failed >= 1) {
+ dev = &sh->dev[failed_num[0]];
+ locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
+
+ if (update_p) {
+ dev = &sh->dev[pd_idx];
+ locked ++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
+ if (update_q) {
+ dev = &sh->dev[qd_idx];
+ locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
+ clear_bit(STRIPE_DEGRADED, &sh->state);
+
+ set_bit(STRIPE_INSYNC, &sh->state);
+ }
+ }
+
+ if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
+ md_done_sync(conf->mddev, STRIPE_SECTORS,1);
+ clear_bit(STRIPE_SYNCING, &sh->state);
+ }
+
+ /* If the failed drives are just a ReadError, then we might need
+ * to progress the repair/check process
+ */
+ if (failed <= 2 && ! conf->mddev->ro)
+ for (i=0; i<failed;i++) {
+ dev = &sh->dev[failed_num[i]];
+ if (test_bit(R5_ReadError, &dev->flags)
+ && !test_bit(R5_LOCKED, &dev->flags)
+ && test_bit(R5_UPTODATE, &dev->flags)
+ ) {
+ if (!test_bit(R5_ReWrite, &dev->flags)) {
+ set_bit(R5_Wantwrite, &dev->flags);
+ set_bit(R5_ReWrite, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ } else {
+ /* let's read it back */
+ set_bit(R5_Wantread, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ }
+ }
+ }
+ spin_unlock(&sh->lock);
+
+ while ((bi=return_bi)) {
+ int bytes = bi->bi_size;
+
+ return_bi = bi->bi_next;
+ bi->bi_next = NULL;
+ bi->bi_size = 0;
+ bi->bi_end_io(bi, bytes, 0);
+ }
+ for (i=disks; i-- ;) {
+ int rw;
+ struct bio *bi;
+ mdk_rdev_t *rdev;
+ if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
+ rw = 1;
+ else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+ rw = 0;
+ else
+ continue;
+
+ bi = &sh->dev[i].req;
+
+ bi->bi_rw = rw;
+ if (rw)
+ bi->bi_end_io = raid5_end_write_request;
+ else
+ bi->bi_end_io = raid5_end_read_request;
+
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = NULL;
+ if (rdev)
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+
+ if (rdev) {
+ if (syncing)
+ md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+
+ bi->bi_bdev = rdev->bdev;
+ PRINTK("for %llu schedule op %ld on disc %d\n",
+ (unsigned long long)sh->sector, bi->bi_rw, i);
+ atomic_inc(&sh->count);
+ bi->bi_sector = sh->sector + rdev->data_offset;
+ bi->bi_flags = 1 << BIO_UPTODATE;
+ bi->bi_vcnt = 1;
+ bi->bi_max_vecs = 1;
+ bi->bi_idx = 0;
+ bi->bi_io_vec = &sh->dev[i].vec;
+ bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
+ bi->bi_io_vec[0].bv_offset = 0;
+ bi->bi_size = STRIPE_SIZE;
+ bi->bi_next = NULL;
+ if (rw == WRITE &&
+ test_bit(R5_ReWrite, &sh->dev[i].flags))
+ atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
+ generic_make_request(bi);
+ } else {
+ if (rw == 1)
+ set_bit(STRIPE_DEGRADED, &sh->state);
+ PRINTK("skip op %ld on disc %d for sector %llu\n",
+ bi->bi_rw, i, (unsigned long long)sh->sector);
+ clear_bit(R5_LOCKED, &sh->dev[i].flags);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ }
+ }
+}
+
+static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
+{
+ if (sh->raid_conf->level == 6)
+ handle_stripe6(sh, tmp_page);
+ else
+ handle_stripe5(sh);
+}
+
+
+
+static void raid5_activate_delayed(raid5_conf_t *conf)
+{
+ if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
+ while (!list_empty(&conf->delayed_list)) {
+ struct list_head *l = conf->delayed_list.next;
+ struct stripe_head *sh;
+ sh = list_entry(l, struct stripe_head, lru);
+ list_del_init(l);
+ clear_bit(STRIPE_DELAYED, &sh->state);
+ if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ atomic_inc(&conf->preread_active_stripes);
+ list_add_tail(&sh->lru, &conf->handle_list);
+ }
+ }
+}
+
+static void activate_bit_delay(raid5_conf_t *conf)
+{
+ /* device_lock is held */
+ struct list_head head;
+ list_add(&head, &conf->bitmap_list);
+ list_del_init(&conf->bitmap_list);
+ while (!list_empty(&head)) {
+ struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
+ list_del_init(&sh->lru);
+ atomic_inc(&sh->count);
+ __release_stripe(conf, sh);
+ }
+}
+
+static void unplug_slaves(mddev_t *mddev)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ int i;
+
+ rcu_read_lock();
+ for (i=0; i<mddev->raid_disks; i++) {
+ mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
+ request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
+
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+
+ if (r_queue->unplug_fn)
+ r_queue->unplug_fn(r_queue);
+
+ rdev_dec_pending(rdev, mddev);
+ rcu_read_lock();
+ }
+ }
rcu_read_unlock();
}
spin_unlock_irq(&conf->device_lock);
}
-static int make_request (request_queue_t *q, struct bio * bi)
+static int make_request(request_queue_t *q, struct bio * bi)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
- const unsigned int raid_disks = conf->raid_disks;
- const unsigned int data_disks = raid_disks - 1;
unsigned int dd_idx, pd_idx;
sector_t new_sector;
sector_t logical_sector, last_sector;
struct stripe_head *sh;
const int rw = bio_data_dir(bi);
+ int remaining;
if (unlikely(bio_barrier(bi))) {
bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
DEFINE_WAIT(w);
-
- new_sector = raid5_compute_sector(logical_sector,
- raid_disks, data_disks, &dd_idx, &pd_idx, conf);
+ int disks, data_disks;
+
+ retry:
+ prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
+ if (likely(conf->expand_progress == MaxSector))
+ disks = conf->raid_disks;
+ else {
+ /* spinlock is needed as expand_progress may be
+ * 64bit on a 32bit platform, and so it might be
+ * possible to see a half-updated value
+ * Ofcourse expand_progress could change after
+ * the lock is dropped, so once we get a reference
+ * to the stripe that we think it is, we will have
+ * to check again.
+ */
+ spin_lock_irq(&conf->device_lock);
+ disks = conf->raid_disks;
+ if (logical_sector >= conf->expand_progress)
+ disks = conf->previous_raid_disks;
+ else {
+ if (logical_sector >= conf->expand_lo) {
+ spin_unlock_irq(&conf->device_lock);
+ schedule();
+ goto retry;
+ }
+ }
+ spin_unlock_irq(&conf->device_lock);
+ }
+ data_disks = disks - conf->max_degraded;
+ new_sector = raid5_compute_sector(logical_sector, disks, data_disks,
+ &dd_idx, &pd_idx, conf);
PRINTK("raid5: make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
- retry:
- prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
- sh = get_active_stripe(conf, new_sector, pd_idx, (bi->bi_rw&RWA_MASK));
+ sh = get_active_stripe(conf, new_sector, disks, pd_idx, (bi->bi_rw&RWA_MASK));
if (sh) {
- if (!add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
- /* Add failed due to overlap. Flush everything
+ if (unlikely(conf->expand_progress != MaxSector)) {
+ /* expansion might have moved on while waiting for a
+ * stripe, so we must do the range check again.
+ * Expansion could still move past after this
+ * test, but as we are holding a reference to
+ * 'sh', we know that if that happens,
+ * STRIPE_EXPANDING will get set and the expansion
+ * won't proceed until we finish with the stripe.
+ */
+ int must_retry = 0;
+ spin_lock_irq(&conf->device_lock);
+ if (logical_sector < conf->expand_progress &&
+ disks == conf->previous_raid_disks)
+ /* mismatch, need to try again */
+ must_retry = 1;
+ spin_unlock_irq(&conf->device_lock);
+ if (must_retry) {
+ release_stripe(sh);
+ goto retry;
+ }
+ }
+ /* FIXME what if we get a false positive because these
+ * are being updated.
+ */
+ if (logical_sector >= mddev->suspend_lo &&
+ logical_sector < mddev->suspend_hi) {
+ release_stripe(sh);
+ schedule();
+ goto retry;
+ }
+
+ if (test_bit(STRIPE_EXPANDING, &sh->state) ||
+ !add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
+ /* Stripe is busy expanding or
+ * add failed due to overlap. Flush everything
* and wait a while
*/
raid5_unplug_device(mddev->queue);
}
finish_wait(&conf->wait_for_overlap, &w);
raid5_plug_device(conf);
- handle_stripe(sh);
+ handle_stripe(sh, NULL);
release_stripe(sh);
-
} else {
/* cannot get stripe for read-ahead, just give-up */
clear_bit(BIO_UPTODATE, &bi->bi_flags);
}
spin_lock_irq(&conf->device_lock);
- if (--bi->bi_phys_segments == 0) {
+ remaining = --bi->bi_phys_segments;
+ spin_unlock_irq(&conf->device_lock);
+ if (remaining == 0) {
int bytes = bi->bi_size;
- if ( bio_data_dir(bi) == WRITE )
+ if ( rw == WRITE )
md_write_end(mddev);
bi->bi_size = 0;
bi->bi_end_io(bi, bytes, 0);
}
- spin_unlock_irq(&conf->device_lock);
return 0;
}
+static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped)
+{
+ /* reshaping is quite different to recovery/resync so it is
+ * handled quite separately ... here.
+ *
+ * On each call to sync_request, we gather one chunk worth of
+ * destination stripes and flag them as expanding.
+ * Then we find all the source stripes and request reads.
+ * 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;
+ struct stripe_head *sh;
+ int pd_idx;
+ sector_t first_sector, last_sector;
+ int raid_disks;
+ int data_disks;
+ int i;
+ int dd_idx;
+ sector_t writepos, safepos, gap;
+
+ if (sector_nr == 0 &&
+ conf->expand_progress != 0) {
+ /* restarting in the middle, skip the initial sectors */
+ sector_nr = conf->expand_progress;
+ sector_div(sector_nr, conf->raid_disks-1);
+ *skipped = 1;
+ return sector_nr;
+ }
+
+ /* we update the metadata when there is more than 3Meg
+ * in the block range (that is rather arbitrary, should
+ * probably be time based) or when the data about to be
+ * copied would over-write the source of the data at
+ * the front of the range.
+ * i.e. one new_stripe forward from expand_progress new_maps
+ * to after where expand_lo old_maps to
+ */
+ writepos = conf->expand_progress +
+ conf->chunk_size/512*(conf->raid_disks-1);
+ sector_div(writepos, conf->raid_disks-1);
+ safepos = conf->expand_lo;
+ sector_div(safepos, conf->previous_raid_disks-1);
+ gap = conf->expand_progress - conf->expand_lo;
+
+ if (writepos >= safepos ||
+ gap > (conf->raid_disks-1)*3000*2 /*3Meg*/) {
+ /* Cannot proceed until we've updated the superblock... */
+ wait_event(conf->wait_for_overlap,
+ atomic_read(&conf->reshape_stripes)==0);
+ mddev->reshape_position = conf->expand_progress;
+ mddev->sb_dirty = 1;
+ md_wakeup_thread(mddev->thread);
+ wait_event(mddev->sb_wait, mddev->sb_dirty == 0 ||
+ kthread_should_stop());
+ spin_lock_irq(&conf->device_lock);
+ conf->expand_lo = mddev->reshape_position;
+ spin_unlock_irq(&conf->device_lock);
+ wake_up(&conf->wait_for_overlap);
+ }
+
+ for (i=0; i < conf->chunk_size/512; i+= STRIPE_SECTORS) {
+ int j;
+ int skipped = 0;
+ pd_idx = stripe_to_pdidx(sector_nr+i, conf, conf->raid_disks);
+ sh = get_active_stripe(conf, sector_nr+i,
+ conf->raid_disks, pd_idx, 0);
+ set_bit(STRIPE_EXPANDING, &sh->state);
+ atomic_inc(&conf->reshape_stripes);
+ /* If any of this stripe is beyond the end of the old
+ * array, then we need to zero those blocks
+ */
+ for (j=sh->disks; j--;) {
+ sector_t s;
+ if (j == sh->pd_idx)
+ continue;
+ s = compute_blocknr(sh, j);
+ if (s < (mddev->array_size<<1)) {
+ skipped = 1;
+ continue;
+ }
+ memset(page_address(sh->dev[j].page), 0, STRIPE_SIZE);
+ set_bit(R5_Expanded, &sh->dev[j].flags);
+ set_bit(R5_UPTODATE, &sh->dev[j].flags);
+ }
+ if (!skipped) {
+ set_bit(STRIPE_EXPAND_READY, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ }
+ release_stripe(sh);
+ }
+ spin_lock_irq(&conf->device_lock);
+ conf->expand_progress = (sector_nr + i)*(conf->raid_disks-1);
+ spin_unlock_irq(&conf->device_lock);
+ /* Ok, those stripe are ready. We can start scheduling
+ * reads on the source stripes.
+ * The source stripes are determined by mapping the first and last
+ * block on the destination stripes.
+ */
+ raid_disks = conf->previous_raid_disks;
+ data_disks = raid_disks - 1;
+ first_sector =
+ raid5_compute_sector(sector_nr*(conf->raid_disks-1),
+ raid_disks, data_disks,
+ &dd_idx, &pd_idx, conf);
+ last_sector =
+ raid5_compute_sector((sector_nr+conf->chunk_size/512)
+ *(conf->raid_disks-1) -1,
+ raid_disks, data_disks,
+ &dd_idx, &pd_idx, conf);
+ if (last_sector >= (mddev->size<<1))
+ last_sector = (mddev->size<<1)-1;
+ while (first_sector <= last_sector) {
+ pd_idx = stripe_to_pdidx(first_sector, conf, conf->previous_raid_disks);
+ sh = get_active_stripe(conf, first_sector,
+ conf->previous_raid_disks, pd_idx, 0);
+ set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ release_stripe(sh);
+ first_sector += STRIPE_SECTORS;
+ }
+ return conf->chunk_size>>9;
+}
+
/* FIXME go_faster isn't used */
-static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
+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;
struct stripe_head *sh;
- int sectors_per_chunk = conf->chunk_size >> 9;
- sector_t x;
- unsigned long stripe;
- int chunk_offset;
- int dd_idx, pd_idx;
- sector_t first_sector;
+ int pd_idx;
int raid_disks = conf->raid_disks;
- int data_disks = raid_disks-1;
+ int data_disks = raid_disks - conf->max_degraded;
sector_t max_sector = mddev->size << 1;
int sync_blocks;
+ int still_degraded = 0;
+ int i;
if (sector_nr >= max_sector) {
/* just being told to finish up .. nothing much to do */
unplug_slaves(mddev);
+ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
+ end_reshape(conf);
+ return 0;
+ }
if (mddev->curr_resync < max_sector) /* aborted */
bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
&sync_blocks, 1);
- else /* compelted sync */
+ else /* completed sync */
conf->fullsync = 0;
bitmap_close_sync(mddev->bitmap);
return 0;
}
- /* if there is 1 or more failed drives and we are trying
+
+ if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ return reshape_request(mddev, sector_nr, skipped);
+
+ /* if there is too many failed drives and we are trying
* to resync, then assert that we are finished, because there is
* nothing we can do.
*/
- if (mddev->degraded >= 1 && test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (mddev->degraded >= conf->max_degraded &&
+ test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
sector_t rv = (mddev->size << 1) - sector_nr;
*skipped = 1;
return rv;
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
- x = sector_nr;
- chunk_offset = sector_div(x, sectors_per_chunk);
- stripe = x;
- BUG_ON(x != stripe);
-
- first_sector = raid5_compute_sector((sector_t)stripe*data_disks*sectors_per_chunk
- + chunk_offset, raid_disks, data_disks, &dd_idx, &pd_idx, conf);
- sh = get_active_stripe(conf, sector_nr, pd_idx, 1);
+ pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
+ sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
if (sh == NULL) {
- sh = get_active_stripe(conf, sector_nr, pd_idx, 0);
+ sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 0);
/* make sure we don't swamp the stripe cache if someone else
- * is trying to get access
+ * is trying to get access
*/
schedule_timeout_uninterruptible(1);
}
- bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 0);
- spin_lock(&sh->lock);
+ /* Need to check if array will still be degraded after recovery/resync
+ * We don't need to check the 'failed' flag as when that gets set,
+ * recovery aborts.
+ */
+ for (i=0; i<mddev->raid_disks; i++)
+ if (conf->disks[i].rdev == NULL)
+ still_degraded = 1;
+
+ bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
+
+ spin_lock(&sh->lock);
set_bit(STRIPE_SYNCING, &sh->state);
clear_bit(STRIPE_INSYNC, &sh->state);
spin_unlock(&sh->lock);
- handle_stripe(sh);
+ handle_stripe(sh, NULL);
release_stripe(sh);
return STRIPE_SECTORS;
list_del_init(first);
atomic_inc(&sh->count);
- if (atomic_read(&sh->count)!= 1)
- BUG();
+ BUG_ON(atomic_read(&sh->count)!= 1);
spin_unlock_irq(&conf->device_lock);
handled++;
- handle_stripe(sh);
+ handle_stripe(sh, conf->spare_page);
release_stripe(sh);
spin_lock_irq(&conf->device_lock);
struct disk_info *disk;
struct list_head *tmp;
- if (mddev->level != 5 && mddev->level != 4) {
- printk(KERN_ERR "raid5: %s: raid level not set to 4/5 (%d)\n",
+ if (mddev->level != 5 && mddev->level != 4 && mddev->level != 6) {
+ printk(KERN_ERR "raid5: %s: raid level not set to 4/5/6 (%d)\n",
mdname(mddev), mddev->level);
return -EIO;
}
- mddev->private = kzalloc(sizeof (raid5_conf_t)
- + mddev->raid_disks * sizeof(struct disk_info),
- GFP_KERNEL);
+ if (mddev->reshape_position != MaxSector) {
+ /* Check that we can continue the reshape.
+ * Currently only disks can change, it must
+ * increase, and we must be past the point where
+ * a stripe over-writes itself
+ */
+ sector_t here_new, here_old;
+ int old_disks;
+
+ if (mddev->new_level != mddev->level ||
+ mddev->new_layout != mddev->layout ||
+ mddev->new_chunk != mddev->chunk_size) {
+ printk(KERN_ERR "raid5: %s: unsupported reshape required - aborting.\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ if (mddev->delta_disks <= 0) {
+ printk(KERN_ERR "raid5: %s: unsupported reshape (reduce disks) required - aborting.\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ old_disks = mddev->raid_disks - mddev->delta_disks;
+ /* reshape_position must be on a new-stripe boundary, and one
+ * further up in new geometry must map after here in old geometry.
+ */
+ here_new = mddev->reshape_position;
+ if (sector_div(here_new, (mddev->chunk_size>>9)*(mddev->raid_disks-1))) {
+ printk(KERN_ERR "raid5: reshape_position not on a stripe boundary\n");
+ return -EINVAL;
+ }
+ /* here_new is the stripe we will write to */
+ here_old = mddev->reshape_position;
+ sector_div(here_old, (mddev->chunk_size>>9)*(old_disks-1));
+ /* here_old is the first stripe that we might need to read from */
+ if (here_new >= here_old) {
+ /* Reading from the same stripe as writing to - bad */
+ printk(KERN_ERR "raid5: reshape_position too early for auto-recovery - aborting.\n");
+ return -EINVAL;
+ }
+ printk(KERN_INFO "raid5: reshape will continue\n");
+ /* OK, we should be able to continue; */
+ }
+
+
+ mddev->private = kzalloc(sizeof (raid5_conf_t), GFP_KERNEL);
if ((conf = mddev->private) == NULL)
goto abort;
+ if (mddev->reshape_position == MaxSector) {
+ conf->previous_raid_disks = conf->raid_disks = mddev->raid_disks;
+ } else {
+ conf->raid_disks = mddev->raid_disks;
+ conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks;
+ }
+
+ conf->disks = kzalloc(conf->raid_disks * sizeof(struct disk_info),
+ GFP_KERNEL);
+ if (!conf->disks)
+ goto abort;
conf->mddev = mddev;
if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
goto abort;
+ if (mddev->level == 6) {
+ conf->spare_page = alloc_page(GFP_KERNEL);
+ if (!conf->spare_page)
+ goto abort;
+ }
spin_lock_init(&conf->device_lock);
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
ITERATE_RDEV(mddev,rdev,tmp) {
raid_disk = rdev->raid_disk;
- if (raid_disk >= mddev->raid_disks
+ if (raid_disk >= conf->raid_disks
|| raid_disk < 0)
continue;
disk = conf->disks + raid_disk;
}
}
- conf->raid_disks = mddev->raid_disks;
/*
- * 0 for a fully functional array, 1 for a degraded array.
+ * 0 for a fully functional array, 1 or 2 for a degraded array.
*/
mddev->degraded = conf->failed_disks = conf->raid_disks - conf->working_disks;
conf->mddev = mddev;
conf->chunk_size = mddev->chunk_size;
conf->level = mddev->level;
+ if (conf->level == 6)
+ conf->max_degraded = 2;
+ else
+ conf->max_degraded = 1;
conf->algorithm = mddev->layout;
conf->max_nr_stripes = NR_STRIPES;
+ conf->expand_progress = mddev->reshape_position;
/* device size must be a multiple of chunk size */
mddev->size &= ~(mddev->chunk_size/1024 -1);
mddev->resync_max_sectors = mddev->size << 1;
+ if (conf->level == 6 && conf->raid_disks < 4) {
+ printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
+ mdname(mddev), conf->raid_disks);
+ goto abort;
+ }
if (!conf->chunk_size || conf->chunk_size % 4) {
printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
conf->chunk_size, mdname(mddev));
conf->algorithm, mdname(mddev));
goto abort;
}
- if (mddev->degraded > 1) {
+ if (mddev->degraded > conf->max_degraded) {
printk(KERN_ERR "raid5: not enough operational devices for %s"
" (%d/%d failed)\n",
mdname(mddev), conf->failed_disks, conf->raid_disks);
goto abort;
}
- if (mddev->degraded == 1 &&
+ if (mddev->degraded > 0 &&
mddev->recovery_cp != MaxSector) {
if (mddev->ok_start_degraded)
printk(KERN_WARNING
print_raid5_conf(conf);
+ if (conf->expand_progress != MaxSector) {
+ printk("...ok start reshape thread\n");
+ conf->expand_lo = conf->expand_progress;
+ atomic_set(&conf->reshape_stripes, 0);
+ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ mddev->sync_thread = md_register_thread(md_do_sync, mddev,
+ "%s_reshape");
+ /* FIXME if md_register_thread fails?? */
+ md_wakeup_thread(mddev->sync_thread);
+
+ }
+
/* read-ahead size must cover two whole stripes, which is
- * 2 * (n-1) * chunksize where 'n' is the number of raid devices
+ * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
*/
{
- int stripe = (mddev->raid_disks-1) * mddev->chunk_size
- / PAGE_SIZE;
+ int data_disks = conf->previous_raid_disks - conf->max_degraded;
+ int stripe = data_disks *
+ (mddev->chunk_size / PAGE_SIZE);
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
}
mddev->queue->unplug_fn = raid5_unplug_device;
mddev->queue->issue_flush_fn = raid5_issue_flush;
+ mddev->array_size = mddev->size * (conf->previous_raid_disks -
+ conf->max_degraded);
- mddev->array_size = mddev->size * (mddev->raid_disks - 1);
return 0;
abort:
if (conf) {
print_raid5_conf(conf);
+ safe_put_page(conf->spare_page);
+ kfree(conf->disks);
kfree(conf->stripe_hashtbl);
kfree(conf);
}
kfree(conf->stripe_hashtbl);
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
+ kfree(conf->disks);
kfree(conf);
mddev->private = NULL;
return 0;
}
#if RAID5_DEBUG
-static void print_sh (struct stripe_head *sh)
+static void print_sh (struct seq_file *seq, struct stripe_head *sh)
{
int i;
- printk("sh %llu, pd_idx %d, state %ld.\n",
- (unsigned long long)sh->sector, sh->pd_idx, sh->state);
- printk("sh %llu, count %d.\n",
- (unsigned long long)sh->sector, atomic_read(&sh->count));
- printk("sh %llu, ", (unsigned long long)sh->sector);
- for (i = 0; i < sh->raid_conf->raid_disks; i++) {
- printk("(cache%d: %p %ld) ",
- i, sh->dev[i].page, sh->dev[i].flags);
+ seq_printf(seq, "sh %llu, pd_idx %d, state %ld.\n",
+ (unsigned long long)sh->sector, sh->pd_idx, sh->state);
+ seq_printf(seq, "sh %llu, count %d.\n",
+ (unsigned long long)sh->sector, atomic_read(&sh->count));
+ seq_printf(seq, "sh %llu, ", (unsigned long long)sh->sector);
+ for (i = 0; i < sh->disks; i++) {
+ seq_printf(seq, "(cache%d: %p %ld) ",
+ i, sh->dev[i].page, sh->dev[i].flags);
}
- printk("\n");
+ seq_printf(seq, "\n");
}
-static void printall (raid5_conf_t *conf)
+static void printall (struct seq_file *seq, raid5_conf_t *conf)
{
struct stripe_head *sh;
struct hlist_node *hn;
hlist_for_each_entry(sh, hn, &conf->stripe_hashtbl[i], hash) {
if (sh->raid_conf != conf)
continue;
- print_sh(sh);
+ print_sh(seq, sh);
}
}
spin_unlock_irq(&conf->device_lock);
test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
#if RAID5_DEBUG
-#define D(x) \
- seq_printf (seq, "<"#x":%d>", atomic_read(&conf->x))
- printall(conf);
+ seq_printf (seq, "\n");
+ printall(seq, conf);
#endif
}
int disk;
struct disk_info *p;
- if (mddev->degraded > 1)
+ if (mddev->degraded > conf->max_degraded)
/* no point adding a device */
return 0;
/*
- * find the disk ...
+ * find the disk ... but prefer rdev->saved_raid_disk
+ * if possible.
*/
- for (disk=0; disk < mddev->raid_disks; disk++)
+ if (rdev->saved_raid_disk >= 0 &&
+ conf->disks[rdev->saved_raid_disk].rdev == NULL)
+ disk = rdev->saved_raid_disk;
+ else
+ disk = 0;
+ for ( ; disk < conf->raid_disks; disk++)
if ((p=conf->disks + disk)->rdev == NULL) {
clear_bit(In_sync, &rdev->flags);
rdev->raid_disk = disk;
* any io in the removed space completes, but it hardly seems
* worth it.
*/
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+
sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
- mddev->array_size = (sectors * (mddev->raid_disks-1))>>1;
+ mddev->array_size = (sectors * (mddev->raid_disks-conf->max_degraded))>>1;
set_capacity(mddev->gendisk, mddev->array_size << 1);
mddev->changed = 1;
if (sectors/2 > mddev->size && mddev->recovery_cp == MaxSector) {
return 0;
}
+#ifdef CONFIG_MD_RAID5_RESHAPE
+static int raid5_check_reshape(mddev_t *mddev)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ int err;
+
+ if (mddev->delta_disks < 0 ||
+ mddev->new_level != mddev->level)
+ return -EINVAL; /* Cannot shrink array or change level yet */
+ if (mddev->delta_disks == 0)
+ return 0; /* nothing to do */
+
+ /* Can only proceed if there are plenty of stripe_heads.
+ * We need a minimum of one full stripe,, and for sensible progress
+ * it is best to have about 4 times that.
+ * If we require 4 times, then the default 256 4K stripe_heads will
+ * allow for chunk sizes up to 256K, which is probably OK.
+ * If the chunk size is greater, user-space should request more
+ * stripe_heads first.
+ */
+ if ((mddev->chunk_size / STRIPE_SIZE) * 4 > conf->max_nr_stripes ||
+ (mddev->new_chunk / STRIPE_SIZE) * 4 > conf->max_nr_stripes) {
+ printk(KERN_WARNING "raid5: reshape: not enough stripes. Needed %lu\n",
+ (mddev->chunk_size / STRIPE_SIZE)*4);
+ return -ENOSPC;
+ }
+
+ err = resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
+ if (err)
+ return err;
+
+ /* looks like we might be able to manage this */
+ return 0;
+}
+
+static int raid5_start_reshape(mddev_t *mddev)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ mdk_rdev_t *rdev;
+ struct list_head *rtmp;
+ int spares = 0;
+ int added_devices = 0;
+
+ if (mddev->degraded ||
+ test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ return -EBUSY;
+
+ ITERATE_RDEV(mddev, rdev, rtmp)
+ if (rdev->raid_disk < 0 &&
+ !test_bit(Faulty, &rdev->flags))
+ spares++;
+
+ if (spares < mddev->delta_disks-1)
+ /* Not enough devices even to make a degraded array
+ * of that size
+ */
+ return -EINVAL;
+
+ atomic_set(&conf->reshape_stripes, 0);
+ spin_lock_irq(&conf->device_lock);
+ conf->previous_raid_disks = conf->raid_disks;
+ conf->raid_disks += mddev->delta_disks;
+ conf->expand_progress = 0;
+ conf->expand_lo = 0;
+ spin_unlock_irq(&conf->device_lock);
+
+ /* Add some new drives, as many as will fit.
+ * We know there are enough to make the newly sized array work.
+ */
+ ITERATE_RDEV(mddev, rdev, rtmp)
+ if (rdev->raid_disk < 0 &&
+ !test_bit(Faulty, &rdev->flags)) {
+ if (raid5_add_disk(mddev, rdev)) {
+ char nm[20];
+ set_bit(In_sync, &rdev->flags);
+ conf->working_disks++;
+ added_devices++;
+ rdev->recovery_offset = 0;
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+ } else
+ break;
+ }
+
+ mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) - added_devices;
+ mddev->raid_disks = conf->raid_disks;
+ mddev->reshape_position = 0;
+ mddev->sb_dirty = 1;
+
+ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ mddev->sync_thread = md_register_thread(md_do_sync, mddev,
+ "%s_reshape");
+ if (!mddev->sync_thread) {
+ mddev->recovery = 0;
+ spin_lock_irq(&conf->device_lock);
+ mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
+ conf->expand_progress = MaxSector;
+ spin_unlock_irq(&conf->device_lock);
+ return -EAGAIN;
+ }
+ md_wakeup_thread(mddev->sync_thread);
+ md_new_event(mddev);
+ return 0;
+}
+#endif
+
+static void end_reshape(raid5_conf_t *conf)
+{
+ struct block_device *bdev;
+
+ if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
+ conf->mddev->array_size = conf->mddev->size * (conf->raid_disks-1);
+ set_capacity(conf->mddev->gendisk, conf->mddev->array_size << 1);
+ conf->mddev->changed = 1;
+
+ bdev = bdget_disk(conf->mddev->gendisk, 0);
+ if (bdev) {
+ mutex_lock(&bdev->bd_inode->i_mutex);
+ i_size_write(bdev->bd_inode, conf->mddev->array_size << 10);
+ mutex_unlock(&bdev->bd_inode->i_mutex);
+ bdput(bdev);
+ }
+ spin_lock_irq(&conf->device_lock);
+ conf->expand_progress = MaxSector;
+ spin_unlock_irq(&conf->device_lock);
+ conf->mddev->reshape_position = MaxSector;
+
+ /* read-ahead size must cover two whole stripes, which is
+ * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
+ */
+ {
+ int data_disks = conf->previous_raid_disks - conf->max_degraded;
+ int stripe = data_disks *
+ (conf->mddev->chunk_size / PAGE_SIZE);
+ if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
+ conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+ }
+ }
+}
+
static void raid5_quiesce(mddev_t *mddev, int state)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
switch(state) {
+ case 2: /* resume for a suspend */
+ wake_up(&conf->wait_for_overlap);
+ break;
+
case 1: /* stop all writes */
spin_lock_irq(&conf->device_lock);
conf->quiesce = 1;
spin_lock_irq(&conf->device_lock);
conf->quiesce = 0;
wake_up(&conf->wait_for_stripe);
+ wake_up(&conf->wait_for_overlap);
spin_unlock_irq(&conf->device_lock);
break;
}
}
+static struct mdk_personality raid6_personality =
+{
+ .name = "raid6",
+ .level = 6,
+ .owner = THIS_MODULE,
+ .make_request = make_request,
+ .run = run,
+ .stop = stop,
+ .status = status,
+ .error_handler = error,
+ .hot_add_disk = raid5_add_disk,
+ .hot_remove_disk= raid5_remove_disk,
+ .spare_active = raid5_spare_active,
+ .sync_request = sync_request,
+ .resize = raid5_resize,
+ .quiesce = raid5_quiesce,
+};
static struct mdk_personality raid5_personality =
{
.name = "raid5",
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
+#ifdef CONFIG_MD_RAID5_RESHAPE
+ .check_reshape = raid5_check_reshape,
+ .start_reshape = raid5_start_reshape,
+#endif
.quiesce = raid5_quiesce,
};
static int __init raid5_init(void)
{
+ int e;
+
+ e = raid6_select_algo();
+ if ( e )
+ return e;
+ register_md_personality(&raid6_personality);
register_md_personality(&raid5_personality);
register_md_personality(&raid4_personality);
return 0;
static void raid5_exit(void)
{
+ unregister_md_personality(&raid6_personality);
unregister_md_personality(&raid5_personality);
unregister_md_personality(&raid4_personality);
}
MODULE_ALIAS("md-raid4");
MODULE_ALIAS("md-level-5");
MODULE_ALIAS("md-level-4");
+MODULE_ALIAS("md-personality-8"); /* RAID6 */
+MODULE_ALIAS("md-raid6");
+MODULE_ALIAS("md-level-6");
+
+/* This used to be two separate modules, they were: */
+MODULE_ALIAS("raid5");
+MODULE_ALIAS("raid6");
projects / linux.git / blobdiff