raid5.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,920 行 · 第 1/4 页

	spin_unlock_irq(&conf->device_lock);
	return 0;
}

/* FIXME go_faster isn't used */
static int sync_request (mddev_t *mddev, sector_t sector_nr, 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 raid_disks = conf->raid_disks;
	int data_disks = raid_disks-1;

	if (sector_nr >= mddev->size <<1) {
		/* just being told to finish up .. nothing much to do */
		unplug_slaves(mddev);
		return 0;
	}

	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);
	if (sh == NULL) {
		sh = get_active_stripe(conf, sector_nr, pd_idx, 0);
		/* make sure we don't swamp the stripe cache if someone else
		 * is trying to get access 
		 */
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(1);
	}
	spin_lock(&sh->lock);	
	set_bit(STRIPE_SYNCING, &sh->state);
	clear_bit(STRIPE_INSYNC, &sh->state);
	spin_unlock(&sh->lock);

	handle_stripe(sh);
	release_stripe(sh);

	return STRIPE_SECTORS;
}

/*
 * This is our raid5 kernel thread.
 *
 * We scan the hash table for stripes which can be handled now.
 * During the scan, completed stripes are saved for us by the interrupt
 * handler, so that they will not have to wait for our next wakeup.
 */
static void raid5d (mddev_t *mddev)
{
	struct stripe_head *sh;
	raid5_conf_t *conf = mddev_to_conf(mddev);
	int handled;

	PRINTK("+++ raid5d active\n");

	md_check_recovery(mddev);
	md_handle_safemode(mddev);

	handled = 0;
	spin_lock_irq(&conf->device_lock);
	while (1) {
		struct list_head *first;

		if (list_empty(&conf->handle_list) &&
		    atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
		    !blk_queue_plugged(mddev->queue) &&
		    !list_empty(&conf->delayed_list))
			raid5_activate_delayed(conf);

		if (list_empty(&conf->handle_list))
			break;

		first = conf->handle_list.next;
		sh = list_entry(first, struct stripe_head, lru);

		list_del_init(first);
		atomic_inc(&sh->count);
		if (atomic_read(&sh->count)!= 1)
			BUG();
		spin_unlock_irq(&conf->device_lock);
		
		handled++;
		handle_stripe(sh);
		release_stripe(sh);

		spin_lock_irq(&conf->device_lock);
	}
	PRINTK("%d stripes handled\n", handled);

	spin_unlock_irq(&conf->device_lock);

	unplug_slaves(mddev);

	PRINTK("--- raid5d inactive\n");
}

static int run (mddev_t *mddev)
{
	raid5_conf_t *conf;
	int raid_disk, memory;
	mdk_rdev_t *rdev;
	struct disk_info *disk;
	struct list_head *tmp;

	if (mddev->level != 5 && mddev->level != 4) {
		printk("raid5: %s: raid level not set to 4/5 (%d)\n", mdname(mddev), mddev->level);
		return -EIO;
	}

	mddev->private = kmalloc (sizeof (raid5_conf_t)
				  + mddev->raid_disks * sizeof(struct disk_info),
				  GFP_KERNEL);
	if ((conf = mddev->private) == NULL)
		goto abort;
	memset (conf, 0, sizeof (*conf) + mddev->raid_disks * sizeof(struct disk_info) );
	conf->mddev = mddev;

	if ((conf->stripe_hashtbl = (struct stripe_head **) __get_free_pages(GFP_ATOMIC, HASH_PAGES_ORDER)) == NULL)
		goto abort;
	memset(conf->stripe_hashtbl, 0, HASH_PAGES * PAGE_SIZE);

	conf->device_lock = SPIN_LOCK_UNLOCKED;
	init_waitqueue_head(&conf->wait_for_stripe);
	INIT_LIST_HEAD(&conf->handle_list);
	INIT_LIST_HEAD(&conf->delayed_list);
	INIT_LIST_HEAD(&conf->inactive_list);
	atomic_set(&conf->active_stripes, 0);
	atomic_set(&conf->preread_active_stripes, 0);

	mddev->queue->unplug_fn = raid5_unplug_device;
	mddev->queue->issue_flush_fn = raid5_issue_flush;

	PRINTK("raid5: run(%s) called.\n", mdname(mddev));

	ITERATE_RDEV(mddev,rdev,tmp) {
		raid_disk = rdev->raid_disk;
		if (raid_disk >= mddev->raid_disks
		    || raid_disk < 0)
			continue;
		disk = conf->disks + raid_disk;

		disk->rdev = rdev;

		if (rdev->in_sync) {
			char b[BDEVNAME_SIZE];
			printk(KERN_INFO "raid5: device %s operational as raid"
				" disk %d\n", bdevname(rdev->bdev,b),
				raid_disk);
			conf->working_disks++;
		}
	}

	conf->raid_disks = mddev->raid_disks;
	/*
	 * 0 for a fully functional array, 1 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;
	conf->algorithm = mddev->layout;
	conf->max_nr_stripes = NR_STRIPES;

	/* device size must be a multiple of chunk size */
	mddev->size &= ~(mddev->chunk_size/1024 -1);

	if (!conf->chunk_size || conf->chunk_size % 4) {
		printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
			conf->chunk_size, mdname(mddev));
		goto abort;
	}
	if (conf->algorithm > ALGORITHM_RIGHT_SYMMETRIC) {
		printk(KERN_ERR 
			"raid5: unsupported parity algorithm %d for %s\n",
			conf->algorithm, mdname(mddev));
		goto abort;
	}
	if (mddev->degraded > 1) {
		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 &&
	    mddev->recovery_cp != MaxSector) {
		printk(KERN_ERR 
			"raid5: cannot start dirty degraded array for %s\n",
			mdname(mddev));
		goto abort;
	}

	{
		mddev->thread = md_register_thread(raid5d, mddev, "%s_raid5");
		if (!mddev->thread) {
			printk(KERN_ERR 
				"raid5: couldn't allocate thread for %s\n",
				mdname(mddev));
			goto abort;
		}
	}
memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
		 conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
	if (grow_stripes(conf, conf->max_nr_stripes)) {
		printk(KERN_ERR 
			"raid5: couldn't allocate %dkB for buffers\n", memory);
		shrink_stripes(conf);
		md_unregister_thread(mddev->thread);
		goto abort;
	} else
		printk(KERN_INFO "raid5: allocated %dkB for %s\n",
			memory, mdname(mddev));

	if (mddev->degraded == 0)
		printk("raid5: raid level %d set %s active with %d out of %d"
			" devices, algorithm %d\n", conf->level, mdname(mddev), 
			mddev->raid_disks-mddev->degraded, mddev->raid_disks,
			conf->algorithm);
	else
		printk(KERN_ALERT "raid5: raid level %d set %s active with %d"
			" out of %d devices, algorithm %d\n", conf->level,
			mdname(mddev), mddev->raid_disks - mddev->degraded,
			mddev->raid_disks, conf->algorithm);

	print_raid5_conf(conf);

	/* read-ahead size must cover two whole stripes, which is
	 * 2 * (n-1) * chunksize where 'n' is the number of raid devices
	 */
	{
		int stripe = (mddev->raid_disks-1) * mddev->chunk_size
			/ PAGE_CACHE_SIZE;
		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
	}

	/* Ok, everything is just fine now */
	mddev->array_size =  mddev->size * (mddev->raid_disks - 1);
	return 0;
abort:
	if (conf) {
		print_raid5_conf(conf);
		if (conf->stripe_hashtbl)
			free_pages((unsigned long) conf->stripe_hashtbl,
							HASH_PAGES_ORDER);
		kfree(conf);
	}
	mddev->private = NULL;
	printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev));
	return -EIO;
}



static int stop (mddev_t *mddev)
{
	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;

	md_unregister_thread(mddev->thread);
	mddev->thread = NULL;
	shrink_stripes(conf);
	free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
	kfree(conf);
	mddev->private = NULL;
	return 0;
}

#if RAID5_DEBUG
static void print_sh (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);
	}
	printk("\n");
}

static void printall (raid5_conf_t *conf)
{
	struct stripe_head *sh;
	int i;

	spin_lock_irq(&conf->device_lock);
	for (i = 0; i < NR_HASH; i++) {
		sh = conf->stripe_hashtbl[i];
		for (; sh; sh = sh->hash_next) {
			if (sh->raid_conf != conf)
				continue;
			print_sh(sh);
		}
	}
	spin_unlock_irq(&conf->device_lock);
}
#endif

static void status (struct seq_file *seq, mddev_t *mddev)
{
	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
	int i;

	seq_printf (seq, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
	seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->working_disks);
	for (i = 0; i < conf->raid_disks; i++)
		seq_printf (seq, "%s",
			       conf->disks[i].rdev &&
			       conf->disks[i].rdev->in_sync ? "U" : "_");
	seq_printf (seq, "]");
#if RAID5_DEBUG
#define D(x) \
	seq_printf (seq, "<"#x":%d>", atomic_read(&conf->x))
	printall(conf);
#endif
}

static void print_raid5_conf (raid5_conf_t *conf)
{
	int i;
	struct disk_info *tmp;

	printk("RAID5 conf printout:\n");
	if (!conf) {
		printk("(conf==NULL)\n");
		return;
	}
	printk(" --- rd:%d wd:%d fd:%d\n", conf->raid_disks,
		 conf->working_disks, conf->failed_disks);

	for (i = 0; i < conf->raid_disks; i++) {
		char b[BDEVNAME_SIZE];
		tmp = conf->disks + i;
		if (tmp->rdev)
		printk(" disk %d, o:%d, dev:%s\n",
			i, !tmp->rdev->faulty,
			bdevname(tmp->rdev->bdev,b));
	}
}

static int raid5_spare_active(mddev_t *mddev)
{
	int i;
	raid5_conf_t *conf = mddev->private;
	struct disk_info *tmp;

	spin_lock_irq(&conf->device_lock);
	for (i = 0; i < conf->raid_disks; i++) {
		tmp = conf->disks + i;
		if (tmp->rdev
		    && !tmp->rdev->faulty
		    && !tmp->rdev->in_sync) {
			mddev->degraded--;
			conf->failed_disks--;
			conf->working_disks++;
			tmp->rdev->in_sync = 1;
		}
	}
	spin_unlock_irq(&conf->device_lock);
	print_raid5_conf(conf);
	return 0;
}

static int raid5_remove_disk(mddev_t *mddev, int number)
{
	raid5_conf_t *conf = mddev->private;
	int err = 1;
	struct disk_info *p = conf->disks + number;

	print_raid5_conf(conf);
	spin_lock_irq(&conf->device_lock);

	if (p->rdev) {
		if (p->rdev->in_sync || 
		    atomic_read(&p->rdev->nr_pending)) {
			err = -EBUSY;
			goto abort;
		}
		p->rdev = NULL;
		err = 0;
	}
	if (err)
		MD_BUG();
abort:
	spin_unlock_irq(&conf->device_lock);
	print_raid5_conf(conf);
	return err;
}

static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
	raid5_conf_t *conf = mddev->private;
	int found = 0;
	int disk;
	struct disk_info *p;

	spin_lock_irq(&conf->device_lock);
	/*
	 * find the disk ...
	 */
	for (disk=0; disk < mddev->raid_disks; disk++)
		if ((p=conf->disks + disk)->rdev == NULL) {
			p->rdev = rdev;
			rdev->in_sync = 0;
			rdev->raid_disk = disk;
			found = 1;
			break;
		}
	spin_unlock_irq(&conf->device_lock);
	print_raid5_conf(conf);
	return found;
}

static int raid5_resize(mddev_t *mddev, sector_t sectors)
{
	/* no resync is happening, and there is enough space
	 * on all devices, so we can resize.
	 * We need to make sure resync covers any new space.
	 * If the array is shrinking we should possibly wait until
	 * any io in the removed space completes, but it hardly seems
	 * worth it.
	 */
	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
	mddev->array_size = (sectors * (mddev->raid_disks-1))>>1;
	set_capacity(mddev->gendisk, mddev->array_size << 1);
	mddev->changed = 1;
	if (sectors/2  > mddev->size && mddev->recovery_cp == MaxSector) {
		mddev->recovery_cp = mddev->size << 1;
		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	}
	mddev->size = sectors /2;
	return 0;
}

static mdk_personality_t raid5_personality=
{
	.name		= "raid5",
	.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,
};

static int __init raid5_init (void)
{
	return register_md_personality (RAID5, &raid5_personality);
}

static void raid5_exit (void)
{
	unregister_md_personality (RAID5);
}

module_init(raid5_init);
module_exit(raid5_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-4"); /* RAID5 */