raid10.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,781 行 · 第 1/4 页

		return sectors_skipped;
	}
	if (chunks_skipped >= conf->raid_disks) {
		/* if there has been nothing to do on any drive,
		 * then there is nothing to do at all..
		 */
		sector_t sec = max_sector - sector_nr;
		md_done_sync(mddev, sec, 1);
		return sec + sectors_skipped;
	}

	/* make sure whole request will fit in a chunk - if chunks
	 * are meaningful
	 */
	if (conf->near_copies < conf->raid_disks &&
	    max_sector > (sector_nr | conf->chunk_mask))
		max_sector = (sector_nr | conf->chunk_mask) + 1;
	/*
	 * If there is non-resync activity waiting for us then
	 * put in a delay to throttle resync.
	 */
	if (!go_faster && waitqueue_active(&conf->wait_resume))
		schedule_timeout(HZ);
	device_barrier(conf, sector_nr + RESYNC_SECTORS);

	/* Again, very different code for resync and recovery.
	 * Both must result in an r10bio with a list of bios that
	 * have bi_end_io, bi_sector, bi_bdev set,
	 * and bi_private set to the r10bio.
	 * For recovery, we may actually create several r10bios
	 * with 2 bios in each, that correspond to the bios in the main one.
	 * In this case, the subordinate r10bios link back through a
	 * borrowed master_bio pointer, and the counter in the master
	 * includes a ref from each subordinate.
	 */
	/* First, we decide what to do and set ->bi_end_io
	 * To end_sync_read if we want to read, and
	 * end_sync_write if we will want to write.
	 */

	if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
		/* recovery... the complicated one */
		int i, j, k;
		r10_bio = NULL;

		for (i=0 ; i<conf->raid_disks; i++)
			if (conf->mirrors[i].rdev &&
			    !conf->mirrors[i].rdev->in_sync) {
				/* want to reconstruct this device */
				r10bio_t *rb2 = r10_bio;

				r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
				spin_lock_irq(&conf->resync_lock);
				conf->nr_pending++;
				if (rb2) conf->barrier++;
				spin_unlock_irq(&conf->resync_lock);
				atomic_set(&r10_bio->remaining, 0);

				r10_bio->master_bio = (struct bio*)rb2;
				if (rb2)
					atomic_inc(&rb2->remaining);
				r10_bio->mddev = mddev;
				set_bit(R10BIO_IsRecover, &r10_bio->state);
				r10_bio->sector = raid10_find_virt(conf, sector_nr, i);
				raid10_find_phys(conf, r10_bio);
				for (j=0; j<conf->copies;j++) {
					int d = r10_bio->devs[j].devnum;
					if (conf->mirrors[d].rdev &&
					    conf->mirrors[d].rdev->in_sync) {
						/* This is where we read from */
						bio = r10_bio->devs[0].bio;
						bio->bi_next = biolist;
						biolist = bio;
						bio->bi_private = r10_bio;
						bio->bi_end_io = end_sync_read;
						bio->bi_rw = 0;
						bio->bi_sector = r10_bio->devs[j].addr +
							conf->mirrors[d].rdev->data_offset;
						bio->bi_bdev = conf->mirrors[d].rdev->bdev;
						atomic_inc(&conf->mirrors[d].rdev->nr_pending);
						atomic_inc(&r10_bio->remaining);
						/* and we write to 'i' */

						for (k=0; k<conf->copies; k++)
							if (r10_bio->devs[k].devnum == i)
								break;
						bio = r10_bio->devs[1].bio;
						bio->bi_next = biolist;
						biolist = bio;
						bio->bi_private = r10_bio;
						bio->bi_end_io = end_sync_write;
						bio->bi_rw = 1;
						bio->bi_sector = r10_bio->devs[k].addr +
							conf->mirrors[i].rdev->data_offset;
						bio->bi_bdev = conf->mirrors[i].rdev->bdev;

						r10_bio->devs[0].devnum = d;
						r10_bio->devs[1].devnum = i;

						break;
					}
				}
				if (j == conf->copies) {
					BUG();
				}
			}
		if (biolist == NULL) {
			while (r10_bio) {
				r10bio_t *rb2 = r10_bio;
				r10_bio = (r10bio_t*) rb2->master_bio;
				rb2->master_bio = NULL;
				put_buf(rb2);
			}
			goto giveup;
		}
	} else {
		/* resync. Schedule a read for every block at this virt offset */
		int count = 0;
		r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);

		spin_lock_irq(&conf->resync_lock);
		conf->nr_pending++;
		spin_unlock_irq(&conf->resync_lock);

		r10_bio->mddev = mddev;
		atomic_set(&r10_bio->remaining, 0);

		r10_bio->master_bio = NULL;
		r10_bio->sector = sector_nr;
		set_bit(R10BIO_IsSync, &r10_bio->state);
		raid10_find_phys(conf, r10_bio);
		r10_bio->sectors = (sector_nr | conf->chunk_mask) - sector_nr +1;
		spin_lock_irq(&conf->device_lock);
		for (i=0; i<conf->copies; i++) {
			int d = r10_bio->devs[i].devnum;
			bio = r10_bio->devs[i].bio;
			bio->bi_end_io = NULL;
			if (conf->mirrors[d].rdev == NULL ||
			    conf->mirrors[d].rdev->faulty)
				continue;
			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
			atomic_inc(&r10_bio->remaining);
			bio->bi_next = biolist;
			biolist = bio;
			bio->bi_private = r10_bio;
			bio->bi_end_io = end_sync_read;
			bio->bi_rw = 0;
			bio->bi_sector = r10_bio->devs[i].addr +
				conf->mirrors[d].rdev->data_offset;
			bio->bi_bdev = conf->mirrors[d].rdev->bdev;
			count++;
		}
		spin_unlock_irq(&conf->device_lock);
		if (count < 2) {
			for (i=0; i<conf->copies; i++) {
				int d = r10_bio->devs[i].devnum;
				if (r10_bio->devs[i].bio->bi_end_io)
					atomic_dec(&conf->mirrors[d].rdev->nr_pending);
			}
			put_buf(r10_bio);
			goto giveup;
		}
	}

	for (bio = biolist; bio ; bio=bio->bi_next) {

		bio->bi_flags &= ~(BIO_POOL_MASK - 1);
		if (bio->bi_end_io)
			bio->bi_flags |= 1 << BIO_UPTODATE;
		bio->bi_vcnt = 0;
		bio->bi_idx = 0;
		bio->bi_phys_segments = 0;
		bio->bi_hw_segments = 0;
		bio->bi_size = 0;
	}

	nr_sectors = 0;
	do {
		struct page *page;
		int len = PAGE_SIZE;
		disk = 0;
		if (sector_nr + (len>>9) > max_sector)
			len = (max_sector - sector_nr) << 9;
		if (len == 0)
			break;
		for (bio= biolist ; bio ; bio=bio->bi_next) {
			page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
			if (bio_add_page(bio, page, len, 0) == 0) {
				/* stop here */
				struct bio *bio2;
				bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
				for (bio2 = biolist; bio2 && bio2 != bio; bio2 = bio2->bi_next) {
					/* remove last page from this bio */
					bio2->bi_vcnt--;
					bio2->bi_size -= len;
					bio2->bi_flags &= ~(1<< BIO_SEG_VALID);
				}
				goto bio_full;
			}
			disk = i;
		}
		nr_sectors += len>>9;
		sector_nr += len>>9;
	} while (biolist->bi_vcnt < RESYNC_PAGES);
 bio_full:
	r10_bio->sectors = nr_sectors;

	while (biolist) {
		bio = biolist;
		biolist = biolist->bi_next;

		bio->bi_next = NULL;
		r10_bio = bio->bi_private;
		r10_bio->sectors = nr_sectors;

		if (bio->bi_end_io == end_sync_read) {
			md_sync_acct(bio->bi_bdev, nr_sectors);
			generic_make_request(bio);
		}
	}

	return nr_sectors;
 giveup:
	/* There is nowhere to write, so all non-sync
	 * drives must be failed, so try the next chunk...
	 */
	{
	int sec = max_sector - sector_nr;
	sectors_skipped += sec;
	chunks_skipped ++;
	sector_nr = max_sector;
	md_done_sync(mddev, sec, 1);
	goto skipped;
	}
}

static int run(mddev_t *mddev)
{
	conf_t *conf;
	int i, disk_idx;
	mirror_info_t *disk;
	mdk_rdev_t *rdev;
	struct list_head *tmp;
	int nc, fc;
	sector_t stride, size;

	if (mddev->level != 10) {
		printk(KERN_ERR "raid10: %s: raid level not set correctly... (%d)\n",
		       mdname(mddev), mddev->level);
		goto out;
	}
	nc = mddev->layout & 255;
	fc = (mddev->layout >> 8) & 255;
	if ((nc*fc) <2 || (nc*fc) > mddev->raid_disks ||
	    (mddev->layout >> 16)) {
		printk(KERN_ERR "raid10: %s: unsupported raid10 layout: 0x%8x\n",
		       mdname(mddev), mddev->layout);
		goto out;
	}
	/*
	 * copy the already verified devices into our private RAID10
	 * bookkeeping area. [whatever we allocate in run(),
	 * should be freed in stop()]
	 */
	conf = kmalloc(sizeof(conf_t), GFP_KERNEL);
	mddev->private = conf;
	if (!conf) {
		printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
			mdname(mddev));
		goto out;
	}
	memset(conf, 0, sizeof(*conf));
	conf->mirrors = kmalloc(sizeof(struct mirror_info)*mddev->raid_disks,
				 GFP_KERNEL);
	if (!conf->mirrors) {
		printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
		       mdname(mddev));
		goto out_free_conf;
	}
	memset(conf->mirrors, 0, sizeof(struct mirror_info)*mddev->raid_disks);

	conf->near_copies = nc;
	conf->far_copies = fc;
	conf->copies = nc*fc;
	conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
	conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
	stride = mddev->size >> (conf->chunk_shift-1);
	sector_div(stride, fc);
	conf->stride = stride << conf->chunk_shift;

	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
						r10bio_pool_free, conf);
	if (!conf->r10bio_pool) {
		printk(KERN_ERR "raid10: couldn't allocate memory for %s\n",
			mdname(mddev));
		goto out_free_conf;
	}
	mddev->queue->unplug_fn = raid10_unplug;

	mddev->queue->issue_flush_fn = raid10_issue_flush;

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

		disk->rdev = rdev;

		blk_queue_stack_limits(mddev->queue,
				       rdev->bdev->bd_disk->queue);
		/* as we don't honour merge_bvec_fn, we must never risk
		 * violating it, so limit ->max_sector to one PAGE, as
		 * a one page request is never in violation.
		 */
		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
			mddev->queue->max_sectors = (PAGE_SIZE>>9);

		disk->head_position = 0;
		if (!rdev->faulty && rdev->in_sync)
			conf->working_disks++;
	}
	conf->raid_disks = mddev->raid_disks;
	conf->mddev = mddev;
	conf->device_lock = SPIN_LOCK_UNLOCKED;
	INIT_LIST_HEAD(&conf->retry_list);

	conf->resync_lock = SPIN_LOCK_UNLOCKED;
	init_waitqueue_head(&conf->wait_idle);
	init_waitqueue_head(&conf->wait_resume);

	if (!conf->working_disks) {
		printk(KERN_ERR "raid10: no operational mirrors for %s\n",
			mdname(mddev));
		goto out_free_conf;
	}

	mddev->degraded = 0;
	for (i = 0; i < conf->raid_disks; i++) {

		disk = conf->mirrors + i;

		if (!disk->rdev) {
			disk->head_position = 0;
			mddev->degraded++;
		}
	}


	mddev->thread = md_register_thread(raid10d, mddev, "%s_raid10");
	if (!mddev->thread) {
		printk(KERN_ERR
		       "raid10: couldn't allocate thread for %s\n",
		       mdname(mddev));
		goto out_free_conf;
	}

	printk(KERN_INFO
		"raid10: raid set %s active with %d out of %d devices\n",
		mdname(mddev), mddev->raid_disks - mddev->degraded,
		mddev->raid_disks);
	/*
	 * Ok, everything is just fine now
	 */
	size = conf->stride * conf->raid_disks;
	sector_div(size, conf->near_copies);
	mddev->array_size = size/2;
	mddev->resync_max_sectors = size;

	/* Calculate max read-ahead size.
	 * We need to readahead at least twice a whole stripe....
	 * maybe...
	 */
	{
		int stripe = conf->raid_disks * mddev->chunk_size / PAGE_CACHE_SIZE;
		stripe /= conf->near_copies;
		if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
	}

	if (conf->near_copies < mddev->raid_disks)
		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
	return 0;

out_free_conf:
	if (conf->r10bio_pool)
		mempool_destroy(conf->r10bio_pool);
	if (conf->mirrors)
		kfree(conf->mirrors);
	kfree(conf);
	mddev->private = NULL;
out:
	return -EIO;
}

static int stop(mddev_t *mddev)
{
	conf_t *conf = mddev_to_conf(mddev);

	md_unregister_thread(mddev->thread);
	mddev->thread = NULL;
	if (conf->r10bio_pool)
		mempool_destroy(conf->r10bio_pool);
	if (conf->mirrors)
		kfree(conf->mirrors);
	kfree(conf);
	mddev->private = NULL;
	return 0;
}


static mdk_personality_t raid10_personality =
{
	.name		= "raid10",
	.owner		= THIS_MODULE,
	.make_request	= make_request,
	.run		= run,
	.stop		= stop,
	.status		= status,
	.error_handler	= error,
	.hot_add_disk	= raid10_add_disk,
	.hot_remove_disk= raid10_remove_disk,
	.spare_active	= raid10_spare_active,
	.sync_request	= sync_request,
};

static int __init raid_init(void)
{
	return register_md_personality(RAID10, &raid10_personality);
}

static void raid_exit(void)
{
	unregister_md_personality(RAID10);
}

module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-9"); /* RAID10 */