raid1.c

来自「linux 内核源代码」· C语言 代码 · 共 2,200 行 · 第 1/4 页

static void end_sync_read(struct bio *bio, int error)
{
	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
	int i;

	for (i=r1_bio->mddev->raid_disks; i--; )
		if (r1_bio->bios[i] == bio)
			break;
	BUG_ON(i < 0);
	update_head_pos(i, r1_bio);
	/*
	 * we have read a block, now it needs to be re-written,
	 * or re-read if the read failed.
	 * We don't do much here, just schedule handling by raid1d
	 */
	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
		set_bit(R1BIO_Uptodate, &r1_bio->state);

	if (atomic_dec_and_test(&r1_bio->remaining))
		reschedule_retry(r1_bio);
}

static void end_sync_write(struct bio *bio, int error)
{
	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
	mddev_t *mddev = r1_bio->mddev;
	conf_t *conf = mddev_to_conf(mddev);
	int i;
	int mirror=0;

	for (i = 0; i < conf->raid_disks; i++)
		if (r1_bio->bios[i] == bio) {
			mirror = i;
			break;
		}
	if (!uptodate) {
		int sync_blocks = 0;
		sector_t s = r1_bio->sector;
		long sectors_to_go = r1_bio->sectors;
		/* make sure these bits doesn't get cleared. */
		do {
			bitmap_end_sync(mddev->bitmap, s,
					&sync_blocks, 1);
			s += sync_blocks;
			sectors_to_go -= sync_blocks;
		} while (sectors_to_go > 0);
		md_error(mddev, conf->mirrors[mirror].rdev);
	}

	update_head_pos(mirror, r1_bio);

	if (atomic_dec_and_test(&r1_bio->remaining)) {
		md_done_sync(mddev, r1_bio->sectors, uptodate);
		put_buf(r1_bio);
	}
}

static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
{
	conf_t *conf = mddev_to_conf(mddev);
	int i;
	int disks = conf->raid_disks;
	struct bio *bio, *wbio;

	bio = r1_bio->bios[r1_bio->read_disk];


	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
		/* We have read all readable devices.  If we haven't
		 * got the block, then there is no hope left.
		 * If we have, then we want to do a comparison
		 * and skip the write if everything is the same.
		 * If any blocks failed to read, then we need to
		 * attempt an over-write
		 */
		int primary;
		if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
			for (i=0; i<mddev->raid_disks; i++)
				if (r1_bio->bios[i]->bi_end_io == end_sync_read)
					md_error(mddev, conf->mirrors[i].rdev);

			md_done_sync(mddev, r1_bio->sectors, 1);
			put_buf(r1_bio);
			return;
		}
		for (primary=0; primary<mddev->raid_disks; primary++)
			if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
			    test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
				r1_bio->bios[primary]->bi_end_io = NULL;
				rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
				break;
			}
		r1_bio->read_disk = primary;
		for (i=0; i<mddev->raid_disks; i++)
			if (r1_bio->bios[i]->bi_end_io == end_sync_read) {
				int j;
				int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
				struct bio *pbio = r1_bio->bios[primary];
				struct bio *sbio = r1_bio->bios[i];

				if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) {
					for (j = vcnt; j-- ; ) {
						struct page *p, *s;
						p = pbio->bi_io_vec[j].bv_page;
						s = sbio->bi_io_vec[j].bv_page;
						if (memcmp(page_address(p),
							   page_address(s),
							   PAGE_SIZE))
							break;
					}
				} else
					j = 0;
				if (j >= 0)
					mddev->resync_mismatches += r1_bio->sectors;
				if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
					      && test_bit(BIO_UPTODATE, &sbio->bi_flags))) {
					sbio->bi_end_io = NULL;
					rdev_dec_pending(conf->mirrors[i].rdev, mddev);
				} else {
					/* fixup the bio for reuse */
					sbio->bi_vcnt = vcnt;
					sbio->bi_size = r1_bio->sectors << 9;
					sbio->bi_idx = 0;
					sbio->bi_phys_segments = 0;
					sbio->bi_hw_segments = 0;
					sbio->bi_hw_front_size = 0;
					sbio->bi_hw_back_size = 0;
					sbio->bi_flags &= ~(BIO_POOL_MASK - 1);
					sbio->bi_flags |= 1 << BIO_UPTODATE;
					sbio->bi_next = NULL;
					sbio->bi_sector = r1_bio->sector +
						conf->mirrors[i].rdev->data_offset;
					sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
					for (j = 0; j < vcnt ; j++)
						memcpy(page_address(sbio->bi_io_vec[j].bv_page),
						       page_address(pbio->bi_io_vec[j].bv_page),
						       PAGE_SIZE);

				}
			}
	}
	if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
		/* ouch - failed to read all of that.
		 * Try some synchronous reads of other devices to get
		 * good data, much like with normal read errors.  Only
		 * read into the pages we already have so we don't
		 * need to re-issue the read request.
		 * We don't need to freeze the array, because being in an
		 * active sync request, there is no normal IO, and
		 * no overlapping syncs.
		 */
		sector_t sect = r1_bio->sector;
		int sectors = r1_bio->sectors;
		int idx = 0;

		while(sectors) {
			int s = sectors;
			int d = r1_bio->read_disk;
			int success = 0;
			mdk_rdev_t *rdev;

			if (s > (PAGE_SIZE>>9))
				s = PAGE_SIZE >> 9;
			do {
				if (r1_bio->bios[d]->bi_end_io == end_sync_read) {
					/* No rcu protection needed here devices
					 * can only be removed when no resync is
					 * active, and resync is currently active
					 */
					rdev = conf->mirrors[d].rdev;
					if (sync_page_io(rdev->bdev,
							 sect + rdev->data_offset,
							 s<<9,
							 bio->bi_io_vec[idx].bv_page,
							 READ)) {
						success = 1;
						break;
					}
				}
				d++;
				if (d == conf->raid_disks)
					d = 0;
			} while (!success && d != r1_bio->read_disk);

			if (success) {
				int start = d;
				/* write it back and re-read */
				set_bit(R1BIO_Uptodate, &r1_bio->state);
				while (d != r1_bio->read_disk) {
					if (d == 0)
						d = conf->raid_disks;
					d--;
					if (r1_bio->bios[d]->bi_end_io != end_sync_read)
						continue;
					rdev = conf->mirrors[d].rdev;
					atomic_add(s, &rdev->corrected_errors);
					if (sync_page_io(rdev->bdev,
							 sect + rdev->data_offset,
							 s<<9,
							 bio->bi_io_vec[idx].bv_page,
							 WRITE) == 0)
						md_error(mddev, rdev);
				}
				d = start;
				while (d != r1_bio->read_disk) {
					if (d == 0)
						d = conf->raid_disks;
					d--;
					if (r1_bio->bios[d]->bi_end_io != end_sync_read)
						continue;
					rdev = conf->mirrors[d].rdev;
					if (sync_page_io(rdev->bdev,
							 sect + rdev->data_offset,
							 s<<9,
							 bio->bi_io_vec[idx].bv_page,
							 READ) == 0)
						md_error(mddev, rdev);
				}
			} else {
				char b[BDEVNAME_SIZE];
				/* Cannot read from anywhere, array is toast */
				md_error(mddev, conf->mirrors[r1_bio->read_disk].rdev);
				printk(KERN_ALERT "raid1: %s: unrecoverable I/O read error"
				       " for block %llu\n",
				       bdevname(bio->bi_bdev,b),
				       (unsigned long long)r1_bio->sector);
				md_done_sync(mddev, r1_bio->sectors, 0);
				put_buf(r1_bio);
				return;
			}
			sectors -= s;
			sect += s;
			idx ++;
		}
	}

	/*
	 * schedule writes
	 */
	atomic_set(&r1_bio->remaining, 1);
	for (i = 0; i < disks ; i++) {
		wbio = r1_bio->bios[i];
		if (wbio->bi_end_io == NULL ||
		    (wbio->bi_end_io == end_sync_read &&
		     (i == r1_bio->read_disk ||
		      !test_bit(MD_RECOVERY_SYNC, &mddev->recovery))))
			continue;

		wbio->bi_rw = WRITE;
		wbio->bi_end_io = end_sync_write;
		atomic_inc(&r1_bio->remaining);
		md_sync_acct(conf->mirrors[i].rdev->bdev, wbio->bi_size >> 9);

		generic_make_request(wbio);
	}

	if (atomic_dec_and_test(&r1_bio->remaining)) {
		/* if we're here, all write(s) have completed, so clean up */
		md_done_sync(mddev, r1_bio->sectors, 1);
		put_buf(r1_bio);
	}
}

/*
 * This is a kernel thread which:
 *
 *	1.	Retries failed read operations on working mirrors.
 *	2.	Updates the raid superblock when problems encounter.
 *	3.	Performs writes following reads for array syncronising.
 */

static void fix_read_error(conf_t *conf, int read_disk,
			   sector_t sect, int sectors)
{
	mddev_t *mddev = conf->mddev;
	while(sectors) {
		int s = sectors;
		int d = read_disk;
		int success = 0;
		int start;
		mdk_rdev_t *rdev;

		if (s > (PAGE_SIZE>>9))
			s = PAGE_SIZE >> 9;

		do {
			/* Note: no rcu protection needed here
			 * as this is synchronous in the raid1d thread
			 * which is the thread that might remove
			 * a device.  If raid1d ever becomes multi-threaded....
			 */
			rdev = conf->mirrors[d].rdev;
			if (rdev &&
			    test_bit(In_sync, &rdev->flags) &&
			    sync_page_io(rdev->bdev,
					 sect + rdev->data_offset,
					 s<<9,
					 conf->tmppage, READ))
				success = 1;
			else {
				d++;
				if (d == conf->raid_disks)
					d = 0;
			}
		} while (!success && d != read_disk);

		if (!success) {
			/* Cannot read from anywhere -- bye bye array */
			md_error(mddev, conf->mirrors[read_disk].rdev);
			break;
		}
		/* write it back and re-read */
		start = d;
		while (d != read_disk) {
			if (d==0)
				d = conf->raid_disks;
			d--;
			rdev = conf->mirrors[d].rdev;
			if (rdev &&
			    test_bit(In_sync, &rdev->flags)) {
				if (sync_page_io(rdev->bdev,
						 sect + rdev->data_offset,
						 s<<9, conf->tmppage, WRITE)
				    == 0)
					/* Well, this device is dead */
					md_error(mddev, rdev);
			}
		}
		d = start;
		while (d != read_disk) {
			char b[BDEVNAME_SIZE];
			if (d==0)
				d = conf->raid_disks;
			d--;
			rdev = conf->mirrors[d].rdev;
			if (rdev &&
			    test_bit(In_sync, &rdev->flags)) {
				if (sync_page_io(rdev->bdev,
						 sect + rdev->data_offset,
						 s<<9, conf->tmppage, READ)
				    == 0)
					/* Well, this device is dead */
					md_error(mddev, rdev);
				else {
					atomic_add(s, &rdev->corrected_errors);
					printk(KERN_INFO
					       "raid1:%s: read error corrected "
					       "(%d sectors at %llu on %s)\n",
					       mdname(mddev), s,
					       (unsigned long long)(sect +
					           rdev->data_offset),
					       bdevname(rdev->bdev, b));
				}
			}
		}
		sectors -= s;
		sect += s;
	}
}

static void raid1d(mddev_t *mddev)
{
	r1bio_t *r1_bio;
	struct bio *bio;
	unsigned long flags;
	conf_t *conf = mddev_to_conf(mddev);
	struct list_head *head = &conf->retry_list;
	int unplug=0;
	mdk_rdev_t *rdev;

	md_check_recovery(mddev);
	
	for (;;) {
		char b[BDEVNAME_SIZE];
		spin_lock_irqsave(&conf->device_lock, flags);

		if (conf->pending_bio_list.head) {
			bio = bio_list_get(&conf->pending_bio_list);
			blk_remove_plug(mddev->queue);
			spin_unlock_irqrestore(&conf->device_lock, flags);
			/* flush any pending bitmap writes to disk before proceeding w/ I/O */
			bitmap_unplug(mddev->bitmap);

			while (bio) { /* submit pending writes */
				struct bio *next = bio->bi_next;
				bio->bi_next = NULL;
				generic_make_request(bio);
				bio = next;
			}
			unplug = 1;

			continue;
		}

		if (list_empty(head))
			break;
		r1_bio = list_entry(head->prev, r1bio_t, retry_list);
		list_del(head->prev);
		conf->nr_queued--;
		spin_unlock_irqrestore(&conf->device_lock, flags);

		mddev = r1_bio->mddev;
		conf = mddev_to_conf(mddev);
		if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
			sync_request_write(mddev, r1_bio);
			unplug = 1;
		} else if (test_bit(R1BIO_BarrierRetry, &r1_bio->state)) {
			/* some requests in the r1bio were BIO_RW_BARRIER
			 * requests which failed with -EOPNOTSUPP.  Hohumm..
			 * Better resubmit without the barrier.
			 * We know which devices to resubmit for, because
			 * all others have had their bios[] entry cleared.
			 * We already have a nr_pending reference on these rdevs.
			 */
			int i;
			const int do_sync = bio_sync(r1_bio->master_bio);
			clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
			clear_bit(R1BIO_Barrier, &r1_bio->state);
			for (i=0; i < conf->raid_disks; i++)
				if (r1_bio->bios[i])
					atomic_inc(&r1_bio->remaining);
			for (i=0; i < conf->raid_disks; i++)
				if (r1_bio->bios[i]) {
					struct bio_vec *bvec;
					int j;

					bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
					/* copy pages from the failed bio, as
					 * this might be a write-behind device */
					__bio_for_each_segment(bvec, bio, j, 0)
						bvec->bv_page = bio_iovec_idx(r1_bio->bios[i], j)->bv_page;
					bio_put(r1_bio->bios[i]);
					bio->bi_sector = r1_bio->sector +
						conf->mirrors[i].rdev->data_offset;
					bio->bi_bdev = conf->mirrors[i].rdev->bdev;
					bio->bi_end_io = raid1_end_write_request;
					bio->bi_rw = WRITE | do_sync;
					bio->bi_private = r1_bio;
					r1_bio->bios[i] = bio;
					generic_make_request(bio);
				}
		} else {
			int disk;

			/* we got a read error. Maybe the drive is bad.  Maybe just
			 * the block and we can fix it.
			 * We freeze all other IO, and try reading the block from
			 * other devices.  When we find one, we re-write
			 * and check it that fixes the read error.
			 * This is all done synchronously while the array is
			 * frozen
			 */
			if (mddev->ro == 0) {
				freeze_array(conf);
				fix_read_error(conf, r1_bio->read_disk,
					       r1_bio->sector,
					       r1_bio->sectors);
				unfreeze_array(conf);
			}

			bio = r1_bio->bios[r1_bio->read_disk];
			if ((disk=read_balance(conf, r1_bio)) == -1) {
				printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
				       " read error for block %llu\n",
				       bdevname(bio->bi_bdev,b),
				       (unsigned long long)r1_bio->sector);
				raid_end_bio_io(r1_bio);
			} else {
				const int do_sync = bio_sync(r1_bio->master_bio);
				r1_bio->bios[r1_bio->read_disk] =
					mddev->ro ? IO_BLOCKED : NULL;
				r1_bio->read_disk = disk;
				bio_put(bio);
				bio = bio_clone(r1_bio->master_bio, GFP_NOIO);
				r1_bio->bios[r1_bio->read_disk] = bio;
				rdev = conf->mirrors[disk].rdev;
				if (printk_ratelimit())
					printk(KERN_ERR "raid1: %s: redirecting sector %llu to"
					       " another mirror\n",
					       bdevname(rdev->bdev,b),
					       (unsigned long long)r1_bio->sector);
				bio->bi_sector = r1_bio->sector + rdev->data_offset;
				bio->bi_bdev = rdev->bdev;
				bio->bi_end_io = raid1_end_read_request;
				bio->bi_rw = READ | do_sync;
				bio->bi_private = r1_bio;
				unplug = 1;
				generic_make_request(bio);
			}
		}
	}
	spin_unlock_irqrestore(&conf->device_lock, flags);
	if (unplug)
		unplug_slaves(mddev);
}


static int init_resync(conf_t *conf)
{
	int buffs;

	buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
	BUG_ON(conf->r1buf_pool);
	conf->r1buf_pool = mempool_create(buffs, r1buf_pool_alloc, r1buf_pool_free,
					  conf->poolinfo);
	if (!conf->r1buf_pool)
		return -ENOMEM;
	conf->next_resync = 0;
	return 0;
}

/*
 * perform a "sync" on one "block"
 *
 * We need to make sure that no normal I/O request - particularly write
 * requests - conflict with active sync requests.
 *
 * This is achieved by tracking pending requests and a 'barrier' concept
 * that can be installed to exclude normal IO requests.
 */

static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
	conf_t *conf = mddev_to_conf(mddev);
	r1bio_t *r1_bio;
	struct bio *bio;
	sector_t max_sector, nr_sectors;
	int disk = -1;
	int i;
	int wonly = -1;
	int write_targets = 0, read_targets = 0;
	int sync_blocks;
	int still_degraded = 0;

	if (!conf->r1buf_pool)
	{
/*
		printk("sync start - bitmap %p\n", mddev->bitmap);
*/
		if (init_resync(conf))
			return 0;
	}

	max_sector = mddev->size << 1;
	if (sector_nr >= max_sector) {
		/* If we aborted, we need to abort the
		 * sync on the 'current' bitmap chunk (there will
		 * only be one in raid1 resync.
		 * We can find the current addess in mddev->curr_resync