Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 56d99121 authored by NeilBrown's avatar NeilBrown
Browse files

md: simplify raid10 read_balance 



raid10 read balance has two different loop for looking through
possible devices to chose the best.
Collapse those into one loop and generally make the code more
readable.

Signed-off-by: default avatarNeilBrown <neilb@suse.de>
parent 8258c532

drivers/md/raid10.c

+44 −66
Original line number Original line Diff line number Diff line
@@ -488,13 +488,19 @@ static int raid10_mergeable_bvec(struct request_queue *q, 
static int read_balance(conf_t *conf, r10bio_t *r10_bio)

static int read_balance(conf_t *conf, r10bio_t *r10_bio)

{

{

	const sector_t this_sector = r10_bio->sector;

	const sector_t this_sector = r10_bio->sector;

	int disk, slot, nslot;

	int disk, slot;

	const int sectors = r10_bio->sectors;

	const int sectors = r10_bio->sectors;

	sector_t new_distance, current_distance;

	sector_t new_distance, best_dist;

	mdk_rdev_t *rdev;

	mdk_rdev_t *rdev;

	int do_balance;

	int best_slot;





	raid10_find_phys(conf, r10_bio);

	raid10_find_phys(conf, r10_bio);

	rcu_read_lock();

	rcu_read_lock();

retry:

	best_slot = -1;

	best_dist = MaxSector;

	do_balance = 1;

	/*

	/*

	 * Check if we can balance. We can balance on the whole

	 * Check if we can balance. We can balance on the whole

	 * device if no resync is going on (recovery is ok), or below

	 * device if no resync is going on (recovery is ok), or below
@@ -502,86 +508,58 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio) 
	 * above the resync window.

	 * above the resync window.

	 */

	 */

	if (conf->mddev->recovery_cp < MaxSector

	if (conf->mddev->recovery_cp < MaxSector

	    && (this_sector + sectors >= conf->next_resync)) {

	    && (this_sector + sectors >= conf->next_resync))

		/* make sure that disk is operational */

		do_balance = 0;

		slot = 0;

		disk = r10_bio->devs[slot].devnum;



		while ((rdev = rcu_dereference(conf->mirrors[disk].rdev)) == NULL ||

		       r10_bio->devs[slot].bio == IO_BLOCKED ||

		       !test_bit(In_sync, &rdev->flags)) {

			slot++;

			if (slot == conf->copies) {

				slot = 0;

				disk = -1;

				break;

			}

			disk = r10_bio->devs[slot].devnum;

		}

		goto rb_out;

	}







	for (slot = 0; slot < conf->copies ; slot++) {

	/* make sure the disk is operational */

		if (r10_bio->devs[slot].bio == IO_BLOCKED)

	slot = 0;

			continue;

	disk = r10_bio->devs[slot].devnum;

	while ((rdev=rcu_dereference(conf->mirrors[disk].rdev)) == NULL ||

	       r10_bio->devs[slot].bio == IO_BLOCKED ||

	       !test_bit(In_sync, &rdev->flags)) {

		slot ++;

		if (slot == conf->copies) {

			disk = -1;

			goto rb_out;

		}

		disk = r10_bio->devs[slot].devnum;

		disk = r10_bio->devs[slot].devnum;

	}

		rdev = rcu_dereference(conf->mirrors[disk].rdev);



		if (rdev == NULL)



	current_distance = abs(r10_bio->devs[slot].addr -

			       conf->mirrors[disk].head_position);



	/* Find the disk whose head is closest,

	 * or - for far > 1 - find the closest to partition beginning */



	for (nslot = slot; nslot < conf->copies; nslot++) {

		int ndisk = r10_bio->devs[nslot].devnum;





		if ((rdev=rcu_dereference(conf->mirrors[ndisk].rdev)) == NULL ||

		    r10_bio->devs[nslot].bio == IO_BLOCKED ||

		    !test_bit(In_sync, &rdev->flags))

			continue;

			continue;

		if (!test_bit(In_sync, &rdev->flags))

			continue;



		if (!do_balance)

			break;





		/* This optimisation is debatable, and completely destroys

		/* This optimisation is debatable, and completely destroys

		 * sequential read speed for 'far copies' arrays.  So only

		 * sequential read speed for 'far copies' arrays.  So only

		 * keep it for 'near' arrays, and review those later.

		 * keep it for 'near' arrays, and review those later.

		 */

		 */

		if (conf->near_copies > 1 && !atomic_read(&rdev->nr_pending)) {

		if (conf->near_copies > 1 && !atomic_read(&rdev->nr_pending))

			disk = ndisk;

			slot = nslot;

			break;

			break;

		}





		/* for far > 1 always use the lowest address */

		/* for far > 1 always use the lowest address */

		if (conf->far_copies > 1)

		if (conf->far_copies > 1)

			new_distance = r10_bio->devs[nslot].addr;

			new_distance = r10_bio->devs[slot].addr;

		else

		else

			new_distance = abs(r10_bio->devs[nslot].addr -

			new_distance = abs(r10_bio->devs[slot].addr -

					   conf->mirrors[ndisk].head_position);

					   conf->mirrors[disk].head_position);

		if (new_distance < current_distance) {

		if (new_distance < best_dist) {

			current_distance = new_distance;

			best_dist = new_distance;

			disk = ndisk;

			best_slot = slot;

			slot = nslot;

		}

		}

	}

	}

	if (slot == conf->copies)

		slot = best_slot;





rb_out:

	if (slot >= 0) {

		disk = r10_bio->devs[slot].devnum;

		rdev = rcu_dereference(conf->mirrors[disk].rdev);

		if (!rdev)

			goto retry;

		atomic_inc(&rdev->nr_pending);

		if (test_bit(Faulty, &rdev->flags)) {

			/* Cannot risk returning a device that failed

			 * before we inc'ed nr_pending

			 */

			rdev_dec_pending(rdev, conf->mddev);

			goto retry;

		}

		r10_bio->read_slot = slot;

		r10_bio->read_slot = slot;

/*	conf->next_seq_sect = this_sector + sectors;*/

	} else



	if (disk >= 0 && (rdev=rcu_dereference(conf->mirrors[disk].rdev))!= NULL)

		atomic_inc(&conf->mirrors[disk].rdev->nr_pending);

	else

		disk = -1;

		disk = -1;

	rcu_read_unlock();

	rcu_read_unlock();