Commit d787be40 authored by NeilBrown's avatar NeilBrown Committed by Shaohua Li
Browse files

md: reduce the number of synchronize_rcu() calls when multiple devices fail. 



Every time a device is removed with ->hot_remove_disk() a synchronize_rcu() call is made
which can delay several milliseconds in some case.
If lots of devices fail at once - as could happen with a large RAID10 where one set
of devices are removed all at once - these delays can add up to be very inconcenient.

As failure is not reversible we can check for that first, setting a
separate flag if it is found, and then all synchronize_rcu() once for
all the flagged devices.  Then ->hot_remove_disk() function can skip the
synchronize_rcu() step if the flag is set.

fix build error(Shaohua)
Signed-off-by: default avatarNeilBrown <neilb@suse.com>
Signed-off-by: default avatarShaohua Li <shli@fb.com>
parent f5b67ae8

drivers/md/md.c

+26 −3
Original line number Diff line number Diff line
@@ -8180,15 +8180,34 @@ static int remove_and_add_spares(struct mddev *mddev, 
	struct md_rdev *rdev;

	int spares = 0;

	int removed = 0;

	bool remove_some = false;



	rdev_for_each(rdev, mddev)

	rdev_for_each(rdev, mddev) {

		if ((this == NULL || rdev == this) &&

		    rdev->raid_disk >= 0 &&

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

		    (test_bit(Faulty, &rdev->flags) ||

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

		    atomic_read(&rdev->nr_pending)==0) {

			/* Faulty non-Blocked devices with nr_pending == 0

			 * never get nr_pending incremented,

			 * never get Faulty cleared, and never get Blocked set.

			 * So we can synchronize_rcu now rather than once per device

			 */

			remove_some = true;

			set_bit(RemoveSynchronized, &rdev->flags);

		}

	}



	if (remove_some)

		synchronize_rcu();

	rdev_for_each(rdev, mddev) {

		if ((this == NULL || rdev == this) &&

		    rdev->raid_disk >= 0 &&

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

		    ((test_bit(RemoveSynchronized, &rdev->flags) ||

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

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

		    atomic_read(&rdev->nr_pending)==0) {

		    atomic_read(&rdev->nr_pending)==0)) {

			if (mddev->pers->hot_remove_disk(

				    mddev, rdev) == 0) {

				sysfs_unlink_rdev(mddev, rdev);
@@ -8196,6 +8215,10 @@ static int remove_and_add_spares(struct mddev *mddev, 
				removed++;

			}

		}

		if (remove_some && test_bit(RemoveSynchronized, &rdev->flags))

			clear_bit(RemoveSynchronized, &rdev->flags);

	}



	if (removed && mddev->kobj.sd)

		sysfs_notify(&mddev->kobj, NULL, "degraded");

drivers/md/md.h

+5 −0
Original line number Diff line number Diff line
@@ -163,6 +163,11 @@ enum flag_bits { 
				 * than other devices in the array

				 */

	ClusterRemove,

	RemoveSynchronized,	/* synchronize_rcu() was called after

				 * this device was known to be faulty,

				 * so it is safe to remove without

				 * another synchronize_rcu() call.

				 */

};



static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,

drivers/md/multipath.c

+8 −6
Original line number Diff line number Diff line
@@ -298,6 +298,7 @@ static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev) 
			goto abort;

		}

		p->rdev = NULL;

		if (!test_bit(RemoveSynchronized, &rdev->flags)) {

			synchronize_rcu();

			if (atomic_read(&rdev->nr_pending)) {

				/* lost the race, try later */
@@ -305,6 +306,7 @@ static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev) 
				p->rdev = rdev;

				goto abort;

			}

		}

		err = md_integrity_register(mddev);

	}

abort:

drivers/md/raid1.c

+10 −7
Original line number Diff line number Diff line
@@ -1656,13 +1656,16 @@ static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev) 
			goto abort;

		}

		p->rdev = NULL;

		if (!test_bit(RemoveSynchronized, &rdev->flags)) {

			synchronize_rcu();

			if (atomic_read(&rdev->nr_pending)) {

				/* lost the race, try later */

				err = -EBUSY;

				p->rdev = rdev;

				goto abort;

		} else if (conf->mirrors[conf->raid_disks + number].rdev) {

			}

		}

		if (conf->mirrors[conf->raid_disks + number].rdev) {

			/* We just removed a device that is being replaced.

			 * Move down the replacement.  We drain all IO before

			 * doing this to avoid confusion.

drivers/md/raid10.c

+11 −8
Original line number Diff line number Diff line
@@ -1766,7 +1766,7 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) 
		err = -EBUSY;

		goto abort;

	}

	/* Only remove faulty devices if recovery

	/* Only remove non-faulty devices if recovery

	 * is not possible.

	 */

	if (!test_bit(Faulty, &rdev->flags) &&
@@ -1778,13 +1778,16 @@ static int raid10_remove_disk(struct mddev *mddev, struct md_rdev *rdev) 
		goto abort;

	}

	*rdevp = NULL;

	if (!test_bit(RemoveSynchronized, &rdev->flags)) {

		synchronize_rcu();

		if (atomic_read(&rdev->nr_pending)) {

			/* lost the race, try later */

			err = -EBUSY;

			*rdevp = rdev;

			goto abort;

	} else if (p->replacement) {

		}

	}

	if (p->replacement) {

		/* We must have just cleared 'rdev' */

		p->rdev = p->replacement;

		clear_bit(Replacement, &p->replacement->flags);

CRA Git | Maintained and supported by SUSTech CRA and CCSE