A kernel patch needed to add a spare to an active external-metadata arraydevel

1 files changed, 199 insertions, 0 deletions

diff --git a/kernel-patch-2.6.25 b/kernel-patch-2.6.25
new file mode 100644
index 00000000..d42bf314
--- /dev/null
+++ b/kernel-patch-2.6.25
@@ -0,0 +1,199 @@
+Status: ok
+
+Support adding a spare to a live md array with external metadata.
+
+i.e. extend the 'md/dev-XXX/slot' attribute so that you can
+tell a device to fill an vacant slot in an and md array.
+
+
+Signed-off-by: Neil Brown <neilb@suse.de>
+
+### Diffstat output
+ ./drivers/md/md.c        |   44 ++++++++++++++++++++++++++++++++++++++++----
+ ./drivers/md/multipath.c |    7 ++++++-
+ ./drivers/md/raid1.c     |    7 ++++++-
+ ./drivers/md/raid10.c    |   10 ++++++++--
+ ./drivers/md/raid5.c     |   10 ++++++++--
+ 5 files changed, 68 insertions(+), 10 deletions(-)
+
+diff .prev/drivers/md/md.c ./drivers/md/md.c
+--- .prev/drivers/md/md.c	2008-06-05 09:19:56.000000000 +1000
++++ ./drivers/md/md.c	2008-06-10 10:41:21.000000000 +1000
+@@ -1932,7 +1932,7 @@ slot_store(mdk_rdev_t *rdev, const char 
+ 		slot = -1;
+ 	else if (e==buf || (*e && *e!= '\n'))
+ 		return -EINVAL;
+-	if (rdev->mddev->pers) {
++	if (rdev->mddev->pers && slot == -1) {
+ 		/* Setting 'slot' on an active array requires also
+ 		 * updating the 'rd%d' link, and communicating
+ 		 * with the personality with ->hot_*_disk.
+@@ -1940,8 +1940,6 @@ slot_store(mdk_rdev_t *rdev, const char 
+ 		 * failed/spare devices.  This normally happens automatically,
+ 		 * but not when the metadata is externally managed.
+ 		 */
+-		if (slot != -1)
+-			return -EBUSY;
+ 		if (rdev->raid_disk == -1)
+ 			return -EEXIST;
+ 		/* personality does all needed checks */
+@@ -1955,6 +1953,44 @@ slot_store(mdk_rdev_t *rdev, const char 
+ 		sysfs_remove_link(&rdev->mddev->kobj, nm);
+ 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
+ 		md_wakeup_thread(rdev->mddev->thread);
++	} else if (rdev->mddev->pers) {
++		mdk_rdev_t *rdev2;
++		struct list_head *tmp;
++		/* Activating a spare .. or possibly reactivating
++		 * if we every get bitmaps working here.
++		 */
++
++		if (rdev->raid_disk != -1)
++			return -EBUSY;
++
++		if (rdev->mddev->pers->hot_add_disk == NULL)
++			return -EINVAL;
++
++		rdev_for_each(rdev2, tmp, rdev->mddev)
++			if (rdev2->raid_disk == slot)
++				return -EEXIST;
++
++		rdev->raid_disk = slot;
++		if (test_bit(In_sync, &rdev->flags))
++			rdev->saved_raid_disk = slot;
++		else
++			rdev->saved_raid_disk = -1;
++		err = rdev->mddev->pers->
++			hot_add_disk(rdev->mddev, rdev);
++		if (err != 1) {
++			rdev->raid_disk = -1;
++			if (err == 0)
++				return -EEXIST;
++			return err;
++		}
++		sprintf(nm, "rd%d", rdev->raid_disk);
++		if (sysfs_create_link(&rdev->mddev->kobj, &rdev->kobj, nm))
++			printk(KERN_WARNING
++			       "md: cannot register "
++			       "%s for %s\n",
++			       nm, mdname(rdev->mddev));
++
++		/* don't wakeup anyone, leave that to userspace. */
+ 	} else {
+ 		if (slot >= rdev->mddev->raid_disks)
+ 			return -ENOSPC;
+@@ -4205,7 +4241,7 @@ static int add_new_disk(mddev_t * mddev,
+ 			super_types[mddev->major_version].
+ 				validate_super(mddev, rdev);
+ 			err = mddev->pers->hot_add_disk(mddev, rdev);
+-			if (err)
++			if (err < 0)
+ 				unbind_rdev_from_array(rdev);
+ 		}
+ 		if (err)
+
+diff .prev/drivers/md/multipath.c ./drivers/md/multipath.c
+--- .prev/drivers/md/multipath.c	2008-05-30 14:49:31.000000000 +1000
++++ ./drivers/md/multipath.c	2008-06-10 10:35:03.000000000 +1000
+@@ -284,10 +284,15 @@ static int multipath_add_disk(mddev_t *m
+ 	int found = 0;
+ 	int path;
+ 	struct multipath_info *p;
++	int first = 0;
++	int last = mddev->raid_disks - 1;
++
++	if (rdev->raid_disk >= 0)
++		first = last = rdev->raid_disk;
+ 
+ 	print_multipath_conf(conf);
+ 
+-	for (path=0; path<mddev->raid_disks; path++) 
++	for (path = first; path <= last; path++)
+ 		if ((p=conf->multipaths+path)->rdev == NULL) {
+ 			q = rdev->bdev->bd_disk->queue;
+ 			blk_queue_stack_limits(mddev->queue, q);
+
+diff .prev/drivers/md/raid10.c ./drivers/md/raid10.c
+--- .prev/drivers/md/raid10.c	2008-05-30 14:49:31.000000000 +1000
++++ ./drivers/md/raid10.c	2008-06-10 10:28:53.000000000 +1000
+@@ -1116,6 +1116,8 @@ static int raid10_add_disk(mddev_t *mdde
+ 	int found = 0;
+ 	int mirror;
+ 	mirror_info_t *p;
++	int first = 0;
++	int last = mddev->raid_disks;
+ 
+ 	if (mddev->recovery_cp < MaxSector)
+ 		/* only hot-add to in-sync arrays, as recovery is
+@@ -1125,12 +1127,16 @@ static int raid10_add_disk(mddev_t *mdde
+ 	if (!enough(conf))
+ 		return 0;
+ 
++	if (rdev->raid_disk)
++		first = last = rdev->raid_disk;
++
+ 	if (rdev->saved_raid_disk >= 0 &&
++	    rdev->saved_raid_disk >= first &&
+ 	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
+ 		mirror = rdev->saved_raid_disk;
+ 	else
+-		mirror = 0;
+-	for ( ; mirror < mddev->raid_disks; mirror++)
++		mirror = first;
++	for ( ; mirror <= last ; mirror++)
+ 		if ( !(p=conf->mirrors+mirror)->rdev) {
+ 
+ 			blk_queue_stack_limits(mddev->queue,
+
+diff .prev/drivers/md/raid1.c ./drivers/md/raid1.c
+--- .prev/drivers/md/raid1.c	2008-05-30 14:49:31.000000000 +1000
++++ ./drivers/md/raid1.c	2008-06-10 10:41:00.000000000 +1000
+@@ -1103,8 +1103,13 @@ static int raid1_add_disk(mddev_t *mddev
+ 	int found = 0;
+ 	int mirror = 0;
+ 	mirror_info_t *p;
++	int first = 0;
++	int last = mddev->raid_disks - 1;
+ 
+-	for (mirror=0; mirror < mddev->raid_disks; mirror++)
++	if (rdev->raid_disk >= 0)
++		first = last = rdev->raid_disk;
++
++	for (mirror = first; mirror <= last; mirror++)
+ 		if ( !(p=conf->mirrors+mirror)->rdev) {
+ 
+ 			blk_queue_stack_limits(mddev->queue,
+
+diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
+--- .prev/drivers/md/raid5.c	2008-05-30 14:49:35.000000000 +1000
++++ ./drivers/md/raid5.c	2008-06-10 10:27:51.000000000 +1000
+@@ -4399,21 +4399,27 @@ static int raid5_add_disk(mddev_t *mddev
+ 	int found = 0;
+ 	int disk;
+ 	struct disk_info *p;
++	int first = 0;
++	int last = conf->raid_disks - 1;
+ 
+ 	if (mddev->degraded > conf->max_degraded)
+ 		/* no point adding a device */
+ 		return 0;
+ 
++	if (rdev->raid_disk >= 0)
++		first = last = rdev->raid_disk;
++
+ 	/*
+ 	 * find the disk ... but prefer rdev->saved_raid_disk
+ 	 * if possible.
+ 	 */
+ 	if (rdev->saved_raid_disk >= 0 &&
++	    rdev->saved_raid_disk >= first &&
+ 	    conf->disks[rdev->saved_raid_disk].rdev == NULL)
+ 		disk = rdev->saved_raid_disk;
+ 	else
+-		disk = 0;
+-	for ( ; disk < conf->raid_disks; disk++)
++		disk = first;
++	for ( ; disk <= last ; disk++)
+ 		if ((p=conf->disks + disk)->rdev == NULL) {
+ 			clear_bit(In_sync, &rdev->flags);
+ 			rdev->raid_disk = disk;