From 671488cc25f7c194c7c7a9f258bab1df17a6ff69 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 23 Dec 2011 10:17:52 +1100 Subject: md/raid5: allow each slot to have an extra replacement device Just enhance data structures to record a second device per slot to be used as a 'replacement' device, replacing the original. We also have a second bio in each slot in each stripe_head. This will only be used when writing to the array - we need to write to both the original and the replacement at the same time, so will need two bios. For now, only try using the replacement drive for aligned-reads. In this case, we prefer the replacement if it has been recovered far enough, otherwise use the original. This includes a small enhancement. Previously we would only do aligned reads if the target device was fully recovered. Now we also do them if it has recovered far enough. Reviewed-by: Dan Williams Signed-off-by: NeilBrown --- drivers/md/raid5.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'drivers/md/raid5.c') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 6b9fc58e8f2d..94bc35ba4c81 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3594,6 +3594,7 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) int dd_idx; struct bio* align_bi; struct md_rdev *rdev; + sector_t end_sector; if (!in_chunk_boundary(mddev, raid_bio)) { pr_debug("chunk_aligned_read : non aligned\n"); @@ -3618,9 +3619,19 @@ static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) 0, &dd_idx, NULL); + end_sector = align_bi->bi_sector + (align_bi->bi_size >> 9); rcu_read_lock(); - rdev = rcu_dereference(conf->disks[dd_idx].rdev); - if (rdev && test_bit(In_sync, &rdev->flags)) { + rdev = rcu_dereference(conf->disks[dd_idx].replacement); + if (!rdev || test_bit(Faulty, &rdev->flags) || + rdev->recovery_offset < end_sector) { + rdev = rcu_dereference(conf->disks[dd_idx].rdev); + if (rdev && + (test_bit(Faulty, &rdev->flags) || + !(test_bit(In_sync, &rdev->flags) || + rdev->recovery_offset >= end_sector))) + rdev = NULL; + } + if (rdev) { sector_t first_bad; int bad_sectors; -- cgit v1.2.3