From 17999be4aa408e7ff3b9d32c735649676567a3cd Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 6 Jan 2006 00:20:12 -0800 Subject: [PATCH] md: improve raid1 "IO Barrier" concept raid1 needs to put up a barrier to new requests while it does resync or other background recovery. The code for this is currently open-coded, slighty obscure by its use of two waitqueues, and not documented. This patch gathers all the related code into 4 functions, and includes a comment which (hopefully) explains what is happening. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid1.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/raid/raid1.h') diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index 292b98f2b408..c55674252533 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -45,6 +45,7 @@ struct r1_private_data_s { spinlock_t resync_lock; int nr_pending; + int nr_waiting; int barrier; sector_t next_resync; int fullsync; /* set to 1 if a full sync is needed, @@ -52,8 +53,7 @@ struct r1_private_data_s { * Cleared when a sync completes. */ - wait_queue_head_t wait_idle; - wait_queue_head_t wait_resume; + wait_queue_head_t wait_barrier; struct pool_info *poolinfo; -- cgit v1.2.2 From ddaf22abaa831763e75775e6d4c7693504237997 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 6 Jan 2006 00:20:19 -0800 Subject: [PATCH] md: attempt to auto-correct read errors in raid1 On a read-error we suspend the array, then synchronously read the block from other arrays until we find one where we can read it. Then we try writing the good data back everywhere and make sure it works. If any write or subsequent read fails, only then do we fail the device out of the array. To be able to suspend the array, we need to also keep track of how many requests are queued for handling by raid1d. Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid1.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/raid/raid1.h') diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index c55674252533..cbe4238d3f9f 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -46,6 +46,7 @@ struct r1_private_data_s { spinlock_t resync_lock; int nr_pending; int nr_waiting; + int nr_queued; int barrier; sector_t next_resync; int fullsync; /* set to 1 if a full sync is needed, @@ -57,6 +58,8 @@ struct r1_private_data_s { struct pool_info *poolinfo; + struct page *tmppage; + mempool_t *r1bio_pool; mempool_t *r1buf_pool; }; -- cgit v1.2.2 From cf30a473a02901fe4db37abc0b0fa26dd5ba3f72 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 6 Jan 2006 00:20:23 -0800 Subject: [PATCH] md: handle errors when read-only Signed-off-by: Neil Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/raid/raid1.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/raid/raid1.h') diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h index cbe4238d3f9f..9d5494aaac0f 100644 --- a/include/linux/raid/raid1.h +++ b/include/linux/raid/raid1.h @@ -109,6 +109,13 @@ struct r1bio_s { /* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/ }; +/* when we get a read error on a read-only array, we redirect to another + * device without failing the first device, or trying to over-write to + * correct the read error. To keep track of bad blocks on a per-bio + * level, we store IO_BLOCKED in the appropriate 'bios' pointer + */ +#define IO_BLOCKED ((struct bio*)1) + /* bits for r1bio.state */ #define R1BIO_Uptodate 0 #define R1BIO_IsSync 1 -- cgit v1.2.2