e9c7469bb4
This patch converts md to support REQ_FLUSH/FUA instead of now deprecated REQ_HARDBARRIER. In the core part (md.c), the following changes are notable. * Unlike REQ_HARDBARRIER, REQ_FLUSH/FUA don't interfere with processing of other requests and thus there is no reason to mark the queue congested while FLUSH/FUA is in progress. * REQ_FLUSH/FUA failures are final and its users don't need retry logic. Retry logic is removed. * Preflush needs to be issued to all member devices but FUA writes can be handled the same way as other writes - their processing can be deferred to request_queue of member devices. md_barrier_request() is renamed to md_flush_request() and simplified accordingly. For linear, raid0 and multipath, the core changes are enough. raid1, 5 and 10 need the following conversions. * raid1: Handling of FLUSH/FUA bio's can simply be deferred to request_queues of member devices. Barrier related logic removed. * raid5: Queue draining logic dropped. FUA bit is propagated through biodrain and stripe resconstruction such that all the updated parts of the stripe are written out with FUA writes if any of the dirtying writes was FUA. preread_active_stripes handling in make_request() is updated as suggested by Neil Brown. * raid10: FUA bit needs to be propagated to write clones. linear, raid0, 1, 5 and 10 tested. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Neil Brown <neilb@suse.de> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
130 lines
3.3 KiB
C
130 lines
3.3 KiB
C
#ifndef _RAID1_H
|
|
#define _RAID1_H
|
|
|
|
typedef struct mirror_info mirror_info_t;
|
|
|
|
struct mirror_info {
|
|
mdk_rdev_t *rdev;
|
|
sector_t head_position;
|
|
};
|
|
|
|
/*
|
|
* memory pools need a pointer to the mddev, so they can force an unplug
|
|
* when memory is tight, and a count of the number of drives that the
|
|
* pool was allocated for, so they know how much to allocate and free.
|
|
* mddev->raid_disks cannot be used, as it can change while a pool is active
|
|
* These two datums are stored in a kmalloced struct.
|
|
*/
|
|
|
|
struct pool_info {
|
|
mddev_t *mddev;
|
|
int raid_disks;
|
|
};
|
|
|
|
|
|
typedef struct r1bio_s r1bio_t;
|
|
|
|
struct r1_private_data_s {
|
|
mddev_t *mddev;
|
|
mirror_info_t *mirrors;
|
|
int raid_disks;
|
|
int last_used;
|
|
sector_t next_seq_sect;
|
|
spinlock_t device_lock;
|
|
|
|
struct list_head retry_list;
|
|
/* queue pending writes and submit them on unplug */
|
|
struct bio_list pending_bio_list;
|
|
/* queue of writes that have been unplugged */
|
|
struct bio_list flushing_bio_list;
|
|
|
|
/* for use when syncing mirrors: */
|
|
|
|
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,
|
|
* (fresh device added).
|
|
* Cleared when a sync completes.
|
|
*/
|
|
|
|
wait_queue_head_t wait_barrier;
|
|
|
|
struct pool_info *poolinfo;
|
|
|
|
struct page *tmppage;
|
|
|
|
mempool_t *r1bio_pool;
|
|
mempool_t *r1buf_pool;
|
|
|
|
/* When taking over an array from a different personality, we store
|
|
* the new thread here until we fully activate the array.
|
|
*/
|
|
struct mdk_thread_s *thread;
|
|
};
|
|
|
|
typedef struct r1_private_data_s conf_t;
|
|
|
|
/*
|
|
* this is our 'private' RAID1 bio.
|
|
*
|
|
* it contains information about what kind of IO operations were started
|
|
* for this RAID1 operation, and about their status:
|
|
*/
|
|
|
|
struct r1bio_s {
|
|
atomic_t remaining; /* 'have we finished' count,
|
|
* used from IRQ handlers
|
|
*/
|
|
atomic_t behind_remaining; /* number of write-behind ios remaining
|
|
* in this BehindIO request
|
|
*/
|
|
sector_t sector;
|
|
int sectors;
|
|
unsigned long state;
|
|
mddev_t *mddev;
|
|
/*
|
|
* original bio going to /dev/mdx
|
|
*/
|
|
struct bio *master_bio;
|
|
/*
|
|
* if the IO is in READ direction, then this is where we read
|
|
*/
|
|
int read_disk;
|
|
|
|
struct list_head retry_list;
|
|
struct bitmap_update *bitmap_update;
|
|
/*
|
|
* if the IO is in WRITE direction, then multiple bios are used.
|
|
* We choose the number when they are allocated.
|
|
*/
|
|
struct bio *bios[0];
|
|
/* 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
|
|
#define R1BIO_Degraded 2
|
|
#define R1BIO_BehindIO 3
|
|
/* For write-behind requests, we call bi_end_io when
|
|
* the last non-write-behind device completes, providing
|
|
* any write was successful. Otherwise we call when
|
|
* any write-behind write succeeds, otherwise we call
|
|
* with failure when last write completes (and all failed).
|
|
* Record that bi_end_io was called with this flag...
|
|
*/
|
|
#define R1BIO_Returned 6
|
|
|
|
#endif
|