mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-13 14:14:37 +00:00
d2eb35acfd
Now that we have a bad block list, we should not read from those
blocks.
There are several main parts to this:
1/ read_balance needs to check for bad blocks, and return not only
the chosen device, but also how many good blocks are available
there.
2/ fix_read_error needs to avoid trying to read from bad blocks.
3/ read submission must be ready to issue multiple reads to
different devices as different bad blocks on different devices
could mean that a single large read cannot be served by any one
device, but can still be served by the array.
This requires keeping count of the number of outstanding requests
per bio. This count is stored in 'bi_phys_segments'
4/ retrying a read needs to also be ready to submit a smaller read
and queue another request for the rest.
This does not yet handle bad blocks when reading to perform resync,
recovery, or check.
'md_trim_bio' will also be used for RAID10, so put it in md.c and
export it.
Signed-off-by: NeilBrown <neilb@suse.de>
141 lines
3.6 KiB
C
141 lines
3.6 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;
|
|
|
|
/* 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.
|
|
*/
|
|
int recovery_disabled; /* when the same as
|
|
* mddev->recovery_disabled
|
|
* we don't allow recovery
|
|
* to be attempted as we
|
|
* expect a read error
|
|
*/
|
|
|
|
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;
|
|
/* Next two are only valid when R1BIO_BehindIO is set */
|
|
struct page **behind_pages;
|
|
int behind_page_count;
|
|
/*
|
|
* 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
|
|
/* Set ReadError on bios that experience a readerror so that
|
|
* raid1d knows what to do with them.
|
|
*/
|
|
#define R1BIO_ReadError 4
|
|
/* 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
|
|
|
|
extern int md_raid1_congested(mddev_t *mddev, int bits);
|
|
|
|
#endif
|