forked from Minki/linux
fc9977dd06
raid10 splits requests in two different ways for two different reasons. First, bio_split() is used to ensure the bio fits with a chunk. Second, multiple r10bio structures are allocated to represent the different sections that need to go to different devices, to avoid known bad blocks. This can be simplified to just use bio_split() once, and not to use multiple r10bios. We delay the split until we know a maximum bio size that can be handled with a single r10bio, and then split the bio and queue the remainder for later handling. As with raid1, we allocate a new bio_set to help with the splitting. It is not correct to use fs_bio_set in a device driver. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
164 lines
4.3 KiB
C
164 lines
4.3 KiB
C
#ifndef _RAID10_H
|
|
#define _RAID10_H
|
|
|
|
struct raid10_info {
|
|
struct md_rdev *rdev, *replacement;
|
|
sector_t head_position;
|
|
int recovery_disabled; /* matches
|
|
* mddev->recovery_disabled
|
|
* when we shouldn't try
|
|
* recovering this device.
|
|
*/
|
|
};
|
|
|
|
struct r10conf {
|
|
struct mddev *mddev;
|
|
struct raid10_info *mirrors;
|
|
struct raid10_info *mirrors_new, *mirrors_old;
|
|
spinlock_t device_lock;
|
|
|
|
/* geometry */
|
|
struct geom {
|
|
int raid_disks;
|
|
int near_copies; /* number of copies laid out
|
|
* raid0 style */
|
|
int far_copies; /* number of copies laid out
|
|
* at large strides across drives
|
|
*/
|
|
int far_offset; /* far_copies are offset by 1
|
|
* stripe instead of many
|
|
*/
|
|
sector_t stride; /* distance between far copies.
|
|
* This is size / far_copies unless
|
|
* far_offset, in which case it is
|
|
* 1 stripe.
|
|
*/
|
|
int far_set_size; /* The number of devices in a set,
|
|
* where a 'set' are devices that
|
|
* contain far/offset copies of
|
|
* each other.
|
|
*/
|
|
int chunk_shift; /* shift from chunks to sectors */
|
|
sector_t chunk_mask;
|
|
} prev, geo;
|
|
int copies; /* near_copies * far_copies.
|
|
* must be <= raid_disks
|
|
*/
|
|
|
|
sector_t dev_sectors; /* temp copy of
|
|
* mddev->dev_sectors */
|
|
sector_t reshape_progress;
|
|
sector_t reshape_safe;
|
|
unsigned long reshape_checkpoint;
|
|
sector_t offset_diff;
|
|
|
|
struct list_head retry_list;
|
|
/* A separate list of r1bio which just need raid_end_bio_io called.
|
|
* This mustn't happen for writes which had any errors if the superblock
|
|
* needs to be written.
|
|
*/
|
|
struct list_head bio_end_io_list;
|
|
|
|
/* queue pending writes and submit them on unplug */
|
|
struct bio_list pending_bio_list;
|
|
int pending_count;
|
|
|
|
spinlock_t resync_lock;
|
|
atomic_t nr_pending;
|
|
int nr_waiting;
|
|
int nr_queued;
|
|
int barrier;
|
|
int array_freeze_pending;
|
|
sector_t next_resync;
|
|
int fullsync; /* set to 1 if a full sync is needed,
|
|
* (fresh device added).
|
|
* Cleared when a sync completes.
|
|
*/
|
|
int have_replacement; /* There is at least one
|
|
* replacement device.
|
|
*/
|
|
wait_queue_head_t wait_barrier;
|
|
|
|
mempool_t *r10bio_pool;
|
|
mempool_t *r10buf_pool;
|
|
struct page *tmppage;
|
|
struct bio_set *bio_split;
|
|
|
|
/* When taking over an array from a different personality, we store
|
|
* the new thread here until we fully activate the array.
|
|
*/
|
|
struct md_thread *thread;
|
|
};
|
|
|
|
/*
|
|
* this is our 'private' RAID10 bio.
|
|
*
|
|
* it contains information about what kind of IO operations were started
|
|
* for this RAID10 operation, and about their status:
|
|
*/
|
|
|
|
struct r10bio {
|
|
atomic_t remaining; /* 'have we finished' count,
|
|
* used from IRQ handlers
|
|
*/
|
|
sector_t sector; /* virtual sector number */
|
|
int sectors;
|
|
unsigned long state;
|
|
struct mddev *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_slot;
|
|
|
|
struct list_head retry_list;
|
|
/*
|
|
* if the IO is in WRITE direction, then multiple bios are used,
|
|
* one for each copy.
|
|
* When resyncing we also use one for each copy.
|
|
* When reconstructing, we use 2 bios, one for read, one for write.
|
|
* We choose the number when they are allocated.
|
|
* We sometimes need an extra bio to write to the replacement.
|
|
*/
|
|
struct r10dev {
|
|
struct bio *bio;
|
|
union {
|
|
struct bio *repl_bio; /* used for resync and
|
|
* writes */
|
|
struct md_rdev *rdev; /* used for reads
|
|
* (read_slot >= 0) */
|
|
};
|
|
sector_t addr;
|
|
int devnum;
|
|
} devs[0];
|
|
};
|
|
|
|
/* bits for r10bio.state */
|
|
enum r10bio_state {
|
|
R10BIO_Uptodate,
|
|
R10BIO_IsSync,
|
|
R10BIO_IsRecover,
|
|
R10BIO_IsReshape,
|
|
R10BIO_Degraded,
|
|
/* Set ReadError on bios that experience a read error
|
|
* so that raid10d knows what to do with them.
|
|
*/
|
|
R10BIO_ReadError,
|
|
/* If a write for this request means we can clear some
|
|
* known-bad-block records, we set this flag.
|
|
*/
|
|
R10BIO_MadeGood,
|
|
R10BIO_WriteError,
|
|
/* During a reshape we might be performing IO on the
|
|
* 'previous' part of the array, in which case this
|
|
* flag is set
|
|
*/
|
|
R10BIO_Previous,
|
|
/* failfast devices did receive failfast requests. */
|
|
R10BIO_FailFast,
|
|
};
|
|
#endif
|