|
|
|
#ifndef _RAID1_H
|
|
|
|
#define _RAID1_H
|
|
|
|
|
|
|
|
#include <linux/raid/md.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 working_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;
|
|
|
|
};
|
|
|
|
|
|
|
|
typedef struct r1_private_data_s conf_t;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* this is the only point in the RAID code where we violate
|
|
|
|
* C type safety. mddev->private is an 'opaque' pointer.
|
|
|
|
*/
|
|
|
|
#define mddev_to_conf(mddev) ((conf_t *) mddev->private)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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
|
[PATCH] md: support BIO_RW_BARRIER for md/raid1
We can only accept BARRIER requests if all slaves handle
barriers, and that can, of course, change with time....
So we keep track of whether the whole array seems safe for barriers,
and also whether each individual rdev handles barriers.
We initially assumes barriers are OK.
When writing the superblock we try a barrier, and if that fails, we flag
things for no-barriers. This will usually clear the flags fairly quickly.
If writing the superblock finds that BIO_RW_BARRIER is -ENOTSUPP, we need to
resubmit, so introduce function "md_super_wait" which waits for requests to
finish, and retries ENOTSUPP requests without the barrier flag.
When writing the real raid1, write requests which were BIO_RW_BARRIER but
which aresn't supported need to be retried. So raid1d is enhanced to do this,
and when any bio write completes (i.e. no retry needed) we remove it from the
r1bio, so that devices needing retry are easy to find.
We should hardly ever get -ENOTSUPP errors when writing data to the raid.
It should only happen if:
1/ the device used to support BARRIER, but now doesn't. Few devices
change like this, though raid1 can!
or
2/ the array has no persistent superblock, so there was no opportunity to
pre-test for barriers when writing the superblock.
Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
19 years ago
|
|
|
#define R1BIO_BehindIO 3
|
|
|
|
#define R1BIO_Barrier 4
|
|
|
|
#define R1BIO_BarrierRetry 5
|
|
|
|
/* 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 4
|
|
|
|
|
|
|
|
#endif
|