raid1.h 4.95 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6
#ifndef _RAID1_H
#define _RAID1_H

typedef struct mirror_info mirror_info_t;

struct mirror_info {
7
	struct md_rdev	*rdev;
Linus Torvalds's avatar
Linus Torvalds committed
8 9 10 11 12 13 14 15 16 17 18 19
	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 {
20
	struct mddev *mddev;
Linus Torvalds's avatar
Linus Torvalds committed
21 22 23 24 25 26 27
	int	raid_disks;
};


typedef struct r1bio_s r1bio_t;

struct r1_private_data_s {
28
	struct mddev		*mddev;
Linus Torvalds's avatar
Linus Torvalds committed
29 30
	mirror_info_t		*mirrors;
	int			raid_disks;
31 32 33 34 35

	/* When choose the best device for a read (read_balance())
	 * we try to keep sequential reads one the same device
	 * using 'last_used' and 'next_seq_sect'
	 */
Linus Torvalds's avatar
Linus Torvalds committed
36 37
	int			last_used;
	sector_t		next_seq_sect;
38 39 40 41 42 43
	/* During resync, read_balancing is only allowed on the part
	 * of the array that has been resynced.  'next_resync' tells us
	 * where that is.
	 */
	sector_t		next_resync;

Linus Torvalds's avatar
Linus Torvalds committed
44 45
	spinlock_t		device_lock;

46 47 48 49
	/* list of 'r1bio_t' that need to be processed by raid1d, whether
	 * to retry a read, writeout a resync or recovery block, or
	 * anything else.
	 */
Linus Torvalds's avatar
Linus Torvalds committed
50
	struct list_head	retry_list;
51

52 53
	/* queue pending writes to be submitted on unplug */
	struct bio_list		pending_bio_list;
Linus Torvalds's avatar
Linus Torvalds committed
54

55 56 57 58 59 60 61
	/* for use when syncing mirrors:
	 * We don't allow both normal IO and resync/recovery IO at
	 * the same time - resync/recovery can only happen when there
	 * is no other IO.  So when either is active, the other has to wait.
	 * See more details description in raid1.c near raise_barrier().
	 */
	wait_queue_head_t	wait_barrier;
Linus Torvalds's avatar
Linus Torvalds committed
62
	spinlock_t		resync_lock;
63
	int			nr_pending;
64
	int			nr_waiting;
65
	int			nr_queued;
66
	int			barrier;
Linus Torvalds's avatar
Linus Torvalds committed
67

68 69 70 71
	/* Set to 1 if a full sync is needed, (fresh device added).
	 * Cleared when a sync completes.
	 */
	int			fullsync;
Linus Torvalds's avatar
Linus Torvalds committed
72

73 74 75 76
	/* When the same as mddev->recovery_disabled we don't allow
	 * recovery to be attempted as we expect a read error.
	 */
	int			recovery_disabled;
Linus Torvalds's avatar
Linus Torvalds committed
77

78

79 80 81 82
	/* poolinfo contains information about the content of the
	 * mempools - it changes when the array grows or shrinks
	 */
	struct pool_info	*poolinfo;
Linus Torvalds's avatar
Linus Torvalds committed
83 84
	mempool_t *r1bio_pool;
	mempool_t *r1buf_pool;
85

86 87 88 89 90 91
	/* temporary buffer to synchronous IO when attempting to repair
	 * a read error.
	 */
	struct page		*tmppage;


92 93 94 95
	/* 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;
Linus Torvalds's avatar
Linus Torvalds committed
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110
};

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
					    */
111 112 113
	atomic_t		behind_remaining; /* number of write-behind ios remaining
						 * in this BehindIO request
						 */
Linus Torvalds's avatar
Linus Torvalds committed
114 115 116
	sector_t		sector;
	int			sectors;
	unsigned long		state;
117
	struct mddev		*mddev;
Linus Torvalds's avatar
Linus Torvalds committed
118 119 120 121 122 123 124 125 126 127
	/*
	 * 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;
128
	/* Next two are only valid when R1BIO_BehindIO is set */
129
	struct bio_vec		*behind_bvecs;
130
	int			behind_page_count;
Linus Torvalds's avatar
Linus Torvalds committed
131 132 133 134 135
	/*
	 * if the IO is in WRITE direction, then multiple bios are used.
	 * We choose the number when they are allocated.
	 */
	struct bio		*bios[0];
136
	/* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
Linus Torvalds's avatar
Linus Torvalds committed
137 138
};

139 140 141 142 143
/* 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
 */
144 145 146 147 148 149 150 151
#define IO_BLOCKED ((struct bio *)1)
/* When we successfully write to a known bad-block, we need to remove the
 * bad-block marking which must be done from process context.  So we record
 * the success by setting bios[n] to IO_MADE_GOOD
 */
#define IO_MADE_GOOD ((struct bio *)2)

#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
152

Linus Torvalds's avatar
Linus Torvalds committed
153 154 155
/* bits for r1bio.state */
#define	R1BIO_Uptodate	0
#define	R1BIO_IsSync	1
156
#define	R1BIO_Degraded	2
157
#define	R1BIO_BehindIO	3
158 159 160 161
/* Set ReadError on bios that experience a readerror so that
 * raid1d knows what to do with them.
 */
#define R1BIO_ReadError 4
162 163 164 165 166 167 168
/* 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...
 */
169
#define	R1BIO_Returned 6
170 171 172
/* If a write for this request means we can clear some
 * known-bad-block records, we set this flag
 */
173 174
#define	R1BIO_MadeGood 7
#define	R1BIO_WriteError 8
175

176
extern int md_raid1_congested(struct mddev *mddev, int bits);
177

Linus Torvalds's avatar
Linus Torvalds committed
178
#endif