[deliverable/linux.git] / include / linux / ceph / osdmap.h

#ifndef _FS_CEPH_OSDMAP_H
#define _FS_CEPH_OSDMAP_H

#include <linux/rbtree.h>
#include <linux/ceph/types.h>
#include <linux/ceph/ceph_fs.h>
#include <linux/crush/crush.h>

/*
 * The osd map describes the current membership of the osd cluster and
 * specifies the mapping of objects to placement groups and placement
 * groups to (sets of) osds.  That is, it completely specifies the
 * (desired) distribution of all data objects in the system at some
 * point in time.
 *
 * Each map version is identified by an epoch, which increases monotonically.
 *
 * The map can be updated either via an incremental map (diff) describing
 * the change between two successive epochs, or as a fully encoded map.
 */
struct ceph_pg {
	uint64_t pool;
	uint32_t seed;
};

#define CEPH_POOL_FLAG_HASHPSPOOL  1

struct ceph_pg_pool_info {
	struct rb_node node;
	s64 id;
	u8 type;
	u8 size;
	u8 crush_ruleset;
	u8 object_hash;
	u32 pg_num, pgp_num;
	int pg_num_mask, pgp_num_mask;
	u64 flags;
	char *name;
};

struct ceph_object_locator {
	uint64_t pool;
	char *key;
};

struct ceph_pg_mapping {
	struct rb_node node;
	struct ceph_pg pgid;
	int len;
	int osds[];
};

struct ceph_osdmap {
	struct ceph_fsid fsid;
	u32 epoch;
	u32 mkfs_epoch;
	struct ceph_timespec created, modified;

	u32 flags;         /* CEPH_OSDMAP_* */

	u32 max_osd;       /* size of osd_state, _offload, _addr arrays */
	u8 *osd_state;     /* CEPH_OSD_* */
	u32 *osd_weight;   /* 0 = failed, 0x10000 = 100% normal */
	struct ceph_entity_addr *osd_addr;

	struct rb_root pg_temp;
	struct rb_root pg_pools;
	u32 pool_max;

	/* the CRUSH map specifies the mapping of placement groups to
	 * the list of osds that store+replicate them. */
	struct crush_map *crush;
};

/*
 * file layout helpers
 */
#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
#define ceph_file_layout_stripe_count(l) \
	((__s32)le32_to_cpu((l).fl_stripe_count))
#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
#define ceph_file_layout_object_su(l) \
	((__s32)le32_to_cpu((l).fl_object_stripe_unit))
#define ceph_file_layout_pg_pool(l) \
	((__s32)le32_to_cpu((l).fl_pg_pool))

static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
{
	return le32_to_cpu(l->fl_stripe_unit) *
		le32_to_cpu(l->fl_stripe_count);
}

/* "period" == bytes before i start on a new set of objects */
static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
{
	return le32_to_cpu(l->fl_object_size) *
		le32_to_cpu(l->fl_stripe_count);
}


static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
{
	return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
}

static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
{
	return map && (map->flags & flag);
}

extern char *ceph_osdmap_state_str(char *str, int len, int state);

static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
						     int osd)
{
	if (osd >= map->max_osd)
		return NULL;
	return &map->osd_addr[osd];
}

extern struct ceph_osdmap *osdmap_decode(void **p, void *end);
extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
					    struct ceph_osdmap *map,
					    struct ceph_messenger *msgr);
extern void ceph_osdmap_destroy(struct ceph_osdmap *map);

/* calculate mapping of a file extent to an object */
extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
					 u64 off, u64 len,
					 u64 *bno, u64 *oxoff, u64 *oxlen);

/* calculate mapping of object to a placement group */
extern int ceph_calc_object_layout(struct ceph_pg *pg,
				   const char *oid,
				   struct ceph_file_layout *fl,
				   struct ceph_osdmap *osdmap);
extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
			       struct ceph_pg pgid,
			       int *acting);
extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
				struct ceph_pg pgid);

extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id);
extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);

#endif
Commit	Line	Data
f24e9980 SW	1	#ifndef _FS_CEPH_OSDMAP_H
	2	#define _FS_CEPH_OSDMAP_H
	3
	4	#include <linux/rbtree.h>
a1ce3928 DH	5	#include <linux/ceph/types.h>
a1ce3928 DH	6	#include <linux/ceph/ceph_fs.h>
3d14c5d2	7	#include <linux/crush/crush.h>
f24e9980 SW	8
	9	/*
	10	* The osd map describes the current membership of the osd cluster and
	11	* specifies the mapping of objects to placement groups and placement
	12	* groups to (sets of) osds. That is, it completely specifies the
	13	* (desired) distribution of all data objects in the system at some
	14	* point in time.
	15	*
	16	* Each map version is identified by an epoch, which increases monotonically.
	17	*
	18	* The map can be updated either via an incremental map (diff) describing
	19	* the change between two successive epochs, or as a fully encoded map.
	20	*/
5b191d99 SW	21	struct ceph_pg {
	22	uint64_t pool;
	23	uint32_t seed;
	24	};
	25
83ca14fd SW	26	#define CEPH_POOL_FLAG_HASHPSPOOL 1
83ca14fd SW	27
f24e9980	28	struct ceph_pg_pool_info {
4fc51be8	29	struct rb_node node;
4f6a7e5e SW	30	s64 id;
	31	u8 type;
	32	u8 size;
	33	u8 crush_ruleset;
	34	u8 object_hash;
	35	u32 pg_num, pgp_num;
	36	int pg_num_mask, pgp_num_mask;
	37	u64 flags;
2844a76a	38	char *name;
f24e9980 SW	39	};
f24e9980 SW	40
4f6a7e5e SW	41	struct ceph_object_locator {
	42	uint64_t pool;
	43	char *key;
	44	};
	45
f24e9980 SW	46	struct ceph_pg_mapping {
f24e9980 SW	47	struct rb_node node;
5b191d99	48	struct ceph_pg pgid;
f24e9980 SW	49	int len;
	50	int osds[];
	51	};
	52
	53	struct ceph_osdmap {
	54	struct ceph_fsid fsid;
	55	u32 epoch;
	56	u32 mkfs_epoch;
	57	struct ceph_timespec created, modified;
	58
	59	u32 flags; /* CEPH_OSDMAP_* */
	60
	61	u32 max_osd; /* size of osd_state, _offload, _addr arrays */
	62	u8 osd_state; / CEPH_OSD_* */
	63	u32 osd_weight; / 0 = failed, 0x10000 = 100% normal */
	64	struct ceph_entity_addr *osd_addr;
	65
	66	struct rb_root pg_temp;
4fc51be8 SW	67	struct rb_root pg_pools;
4fc51be8 SW	68	u32 pool_max;
f24e9980 SW	69
	70	/* the CRUSH map specifies the mapping of placement groups to
	71	* the list of osds that store+replicate them. */
	72	struct crush_map *crush;
	73	};
	74
	75	/*
	76	* file layout helpers
	77	*/
	78	#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
	79	#define ceph_file_layout_stripe_count(l) \
	80	((__s32)le32_to_cpu((l).fl_stripe_count))
	81	#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
	82	#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
	83	#define ceph_file_layout_object_su(l) \
	84	((__s32)le32_to_cpu((l).fl_object_stripe_unit))
f24e9980 SW	85	#define ceph_file_layout_pg_pool(l) \
	86	((__s32)le32_to_cpu((l).fl_pg_pool))
	87
	88	static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
	89	{
	90	return le32_to_cpu(l->fl_stripe_unit) *
	91	le32_to_cpu(l->fl_stripe_count);
	92	}
	93
	94	/* "period" == bytes before i start on a new set of objects */
	95	static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
	96	{
	97	return le32_to_cpu(l->fl_object_size) *
	98	le32_to_cpu(l->fl_stripe_count);
	99	}
	100
	101
	102	static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
	103	{
	104	return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
	105	}
	106
	107	static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
	108	{
	109	return map && (map->flags & flag);
	110	}
	111
	112	extern char ceph_osdmap_state_str(char str, int len, int state);
	113
	114	static inline struct ceph_entity_addr ceph_osd_addr(struct ceph_osdmap map,
	115	int osd)
	116	{
	117	if (osd >= map->max_osd)
	118	return NULL;
	119	return &map->osd_addr[osd];
	120	}
	121
	122	extern struct ceph_osdmap osdmap_decode(void p, void end);
	123	extern struct ceph_osdmap osdmap_apply_incremental(void p, void end,
	124	struct ceph_osdmap *map,
	125	struct ceph_messenger *msgr);
	126	extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
	127
	128	/* calculate mapping of a file extent to an object */
d63b77f4	129	extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
e8afad65	130	u64 off, u64 len,
d63b77f4	131	u64 bno, u64 oxoff, u64 *oxlen);
f24e9980 SW	132
f24e9980 SW	133	/* calculate mapping of object to a placement group */
2169aea6	134	extern int ceph_calc_object_layout(struct ceph_pg *pg,
f24e9980 SW	135	const char *oid,
	136	struct ceph_file_layout *fl,
	137	struct ceph_osdmap *osdmap);
12979354	138	extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
5b191d99	139	struct ceph_pg pgid,
d85b7056	140	int *acting);
51042122	141	extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
5b191d99	142	struct ceph_pg pgid);
f24e9980	143
72afc71f	144	extern const char ceph_pg_pool_name_by_id(struct ceph_osdmap map, u64 id);
7669a2c9 YS	145	extern int ceph_pg_poolid_by_name(struct ceph_osdmap map, const char name);
7669a2c9 YS	146
f24e9980	147	#endif