[linux-2.6-block.git] / fs / ceph / osdmap.h

#ifndef _FS_CEPH_OSDMAP_H
#define _FS_CEPH_OSDMAP_H

#include <linux/rbtree.h>
#include "types.h"
#include "ceph_fs.h"
#include "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_pool_info {
	struct rb_node node;
	int id;
	struct ceph_pg_pool v;
	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
	char *name;
};

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_preferred(l) \
	((__s32)le32_to_cpu((l).fl_pg_preferred))
#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 void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
					  u64 off, u64 *plen,
					  u64 *bno, u64 *oxoff, u64 *oxlen);

/* calculate mapping of object to a placement group */
extern int ceph_calc_object_layout(struct ceph_object_layout *ol,
				   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);

#endif
Commit	Line	Data
f24e9980 SW	1	#ifndef _FS_CEPH_OSDMAP_H
	2	#define _FS_CEPH_OSDMAP_H
	3
	4	#include <linux/rbtree.h>
	5	#include "types.h"
	6	#include "ceph_fs.h"
	7	#include "crush/crush.h"
	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	*/
	21	struct ceph_pg_pool_info {
4fc51be8 SW	22	struct rb_node node;
4fc51be8 SW	23	int id;
f24e9980 SW	24	struct ceph_pg_pool v;
f24e9980 SW	25	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
2844a76a	26	char *name;
f24e9980 SW	27	};
	28
	29	struct ceph_pg_mapping {
	30	struct rb_node node;
51042122	31	struct ceph_pg pgid;
f24e9980 SW	32	int len;
	33	int osds[];
	34	};
	35
	36	struct ceph_osdmap {
	37	struct ceph_fsid fsid;
	38	u32 epoch;
	39	u32 mkfs_epoch;
	40	struct ceph_timespec created, modified;
	41
	42	u32 flags; /* CEPH_OSDMAP_* */
	43
	44	u32 max_osd; /* size of osd_state, _offload, _addr arrays */
	45	u8 osd_state; / CEPH_OSD_* */
	46	u32 osd_weight; / 0 = failed, 0x10000 = 100% normal */
	47	struct ceph_entity_addr *osd_addr;
	48
	49	struct rb_root pg_temp;
4fc51be8 SW	50	struct rb_root pg_pools;
4fc51be8 SW	51	u32 pool_max;
f24e9980 SW	52
	53	/* the CRUSH map specifies the mapping of placement groups to
	54	* the list of osds that store+replicate them. */
	55	struct crush_map *crush;
	56	};
	57
	58	/*
	59	* file layout helpers
	60	*/
	61	#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit))
	62	#define ceph_file_layout_stripe_count(l) \
	63	((__s32)le32_to_cpu((l).fl_stripe_count))
	64	#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size))
	65	#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash))
	66	#define ceph_file_layout_object_su(l) \
	67	((__s32)le32_to_cpu((l).fl_object_stripe_unit))
	68	#define ceph_file_layout_pg_preferred(l) \
	69	((__s32)le32_to_cpu((l).fl_pg_preferred))
	70	#define ceph_file_layout_pg_pool(l) \
	71	((__s32)le32_to_cpu((l).fl_pg_pool))
	72
	73	static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l)
	74	{
	75	return le32_to_cpu(l->fl_stripe_unit) *
	76	le32_to_cpu(l->fl_stripe_count);
	77	}
	78
	79	/* "period" == bytes before i start on a new set of objects */
	80	static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l)
	81	{
	82	return le32_to_cpu(l->fl_object_size) *
	83	le32_to_cpu(l->fl_stripe_count);
	84	}
	85
	86
	87	static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
	88	{
	89	return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
	90	}
	91
	92	static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
	93	{
	94	return map && (map->flags & flag);
	95	}
	96
	97	extern char ceph_osdmap_state_str(char str, int len, int state);
	98
	99	static inline struct ceph_entity_addr ceph_osd_addr(struct ceph_osdmap map,
	100	int osd)
	101	{
	102	if (osd >= map->max_osd)
	103	return NULL;
	104	return &map->osd_addr[osd];
	105	}
	106
	107	extern struct ceph_osdmap osdmap_decode(void p, void end);
	108	extern struct ceph_osdmap osdmap_apply_incremental(void p, void end,
	109	struct ceph_osdmap *map,
	110	struct ceph_messenger *msgr);
	111	extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
	112
	113	/* calculate mapping of a file extent to an object */
	114	extern void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
	115	u64 off, u64 *plen,
116	u64 bno, u64 oxoff, u64 *oxlen);
117
118	/* calculate mapping of object to a placement group */
119	extern int ceph_calc_object_layout(struct ceph_object_layout *ol,
120	const char *oid,
121	struct ceph_file_layout *fl,
122	struct ceph_osdmap *osdmap);
d85b7056 SW	123	extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
d85b7056 SW	124	int *acting);
51042122 SW	125	extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
51042122 SW	126	struct ceph_pg pgid);
f24e9980 SW	127
f24e9980 SW	128	#endif