Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit f24e9980 authored by Sage Weil's avatar Sage Weil
Browse files

ceph: OSD client 



The OSD client is responsible for reading and writing data from/to the
object storage pool.  This includes determining where objects are
stored in the cluster, and ensuring that requests are retried or
redirected in the event of a node failure or data migration.

If an OSD does not respond before a timeout expires, keepalive
messages are sent across the lossless, ordered communications channel
to ensure that any break in the TCP is discovered.  If the session
does reset, a reconnection is attempted and affected requests are
resent (by the message transport layer).

Signed-off-by: default avatarSage Weil <sage@newdream.net>
parent 2f2dc053

fs/ceph/osd_client.c

0 → 100644
+1294 −0

File added.

Preview size limit exceeded, changes collapsed.

fs/ceph/osd_client.h

0 → 100644
+144 −0
Original line number Original line Diff line number Diff line 
#ifndef _FS_CEPH_OSD_CLIENT_H

#define _FS_CEPH_OSD_CLIENT_H



#include <linux/completion.h>

#include <linux/mempool.h>

#include <linux/rbtree.h>



#include "types.h"

#include "osdmap.h"

#include "messenger.h"



struct ceph_msg;

struct ceph_snap_context;

struct ceph_osd_request;

struct ceph_osd_client;



/*

 * completion callback for async writepages

 */

typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *,

				     struct ceph_msg *);



/* a given osd we're communicating with */

struct ceph_osd {

	atomic_t o_ref;

	struct ceph_osd_client *o_osdc;

	int o_osd;

	int o_incarnation;

	struct rb_node o_node;

	struct ceph_connection o_con;

	struct list_head o_requests;

};



/* an in-flight request */

struct ceph_osd_request {

	u64             r_tid;              /* unique for this client */

	struct rb_node  r_node;

	struct list_head r_osd_item;

	struct ceph_osd *r_osd;



	struct ceph_msg  *r_request, *r_reply;

	int               r_result;

	int               r_flags;     /* any additional flags for the osd */

	u32               r_sent;      /* >0 if r_request is sending/sent */

	int r_prepared_pages, r_got_reply;



	struct ceph_osd_client *r_osdc;

	atomic_t          r_ref;

	bool              r_mempool;

	struct completion r_completion, r_safe_completion;

	ceph_osdc_callback_t r_callback, r_safe_callback;

	struct ceph_eversion r_reassert_version;

	struct list_head  r_unsafe_item;



	struct inode *r_inode;         	      /* for use by callbacks */

	struct writeback_control *r_wbc;      /* ditto */



	char              r_oid[40];          /* object name */

	int               r_oid_len;

	unsigned long     r_timeout_stamp;

	bool              r_resend;           /* msg send failed, needs retry */



	struct ceph_file_layout r_file_layout;

	struct ceph_snap_context *r_snapc;    /* snap context for writes */

	unsigned          r_num_pages;        /* size of page array (follows) */

	struct page     **r_pages;            /* pages for data payload */

	int               r_pages_from_pool;

	int               r_own_pages;        /* if true, i own page list */

};



struct ceph_osd_client {

	struct ceph_client     *client;



	struct ceph_osdmap     *osdmap;       /* current map */

	struct rw_semaphore    map_sem;

	struct completion      map_waiters;

	u64                    last_requested_map;



	struct mutex           request_mutex;

	struct rb_root         osds;          /* osds */

	u64                    timeout_tid;   /* tid of timeout triggering rq */

	u64                    last_tid;      /* tid of last request */

	struct rb_root         requests;      /* pending requests */

	int                    num_requests;

	struct delayed_work    timeout_work;

	struct dentry 	       *debugfs_file;



	mempool_t              *req_mempool;



	struct ceph_msgpool   msgpool_op;

	struct ceph_msgpool   msgpool_op_reply;

};



extern int ceph_osdc_init(struct ceph_osd_client *osdc,

			  struct ceph_client *client);

extern void ceph_osdc_stop(struct ceph_osd_client *osdc);



extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,

				   struct ceph_msg *msg);

extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,

				 struct ceph_msg *msg);



extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,

				      struct ceph_file_layout *layout,

				      struct ceph_vino vino,

				      u64 offset, u64 *len, int op, int flags,

				      struct ceph_snap_context *snapc,

				      int do_sync, u32 truncate_seq,

				      u64 truncate_size,

				      struct timespec *mtime,

				      bool use_mempool, int num_reply);



static inline void ceph_osdc_get_request(struct ceph_osd_request *req)

{

	atomic_inc(&req->r_ref);

}

extern void ceph_osdc_put_request(struct ceph_osd_request *req);



extern int ceph_osdc_start_request(struct ceph_osd_client *osdc,

				   struct ceph_osd_request *req,

				   bool nofail);

extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,

				  struct ceph_osd_request *req);

extern void ceph_osdc_sync(struct ceph_osd_client *osdc);



extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,

			       struct ceph_vino vino,

			       struct ceph_file_layout *layout,

			       u64 off, u64 *plen,

			       u32 truncate_seq, u64 truncate_size,

			       struct page **pages, int nr_pages);



extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,

				struct ceph_vino vino,

				struct ceph_file_layout *layout,

				struct ceph_snap_context *sc,

				u64 off, u64 len,

				u32 truncate_seq, u64 truncate_size,

				struct timespec *mtime,

				struct page **pages, int nr_pages,

				int flags, int do_sync, bool nofail);



#endif

fs/ceph/osdmap.c

0 → 100644
+875 −0

File added.

Preview size limit exceeded, changes collapsed.

fs/ceph/osdmap.h

0 → 100644
+123 −0
Original line number Original line Diff line number Diff line 
#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 ceph_pg_pool v;

	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;

};



struct ceph_pg_mapping {

	struct rb_node node;

	u64 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;



	u32 num_pools;

	struct ceph_pg_pool_info *pg_pool;



	/* 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_primary(struct ceph_osdmap *osdmap, union ceph_pg pgid);



#endif