2009-10-06 20:31:13 +02:00
|
|
|
#ifndef __FS_CEPH_MESSENGER_H
|
|
|
|
#define __FS_CEPH_MESSENGER_H
|
|
|
|
|
2009-12-08 00:55:05 +01:00
|
|
|
#include <linux/kref.h>
|
2009-10-06 20:31:13 +02:00
|
|
|
#include <linux/mutex.h>
|
|
|
|
#include <linux/net.h>
|
|
|
|
#include <linux/radix-tree.h>
|
|
|
|
#include <linux/uio.h>
|
|
|
|
#include <linux/version.h>
|
|
|
|
#include <linux/workqueue.h>
|
|
|
|
|
|
|
|
#include "types.h"
|
|
|
|
#include "buffer.h"
|
|
|
|
|
|
|
|
struct ceph_msg;
|
|
|
|
struct ceph_connection;
|
|
|
|
|
|
|
|
extern struct workqueue_struct *ceph_msgr_wq; /* receive work queue */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ceph defines these callbacks for handling connection events.
|
|
|
|
*/
|
|
|
|
struct ceph_connection_operations {
|
|
|
|
struct ceph_connection *(*get)(struct ceph_connection *);
|
|
|
|
void (*put)(struct ceph_connection *);
|
|
|
|
|
|
|
|
/* handle an incoming message. */
|
|
|
|
void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m);
|
|
|
|
|
2009-11-19 01:19:57 +01:00
|
|
|
/* authorize an outgoing connection */
|
|
|
|
int (*get_authorizer) (struct ceph_connection *con,
|
|
|
|
void **buf, int *len, int *proto,
|
|
|
|
void **reply_buf, int *reply_len, int force_new);
|
|
|
|
int (*verify_authorizer_reply) (struct ceph_connection *con, int len);
|
2010-02-03 01:21:06 +01:00
|
|
|
int (*invalidate_authorizer)(struct ceph_connection *con);
|
2009-11-19 01:19:57 +01:00
|
|
|
|
2009-10-06 20:31:13 +02:00
|
|
|
/* protocol version mismatch */
|
|
|
|
void (*bad_proto) (struct ceph_connection *con);
|
|
|
|
|
|
|
|
/* there was some error on the socket (disconnect, whatever) */
|
|
|
|
void (*fault) (struct ceph_connection *con);
|
|
|
|
|
|
|
|
/* a remote host as terminated a message exchange session, and messages
|
|
|
|
* we sent (or they tried to send us) may be lost. */
|
|
|
|
void (*peer_reset) (struct ceph_connection *con);
|
|
|
|
|
|
|
|
struct ceph_msg * (*alloc_msg) (struct ceph_connection *con,
|
2010-01-08 22:58:34 +01:00
|
|
|
struct ceph_msg_header *hdr,
|
|
|
|
int *skip);
|
2009-10-06 20:31:13 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
extern const char *ceph_name_type_str(int t);
|
|
|
|
|
|
|
|
/* use format string %s%d */
|
|
|
|
#define ENTITY_NAME(n) ceph_name_type_str((n).type), le64_to_cpu((n).num)
|
|
|
|
|
|
|
|
struct ceph_messenger {
|
|
|
|
struct ceph_entity_inst inst; /* my name+address */
|
2009-11-04 00:17:56 +01:00
|
|
|
struct ceph_entity_addr my_enc_addr;
|
2009-10-06 20:31:13 +02:00
|
|
|
struct page *zero_page; /* used in certain error cases */
|
|
|
|
|
|
|
|
bool nocrc;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* the global_seq counts connections i (attempt to) initiate
|
|
|
|
* in order to disambiguate certain connect race conditions.
|
|
|
|
*/
|
|
|
|
u32 global_seq;
|
|
|
|
spinlock_t global_seq_lock;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* a single message. it contains a header (src, dest, message type, etc.),
|
|
|
|
* footer (crc values, mainly), a "front" message body, and possibly a
|
|
|
|
* data payload (stored in some number of pages).
|
|
|
|
*/
|
|
|
|
struct ceph_msg {
|
|
|
|
struct ceph_msg_header hdr; /* header */
|
|
|
|
struct ceph_msg_footer footer; /* footer */
|
|
|
|
struct kvec front; /* unaligned blobs of message */
|
|
|
|
struct ceph_buffer *middle;
|
|
|
|
struct page **pages; /* data payload. NOT OWNER. */
|
|
|
|
unsigned nr_pages; /* size of page array */
|
2009-12-23 21:12:31 +01:00
|
|
|
struct ceph_pagelist *pagelist; /* instead of pages */
|
2009-10-06 20:31:13 +02:00
|
|
|
struct list_head list_head;
|
2009-12-08 00:55:05 +01:00
|
|
|
struct kref kref;
|
2009-10-06 20:31:13 +02:00
|
|
|
bool front_is_vmalloc;
|
|
|
|
bool more_to_follow;
|
|
|
|
int front_max;
|
|
|
|
|
|
|
|
struct ceph_msgpool *pool;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct ceph_msg_pos {
|
|
|
|
int page, page_pos; /* which page; offset in page */
|
|
|
|
int data_pos; /* offset in data payload */
|
|
|
|
int did_page_crc; /* true if we've calculated crc for current page */
|
|
|
|
};
|
|
|
|
|
|
|
|
/* ceph connection fault delay defaults, for exponential backoff */
|
|
|
|
#define BASE_DELAY_INTERVAL (HZ/2)
|
|
|
|
#define MAX_DELAY_INTERVAL (5 * 60 * HZ)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ceph_connection state bit flags
|
|
|
|
*
|
|
|
|
* QUEUED and BUSY are used together to ensure that only a single
|
|
|
|
* thread is currently opening, reading or writing data to the socket.
|
|
|
|
*/
|
|
|
|
#define LOSSYTX 0 /* we can close channel or drop messages on errors */
|
2009-11-10 23:34:36 +01:00
|
|
|
#define CONNECTING 1
|
|
|
|
#define NEGOTIATING 2
|
2009-10-06 20:31:13 +02:00
|
|
|
#define KEEPALIVE_PENDING 3
|
|
|
|
#define WRITE_PENDING 4 /* we have data ready to send */
|
|
|
|
#define QUEUED 5 /* there is work queued on this connection */
|
|
|
|
#define BUSY 6 /* work is being done */
|
|
|
|
#define STANDBY 8 /* no outgoing messages, socket closed. we keep
|
|
|
|
* the ceph_connection around to maintain shared
|
|
|
|
* state with the peer. */
|
|
|
|
#define CLOSED 10 /* we've closed the connection */
|
|
|
|
#define SOCK_CLOSED 11 /* socket state changed to closed */
|
|
|
|
#define OPENING 13 /* open connection w/ (possibly new) peer */
|
|
|
|
#define DEAD 14 /* dead, about to kfree */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A single connection with another host.
|
|
|
|
*
|
|
|
|
* We maintain a queue of outgoing messages, and some session state to
|
|
|
|
* ensure that we can preserve the lossless, ordered delivery of
|
|
|
|
* messages in the case of a TCP disconnect.
|
|
|
|
*/
|
|
|
|
struct ceph_connection {
|
|
|
|
void *private;
|
|
|
|
atomic_t nref;
|
|
|
|
|
|
|
|
const struct ceph_connection_operations *ops;
|
|
|
|
|
|
|
|
struct ceph_messenger *msgr;
|
|
|
|
struct socket *sock;
|
|
|
|
unsigned long state; /* connection state (see flags above) */
|
|
|
|
const char *error_msg; /* error message, if any */
|
|
|
|
|
|
|
|
struct ceph_entity_addr peer_addr; /* peer address */
|
|
|
|
struct ceph_entity_name peer_name; /* peer name */
|
|
|
|
struct ceph_entity_addr peer_addr_for_me;
|
|
|
|
u32 connect_seq; /* identify the most recent connection
|
|
|
|
attempt for this connection, client */
|
|
|
|
u32 peer_global_seq; /* peer's global seq for this connection */
|
|
|
|
|
2009-11-19 01:19:57 +01:00
|
|
|
int auth_retry; /* true if we need a newer authorizer */
|
|
|
|
void *auth_reply_buf; /* where to put the authorizer reply */
|
|
|
|
int auth_reply_buf_len;
|
|
|
|
|
2009-12-22 19:43:42 +01:00
|
|
|
struct mutex mutex;
|
|
|
|
|
2009-10-06 20:31:13 +02:00
|
|
|
/* out queue */
|
|
|
|
struct list_head out_queue;
|
|
|
|
struct list_head out_sent; /* sending or sent but unacked */
|
|
|
|
u64 out_seq; /* last message queued for send */
|
|
|
|
u64 out_seq_sent; /* last message sent */
|
|
|
|
bool out_keepalive_pending;
|
|
|
|
|
|
|
|
u64 in_seq, in_seq_acked; /* last message received, acked */
|
|
|
|
|
|
|
|
/* connection negotiation temps */
|
|
|
|
char in_banner[CEPH_BANNER_MAX_LEN];
|
|
|
|
union {
|
|
|
|
struct { /* outgoing connection */
|
|
|
|
struct ceph_msg_connect out_connect;
|
|
|
|
struct ceph_msg_connect_reply in_reply;
|
|
|
|
};
|
|
|
|
struct { /* incoming */
|
|
|
|
struct ceph_msg_connect in_connect;
|
|
|
|
struct ceph_msg_connect_reply out_reply;
|
|
|
|
};
|
|
|
|
};
|
|
|
|
struct ceph_entity_addr actual_peer_addr;
|
|
|
|
|
|
|
|
/* message out temps */
|
|
|
|
struct ceph_msg *out_msg; /* sending message (== tail of
|
|
|
|
out_sent) */
|
2009-12-14 23:04:30 +01:00
|
|
|
bool out_msg_done;
|
2009-10-06 20:31:13 +02:00
|
|
|
struct ceph_msg_pos out_msg_pos;
|
|
|
|
|
|
|
|
struct kvec out_kvec[8], /* sending header/footer data */
|
|
|
|
*out_kvec_cur;
|
|
|
|
int out_kvec_left; /* kvec's left in out_kvec */
|
|
|
|
int out_skip; /* skip this many bytes */
|
|
|
|
int out_kvec_bytes; /* total bytes left */
|
|
|
|
bool out_kvec_is_msg; /* kvec refers to out_msg */
|
|
|
|
int out_more; /* there is more data after the kvecs */
|
|
|
|
__le64 out_temp_ack; /* for writing an ack */
|
|
|
|
|
|
|
|
/* message in temps */
|
|
|
|
struct ceph_msg_header in_hdr;
|
|
|
|
struct ceph_msg *in_msg;
|
|
|
|
struct ceph_msg_pos in_msg_pos;
|
|
|
|
u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */
|
|
|
|
|
|
|
|
char in_tag; /* protocol control byte */
|
|
|
|
int in_base_pos; /* bytes read */
|
|
|
|
__le64 in_temp_ack; /* for reading an ack */
|
|
|
|
|
|
|
|
struct delayed_work work; /* send|recv work */
|
|
|
|
unsigned long delay; /* current delay interval */
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
extern const char *pr_addr(const struct sockaddr_storage *ss);
|
|
|
|
extern int ceph_parse_ips(const char *c, const char *end,
|
|
|
|
struct ceph_entity_addr *addr,
|
|
|
|
int max_count, int *count);
|
|
|
|
|
|
|
|
|
|
|
|
extern int ceph_msgr_init(void);
|
|
|
|
extern void ceph_msgr_exit(void);
|
|
|
|
|
|
|
|
extern struct ceph_messenger *ceph_messenger_create(
|
|
|
|
struct ceph_entity_addr *myaddr);
|
|
|
|
extern void ceph_messenger_destroy(struct ceph_messenger *);
|
|
|
|
|
|
|
|
extern void ceph_con_init(struct ceph_messenger *msgr,
|
|
|
|
struct ceph_connection *con);
|
|
|
|
extern void ceph_con_open(struct ceph_connection *con,
|
|
|
|
struct ceph_entity_addr *addr);
|
ceph: avoid reopening osd connections when address hasn't changed
We get a fault callback on _every_ tcp connection fault. Normally, we
want to reopen the connection when that happens. If the address we have
is bad, however, and connection attempts always result in a connection
refused or similar error, explicitly closing and reopening the msgr
connection just prevents the messenger's backoff logic from kicking in.
The result can be a console full of
[ 3974.417106] ceph: osd11 10.3.14.138:6800 connection failed
[ 3974.423295] ceph: osd11 10.3.14.138:6800 connection failed
[ 3974.429709] ceph: osd11 10.3.14.138:6800 connection failed
Instead, if we get a fault, and have outstanding requests, but the osd
address hasn't changed and the connection never successfully connected in
the first place, do nothing to the osd connection. The messenger layer
will back off and retry periodically, because we never connected and thus
the lossy bit is not set.
Instead, touch each request's r_stamp so that handle_timeout can tell the
request is still alive and kicking.
Signed-off-by: Sage Weil <sage@newdream.net>
2010-03-22 22:51:18 +01:00
|
|
|
extern bool ceph_con_opened(struct ceph_connection *con);
|
2009-10-06 20:31:13 +02:00
|
|
|
extern void ceph_con_close(struct ceph_connection *con);
|
|
|
|
extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
|
|
|
|
extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
|
2010-01-14 02:03:23 +01:00
|
|
|
extern void ceph_con_revoke_message(struct ceph_connection *con,
|
|
|
|
struct ceph_msg *msg);
|
2009-10-06 20:31:13 +02:00
|
|
|
extern void ceph_con_keepalive(struct ceph_connection *con);
|
|
|
|
extern struct ceph_connection *ceph_con_get(struct ceph_connection *con);
|
|
|
|
extern void ceph_con_put(struct ceph_connection *con);
|
|
|
|
|
|
|
|
extern struct ceph_msg *ceph_msg_new(int type, int front_len,
|
|
|
|
int page_len, int page_off,
|
|
|
|
struct page **pages);
|
|
|
|
extern void ceph_msg_kfree(struct ceph_msg *m);
|
|
|
|
|
|
|
|
|
|
|
|
static inline struct ceph_msg *ceph_msg_get(struct ceph_msg *msg)
|
|
|
|
{
|
2009-12-08 00:55:05 +01:00
|
|
|
kref_get(&msg->kref);
|
2009-10-06 20:31:13 +02:00
|
|
|
return msg;
|
|
|
|
}
|
2009-12-08 00:55:05 +01:00
|
|
|
extern void ceph_msg_last_put(struct kref *kref);
|
|
|
|
static inline void ceph_msg_put(struct ceph_msg *msg)
|
|
|
|
{
|
|
|
|
kref_put(&msg->kref, ceph_msg_last_put);
|
|
|
|
}
|
2009-10-06 20:31:13 +02:00
|
|
|
|
2009-12-15 00:13:47 +01:00
|
|
|
extern void ceph_msg_dump(struct ceph_msg *msg);
|
|
|
|
|
2009-10-06 20:31:13 +02:00
|
|
|
#endif
|