2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-21 03:33:59 +08:00
linux-next/include/linux/nfs_fs_sb.h
Chuck Lever 0aaaf5c424 NFS: Cache state owners after files are closed
Servers have a finite amount of memory to store NFSv4 open and lock
owners.  Moreover, servers may have a difficult time determining when
they can reap their state owner table, thanks to gray areas in the
NFSv4 protocol specification.  Thus clients should be careful to reuse
state owners when possible.

Currently Linux is not too careful.  When a user has closed all her
files on one mount point, the state owner's reference count goes to
zero, and it is released.  The next OPEN allocates a new one.  A
workload that serially opens and closes files can run through a large
number of open owners this way.

When a state owner's reference count goes to zero, slap it onto a free
list for that nfs_server, with an expiry time.  Garbage collect before
looking for a state owner.  This makes state owners for active users
available for re-use.

Now that there can be unused state owners remaining at umount time,
purge the state owner free list when a server is destroyed.  Also be
sure not to reclaim unused state owners during state recovery.

This change has benefits for the client as well.  For some workloads,
this approach drops the number of OPEN_CONFIRM calls from the same as
the number of OPEN calls, down to just one.  This reduces wire traffic
and thus open(2) latency.  Before this patch, untarring a kernel
source tarball shows the OPEN_CONFIRM call counter steadily increasing
through the test.  With the patch, the OPEN_CONFIRM count remains at 1
throughout the entire untar.

As long as the expiry time is kept short, I don't think garbage
collection should be terribly expensive, although it does bounce the
clp->cl_lock around a bit.

[ At some point we should rationalize the use of the nfs_server
->destroy method. ]

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
[Trond: Fixed a garbage collection race and a few efficiency issues]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2012-01-05 11:59:18 -05:00

235 lines
7.3 KiB
C

#ifndef _NFS_FS_SB
#define _NFS_FS_SB
#include <linux/list.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/nfs_xdr.h>
#include <linux/sunrpc/xprt.h>
#include <linux/atomic.h>
struct nfs4_session;
struct nfs_iostats;
struct nlm_host;
struct nfs4_sequence_args;
struct nfs4_sequence_res;
struct nfs_server;
struct nfs4_minor_version_ops;
struct server_scope;
/*
* The nfs_client identifies our client state to the server.
*/
struct nfs_client {
atomic_t cl_count;
int cl_cons_state; /* current construction state (-ve: init error) */
#define NFS_CS_READY 0 /* ready to be used */
#define NFS_CS_INITING 1 /* busy initialising */
#define NFS_CS_SESSION_INITING 2 /* busy initialising session */
unsigned long cl_res_state; /* NFS resources state */
#define NFS_CS_CALLBACK 1 /* - callback started */
#define NFS_CS_IDMAP 2 /* - idmap started */
#define NFS_CS_RENEWD 3 /* - renewd started */
#define NFS_CS_STOP_RENEW 4 /* no more state to renew */
#define NFS_CS_CHECK_LEASE_TIME 5 /* need to check lease time */
struct sockaddr_storage cl_addr; /* server identifier */
size_t cl_addrlen;
char * cl_hostname; /* hostname of server */
struct list_head cl_share_link; /* link in global client list */
struct list_head cl_superblocks; /* List of nfs_server structs */
struct rpc_clnt * cl_rpcclient;
const struct nfs_rpc_ops *rpc_ops; /* NFS protocol vector */
int cl_proto; /* Network transport protocol */
u32 cl_minorversion;/* NFSv4 minorversion */
struct rpc_cred *cl_machine_cred;
#ifdef CONFIG_NFS_V4
u64 cl_clientid; /* constant */
nfs4_verifier cl_confirm; /* Clientid verifier */
unsigned long cl_state;
spinlock_t cl_lock;
unsigned long cl_lease_time;
unsigned long cl_last_renewal;
struct delayed_work cl_renewd;
struct rpc_wait_queue cl_rpcwaitq;
/* used for the setclientid verifier */
struct timespec cl_boot_time;
/* idmapper */
struct idmap * cl_idmap;
/* Our own IP address, as a null-terminated string.
* This is used to generate the clientid, and the callback address.
*/
char cl_ipaddr[48];
unsigned char cl_id_uniquifier;
u32 cl_cb_ident; /* v4.0 callback identifier */
const struct nfs4_minor_version_ops *cl_mvops;
/* The sequence id to use for the next CREATE_SESSION */
u32 cl_seqid;
/* The flags used for obtaining the clientid during EXCHANGE_ID */
u32 cl_exchange_flags;
struct nfs4_session *cl_session; /* sharred session */
#endif /* CONFIG_NFS_V4 */
#ifdef CONFIG_NFS_FSCACHE
struct fscache_cookie *fscache; /* client index cache cookie */
#endif
struct server_scope *server_scope; /* from exchange_id */
};
/*
* NFS client parameters stored in the superblock.
*/
struct nfs_server {
struct nfs_client * nfs_client; /* shared client and NFS4 state */
struct list_head client_link; /* List of other nfs_server structs
* that share the same client
*/
struct list_head master_link; /* link in master servers list */
struct rpc_clnt * client; /* RPC client handle */
struct rpc_clnt * client_acl; /* ACL RPC client handle */
struct nlm_host *nlm_host; /* NLM client handle */
struct nfs_iostats __percpu *io_stats; /* I/O statistics */
struct backing_dev_info backing_dev_info;
atomic_long_t writeback; /* number of writeback pages */
int flags; /* various flags */
unsigned int caps; /* server capabilities */
unsigned int rsize; /* read size */
unsigned int rpages; /* read size (in pages) */
unsigned int wsize; /* write size */
unsigned int wpages; /* write size (in pages) */
unsigned int wtmult; /* server disk block size */
unsigned int dtsize; /* readdir size */
unsigned short port; /* "port=" setting */
unsigned int bsize; /* server block size */
unsigned int acregmin; /* attr cache timeouts */
unsigned int acregmax;
unsigned int acdirmin;
unsigned int acdirmax;
unsigned int namelen;
unsigned int options; /* extra options enabled by mount */
#define NFS_OPTION_FSCACHE 0x00000001 /* - local caching enabled */
struct nfs_fsid fsid;
__u64 maxfilesize; /* maximum file size */
struct timespec time_delta; /* smallest time granularity */
unsigned long mount_time; /* when this fs was mounted */
dev_t s_dev; /* superblock dev numbers */
#ifdef CONFIG_NFS_FSCACHE
struct nfs_fscache_key *fscache_key; /* unique key for superblock */
struct fscache_cookie *fscache; /* superblock cookie */
#endif
u32 pnfs_blksize; /* layout_blksize attr */
#ifdef CONFIG_NFS_V4
u32 attr_bitmask[3];/* V4 bitmask representing the set
of attributes supported on this
filesystem */
u32 cache_consistency_bitmask[2];
/* V4 bitmask representing the subset
of change attribute, size, ctime
and mtime attributes supported by
the server */
u32 acl_bitmask; /* V4 bitmask representing the ACEs
that are supported on this
filesystem */
struct pnfs_layoutdriver_type *pnfs_curr_ld; /* Active layout driver */
struct rpc_wait_queue roc_rpcwaitq;
void *pnfs_ld_data; /* per mount point data */
/* the following fields are protected by nfs_client->cl_lock */
struct rb_root state_owners;
struct rb_root openowner_id;
struct rb_root lockowner_id;
#endif
struct list_head state_owners_lru;
struct list_head layouts;
struct list_head delegations;
void (*destroy)(struct nfs_server *);
atomic_t active; /* Keep trace of any activity to this server */
/* mountd-related mount options */
struct sockaddr_storage mountd_address;
size_t mountd_addrlen;
u32 mountd_version;
unsigned short mountd_port;
unsigned short mountd_protocol;
};
/* Server capabilities */
#define NFS_CAP_READDIRPLUS (1U << 0)
#define NFS_CAP_HARDLINKS (1U << 1)
#define NFS_CAP_SYMLINKS (1U << 2)
#define NFS_CAP_ACLS (1U << 3)
#define NFS_CAP_ATOMIC_OPEN (1U << 4)
#define NFS_CAP_CHANGE_ATTR (1U << 5)
#define NFS_CAP_FILEID (1U << 6)
#define NFS_CAP_MODE (1U << 7)
#define NFS_CAP_NLINK (1U << 8)
#define NFS_CAP_OWNER (1U << 9)
#define NFS_CAP_OWNER_GROUP (1U << 10)
#define NFS_CAP_ATIME (1U << 11)
#define NFS_CAP_CTIME (1U << 12)
#define NFS_CAP_MTIME (1U << 13)
#define NFS_CAP_POSIX_LOCK (1U << 14)
#define NFS_CAP_UIDGID_NOMAP (1U << 15)
/* maximum number of slots to use */
#define NFS4_MAX_SLOT_TABLE RPC_MAX_SLOT_TABLE
#if defined(CONFIG_NFS_V4)
/* Sessions */
#define SLOT_TABLE_SZ (NFS4_MAX_SLOT_TABLE/(8*sizeof(long)))
struct nfs4_slot_table {
struct nfs4_slot *slots; /* seqid per slot */
unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
spinlock_t slot_tbl_lock;
struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */
int max_slots; /* # slots in table */
int highest_used_slotid; /* sent to server on each SEQ.
* op for dynamic resizing */
int target_max_slots; /* Set by CB_RECALL_SLOT as
* the new max_slots */
struct completion complete;
};
static inline int slot_idx(struct nfs4_slot_table *tbl, struct nfs4_slot *sp)
{
return sp - tbl->slots;
}
/*
* Session related parameters
*/
struct nfs4_session {
struct nfs4_sessionid sess_id;
u32 flags;
unsigned long session_state;
u32 hash_alg;
u32 ssv_len;
/* The fore and back channel */
struct nfs4_channel_attrs fc_attrs;
struct nfs4_slot_table fc_slot_table;
struct nfs4_channel_attrs bc_attrs;
struct nfs4_slot_table bc_slot_table;
struct nfs_client *clp;
};
#endif /* CONFIG_NFS_V4 */
#endif