* Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2013, Intel Corporation.
+ * Copyright (c) 2011, 2014, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
#define __OBD_H
#include <linux/spinlock.h>
-#include <linux/obd.h>
#include <lustre/lustre_idl.h>
#include <lustre_lib.h>
#include <lustre_fld.h>
#include <lustre_handles.h>
#include <lustre_intent.h>
-#include <lustre_capa.h>
#include <lvfs.h>
#define MAX_OBD_DEVICES 8192
{
}
-/* If we are unable to get the maximum object size from the OST in
- * ocd_maxbytes using OBD_CONNECT_MAXBYTES, then we fall back to using
- * the old maximum object size from ext3. */
-#define LUSTRE_EXT3_STRIPE_MAXBYTES 0x1fffffff000ULL
-
-struct lov_stripe_md {
- atomic_t lsm_refc;
- spinlock_t lsm_lock;
- pid_t lsm_lock_owner; /* debugging */
-
- /* maximum possible file size, might change as OSTs status changes,
- * e.g. disconnected, deactivated */
- __u64 lsm_maxbytes;
- struct {
- /* Public members. */
- struct ost_id lw_object_oi; /* lov object id/seq */
-
- /* LOV-private members start here -- only for use in lov/. */
- __u32 lw_magic;
- __u32 lw_stripe_size; /* size of the stripe */
- __u32 lw_pattern; /* striping pattern (RAID0, RAID1) */
- __u16 lw_stripe_count; /* number of objects being striped over */
- __u16 lw_layout_gen; /* generation of the layout */
- char lw_pool_name[LOV_MAXPOOLNAME + 1]; /* pool name */
- } lsm_wire;
-
- struct lov_oinfo *lsm_oinfo[0];
-};
-
-#define lsm_oi lsm_wire.lw_object_oi
-#define lsm_magic lsm_wire.lw_magic
-#define lsm_layout_gen lsm_wire.lw_layout_gen
-#define lsm_stripe_size lsm_wire.lw_stripe_size
-#define lsm_pattern lsm_wire.lw_pattern
-#define lsm_stripe_count lsm_wire.lw_stripe_count
-#define lsm_pool_name lsm_wire.lw_pool_name
-
-static inline bool lsm_is_released(struct lov_stripe_md *lsm)
-{
- return !!(lsm->lsm_pattern & LOV_PATTERN_F_RELEASED);
-}
-
-static inline bool lsm_has_objects(struct lov_stripe_md *lsm)
-{
- if (lsm == NULL)
- return false;
- if (lsm_is_released(lsm))
- return false;
- return true;
-}
-
-static inline int lov_stripe_md_size(unsigned int stripe_count)
-{
- struct lov_stripe_md lsm;
-
- return sizeof(lsm) + stripe_count * sizeof(lsm.lsm_oinfo[0]);
-}
-
+struct lov_stripe_md;
struct obd_info;
typedef int (*obd_enqueue_update_f)(void *cookie, int rc);
/* obd info for a particular level (lov, osc). */
struct obd_info {
- /* Lock policy. It keeps an extent which is specific for a particular
- * OSC. (e.g. lov_prep_enqueue_set initialises extent of the policy,
- * and osc_enqueue passes it into ldlm_lock_match & ldlm_cli_enqueue. */
- ldlm_policy_data_t oi_policy;
- /* Flags used for set request specific flags:
- - while lock handling, the flags obtained on the enqueue
- request are set here.
- - while stats, the flags used for control delay/resend.
- - while setattr, the flags used for distinguish punch operation
- */
+ /* OBD_STATFS_* flags */
__u64 oi_flags;
- /* lsm data specific for every OSC. */
- struct lov_stripe_md *oi_md;
- /* obdo data specific for every OSC, if needed at all. */
- struct obdo *oi_oa;
/* statfs data specific for every OSC, if needed at all. */
struct obd_statfs *oi_osfs;
/* An update callback which is called to update some data on upper
- * level. E.g. it is used for update lsm->lsm_oinfo at every recieved
+ * level. E.g. it is used for update lsm->lsm_oinfo at every received
* request in osc level for enqueue requests. It is also possible to
* update some caller data from LOV layer if needed. */
obd_enqueue_update_f oi_cb_up;
- /* oss capability, its type is obd_capa in client to avoid copy.
- * in contrary its type is lustre_capa in OSS. */
- void *oi_capa;
};
struct obd_type {
};
struct brw_page {
- obd_off off;
- struct page *pg;
- unsigned int count;
- obd_flag flag;
+ u64 off;
+ struct page *pg;
+ u32 count;
+ u32 flag;
};
struct timeout_item {
NUM_SYNC_ON_CANCEL_STATES
};
+/*
+ * Limit reply buffer size for striping data to one x86_64 page. This
+ * value is chosen to fit the striping data for common use cases while
+ * staying well below the limit at which the buffer must be backed by
+ * vmalloc(). Excessive use of vmalloc() may cause spinlock contention
+ * on the MDS.
+ */
+#define OBD_MAX_DEFAULT_EA_SIZE 4096
+
struct mdc_rpc_lock;
struct obd_import;
struct client_obd {
struct rw_semaphore cl_sem;
- struct obd_uuid cl_target_uuid;
- struct obd_import *cl_import; /* ptlrpc connection state */
- int cl_conn_count;
- /* max_mds_easize is purely a performance thing so we don't have to
- * call obd_size_diskmd() all the time. */
+ struct obd_uuid cl_target_uuid;
+ struct obd_import *cl_import; /* ptlrpc connection state */
+ size_t cl_conn_count;
+
+ /* Cache maximum and default values for easize. This is
+ * strictly a performance optimization to minimize calls to
+ * obd_size_diskmd(). The default values are used to calculate the
+ * initial size of a request buffer. The ptlrpc layer will resize the
+ * buffer as needed to accommodate a larger reply from the
+ * server. The default values should be small enough to avoid wasted
+ * memory and excessive use of vmalloc(), yet large enough to avoid
+ * reallocating the buffer in the common use case. */
+
+ /* Default EA size for striping attributes. It is initialized at
+ * mount-time based on the default stripe width of the filesystem,
+ * then it tracks the largest observed EA size advertised by
+ * the MDT, up to a maximum value of OBD_MAX_DEFAULT_EA_SIZE. */
__u32 cl_default_mds_easize;
+
+ /* Maximum possible EA size computed at mount-time based on
+ * the number of OSTs in the filesystem. May be increased at
+ * run-time if a larger observed size is advertised by the MDT. */
__u32 cl_max_mds_easize;
- __u32 cl_default_mds_cookiesize;
- __u32 cl_max_mds_cookiesize;
- enum lustre_sec_part cl_sp_me;
- enum lustre_sec_part cl_sp_to;
- struct sptlrpc_flavor cl_flvr_mgc; /* fixed flavor of mgc->mgs */
+ enum lustre_sec_part cl_sp_me;
+ enum lustre_sec_part cl_sp_to;
+ struct sptlrpc_flavor cl_flvr_mgc; /* fixed flavor of mgc->mgs */
/* the grant values are protected by loi_list_lock below */
unsigned long cl_dirty_pages; /* all _dirty_ in pages */
/* A chunk is an optimal size used by osc_extent to determine
* the extent size. A chunk is max(PAGE_CACHE_SIZE, OST block size) */
int cl_chunkbits;
- int cl_extent_tax; /* extent overhead, by bytes */
+ unsigned int cl_extent_tax; /* extent overhead, by bytes */
/* keep track of objects that have lois that contain pages which
* have been queued for async brw. this lock also protects the
struct mdc_rpc_lock *cl_rpc_lock;
struct mdc_rpc_lock *cl_close_lock;
+ /* modify rpcs in flight
+ * currently used for metadata only */
+ spinlock_t cl_mod_rpcs_lock;
+ __u16 cl_max_mod_rpcs_in_flight;
+
/* mgc datastruct */
struct mutex cl_mgc_mutex;
struct local_oid_storage *cl_mgc_los;
/* also protected by the poorly named _loi_list_lock lock above */
struct osc_async_rc cl_ar;
- /* used by quotacheck when the servers are older than 2.4 */
- int cl_qchk_stat; /* quotacheck stat of the peer */
-#define CL_NOT_QUOTACHECKED 1 /* client->cl_qchk_stat init value */
-#if LUSTRE_VERSION_CODE >= OBD_OCD_VERSION(2, 7, 53, 0)
-#warning "please consider removing quotacheck compatibility code"
-#endif
-
/* sequence manager */
struct lu_client_seq *cl_seq;
void *cl_writeback_work;
void *cl_lru_work;
/* hash tables for osc_quota_info */
- cfs_hash_t *cl_quota_hash[MAXQUOTAS];
+ struct cfs_hash *cl_quota_hash[MAXQUOTAS];
};
#define obd2cli_tgt(obd) ((char *)(obd)->u.cli.cl_target_uuid.uuid)
struct obd_id_info {
- __u32 idx;
- obd_id *data;
+ u32 idx;
+ u64 *data;
};
struct echo_client_obd {
__u32 lov_tgt_size; /* size of tgts array */
int lov_connects;
int lov_pool_count;
- cfs_hash_t *lov_pools_hash_body; /* used for key access */
+ struct cfs_hash *lov_pools_hash_body; /* used for key access */
struct list_head lov_pool_list; /* used for sequential access */
struct proc_dir_entry *lov_pool_proc_entry;
enum lustre_sec_part lov_sp_me;
/* Cached LRU and unstable data from upper layer */
- void *lov_cache;
+ struct cl_client_cache *lov_cache;
struct rw_semaphore lov_notify_lock;
};
int connected;
int max_easize;
int max_def_easize;
- int max_cookiesize;
- int max_def_cookiesize;
__u32 tgts_size; /* size of tgts array */
struct lmv_tgt_desc **tgts;
#define LUSTRE_MGS_OBDNAME "MGS"
#define LUSTRE_MGC_OBDNAME "MGC"
-struct obd_trans_info {
- __u64 oti_xid;
- /* Only used on the server side for tracking acks. */
- struct oti_req_ack_lock {
- struct lustre_handle lock;
- __u32 mode;
- } oti_ack_locks[4];
- void *oti_handle;
- struct llog_cookie oti_onecookie;
- struct llog_cookie *oti_logcookies;
-
- /** VBR: versions */
- __u64 oti_pre_version;
-};
-
/*
* Events signalled through obd_notify() upcall-chain.
*/
* (for /proc/status only!!) */
obd_no_ir:1, /* no imperative recovery. */
obd_process_conf:1, /* device is processing mgs config */
- obd_uses_nid_stats:1; /* maintain per-client OBD stats */
+ obd_uses_nid_stats:1, /* maintain per-client OBD stats */
+ obd_force_abort_recovery:1; /* abort recovery forcely */
/* use separate field as it is set in interrupt to don't mess with
* protection of other bits using _bh lock */
unsigned long obd_recovery_expired:1;
/* uuid-export hash body */
- cfs_hash_t *obd_uuid_hash;
+ struct cfs_hash *obd_uuid_hash;
/* nid-export hash body */
- cfs_hash_t *obd_nid_hash;
+ struct cfs_hash *obd_nid_hash;
/* nid stats body */
- cfs_hash_t *obd_nid_stats_hash;
+ struct cfs_hash *obd_nid_stats_hash;
struct list_head obd_nid_stats;
atomic_t obd_refcount;
struct list_head obd_exports;
struct proc_dir_entry *obd_proc_exports_entry;
struct proc_dir_entry *obd_svc_procroot;
struct lprocfs_stats *obd_svc_stats;
- struct lprocfs_seq_vars *obd_vars;
+ struct lprocfs_vars *obd_vars;
atomic_t obd_evict_inprogress;
wait_queue_head_t obd_evict_inprogress_waitq;
struct list_head obd_evict_list; /* protected with pet_lock */
/* get/set_info keys */
#define KEY_ASYNC "async"
-#define KEY_CAPA_KEY "capa_key"
#define KEY_CHANGELOG_CLEAR "changelog_clear"
#define KEY_FID2PATH "fid2path"
#define KEY_CHECKSUM "checksum"
#define KEY_INTERMDS "inter_mds"
#define KEY_LAST_ID "last_id"
#define KEY_LAST_FID "last_fid"
-#define KEY_LOVDESC "lovdesc"
#define KEY_MAX_EASIZE "max_easize"
#define KEY_DEFAULT_EASIZE "default_easize"
-#define KEY_MAX_COOKIESIZE "max_cookiesize"
-#define KEY_DEFAULT_COOKIESIZE "default_cookiesize"
#define KEY_MGSSEC "mgssec"
#define KEY_READ_ONLY "read-only"
#define KEY_REGISTER_TARGET "register_target"
return -EINVAL;
}
+enum md_op_flags {
+ MF_MDC_CANCEL_FID1 = 1 << 0,
+ MF_MDC_CANCEL_FID2 = 1 << 1,
+ MF_MDC_CANCEL_FID3 = 1 << 2,
+ MF_MDC_CANCEL_FID4 = 1 << 3,
+ MF_GET_MDT_IDX = 1 << 4,
+};
+
enum md_cli_flags {
CLI_SET_MEA = 1 << 0,
CLI_RM_ENTRY = 1 << 1,
struct lu_fid op_fid3; /* 2 extra fids to find conflicting */
struct lu_fid op_fid4; /* to the operation locks. */
u32 op_mds; /* what mds server open will go to */
- struct lustre_handle op_handle;
- obd_time op_mod_time;
+ struct lustre_handle op_handle;
+ s64 op_mod_time;
const char *op_name;
size_t op_namelen;
__u32 op_mode;
unsigned int op_attr_flags; /* LUSTRE_{SYNC,..}_FL */
__u64 op_valid; /* OBD_MD_* */
- /* Size-on-MDS epoch and flags. */
- __u64 op_ioepoch;
enum md_op_flags op_flags;
- /* Capa fields */
- struct obd_capa *op_capa1;
- struct obd_capa *op_capa2;
-
/* Various operation flags. */
enum mds_op_bias op_bias;
/* File object data version for HSM release, on client */
__u64 op_data_version;
struct lustre_handle op_lease_handle;
+
+ /* default stripe offset */
+ __u32 op_default_stripe_offset;
};
struct md_callback {
struct module *o_owner;
int (*o_iocontrol)(unsigned int cmd, struct obd_export *exp, int len,
void *karg, void __user *uarg);
- int (*o_get_info)(const struct lu_env *env, struct obd_export *,
- __u32 keylen, void *key, __u32 *vallen, void *val,
- struct lov_stripe_md *lsm);
- int (*o_set_info_async)(const struct lu_env *, struct obd_export *,
- __u32 keylen, void *key,
- __u32 vallen, void *val,
- struct ptlrpc_request_set *set);
+ int (*o_get_info)(const struct lu_env *env, struct obd_export *,
+ __u32 keylen, void *key, __u32 *vallen, void *val);
+ int (*o_set_info_async)(const struct lu_env *, struct obd_export *,
+ __u32 keylen, void *key,
+ __u32 vallen, void *val,
+ struct ptlrpc_request_set *set);
int (*o_setup) (struct obd_device *dev, struct lustre_cfg *cfg);
int (*o_precleanup)(struct obd_device *dev,
enum obd_cleanup_stage cleanup_stage);
int (*o_cleanup)(struct obd_device *dev);
- int (*o_process_config)(struct obd_device *dev, obd_count len,
- void *data);
+ int (*o_process_config)(struct obd_device *dev, size_t len, void *data);
int (*o_postrecov)(struct obd_device *dev);
int (*o_add_conn)(struct obd_import *imp, struct obd_uuid *uuid,
int priority);
struct obd_statfs *osfs, __u64 max_age, __u32 flags);
int (*o_statfs_async)(struct obd_export *exp, struct obd_info *oinfo,
__u64 max_age, struct ptlrpc_request_set *set);
- int (*o_packmd)(struct obd_export *exp, struct lov_mds_md **disk_tgt,
- struct lov_stripe_md *mem_src);
- int (*o_unpackmd)(struct obd_export *exp,struct lov_stripe_md **mem_tgt,
- struct lov_mds_md *disk_src, int disk_len);
int (*o_create)(const struct lu_env *env, struct obd_export *exp,
- struct obdo *oa, struct obd_trans_info *oti);
+ struct obdo *oa);
int (*o_destroy)(const struct lu_env *env, struct obd_export *exp,
- struct obdo *oa, struct obd_trans_info *oti);
- int (*o_setattr)(const struct lu_env *, struct obd_export *exp,
- struct obd_info *oinfo, struct obd_trans_info *oti);
- int (*o_setattr_async)(struct obd_export *exp, struct obd_info *oinfo,
- struct obd_trans_info *oti,
- struct ptlrpc_request_set *rqset);
- int (*o_getattr)(const struct lu_env *env, struct obd_export *exp,
- struct obd_info *oinfo);
- int (*o_getattr_async)(struct obd_export *exp, struct obd_info *oinfo,
- struct ptlrpc_request_set *set);
- int (*o_preprw)(const struct lu_env *env, int cmd,
- struct obd_export *exp, struct obdo *oa, int objcount,
- struct obd_ioobj *obj, struct niobuf_remote *remote,
- int *nr_pages, struct niobuf_local *local,
- struct obd_trans_info *oti, struct lustre_capa *capa);
- int (*o_commitrw)(const struct lu_env *env, int cmd,
- struct obd_export *exp, struct obdo *oa,
- int objcount, struct obd_ioobj *obj,
- struct niobuf_remote *remote, int pages,
- struct niobuf_local *local,
- struct obd_trans_info *oti, int rc);
- int (*o_change_cbdata)(struct obd_export *, struct lov_stripe_md *,
- ldlm_iterator_t it, void *data);
- int (*o_find_cbdata)(struct obd_export *, struct lov_stripe_md *,
- ldlm_iterator_t it, void *data);
+ struct obdo *oa);
+ int (*o_setattr)(const struct lu_env *, struct obd_export *exp,
+ struct obdo *oa);
+ int (*o_getattr)(const struct lu_env *env, struct obd_export *exp,
+ struct obdo *oa);
+ int (*o_preprw)(const struct lu_env *env, int cmd,
+ struct obd_export *exp, struct obdo *oa, int objcount,
+ struct obd_ioobj *obj, struct niobuf_remote *remote,
+ int *nr_pages, struct niobuf_local *local);
+ int (*o_commitrw)(const struct lu_env *env, int cmd,
+ struct obd_export *exp, struct obdo *oa,
+ int objcount, struct obd_ioobj *obj,
+ struct niobuf_remote *remote, int pages,
+ struct niobuf_local *local, int rc);
int (*o_init_export)(struct obd_export *exp);
int (*o_destroy_export)(struct obd_export *exp);
struct obd_uuid *(*o_get_uuid) (struct obd_export *exp);
/* quota methods */
- int (*o_quotacheck)(struct obd_device *, struct obd_export *,
- struct obd_quotactl *);
int (*o_quotactl)(struct obd_device *, struct obd_export *,
struct obd_quotactl *);
/* lmv structures */
struct lustre_md {
struct mdt_body *body;
- struct lov_stripe_md *lsm;
+ struct lu_buf layout;
struct lmv_stripe_md *lmv;
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *posix_acl;
#endif
struct mdt_remote_perm *remote_perm;
- struct obd_capa *mds_capa;
- struct obd_capa *oss_capa;
};
struct md_open_data {
struct ptlrpc_request **);
int (*m_setattr)(struct obd_export *, struct md_op_data *, void *,
- size_t , void *, size_t, struct ptlrpc_request **,
- struct md_open_data **mod);
+ size_t , struct ptlrpc_request **);
int (*m_fsync)(struct obd_export *, const struct lu_fid *,
- struct obd_capa *, struct ptlrpc_request **);
+ struct ptlrpc_request **);
int (*m_read_page)(struct obd_export *, struct md_op_data *,
struct md_callback *cb_op, __u64 hash_offset,
struct ptlrpc_request **);
int (*m_setxattr)(struct obd_export *, const struct lu_fid *,
- struct obd_capa *, obd_valid, const char *,
- const char *, int, int, int, __u32,
+ u64, const char *, const char *, int, int, int, u32,
struct ptlrpc_request **);
int (*m_getxattr)(struct obd_export *, const struct lu_fid *,
- struct obd_capa *, obd_valid, const char *,
- const char *, int, int, int,
+ u64, const char *, const char *, int, int, int,
struct ptlrpc_request **);
int (*m_intent_getattr_async)(struct obd_export *,
#define MD_STATS_LAST_OP m_revalidate_lock
- int (*m_getstatus)(struct obd_export *, struct lu_fid *,
- struct obd_capa **);
-
+ int (*m_getstatus)(struct obd_export *, struct lu_fid *);
int (*m_null_inode)(struct obd_export *, const struct lu_fid *);
int (*m_find_cbdata)(struct obd_export *, const struct lu_fid *,
ldlm_iterator_t, void *);
- int (*m_done_writing)(struct obd_export *, struct md_op_data *,
- struct md_open_data *);
-
int (*m_getattr_name)(struct obd_export *, struct md_op_data *,
struct ptlrpc_request **);
- int (*m_init_ea_size)(struct obd_export *, __u32, __u32, __u32, __u32);
+ int (*m_init_ea_size)(struct obd_export *, __u32, __u32);
int (*m_get_lustre_md)(struct obd_export *, struct ptlrpc_request *,
struct obd_export *, struct obd_export *,
int (*m_merge_attr)(struct obd_export *,
const struct lmv_stripe_md *lsm,
- struct cl_attr *attr);
-
- int (*m_update_lsm_md)(struct obd_export *, struct lmv_stripe_md *lsm,
- struct mdt_body *, ldlm_blocking_callback);
+ struct cl_attr *attr, ldlm_blocking_callback);
int (*m_set_open_replay_data)(struct obd_export *,
struct obd_client_handle *,
ldlm_policy_data_t *, ldlm_mode_t,
ldlm_cancel_flags_t flags, void *opaque);
- int (*m_renew_capa)(struct obd_export *, struct obd_capa *oc,
- renew_capa_cb_t cb);
-
- int (*m_unpack_capa)(struct obd_export *, struct ptlrpc_request *,
- const struct req_msg_field *, struct obd_capa **);
-
int (*m_get_remote_perm)(struct obd_export *, const struct lu_fid *,
- struct obd_capa *, __u32,
- struct ptlrpc_request **);
+ u32, struct ptlrpc_request **);
int (*m_get_fid_from_lsm)(struct obd_export *,
const struct lmv_stripe_md *,
const char *name, int namelen,
struct lu_fid *fid);
+ int (*m_unpackmd)(struct obd_export *exp, struct lmv_stripe_md **plsm,
+ const union lmv_mds_md *lmv, size_t lmv_size);
};
-struct lsm_operations {
- void (*lsm_free)(struct lov_stripe_md *);
- void (*lsm_stripe_by_index)(struct lov_stripe_md *, int *, obd_off *,
- obd_off *);
- void (*lsm_stripe_by_offset)(struct lov_stripe_md *, int *, obd_off *,
- obd_off *);
- int (*lsm_lmm_verify) (struct lov_mds_md *lmm, int lmm_bytes,
- __u16 *stripe_count);
- int (*lsm_unpackmd) (struct lov_obd *lov, struct lov_stripe_md *lsm,
- struct lov_mds_md *lmm);
-};
-
-extern const struct lsm_operations lsm_v1_ops;
-extern const struct lsm_operations lsm_v3_ops;
-static inline const struct lsm_operations *lsm_op_find(int magic)
-{
- switch(magic) {
- case LOV_MAGIC_V1:
- return &lsm_v1_ops;
- case LOV_MAGIC_V3:
- return &lsm_v3_ops;
- default:
- CERROR("Cannot recognize lsm_magic %08x\n", magic);
- return NULL;
- }
-}
-
static inline struct md_open_data *obd_mod_alloc(void)
{
struct md_open_data *mod;
} \
})
-void obdo_from_inode(struct obdo *dst, struct inode *src, obd_flag valid);
+void obdo_from_inode(struct obdo *dst, struct inode *src, u64 valid);
void obdo_set_parent_fid(struct obdo *dst, const struct lu_fid *parent);
/* return 1 if client should be resend request */
}
/* we have an idx, read it */
start = name + LUSTRE_VOLATILE_HDR_LEN + 1;
- *idx = strtoul(start, &end, 16);
+ *idx = simple_strtoul(start, &end, 16);
/* error cases:
* no digit, no trailing :, negative value
*/
git://git.whamcloud.com / fs / lustre-release.git / blobdiff