* 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/
#ifndef __OBD_H
#define __OBD_H
-#include <linux/obd.h>
+#include <linux/spinlock.h>
#include <lustre/lustre_idl.h>
#include <lustre_lib.h>
{
}
-/* Until such time as we get_info the per-stripe maximum from the OST,
- * we define this to be 2T - 4k, which is the ext3 maxbytes. */
-#define LUSTRE_STRIPE_MAXBYTES 0x1fffffff000ULL
+/* 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;
/* 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]; /* pool name */
- } lsm_wire;
-
- struct lov_oinfo *lsm_oinfo[0];
+ __u64 lsm_maxbytes;
+ struct ost_id lsm_oi;
+ __u32 lsm_magic;
+ __u32 lsm_stripe_size;
+ __u32 lsm_pattern; /* RAID0, RAID1, released, ... */
+ __u16 lsm_stripe_count;
+ __u16 lsm_layout_gen;
+ char lsm_pool_name[LOV_MAXPOOLNAME + 1];
+ 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);
/* 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;
};
struct brw_page {
- obd_off off;
- struct page *pg;
- 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
+#define OBD_MAX_DEFAULT_COOKIE_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. */
- int cl_default_mds_easize;
- int cl_max_mds_easize;
- int cl_default_mds_cookiesize;
- int 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 */
+ 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 and cookiesize. 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;
+
+ /* Default cookie size for llog cookies (see struct llog_cookie). It is
+ * initialized to zero at mount-time, then it tracks the largest
+ * observed cookie size advertised by the MDT, up to a maximum value of
+ * OBD_MAX_DEFAULT_COOKIE_SIZE. Note that llog_cookies are not
+ * used by clients communicating with MDS versions 2.4.0 and later.*/
+ __u32 cl_default_mds_cookiesize;
+
+ /* Maximum possible cookie 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_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 */
/* 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
* blocking everywhere, but we don't want to slow down fast-path of
* our main platform.)
*
- * Exact type of ->cl_loi_list_lock is defined in arch/obd.h together
- * with client_obd_list_{un,}lock() and
- * client_obd_list_lock_{init,done}() functions.
- *
* NB by Jinshan: though field names are still _loi_, but actually
* osc_object{}s are in the list.
*/
- client_obd_lock_t cl_loi_list_lock;
+ spinlock_t cl_loi_list_lock;
struct list_head cl_loi_ready_list;
struct list_head cl_loi_hp_ready_list;
struct list_head cl_loi_write_list;
/* lru for osc caching pages */
struct cl_client_cache *cl_cache;
struct list_head cl_lru_osc; /* member of cl_cache->ccc_lru */
- atomic_t *cl_lru_left;
- atomic_t cl_lru_busy;
- atomic_t cl_lru_shrinkers;
- atomic_t cl_lru_in_list;
+ atomic_long_t *cl_lru_left;
+ atomic_long_t cl_lru_busy;
+ atomic_long_t cl_lru_in_list;
+ atomic_long_t cl_unstable_count;
struct list_head cl_lru_list; /* lru page list */
- client_obd_lock_t cl_lru_list_lock; /* page list protector */
- atomic_t cl_unstable_count;
+ spinlock_t cl_lru_list_lock; /* page list protector */
+ atomic_t cl_lru_shrinkers;
/* number of in flight destroy rpcs is limited to max_rpcs_in_flight */
atomic_t cl_destroy_in_flight;
#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 {
spinlock_t ec_lock;
struct list_head ec_objects;
struct list_head ec_locks;
- int ec_nstripes;
__u64 ec_unique;
};
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;
};
struct lmv_tgt_desc {
struct obd_uuid ltd_uuid;
struct obd_export *ltd_exp;
- int ltd_idx;
+ __u32 ltd_idx;
struct mutex ltd_fid_mutex;
unsigned long ltd_active:1; /* target up for requests */
};
struct obd_export *exp;
struct proc_dir_entry *targets_proc_entry;
- struct mutex init_mutex;
+ struct mutex lmv_init_mutex;
int connected;
int max_easize;
int max_def_easize;
int max_cookiesize;
int max_def_cookiesize;
- int server_timeout;
- int tgts_size; /* size of tgts array */
+ __u32 tgts_size; /* size of tgts array */
struct lmv_tgt_desc **tgts;
struct obd_connect_data conn_data;
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 */
#define KEY_INTERMDS "inter_mds"
#define KEY_LAST_ID "last_id"
#define KEY_LAST_FID "last_fid"
-#define KEY_LOCK_TO_STRIPE "lock_to_stripe"
#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_MDS_CONN "mds_conn"
#define KEY_MGSSEC "mgssec"
-#define KEY_NEXT_ID "next_id"
#define KEY_READ_ONLY "read-only"
#define KEY_REGISTER_TARGET "register_target"
#define KEY_SET_FS "set_fs"
#define KEY_TGT_COUNT "tgt_count"
/* KEY_SET_INFO in lustre_idl.h */
#define KEY_SPTLRPC_CONF "sptlrpc_conf"
-#define KEY_CONNECT_FLAG "connect_flags"
#define KEY_CACHE_SET "cache_set"
#define KEY_CACHE_LRU_SHRINK "cache_lru_shrink"
return -EINVAL;
}
+enum md_cli_flags {
+ CLI_SET_MEA = 1 << 0,
+ CLI_RM_ENTRY = 1 << 1,
+ CLI_HASH64 = 1 << 2,
+ CLI_API32 = 1 << 3,
+ CLI_MIGRATE = 1 << 4,
+};
+
struct md_op_data {
struct lu_fid op_fid1; /* operation fid1 (usualy parent) */
struct lu_fid op_fid2; /* operation fid2 (usualy child) */
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;
- int op_namelen;
+ size_t op_namelen;
__u32 op_mode;
struct lmv_stripe_md *op_mea1;
struct lmv_stripe_md *op_mea2;
size_t op_data_size;
/* iattr fields and blocks. */
- struct iattr op_attr;
- __u64 op_valid;
+ struct iattr op_attr;
loff_t op_attr_blocks;
+ unsigned int op_attr_flags; /* LUSTRE_{SYNC,..}_FL */
+ __u64 op_valid; /* OBD_MD_* */
- /* Size-on-MDS epoch and flags. */
- __u64 op_ioepoch;
- __u32 op_flags;
+ enum md_op_flags op_flags;
/* Capa fields */
struct obd_capa *op_capa1;
enum mds_op_bias op_bias;
/* Used by readdir */
- __u32 op_npages;
+ unsigned int op_max_pages;
/* used to transfer info between the stacks of MD client
* see enum op_cli_flags */
- __u32 op_cli_flags;
+ enum md_cli_flags op_cli_flags;
/* File object data version for HSM release, on client */
__u64 op_data_version;
struct lustre_handle op_lease_handle;
-};
-#define op_stripe_offset op_ioepoch
-#define op_max_pages op_valid
+ /* default stripe offset */
+ __u32 op_default_stripe_offset;
+};
struct md_callback {
int (*md_blocking_ast)(struct ldlm_lock *lock,
int rc);
struct md_enqueue_info {
- struct md_op_data mi_data;
- struct lookup_intent mi_it;
- struct lustre_handle mi_lockh;
- struct inode *mi_dir;
- md_enqueue_cb_t mi_cb;
- __u64 mi_cbdata;
+ struct md_op_data mi_data;
+ struct lookup_intent mi_it;
+ struct lustre_handle mi_lockh;
+ struct inode *mi_dir;
+ md_enqueue_cb_t mi_cb;
+ void *mi_cbdata;
};
struct obd_ops {
struct module *o_owner;
int (*o_iocontrol)(unsigned int cmd, struct obd_export *exp, int len,
- void *karg, void *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);
+ 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_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 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 lov_stripe_md **ea,
- struct obd_trans_info *oti);
- int (*o_destroy)(const struct lu_env *env, struct obd_export *exp,
- struct obdo *oa, struct lov_stripe_md *ea,
- struct obd_trans_info *oti, struct obd_export *md_exp,
- void *capa);
+ int (*o_create)(const struct lu_env *env, struct obd_export *exp,
+ struct obdo *oa, struct obd_trans_info *oti);
+ 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 *nr_pages, struct niobuf_local *local,
+ struct obd_trans_info *oti);
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);
int (*o_init_export)(struct obd_export *exp);
int (*o_destroy_export)(struct obd_export *exp);
- /* llog related obd_methods */
- int (*o_llog_init)(struct obd_device *obd, struct obd_llog_group *grp,
- struct obd_device *disk_obd, int *idx);
- int (*o_llog_finish)(struct obd_device *obd, int count);
-
int (*o_import_event)(struct obd_device *, struct obd_import *,
enum obd_import_event);
struct md_open_data *, struct ptlrpc_request **);
int (*m_create)(struct obd_export *, struct md_op_data *,
- const void *, int, int, __u32, __u32, cfs_cap_t,
- __u64, struct ptlrpc_request **);
+ const void *, size_t, umode_t, uid_t, gid_t,
+ cfs_cap_t, __u64, struct ptlrpc_request **);
int (*m_enqueue)(struct obd_export *, struct ldlm_enqueue_info *,
const union ldlm_policy_data *,
struct ptlrpc_request **);
int (*m_rename)(struct obd_export *, struct md_op_data *,
- const char *, int, const char *, int,
+ const char *, size_t, const char *, size_t,
struct ptlrpc_request **);
int (*m_setattr)(struct obd_export *, struct md_op_data *, void *,
- int , void *, int, 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_setxattr)(struct obd_export *, const struct lu_fid *,
- struct obd_capa *, obd_valid, const char *,
+ struct obd_capa *, 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 *,
+ struct obd_capa *, u64, const char *,
const char *, int, int, int,
struct ptlrpc_request **);
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 *, int, int, int, int);
+ int (*m_init_ea_size)(struct obd_export *, __u32, __u32, __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 *,
};
struct lsm_operations {
- void (*lsm_free)(struct lov_stripe_md *);
- int (*lsm_destroy)(struct lov_stripe_md *, struct obdo *oa,
- struct obd_export *md_exp);
- 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 *);
+ void (*lsm_free)(struct lov_stripe_md *);
+ void (*lsm_stripe_by_index)(struct lov_stripe_md *, int *,
+ loff_t *, loff_t *);
+ void (*lsm_stripe_by_offset)(struct lov_stripe_md *, int *,
+ loff_t *, loff_t *);
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,
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)
+static inline const struct lsm_operations *lsm_op_find(u32 magic)
{
switch(magic) {
case LOV_MAGIC_V1:
} \
})
-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 */
return lu_dev->ld_obd->obd_name;
}
-static inline bool filename_is_volatile(const char *name, int namelen, int *idx)
+static inline bool filename_is_volatile(const char *name, size_t namelen,
+ int *idx)
{
const char *start;
char *end;
}
/* 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
*/