#include <linux/spinlock.h>
-#define IOC_OSC_TYPE 'h'
-#define IOC_OSC_MIN_NR 20
-#define IOC_OSC_SET_ACTIVE _IOWR(IOC_OSC_TYPE, 21, struct obd_device *)
-#define IOC_OSC_MAX_NR 50
-
-#define IOC_MDC_TYPE 'i'
-#define IOC_MDC_MIN_NR 20
-#define IOC_MDC_MAX_NR 50
-
#include "lustre/lustre_idl.h"
#include "lustre_lib.h"
#include "lu_ref.h"
u32 flag;
};
-/* llog contexts */
-enum llog_ctxt_id {
- LLOG_CONFIG_ORIG_CTXT = 0,
- LLOG_CONFIG_REPL_CTXT,
- LLOG_MDS_OST_ORIG_CTXT,
- LLOG_MDS_OST_REPL_CTXT,
- LLOG_SIZE_ORIG_CTXT,
- LLOG_SIZE_REPL_CTXT,
- LLOG_RD1_ORIG_CTXT,
- LLOG_RD1_REPL_CTXT,
- LLOG_TEST_ORIG_CTXT,
- LLOG_TEST_REPL_CTXT,
- LLOG_LOVEA_ORIG_CTXT,
- LLOG_LOVEA_REPL_CTXT,
- LLOG_CHANGELOG_ORIG_CTXT, /**< changelog generation on mdd */
- LLOG_CHANGELOG_REPL_CTXT, /**< changelog access on clients */
- LLOG_CHANGELOG_USER_ORIG_CTXT, /**< for multiple changelog consumers */
- LLOG_AGENT_ORIG_CTXT, /**< agent requests generation on cdt */
- LLOG_MAX_CTXTS
-};
-
struct timeout_item {
enum timeout_event ti_event;
unsigned long ti_timeout;
struct list_head ti_chain;
};
-#define OSC_MAX_RIF_DEFAULT 8
-#define OSC_MAX_RIF_MAX 256
-#define OSC_MAX_DIRTY_DEFAULT (OSC_MAX_RIF_DEFAULT * 4)
-#define OSC_MAX_DIRTY_MB_MAX 2048 /* arbitrary, but < MAX_LONG bytes */
-#define OSC_DEFAULT_RESENDS 10
+#define OBD_MAX_RIF_DEFAULT 8
+#define OBD_MAX_RIF_MAX 512
+#define OSC_MAX_RIF_MAX 256
+#define OSC_MAX_DIRTY_DEFAULT (OBD_MAX_RIF_DEFAULT * 4)
+#define OSC_MAX_DIRTY_MB_MAX 2048 /* arbitrary, but < MAX_LONG bytes */
+#define OSC_DEFAULT_RESENDS 10
/* possible values for fo_sync_lock_cancel */
enum {
NUM_SYNC_ON_CANCEL_STATES
};
-#define MDC_MAX_RIF_DEFAULT 8
-#define MDC_MAX_RIF_MAX 512
-
enum obd_cl_sem_lock_class {
OBD_CLI_SEM_NORMAL,
OBD_CLI_SEM_MGC,
struct sptlrpc_flavor cl_flvr_mgc; /* fixed flavor of mgc->mgs */
/* the grant values are protected by loi_list_lock below */
- long cl_dirty; /* all _dirty_ in bytes */
- long cl_dirty_max; /* allowed w/o rpc */
- long cl_dirty_transit; /* dirty synchronous */
- long cl_avail_grant; /* bytes of credit for ost */
- long cl_lost_grant; /* lost credits (trunc) */
+ unsigned long cl_dirty_pages; /* all _dirty_ in pahges */
+ unsigned long cl_dirty_max_pages; /* allowed w/o rpc */
+ unsigned long cl_dirty_transit; /* dirty synchronous */
+ unsigned long cl_avail_grant; /* bytes of credit for ost */
+ unsigned long cl_lost_grant; /* lost credits (trunc) */
/* since we allocate grant by blocks, we don't know how many grant will
* be used to add a page into cache. As a solution, we reserve maximum
* the extent size. A chunk is max(PAGE_SIZE, OST block size)
*/
int cl_chunkbits;
- int cl_chunk;
int cl_extent_tax; /* extent overhead, by bytes */
/* keep track of objects that have lois that contain pages which
struct list_head cl_loi_hp_ready_list;
struct list_head cl_loi_write_list;
struct list_head cl_loi_read_list;
- int cl_r_in_flight;
- int cl_w_in_flight;
+ __u32 cl_r_in_flight;
+ __u32 cl_w_in_flight;
/* just a sum of the loi/lop pending numbers to be exported by sysfs */
atomic_t cl_pending_w_pages;
atomic_t cl_pending_r_pages;
__u32 cl_max_pages_per_rpc;
- int cl_max_rpcs_in_flight;
+ __u32 cl_max_rpcs_in_flight;
struct obd_histogram cl_read_rpc_hist;
struct obd_histogram cl_write_rpc_hist;
struct obd_histogram cl_read_page_hist;
struct niobuf_local {
__u64 lnb_file_offset;
__u32 lnb_page_offset;
- __u32 len;
- __u32 flags;
- struct page *page;
- struct dentry *dentry;
- int lnb_grant_used;
- int rc;
+ __u32 lnb_len;
+ __u32 lnb_flags;
+ struct page *lnb_page;
+ void *lnb_data;
+ int lnb_rc;
};
#define LUSTRE_FLD_NAME "fld"
#define N_LOCAL_TEMP_PAGE 0x10000000
struct obd_trans_info {
- __u64 oti_transno;
__u64 oti_xid;
/* Only used on the server side for tracking acks. */
struct oti_req_ack_lock {
void *oti_handle;
struct llog_cookie oti_onecookie;
struct llog_cookie *oti_logcookies;
- int oti_numcookies;
- /** synchronous write is needed */
- unsigned long oti_sync_write:1;
- /* initial thread handling transaction */
- struct ptlrpc_thread *oti_thread;
- __u32 oti_conn_cnt;
/** VBR: versions */
__u64 oti_pre_version;
- /** JobID */
- char *oti_jobid;
-
- struct obd_uuid *oti_ost_uuid;
};
-static inline void oti_alloc_cookies(struct obd_trans_info *oti,
- int num_cookies)
-{
- if (!oti)
- return;
-
- if (num_cookies == 1)
- oti->oti_logcookies = &oti->oti_onecookie;
- else
- oti->oti_logcookies = libcfs_kvzalloc(num_cookies * sizeof(oti->oti_onecookie),
- GFP_NOFS);
-
- oti->oti_numcookies = num_cookies;
-}
-
-static inline void oti_free_cookies(struct obd_trans_info *oti)
-{
- if (!oti || !oti->oti_logcookies)
- return;
-
- if (oti->oti_logcookies == &oti->oti_onecookie)
- LASSERT(oti->oti_numcookies == 1);
- else
- kvfree(oti->oti_logcookies);
-
- oti->oti_logcookies = NULL;
- oti->oti_numcookies = 0;
-}
-
/*
* Events signalled through obd_notify() upcall-chain.
*/
};
struct obd_llog_group {
- int olg_seq;
struct llog_ctxt *olg_ctxts[LLOG_MAX_CTXTS];
wait_queue_head_t olg_waitq;
spinlock_t olg_lock;
/* corresponds to one of the obd's */
#define OBD_DEVICE_MAGIC 0XAB5CD6EF
-#define OBD_DEV_BY_DEVNAME 0xffffd0de
struct lvfs_run_ctxt {
struct dt_device *dt;
obd_starting:1, /* started setup */
obd_force:1, /* cleanup with > 0 obd refcount */
obd_fail:1, /* cleanup with failover */
- obd_async_recov:1, /* allow asynchronous orphan cleanup */
obd_no_conn:1, /* deny new connections */
obd_inactive:1, /* device active/inactive
* (for sysfs status only!!)
struct completion obd_kobj_unregister;
};
-#define OBD_LLOG_FL_SENDNOW 0x0001
-#define OBD_LLOG_FL_EXIT 0x0002
-
enum obd_cleanup_stage {
/* Special case hack for MDS LOVs */
OBD_CLEANUP_EARLY,
/* get/set_info keys */
#define KEY_ASYNC "async"
-#define KEY_BLOCKSIZE_BITS "blocksize_bits"
-#define KEY_BLOCKSIZE "blocksize"
#define KEY_CHANGELOG_CLEAR "changelog_clear"
#define KEY_FID2PATH "fid2path"
#define KEY_CHECKSUM "checksum"
#define KEY_GRANT_SHRINK "grant_shrink"
#define KEY_HSM_COPYTOOL_SEND "hsm_send"
#define KEY_INIT_RECOV_BACKUP "init_recov_bk"
-#define KEY_INIT_RECOV "initial_recov"
#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_LOV_IDX "lov_idx"
#define KEY_MAX_EASIZE "max_easize"
#define KEY_DEFAULT_EASIZE "default_easize"
#define KEY_MDS_CONN "mds_conn"
/* KEY_SET_INFO in lustre_idl.h */
#define KEY_SPTLRPC_CONF "sptlrpc_conf"
#define KEY_CONNECT_FLAG "connect_flags"
-#define KEY_SYNC_LOCK_CANCEL "sync_lock_cancel"
#define KEY_CACHE_SET "cache_set"
#define KEY_CACHE_LRU_SHRINK "cache_lru_shrink"
-#define KEY_CHANGELOG_INDEX "changelog_index"
struct lu_context;
/* CREAT needs to be tested before open (both could be set) */
if (it->it_op & IT_CREAT)
return LCK_CW;
- else if (it->it_op & (IT_READDIR | IT_GETATTR | IT_OPEN | IT_LOOKUP |
+ else if (it->it_op & (IT_GETATTR | IT_OPEN | IT_LOOKUP |
IT_LAYOUT))
return LCK_CR;
+ else if (it->it_op & IT_READDIR)
+ return LCK_PR;
else if (it->it_op & IT_GETXATTR)
return LCK_PR;
else if (it->it_op & IT_SETXATTR)
__u32 op_fsgid;
cfs_cap_t op_cap;
void *op_data;
+ size_t op_data_size;
/* iattr fields and blocks. */
struct iattr op_attr;
/* Various operation flags. */
enum mds_op_bias op_bias;
- /* Operation type */
- __u32 op_opc;
-
/* Used by readdir */
__u64 op_offset;
struct lustre_handle op_lease_handle;
};
+#define op_stripe_offset op_ioepoch
+#define op_max_pages op_valid
+
+struct md_callback {
+ int (*md_blocking_ast)(struct ldlm_lock *lock,
+ struct ldlm_lock_desc *desc,
+ void *data, int flag);
+};
+
enum op_cli_flags {
CLI_SET_MEA = 1 << 0,
CLI_RM_ENTRY = 1 << 1,
+ CLI_HASH64 = BIT(2),
+ CLI_API32 = BIT(3),
+ CLI_MIGRATE = BIT(4),
};
struct md_enqueue_info;
__u32 keylen, void *key,
__u32 vallen, void *val,
struct ptlrpc_request_set *set);
- int (*attach)(struct obd_device *dev, u32 len, void *data);
- int (*detach)(struct obd_device *dev);
int (*setup)(struct obd_device *dev, struct lustre_cfg *cfg);
int (*precleanup)(struct obd_device *dev,
enum obd_cleanup_stage cleanup_stage);
int (*fid_fini)(struct obd_device *obd);
/* Allocate new fid according to passed @hint. */
- int (*fid_alloc)(struct obd_export *exp, struct lu_fid *fid,
- struct md_op_data *op_data);
+ int (*fid_alloc)(const struct lu_env *env, struct obd_export *exp,
+ struct lu_fid *fid, struct md_op_data *op_data);
/*
* Object with @fid is getting deleted, we may want to do something
struct niobuf_remote *remote, int pages,
struct niobuf_local *local,
struct obd_trans_info *oti, int rc);
- int (*find_cbdata)(struct obd_export *, struct lov_stripe_md *,
- ldlm_iterator_t it, void *data);
int (*init_export)(struct obd_export *exp);
int (*destroy_export)(struct obd_export *exp);
*/
};
-enum {
- LUSTRE_OPC_MKDIR = (1 << 0),
- LUSTRE_OPC_SYMLINK = (1 << 1),
- LUSTRE_OPC_MKNOD = (1 << 2),
- LUSTRE_OPC_CREATE = (1 << 3),
- LUSTRE_OPC_ANY = (1 << 4)
-};
-
/* lmv structures */
-#define MEA_MAGIC_LAST_CHAR 0xb2221ca1
-#define MEA_MAGIC_ALL_CHARS 0xb222a11c
-#define MEA_MAGIC_HASH_SEGMENT 0xb222a11b
-
-#define MAX_HASH_SIZE_32 0x7fffffffUL
-#define MAX_HASH_SIZE 0x7fffffffffffffffULL
-#define MAX_HASH_HIGHEST_BIT 0x1000000000000000ULL
-
struct lustre_md {
struct mdt_body *body;
struct lov_stripe_md *lsm;
- struct lmv_stripe_md *mea;
+ struct lmv_stripe_md *lmv;
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *posix_acl;
#endif
};
struct lookup_intent;
+struct cl_attr;
struct md_ops {
int (*getstatus)(struct obd_export *, struct lu_fid *);
int (*null_inode)(struct obd_export *, const struct lu_fid *);
- int (*find_cbdata)(struct obd_export *, const struct lu_fid *,
- ldlm_iterator_t, void *);
int (*close)(struct obd_export *, struct md_op_data *,
struct md_open_data *, struct ptlrpc_request **);
int (*create)(struct obd_export *, struct md_op_data *,
int (*done_writing)(struct obd_export *, struct md_op_data *,
struct md_open_data *);
int (*enqueue)(struct obd_export *, struct ldlm_enqueue_info *,
+ const ldlm_policy_data_t *,
struct lookup_intent *, struct md_op_data *,
- struct lustre_handle *, void *, int,
- struct ptlrpc_request **, __u64);
+ struct lustre_handle *, __u64);
int (*getattr)(struct obd_export *, struct md_op_data *,
struct ptlrpc_request **);
int (*getattr_name)(struct obd_export *, struct md_op_data *,
struct ptlrpc_request **);
int (*intent_lock)(struct obd_export *, struct md_op_data *,
- void *, int, struct lookup_intent *, int,
+ struct lookup_intent *,
struct ptlrpc_request **,
ldlm_blocking_callback, __u64);
int (*link)(struct obd_export *, struct md_op_data *,
int (*rename)(struct obd_export *, struct md_op_data *,
const char *, int, const char *, int,
struct ptlrpc_request **);
- int (*is_subdir)(struct obd_export *, const struct lu_fid *,
- const struct lu_fid *,
- struct ptlrpc_request **);
int (*setattr)(struct obd_export *, struct md_op_data *, void *,
int, void *, int, struct ptlrpc_request **,
struct md_open_data **mod);
int (*sync)(struct obd_export *, const struct lu_fid *,
struct ptlrpc_request **);
- int (*readpage)(struct obd_export *, struct md_op_data *,
- struct page **, struct ptlrpc_request **);
-
+ int (*read_page)(struct obd_export *, struct md_op_data *,
+ struct md_callback *cb_op, __u64 hash_offset,
+ struct page **ppage);
int (*unlink)(struct obd_export *, struct md_op_data *,
struct ptlrpc_request **);
int (*free_lustre_md)(struct obd_export *, struct lustre_md *);
+ int (*merge_attr)(struct obd_export *,
+ const struct lmv_stripe_md *lsm,
+ struct cl_attr *attr);
+
+ int (*update_lsm_md)(struct obd_export *, struct lmv_stripe_md *lsm,
+ struct mdt_body *, ldlm_blocking_callback);
+
int (*set_open_replay_data)(struct obd_export *,
struct obd_client_handle *,
struct lookup_intent *);
int (*clear_open_replay_data)(struct obd_export *,
struct obd_client_handle *);
- int (*set_lock_data)(struct obd_export *, __u64 *, void *, __u64 *);
+ int (*set_lock_data)(struct obd_export *, const struct lustre_handle *,
+ void *, __u64 *);
enum ldlm_mode (*lock_match)(struct obd_export *, __u64,
const struct lu_fid *, enum ldlm_type,
ldlm_policy_data_t *, enum ldlm_mode,
enum ldlm_cancel_flags flags, void *opaque);
+ int (*get_fid_from_lsm)(struct obd_export *,
+ const struct lmv_stripe_md *,
+ const char *name, int namelen,
+ struct lu_fid *fid);
+
int (*intent_getattr_async)(struct obd_export *,
struct md_enqueue_info *,
struct ldlm_enqueue_info *);
}
}
-/* Requests for obd_extent_calc() */
-#define OBD_CALC_STRIPE_START 1
-#define OBD_CALC_STRIPE_END 2
-
static inline struct md_open_data *obd_mod_alloc(void)
{
struct md_open_data *mod;
return obd->u.cli.cl_max_pages_per_rpc << PAGE_SHIFT;
}
+/*
+ * when RPC size or the max RPCs in flight is increased, the max dirty pages
+ * of the client should be increased accordingly to avoid sending fragmented
+ * RPCs over the network when the client runs out of the maximum dirty space
+ * when so many RPCs are being generated.
+ */
+static inline void client_adjust_max_dirty(struct client_obd *cli)
+{
+ /* initializing */
+ if (cli->cl_dirty_max_pages <= 0)
+ cli->cl_dirty_max_pages =
+ (OSC_MAX_DIRTY_DEFAULT * 1024 * 1024) >> PAGE_SHIFT;
+ else {
+ unsigned long dirty_max = cli->cl_max_rpcs_in_flight *
+ cli->cl_max_pages_per_rpc;
+
+ if (dirty_max > cli->cl_dirty_max_pages)
+ cli->cl_dirty_max_pages = dirty_max;
+ }
+
+ if (cli->cl_dirty_max_pages > totalram_pages / 8)
+ cli->cl_dirty_max_pages = totalram_pages / 8;
+}
+
#endif /* __OBD_H */