*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
- * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
- *
- * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
- * CA 95054 USA or visit www.sun.com if you need additional information or
- * have any questions.
+ * http://www.gnu.org/licenses/gpl-2.0.html
*
* GPL HEADER END
*/
* Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
- * Copyright (c) 2011, 2014, Intel Corporation.
+ * Copyright (c) 2011, 2017, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
/*
* super-class definitions.
*/
+#include <linux/aio.h>
+#include <linux/fs.h>
+
#include <libcfs/libcfs.h>
#include <lu_object.h>
#include <linux/atomic.h>
#include <linux/radix-tree.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
+#include <linux/pagevec.h>
#include <lustre_dlm.h>
struct obd_info;
*/
loff_t cat_kms;
/** Modification time. Measured in seconds since epoch. */
- time_t cat_mtime;
+ time64_t cat_mtime;
/** Access time. Measured in seconds since epoch. */
- time_t cat_atime;
+ time64_t cat_atime;
/** Change time. Measured in seconds since epoch. */
- time_t cat_ctime;
+ time64_t cat_ctime;
/**
* Blocks allocated to this cl_object on the server file system.
*
/* nlink of the directory */
__u64 cat_nlink;
+
+ /* Project identifier for quota purpose. */
+ __u32 cat_projid;
};
/**
* Fields in cl_attr that are being set.
*/
enum cl_attr_valid {
- CAT_SIZE = 1 << 0,
- CAT_KMS = 1 << 1,
- CAT_MTIME = 1 << 3,
- CAT_ATIME = 1 << 4,
- CAT_CTIME = 1 << 5,
- CAT_BLOCKS = 1 << 6,
- CAT_UID = 1 << 7,
- CAT_GID = 1 << 8
+ CAT_SIZE = 1 << 0,
+ CAT_KMS = 1 << 1,
+ CAT_MTIME = 1 << 3,
+ CAT_ATIME = 1 << 4,
+ CAT_CTIME = 1 << 5,
+ CAT_BLOCKS = 1 << 6,
+ CAT_UID = 1 << 7,
+ CAT_GID = 1 << 8,
+ CAT_PROJID = 1 << 9
};
/**
struct lu_buf cl_buf;
/** size of layout in lov_mds_md format. */
size_t cl_size;
+ /** size of DoM component if exists or zero otherwise */
+ u64 cl_dom_comp_size;
/** Layout generation. */
u32 cl_layout_gen;
+ /** whether layout is a composite one */
+ bool cl_is_composite;
+ /** Whether layout is a HSM released one */
+ bool cl_is_released;
};
/**
* Object getstripe method.
*/
int (*coo_getstripe)(const struct lu_env *env, struct cl_object *obj,
- struct lov_user_md __user *lum);
- /**
- * Find whether there is any callback data (ldlm lock) attached upon
- * the object.
- */
- int (*coo_find_cbdata)(const struct lu_env *env, struct cl_object *obj,
- ldlm_iterator_t iter, void *data);
+ struct lov_user_md __user *lum, size_t size);
/**
* Get FIEMAP mapping from the object.
*/
void (*coo_req_attr_set)(const struct lu_env *env,
struct cl_object *obj,
struct cl_req_attr *attr);
+ /**
+ * Flush \a obj data corresponding to \a lock. Used for DoM
+ * locks in llite's cancelling blocking ast callback.
+ */
+ int (*coo_object_flush)(const struct lu_env *env,
+ struct cl_object *obj,
+ struct ldlm_lock *lock);
};
/**
/** Transient page, the transient cl_page is used to bind a cl_page
* to vmpage which is not belonging to the same object of cl_page.
- * it is used in DirectIO, lockless IO and liblustre. */
+ * it is used in DirectIO and lockless IO. */
CPT_TRANSIENT,
};
struct cl_page {
/** Reference counter. */
atomic_t cp_ref;
- /** Transfer error. */
- int cp_error;
/** An object this page is a part of. Immutable after creation. */
struct cl_object *cp_obj;
/** vmpage */
struct lu_ref_link cp_queue_ref;
/** Assigned if doing a sync_io */
struct cl_sync_io *cp_sync_io;
+ /** layout_entry + stripe index, composed using lov_comp_index() */
+ unsigned int cp_lov_index;
};
/**
*/
int (*cpo_is_vmlocked)(const struct lu_env *env,
const struct cl_page_slice *slice);
+
+ /**
+ * Update file attributes when all we have is this page. Used for tiny
+ * writes to update attributes when we don't have a full cl_io.
+ */
+ void (*cpo_page_touch)(const struct lu_env *env,
+ const struct cl_page_slice *slice, size_t to);
/**
* Page destruction.
*/
const struct cl_page_slice *slice);
/** Destructor. Frees resources and slice itself. */
void (*cpo_fini)(const struct lu_env *env,
- struct cl_page_slice *slice);
+ struct cl_page_slice *slice,
+ struct pagevec *pvec);
/**
* Optional debugging helper. Prints given page slice.
*
* (struct cl_lock) and a list of layers (struct cl_lock_slice), linked to
* cl_lock::cll_layers list through cl_lock_slice::cls_linkage.
*
- * Typical cl_lock consists of the two layers:
+ * Typical cl_lock consists of one layer:
*
- * - vvp_lock (vvp specific data), and
* - lov_lock (lov specific data).
*
* lov_lock contains an array of sub-locks. Each of these sub-locks is a
* normal cl_lock: it has a header (struct cl_lock) and a list of layers:
*
- * - lovsub_lock, and
* - osc_lock
*
* Each sub-lock is associated with a cl_object (representing stripe
/**
* Per-layer part of cl_lock
*
- * \see vvp_lock, lov_lock, lovsub_lock, osc_lock
+ * \see lov_lock, osc_lock
*/
struct cl_lock_slice {
struct cl_lock *cls_lock;
/**
*
- * \see vvp_lock_ops, lov_lock_ops, lovsub_lock_ops, osc_lock_ops
+ * \see lov_lock_ops, osc_lock_ops
*/
struct cl_lock_operations {
/** @{ */
* @anchor for resources
* \retval -ve failure
*
- * \see vvp_lock_enqueue(), lov_lock_enqueue(), lovsub_lock_enqueue(),
- * \see osc_lock_enqueue()
+ * \see lov_lock_enqueue(), osc_lock_enqueue()
*/
int (*clo_enqueue)(const struct lu_env *env,
const struct cl_lock_slice *slice,
/**
* Destructor. Frees resources and the slice.
*
- * \see vvp_lock_fini(), lov_lock_fini(), lovsub_lock_fini(),
- * \see osc_lock_fini()
+ * \see lov_lock_fini(), osc_lock_fini()
*/
void (*clo_fini)(const struct lu_env *env, struct cl_lock_slice *slice);
/**
struct task_struct *pl_owner;
};
-/**
+/**
* A 2-queue of pages. A convenience data-type for common use case, 2-queue
* contains an incoming page list and an outgoing page list.
*/
/** IO types */
enum cl_io_type {
/** read system call */
- CIT_READ,
+ CIT_READ = 1,
/** write system call */
CIT_WRITE,
/** truncate, utime system calls */
*/
CIT_FSYNC,
/**
+ * glimpse. An io context to acquire glimpse lock.
+ */
+ CIT_GLIMPSE,
+ /**
* Miscellaneous io. This is used for occasional io activity that
* doesn't fit into other types. Currently this is used for:
*
* - VM induced page write-out. An io context for writing page out
* for memory cleansing;
*
- * - glimpse. An io context to acquire glimpse lock.
- *
* - grouplock. An io context to acquire group lock.
*
* CIT_MISC io is used simply as a context in which locks and pages
* cl_io_loop() is never called for it.
*/
CIT_MISC,
+ /**
+ * ladvise handling
+ * To give advice about access of a file
+ */
+ CIT_LADVISE,
CIT_OP_NR
};
};
typedef void (*cl_commit_cbt)(const struct lu_env *, struct cl_io *,
- struct cl_page *);
+ struct pagevec *);
struct cl_read_ahead {
/* Maximum page index the readahead window will end.
* This is determined DLM lock coverage, RPC and stripe boundary.
* cra_end is included. */
pgoff_t cra_end;
- /* Release routine. If readahead holds resources underneath, this
+ /* optimal RPC size for this read, by pages */
+ unsigned long cra_rpc_size;
+ /* Release callback. If readahead holds resources underneath, this
* function should be called to release it. */
void (*cra_release)(const struct lu_env *env, void *cbdata);
/* Callback data for cra_release routine */
void *cra_cbdata;
+ /* whether lock is in contention */
+ bool cra_contention;
};
static inline void cl_read_ahead_release(const struct lu_env *env,
* -EWOULDBLOCK is returned immediately.
*/
CEF_NONBLOCK = 0x00000001,
- /**
- * take lock asynchronously (out of order), as it cannot
- * deadlock. This is for LDLM_FL_HAS_INTENT locks used for glimpsing.
- */
- CEF_ASYNC = 0x00000002,
+ /**
+ * Tell lower layers this is a glimpse request, translated to
+ * LDLM_FL_HAS_INTENT at LDLM layer.
+ *
+ * Also, because glimpse locks never block other locks, we count this
+ * as automatically compatible with other osc locks.
+ * (see osc_lock_compatible)
+ */
+ CEF_GLIMPSE = 0x00000002,
/**
* tell the server to instruct (though a flag in the blocking ast) an
* owner of the conflicting lock, that it can drop dirty pages
* protected by this lock, without sending them to the server.
*/
CEF_DISCARD_DATA = 0x00000004,
- /**
- * tell the sub layers that it must be a `real' lock. This is used for
- * mmapped-buffer locks and glimpse locks that must be never converted
- * into lockless mode.
- *
- * \see vvp_mmap_locks(), cl_glimpse_lock().
- */
- CEF_MUST = 0x00000008,
+ /**
+ * tell the sub layers that it must be a `real' lock. This is used for
+ * mmapped-buffer locks, glimpse locks, manually requested locks
+ * (LU_LADVISE_LOCKAHEAD) that must never be converted into lockless
+ * mode.
+ *
+ * \see vvp_mmap_locks(), cl_glimpse_lock, cl_request_lock().
+ */
+ CEF_MUST = 0x00000008,
/**
* tell the sub layers that never request a `real' lock. This flag is
* not used currently.
*/
CEF_NEVER = 0x00000010,
/**
- * for async glimpse lock.
+ * tell the dlm layer this is a speculative lock request
+ * speculative lock requests are locks which are not requested as part
+ * of an I/O operation. Instead, they are requested because we expect
+ * to use them in the future. They are requested asynchronously at the
+ * ptlrpc layer.
+ *
+ * Currently used for asynchronous glimpse locks and manually requested
+ * locks (LU_LADVISE_LOCKAHEAD).
*/
- CEF_AGL = 0x00000020,
+ CEF_SPECULATIVE = 0x00000020,
/**
* enqueue a lock to test DLM lock existence.
*/
*/
CEF_LOCK_MATCH = 0x00000080,
/**
+ * tell the DLM layer to lock only the requested range
+ */
+ CEF_LOCK_NO_EXPAND = 0x00000100,
+ /**
* mask of enq_flags.
*/
- CEF_MASK = 0x000000ff,
+ CEF_MASK = 0x000001ff,
};
/**
};
struct cl_io_rw_common {
- loff_t crw_pos;
- size_t crw_count;
- int crw_nonblock;
+ loff_t crw_pos;
+ size_t crw_count;
+ int crw_nonblock;
};
-
/**
* State for io.
*
struct cl_lockset ci_lockset;
/** lock requirements, this is just a help info for sublayers. */
enum cl_io_lock_dmd ci_lockreq;
- union {
- struct cl_rd_io {
- struct cl_io_rw_common rd;
- } ci_rd;
+ /** layout version when this IO occurs */
+ __u32 ci_layout_version;
+ union {
+ struct cl_rd_io {
+ struct cl_io_rw_common rd;
+ } ci_rd;
struct cl_wr_io {
struct cl_io_rw_common wr;
int wr_append;
struct cl_setattr_io {
struct ost_lvb sa_attr;
unsigned int sa_attr_flags;
- unsigned int sa_valid;
+ unsigned int sa_avalid; /* ATTR_* */
+ unsigned int sa_xvalid; /* OP_XVALID */
int sa_stripe_index;
+ struct ost_layout sa_layout;
const struct lu_fid *sa_parent_fid;
} ci_setattr;
struct cl_data_version_io {
u64 dv_data_version;
+ u32 dv_layout_version;
int dv_flags;
} ci_data_version;
struct cl_fault_io {
/* how many pages were written/discarded */
unsigned int fi_nr_written;
} ci_fsync;
+ struct cl_ladvise_io {
+ __u64 li_start;
+ __u64 li_end;
+ /** file system level fid */
+ struct lu_fid *li_fid;
+ enum lu_ladvise_type li_advice;
+ __u64 li_flags;
+ } ci_ladvise;
} u;
struct cl_2queue ci_queue;
size_t ci_nob;
*/
ci_ignore_layout:1,
/**
+ * Need MDS intervention to complete a write.
+ * Write intent is required for the following cases:
+ * 1. component being written is not initialized, or
+ * 2. the mirrored files are NOT in WRITE_PENDING state.
+ */
+ ci_need_write_intent:1,
+ /**
* Check if layout changed after the IO finishes. Mainly for HSM
* requirement. If IO occurs to openning files, it doesn't need to
* verify layout because HSM won't release openning files.
/**
* O_NOATIME
*/
- ci_noatime:1;
+ ci_noatime:1,
+ /* Tell sublayers not to expand LDLM locks requested for this IO */
+ ci_lock_no_expand:1,
+ /**
+ * Set if non-delay RPC should be used for this IO.
+ *
+ * If this file has multiple mirrors, and if the OSTs of the current
+ * mirror is inaccessible, non-delay RPC would error out quickly so
+ * that the upper layer can try to access the next mirror.
+ */
+ ci_ndelay:1,
+ /**
+ * Set if IO is triggered by async workqueue readahead.
+ */
+ ci_async_readahead:1,
+ /**
+ * Set if we've tried all mirrors for this read IO, if it's not set,
+ * the read IO will check to-be-read OSCs' status, and make fast-switch
+ * another mirror if some of the OSTs are not healthy.
+ */
+ ci_tried_all_mirrors:1;
+ /**
+ * How many times the read has retried before this one.
+ * Set by the top level and consumed by the LOV.
+ */
+ unsigned ci_ndelay_tried;
+ /**
+ * Designated mirror index for this I/O.
+ */
+ unsigned ci_designated_mirror;
/**
* Number of pages owned by this IO. For invariant checking.
*/
unsigned ci_owned_nr;
+ /**
+ * Range of write intent. Valid if ci_need_write_intent is set.
+ */
+ struct lu_extent ci_write_intent;
};
/** @} cl_io */
int cl_object_prune (const struct lu_env *env, struct cl_object *obj);
void cl_object_kill (const struct lu_env *env, struct cl_object *obj);
int cl_object_getstripe(const struct lu_env *env, struct cl_object *obj,
- struct lov_user_md __user *lum);
-int cl_object_find_cbdata(const struct lu_env *env, struct cl_object *obj,
- ldlm_iterator_t iter, void *data);
+ struct lov_user_md __user *lum, size_t size);
int cl_object_fiemap(const struct lu_env *env, struct cl_object *obj,
struct ll_fiemap_info_key *fmkey, struct fiemap *fiemap,
size_t *buflen);
int cl_object_layout_get(const struct lu_env *env, struct cl_object *obj,
struct cl_layout *cl);
loff_t cl_object_maxbytes(struct cl_object *obj);
+int cl_object_flush(const struct lu_env *env, struct cl_object *obj,
+ struct ldlm_lock *lock);
+
/**
* Returns true, iff \a o0 and \a o1 are slices of the same object.
void cl_page_get (struct cl_page *page);
void cl_page_put (const struct lu_env *env,
struct cl_page *page);
+void cl_pagevec_put (const struct lu_env *env,
+ struct cl_page *page,
+ struct pagevec *pvec);
void cl_page_print (const struct lu_env *env, void *cookie,
lu_printer_t printer,
const struct cl_page *pg);
void cl_page_delete(const struct lu_env *env, struct cl_page *pg);
int cl_page_is_vmlocked(const struct lu_env *env,
const struct cl_page *pg);
+void cl_page_touch(const struct lu_env *env, const struct cl_page *pg,
+ size_t to);
void cl_page_export(const struct lu_env *env,
struct cl_page *pg, int uptodate);
loff_t cl_offset(const struct cl_object *obj, pgoff_t idx);
size_t nob);
int cl_io_cancel (const struct lu_env *env, struct cl_io *io,
struct cl_page_list *queue);
-int cl_io_is_going (const struct lu_env *env);
/**
* True, iff \a io is an O_APPEND write(2).
*/
static inline int cl_io_is_append(const struct cl_io *io)
{
- return io->ci_type == CIT_WRITE && io->u.ci_wr.wr_append;
+ return io->ci_type == CIT_WRITE && io->u.ci_wr.wr_append;
}
static inline int cl_io_is_sync_write(const struct cl_io *io)
*/
static inline int cl_io_is_trunc(const struct cl_io *io)
{
- return io->ci_type == CIT_SETATTR &&
- (io->u.ci_setattr.sa_valid & ATTR_SIZE);
+ return io->ci_type == CIT_SETATTR &&
+ (io->u.ci_setattr.sa_avalid & ATTR_SIZE);
}
struct cl_io *cl_io_top(struct cl_io *io);
void cl_io_print(const struct lu_env *env, void *cookie,
lu_printer_t printer, const struct cl_io *io);
-#define CL_IO_SLICE_CLEAN(foo_io, base) \
-do { \
- typeof(foo_io) __foo_io = (foo_io); \
- \
- CLASSERT(offsetof(typeof(*__foo_io), base) == 0); \
- memset(&__foo_io->base + 1, 0, \
- (sizeof *__foo_io) - sizeof __foo_io->base); \
+#define CL_IO_SLICE_CLEAN(foo_io, base) \
+do { \
+ typeof(foo_io) __foo_io = (foo_io); \
+ \
+ memset(&__foo_io->base, 0, \
+ sizeof(*__foo_io) - offsetof(typeof(*__foo_io), base)); \
} while (0)
/** @} cl_io */
struct cl_page_list *plist, struct cl_page *page);
void cl_page_list_disown (const struct lu_env *env,
struct cl_io *io, struct cl_page_list *plist);
-int cl_page_list_own (const struct lu_env *env,
- struct cl_io *io, struct cl_page_list *plist);
void cl_page_list_assume (const struct lu_env *env,
struct cl_io *io, struct cl_page_list *plist);
void cl_page_list_discard(const struct lu_env *env,
/** \defgroup cl_sync_io cl_sync_io
* @{ */
+struct cl_sync_io;
+
+typedef void (cl_sync_io_end_t)(const struct lu_env *, struct cl_sync_io *);
+
+void cl_sync_io_init_notify(struct cl_sync_io *anchor, int nr,
+ cl_sync_io_end_t *end);
+
+int cl_sync_io_wait(const struct lu_env *env, struct cl_sync_io *anchor,
+ long timeout);
+void cl_sync_io_note(const struct lu_env *env, struct cl_sync_io *anchor,
+ int ioret);
+static inline void cl_sync_io_init(struct cl_sync_io *anchor, int nr)
+{
+ cl_sync_io_init_notify(anchor, nr, NULL);
+}
+
/**
* Anchor for synchronous transfer. This is allocated on a stack by thread
* doing synchronous transfer, and a pointer to this structure is set up in
atomic_t csi_sync_nr;
/** error code. */
int csi_sync_rc;
- /** barrier of destroy this structure */
- atomic_t csi_barrier;
/** completion to be signaled when transfer is complete. */
wait_queue_head_t csi_waitq;
/** callback to invoke when this IO is finished */
- void (*csi_end_io)(const struct lu_env *,
- struct cl_sync_io *);
+ cl_sync_io_end_t *csi_end_io;
};
-void cl_sync_io_init(struct cl_sync_io *anchor, int nr,
- void (*end)(const struct lu_env *, struct cl_sync_io *));
-int cl_sync_io_wait(const struct lu_env *env, struct cl_sync_io *anchor,
- long timeout);
-void cl_sync_io_note(const struct lu_env *env, struct cl_sync_io *anchor,
- int ioret);
-void cl_sync_io_end(const struct lu_env *env, struct cl_sync_io *anchor);
-
/** @} cl_sync_io */
/** \defgroup cl_env cl_env
* - allocation and destruction of environment is amortized by caching no
* longer used environments instead of destroying them;
*
- * - there is a notion of "current" environment, attached to the kernel
- * data structure representing current thread Top-level lustre code
- * allocates an environment and makes it current, then calls into
- * non-lustre code, that in turn calls lustre back. Low-level lustre
- * code thus called can fetch environment created by the top-level code
- * and reuse it, avoiding additional environment allocation.
- * Right now, three interfaces can attach the cl_env to running thread:
- * - cl_env_get
- * - cl_env_implant
- * - cl_env_reexit(cl_env_reenter had to be called priorly)
- *
* \see lu_env, lu_context, lu_context_key
* @{ */
-struct cl_env_nest {
- int cen_refcheck;
- void *cen_cookie;
-};
-
-struct lu_env *cl_env_peek (int *refcheck);
-struct lu_env *cl_env_get (int *refcheck);
-struct lu_env *cl_env_alloc (int *refcheck, __u32 tags);
-struct lu_env *cl_env_nested_get (struct cl_env_nest *nest);
-void cl_env_put (struct lu_env *env, int *refcheck);
-void cl_env_nested_put (struct cl_env_nest *nest, struct lu_env *env);
-void *cl_env_reenter (void);
-void cl_env_reexit (void *cookie);
-void cl_env_implant (struct lu_env *env, int *refcheck);
-void cl_env_unplant (struct lu_env *env, int *refcheck);
-unsigned cl_env_cache_purge(unsigned nr);
-struct lu_env *cl_env_percpu_get (void);
-void cl_env_percpu_put (struct lu_env *env);
+struct lu_env *cl_env_get(__u16 *refcheck);
+struct lu_env *cl_env_alloc(__u16 *refcheck, __u32 tags);
+void cl_env_put(struct lu_env *env, __u16 *refcheck);
+unsigned cl_env_cache_purge(unsigned nr);
+struct lu_env *cl_env_percpu_get(void);
+void cl_env_percpu_put(struct lu_env *env);
/** @} cl_env */
git://git.whamcloud.com / fs / lustre-release.git / blobdiff