aio.3

xen 3.2.2 源码

.TH aio 3 2002-09-12 "Linux 2.4" Linux AIO"
.SH NAME
aio \- Asynchronous IO
.SH SYNOPSIS
.nf
.B #include <errno.h>
.sp
.br 
.B #include <aio.h>
.sp
.fi
.SH DESCRIPTION
The POSIX.1b standard defines a new set of I/O operations which can
significantly reduce the time an application spends waiting at I/O.  The
new functions allow a program to initiate one or more I/O operations and
then immediately resume normal work while the I/O operations are
executed in parallel.  This functionality is available if the
.IR "unistd.h"
file defines the symbol 
.B "_POSIX_ASYNCHRONOUS_IO"
.

These functions are part of the library with realtime functions named
.IR "librt"
.  They are not actually part of the 
.IR "libc" 
binary.
The implementation of these functions can be done using support in the
kernel (if available) or using an implementation based on threads at
userlevel.  In the latter case it might be necessary to link applications
with the thread library 
.IR "libpthread"
in addition to 
.IR "librt"
and
.IR "libaio"
.

All AIO operations operate on files which were opened previously.  There
might be arbitrarily many operations running for one file.  The
asynchronous I/O operations are controlled using a data structure named
.IR "struct aiocb"
It is defined in
.IR "aio.h"
 as follows.

.nf
struct aiocb
{
  int aio_fildes;               /* File desriptor.  */
  int aio_lio_opcode;           /* Operation to be performed.  */
  int aio_reqprio;              /* Request priority offset.  */
  volatile void *aio_buf;       /* Location of buffer.  */
  size_t aio_nbytes;            /* Length of transfer.  */
  struct sigevent aio_sigevent; /* Signal number and value.  */

  /* Internal members.  */
  struct aiocb *__next_prio;
  int __abs_prio;
  int __policy;
  int __error_code;
  __ssize_t __return_value;

#ifndef __USE_FILE_OFFSET64
  __off_t aio_offset;           /* File offset.  */
  char __pad[sizeof (__off64_t) - sizeof (__off_t)];
#else
  __off64_t aio_offset;         /* File offset.  */
#endif
  char __unused[32];
};

.fi
The POSIX.1b standard mandates that the 
.IR "struct aiocb" 
structure
contains at least the members described in the following table.  There
might be more elements which are used by the implementation, but
depending upon these elements is not portable and is highly deprecated.

.TP
.IR "int aio_fildes"
This element specifies the file descriptor to be used for the
operation.  It must be a legal descriptor, otherwise the operation will
fail.

The device on which the file is opened must allow the seek operation.
I.e., it is not possible to use any of the AIO operations on devices
like terminals where an 
.IR "lseek"
 call would lead to an error.
.TP
.IR "off_t aio_offset"
This element specifies the offset in the file at which the operation (input
or output) is performed.  Since the operations are carried out in arbitrary
order and more than one operation for one file descriptor can be
started, one cannot expect a current read/write position of the file
descriptor.
.TP
.IR "volatile void *aio_buf"
This is a pointer to the buffer with the data to be written or the place
where the read data is stored.
.TP
.IR "size_t aio_nbytes"
This element specifies the length of the buffer pointed to by 
.IR "aio_buf"
.
.TP
.IR "int aio_reqprio"
If the platform has defined 
.B "_POSIX_PRIORITIZED_IO"
and
.B "_POSIX_PRIORITY_SCHEDULING"
, the AIO requests are
processed based on the current scheduling priority.  The
.IR "aio_reqprio"
element can then be used to lower the priority of the
AIO operation.
.TP
.IR "struct sigevent aio_sigevent"
This element specifies how the calling process is notified once the
operation terminates.  If the 
.IR "sigev_notify"
element is
.B "SIGEV_NONE"
, no notification is sent.  If it is 
.B "SIGEV_SIGNAL"
,
the signal determined by 
.IR "sigev_signo"
is sent.  Otherwise,
.IR "sigev_notify"
must be 
.B "SIGEV_THREAD"
.  In this case, a thread
is created which starts executing the function pointed to by
.IR "sigev_notify_function"
.
.TP
.IR "int aio_lio_opcode"
This element is only used by the 
.IR "lio_listio"
 and
.IR "lio_listio64"
 functions.  Since these functions allow an
arbitrary number of operations to start at once, and each operation can be
input or output (or nothing), the information must be stored in the
control block.  The possible values are:
.TP
.B "LIO_READ"
Start a read operation.  Read from the file at position
.IR "aio_offset"
 and store the next 
.IR "aio_nbytes"
 bytes in the
buffer pointed to by 
.IR "aio_buf"
.
.TP
.B "LIO_WRITE"
Start a write operation.  Write 
.IR "aio_nbytes" 
bytes starting at
.IR "aio_buf"
into the file starting at position 
.IR "aio_offset"
.
.TP
.B "LIO_NOP"
Do nothing for this control block.  This value is useful sometimes when
an array of 
.IR "struct aiocb"
values contains holes, i.e., some of the
values must not be handled although the whole array is presented to the
.IR "lio_listio"
function.

When the sources are compiled using 
.B "_FILE_OFFSET_BITS == 64"
on a
32 bit machine, this type is in fact 
.IR "struct aiocb64"
, since the LFS
interface transparently replaces the 
.IR "struct aiocb"
definition.
.PP
For use with the AIO functions defined in the LFS, there is a similar type
defined which replaces the types of the appropriate members with larger
types but otherwise is equivalent to 
.IR "struct aiocb"
.  Particularly,
all member names are the same.

.nf
/* The same for the 64bit offsets.  Please note that the members aio_fildes
   to __return_value have to be the same in aiocb and aiocb64.  */
#ifdef __USE_LARGEFILE64
struct aiocb64
{
  int aio_fildes;               /* File desriptor.  */
  int aio_lio_opcode;           /* Operation to be performed.  */
  int aio_reqprio;              /* Request priority offset.  */
  volatile void *aio_buf;       /* Location of buffer.  */
  size_t aio_nbytes;            /* Length of transfer.  */
  struct sigevent aio_sigevent; /* Signal number and value.  */

  /* Internal members.  */
  struct aiocb *__next_prio;
  int __abs_prio;
  int __policy;
  int __error_code;
  __ssize_t __return_value;

  __off64_t aio_offset;         /* File offset.  */
  char __unused[32];
};

.fi
.TP
.IR "int aio_fildes"
This element specifies the file descriptor which is used for the
operation.  It must be a legal descriptor since otherwise the operation
fails for obvious reasons.
The device on which the file is opened must allow the seek operation.
I.e., it is not possible to use any of the AIO operations on devices
like terminals where an 
.IR "lseek"
 call would lead to an error.
.TP
.IR "off64_t aio_offset"
This element specifies at which offset in the file the operation (input
or output) is performed.  Since the operation are carried in arbitrary
order and more than one operation for one file descriptor can be
started, one cannot expect a current read/write position of the file
descriptor.
.TP
.IR "volatile void *aio_buf"
This is a pointer to the buffer with the data to be written or the place
where the read data is stored.
.TP
.IR "size_t aio_nbytes"
This element specifies the length of the buffer pointed to by 
.IR "aio_buf"
.
.TP
.IR "int aio_reqprio"
If for the platform 
.B "_POSIX_PRIORITIZED_IO"
and
.B "_POSIX_PRIORITY_SCHEDULING"
are defined the AIO requests are
processed based on the current scheduling priority.  The
.IR "aio_reqprio"
element can then be used to lower the priority of the
AIO operation.
.TP
.IR "struct sigevent aio_sigevent"
This element specifies how the calling process is notified once the
operation terminates.  If the 
.IR "sigev_notify"
, element is
.B "SIGEV_NONE"
no notification is sent.  If it is 
.B "SIGEV_SIGNAL"
,
the signal determined by 
.IR "sigev_signo"
is sent.  Otherwise,
.IR "sigev_notify"
 must be 
.B "SIGEV_THREAD"
in which case a thread
which starts executing the function pointed to by
.IR "sigev_notify_function"
.
.TP
.IR "int aio_lio_opcode"
This element is only used by the 
.IR "lio_listio"
and
.IR "lio_listio64"
functions.  Since these functions allow an
arbitrary number of operations to start at once, and since each operation can be
input or output (or nothing), the information must be stored in the
control block.  See the description of 
.IR "struct aiocb"
for a description
of the possible values.
.PP
When the sources are compiled using 
.B "_FILE_OFFSET_BITS == 64"
on a
32 bit machine, this type is available under the name 
.IR "struct aiocb64"
, since the LFS transparently replaces the old interface.
.SH "RETURN VALUES"
.SH ERRORS
.SH "SEE ALSO"
.BR aio_cancel(3),
.BR aio_cancel64(3),
.BR aio_error(3),
.BR aio_error64(3),
.BR aio_fsync(3),
.BR aio_fsync64(3),
.BR aio_init(3),
.BR aio_read(3),
.BR aio_read64(3),
.BR aio_return(3),
.BR aio_return64(3),
.BR aio_suspend(3),
.BR aio_suspend64(3),
.BR aio_write(3),
.BR aio_write64(3),
.BR errno(3),