.\" -*- nroff -*-
.\" Copyright 2013 Los Alamos National Security, LLC. All rights reserved.
.\" Copyright 2010 Cisco Systems, Inc.  All rights reserved.
.\" Copyright 2006-2008 Sun Microsystems, Inc.
.\" Copyright (c) 1996 Thinking Machines Corporation
.TH MPI_File_open 3 "#OMPI_DATE#" "#PACKAGE_VERSION#" "#PACKAGE_NAME#"
.SH NAME
\fBMPI_File_open\fP \- Opens a file (collective).
.SH SYNTAX
.ft R
.nf
C Syntax
    #include <mpi.h>
    int MPI_File_open(MPI_Comm \fIcomm\fP, const char \fI*filename\fP,
    	      int \fIamode\fP, MPI_Info \fIinfo\fP, 
	      MPI_File \fI*fh\fP)

.fi
.SH Fortran Syntax
.nf
    INCLUDE 'mpif.h'
    MPI_FILE_OPEN(\fICOMM\fP,\fI FILENAME\fP,\fI AMODE\fP, \fIINFO\fP,\fI FH\fP,\fI IERROR\fP)
   	 CHARACTER*(*)    FILENAME
    	 INTEGER      COMM, AMODE, INFO, FH, IERROR

.fi
.SH C++ Syntax
.nf
#include <mpi.h>
static MPI::File MPI::File::Open(const MPI::Intracomm& \fIcomm\fP,
	const char* \fIfilename\fP, int \fIamode\fP, const MPI::Info& \fIinfo\fP)

.fi
.SH INPUT PARAMETERS
.ft R
.TP 1i
comm  
Communicator (handle).
.TP 1i
filename
Name of file to open (string). 
.TP 1i
amode 
File access mode (integer).
.TP 1i
info
Info object (handle). 

.SH OUTPUT PARAMETERS
.ft R
.TP 1i
fh    
New file handle (handle).
.TP 1i
IERROR
Fortran only: Error status (integer). 

.SH DESCRIPTION
.ft R
MPI_File_open opens the file identified by the filename 
.I
filename
on all processes in the 
.I comm
communicator group. MPI_File_open is a collective routine; all processes
must provide the same value for
.I amode,
and all processes must provide filenames that reference the same
file and which are textually identical. A process can open a file
independently of other processes by using the MPI_COMM_SELF
communicator. The file handle returned, 
.I fh,
can be subsequently used to access the file until the file is closed
using MPI_File_close. Before calling MPI_Finalize, the user is required to
close (via MPI_File_close) all files that were opened with MPI_File_open. Note
that the communicator 
.I comm 
is unaffected by MPI_File_open and continues to be usable in all MPI
routines. Furthermore, use of 
.I comm 
will not interfere with I/O behavior.
.sp
Initially, all processes view the file as a linear byte stream; that is, the 
.I etype 
and 
.I filetype
are both MPI_BYTE. The file view can be changed via the MPI_File_set_view routine.
.sp
The following access modes are supported (specified in amode, in a bit-vector OR in one of the following integer constants):
.TP .5i
  o  
MPI_MODE_APPEND
.TP .5i
  o 
MPI_MODE_CREATE -- Create the file if it does not exist.
.TP .5i
  o  
MPI_MODE_DELETE_ON_CLOSE
.TP .5i
  o  
MPI_MODE_EXCL -- Error creating a file that already exists. 
.TP .5i
  o  
MPI_MODE_RDONLY -- Read only.
.TP .5i
  o 
MPI_MODE_RDWR -- Reading and writing.
.TP .5i
  o  
MPI_MODE_SEQUENTIAL
.TP .5i
  o 
MPI_MODE_WRONLY -- Write only.
.TP .5i
  o  
MPI_MODE_UNIQUE_OPEN
.RE
.sp
The modes MPI_MODE_RDONLY, MPI_MODE_RDWR, MPI_MODE_WRONLY, and MPI_MODE_CREATE have
identical semantics to their POSIX counterparts. It is erroneous to
specify MPI_MODE_CREATE in conjunction with MPI_MODE_RDONLY. Errors related to
the access mode are raised in the class MPI_ERR_AMODE.
.sp
On single-node clusters, files are opened by default using nonatomic mode file consistency
semantics. The more stringent atomic-mode consistency semantics, required for atomicity of overlapping accesses, are the default when processors in a communicator group reside on more than one node. 
This setting can be changed using
MPI_File_set_atomicity.
.sp
The MPI_File_open interface allows the user to pass information via the \fIinfo\fP argument. It can be set to MPI_INFO_NULL. See the HINTS section for a list of hints that can be set. 

.SH HINTS
.ft R
The following hints can be used as values for the \fIinfo\fP argument. 
.sp
SETTABLE HINTS:
.sp
- MPI_INFO_NULL
.sp
- shared_file_timeout: Amount of time (in seconds) to wait for access to the 
shared file pointer before exiting with MPI_ERR_TIMEDOUT.
.sp
- rwlock_timeout: Amount of time (in seconds) to wait for obtaining a read or 
write lock on a contiguous chunk of a UNIX file before exiting with MPI_ERR_TIMEDOUT.
.sp 
- noncoll_read_bufsize:  Maximum size of the buffer used by
MPI I/O to satisfy multiple noncontiguous read requests in
the noncollective data-access routines. (See NOTE, below.)
.sp
- noncoll_write_bufsize: Maximum size of the buffer used by
MPI I/O to satisfy multiple noncontiguous write requests in
the noncollective data-access routines. (See NOTE, below.)
.sp
- coll_read_bufsize:  Maximum size of the buffer used by MPI
I/O to satisfy multiple noncontiguous read requests in the
collective data-access routines. (See NOTE, below.)
.sp
- coll_write_bufsize:  Maximum size of the buffer used by MPI
I/O to satisfy multiple noncontiguous write requests in the
collective data-access routines. (See NOTE, below.)
.sp
NOTE: A buffer size smaller than the distance (in bytes) in a UNIX file between the first byte and the last byte of the access request causes MPI I/O to iterate and perform multiple UNIX read() or write() calls. If the request includes multiple noncontiguous chunks of data, and the buffer size is greater than the size of those chunks, then the UNIX read() or write() (made at the MPI I/O level) will access data not requested by this process in order to reduce the total number of write() calls made. If this is not desirable behavior, you should reduce this buffer size to equal the size of the contiguous chunks within the aggregate request.
.sp
- mpiio_concurrency: (boolean) controls whether nonblocking
I/O routines can bind an extra thread to an LWP.
.sp
- mpiio_coll_contiguous: (boolean) controls whether subsequent collective data accesses will request collectively contiguous regions of the file.
.sp
NON-SETTABLE HINTS: 
.sp
- filename: Access this hint to get the name of the file. 

.SH ERRORS
Almost all MPI routines return an error value; C routines as the value of the function and Fortran routines in the last argument. C++ functions do not return errors. If the default error handler is set to MPI::ERRORS_THROW_EXCEPTIONS, then on error the C++ exception mechanism will be used to throw an MPI::Exception object.
.sp
Before the error value is returned, the current MPI error handler is
called. For MPI I/O function errors, the default error handler is set to MPI_ERRORS_RETURN. The error handler may be changed with MPI_File_set_errhandler; the predefined error handler MPI_ERRORS_ARE_FATAL may be used to make I/O errors fatal. Note that MPI does not guarantee that an MPI program can continue past an error.