I neglected in my earlier post to attach the small C code that the hdf5 folks supplied; it is attached here.
On Wed, Jan 15, 2014 at 10:04 AM, Ronald Cohen <rhco...@lbl.gov> wrote: > I have been struggling trying to get a usable build of openmpi on Mac OSX > Mavericks (10.9.1). I can get openmpi to configure and build without > error, but have problems after that which depend on the openmpi version. > > With 1.6.5, make check fails the opal_datatype_test, ddt_test, and ddt_raw > tests. The various atomic_* tests pass. See checklogs_1.6.5, attached > as a .gz file. > > Following suggestions from openmpi discussions I tried openmpi version > 1.7.4rc1. In this case make check indicates all tests passed. But when I > proceeded to try to build a parallel code (parallel HDF5) it failed. > Following an email exchange with the HDF5 support people, they suggested I > try to compile and run the attached bit of simple code Sample_mpio.c (which > they supplied) which does not use any HDF5, but just attempts a parallel > write to a file and parallel read. That test failed when requesting more > than 1 processor -- which they say indicates a failure of the openmpi > installation. The error message was: > > MPI_INIT: argc 1 > MPI_INIT: argc 1 > Testing simple C MPIO program with 2 processes accessing file > ./mpitest.data > (Filename can be specified via program argument) > Proc 0: hostname=Ron-Cohen-MBP.local > Proc 1: hostname=Ron-Cohen-MBP.local > MPI_BARRIER[0]: comm MPI_COMM_WORLD > MPI_BARRIER[1]: comm MPI_COMM_WORLD > Proc 0: MPI_File_open with MPI_MODE_EXCL failed (MPI_ERR_FILE: invalid > file) > MPI_ABORT[0]: comm MPI_COMM_WORLD errorcode 1 > MPI_BCAST[1]: buffer 7fff5a483048 count 1 datatype MPI_INT root 0 comm > MPI_COMM_WORLD > > I then went back to my openmpi directories and tried running some of the > individual tests in the test and examples directories. In particular in > test/class I found one test that seem to not be run as part of make check > which failed, even with one processor; this is opal_bitmap. Not sure if > this is because 1.7.4rc1 is incomplete, or there is something wrong with > the installation, or maybe a 32 vs 64 bit thing? The error message is > > mpirun detected that one or more processes exited with non-zero status, > thus causing the job to be terminated. The first process to do so was: > > Process name: [[48805,1],0] > Exit code: 255 > > Any suggestions? > > More generally has anyone out there gotten an openmpi build on Mavericks > to work with sufficient success that they can get the attached > Sample_mpio.c (or better yet, parallel HDF5) to build? > > Details: Running Mac OS X 10.9.1 on a mid-2009 Macbook pro with 4 GB > memory; tried openmpi 1.6.5 and 1.7.4rc1. Built openmpi against the stock > gcc that comes with XCode 5.0.2, and gfortran 4.9.0. > > Files attached: config.log.gz, openmpialllog.gz (output of running > ompi_info --all), checklog2.gz (output of make.check in top openmpi > directory). > > I am not attaching logs of make and install since those seem to have been > successful, but can generate those if that would be helpful. >
/* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * Copyright by The HDF Group. * * Copyright by the Board of Trustees of the University of Illinois. * * All rights reserved. * * * * This file is part of HDF5. The full HDF5 copyright notice, including * * terms governing use, modification, and redistribution, is contained in * * the files COPYING and Copyright.html. COPYING can be found at the root * * of the source code distribution tree; Copyright.html can be found at the * * root level of an installed copy of the electronic HDF5 document set and * * is linked from the top-level documents page. It can also be found at * * http://hdfgroup.org/HDF5/doc/Copyright.html. If you do not have * * access to either file, you may request a copy from h...@hdfgroup.org. * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * */ /* Simple MPI-IO program testing if a parallel file can be created. * Default filename can be specified via first program argument. * Each process writes something, then reads all data back. */ #include <stdio.h> #include <mpi.h> #ifndef MPI_FILE_NULL /*MPIO may be defined in mpi.h already */ # include <mpio.h> #endif #define DIMSIZE 10 /* dimension size, avoid powers of 2. */ #define PRINTID printf("Proc %d: ", mpi_rank) main(int ac, char **av) { char hostname[128]; int mpi_size, mpi_rank; MPI_File fh; char *filename = "./mpitest.data"; char mpi_err_str[MPI_MAX_ERROR_STRING]; int mpi_err_strlen; int mpi_err; char writedata[DIMSIZE], readdata[DIMSIZE]; char expect_val; int i, irank; int nerrors = 0; /* number of errors */ MPI_Offset mpi_off; MPI_Status mpi_stat; MPI_Init(&ac, &av); MPI_Comm_size(MPI_COMM_WORLD, &mpi_size); MPI_Comm_rank(MPI_COMM_WORLD, &mpi_rank); /* get file name if provided */ if (ac > 1){ filename = *++av; } if (mpi_rank==0){ printf("Testing simple C MPIO program with %d processes accessing file %s\n", mpi_size, filename); printf(" (Filename can be specified via program argument)\n"); } /* show the hostname so that we can tell where the processes are running */ if (gethostname(hostname, 128) < 0){ PRINTID; printf("gethostname failed\n"); MPI_Abort(MPI_COMM_WORLD, 1); } PRINTID; printf("hostname=%s\n", hostname); if ((mpi_err = MPI_File_open(MPI_COMM_WORLD, filename, MPI_MODE_RDWR | MPI_MODE_CREATE | MPI_MODE_DELETE_ON_CLOSE, MPI_INFO_NULL, &fh)) != MPI_SUCCESS){ MPI_Error_string(mpi_err, mpi_err_str, &mpi_err_strlen); PRINTID; printf("MPI_File_open failed (%s)\n", mpi_err_str); MPI_Abort(MPI_COMM_WORLD, 1); } /* each process writes some data */ for (i=0; i < DIMSIZE; i++) writedata[i] = mpi_rank*DIMSIZE + i; mpi_off = mpi_rank*DIMSIZE; if ((mpi_err = MPI_File_write_at(fh, mpi_off, writedata, DIMSIZE, MPI_BYTE, &mpi_stat)) != MPI_SUCCESS){ MPI_Error_string(mpi_err, mpi_err_str, &mpi_err_strlen); PRINTID; printf("MPI_File_write_at offset(%ld), bytes (%d), failed (%s)\n", (long) mpi_off, (int) DIMSIZE, mpi_err_str); MPI_Abort(MPI_COMM_WORLD, 1); }; /* make sure all processes has done writing. */ MPI_Barrier(MPI_COMM_WORLD); /* each process reads all data and verify. */ for (irank=0; irank < mpi_size; irank++){ mpi_off = irank*DIMSIZE; if ((mpi_err = MPI_File_read_at(fh, mpi_off, readdata, DIMSIZE, MPI_BYTE, &mpi_stat)) != MPI_SUCCESS){ MPI_Error_string(mpi_err, mpi_err_str, &mpi_err_strlen); PRINTID; printf("MPI_File_read_at offset(%ld), bytes (%d), failed (%s)\n", (long) mpi_off, (int) DIMSIZE, mpi_err_str); MPI_Abort(MPI_COMM_WORLD, 1); }; for (i=0; i < DIMSIZE; i++){ expect_val = irank*DIMSIZE + i; if (readdata[i] != expect_val){ PRINTID; printf("read data[%d:%d] got %d, expect %d\n", irank, i, readdata[i], expect_val); nerrors++; } } } if (nerrors) MPI_Abort(MPI_COMM_WORLD, 1); MPI_File_close(&fh); /* Verify that created file is deleted upon closing. */ if ((mpi_err = MPI_File_open(MPI_COMM_WORLD, filename, MPI_MODE_RDWR, MPI_INFO_NULL, &fh)) == MPI_SUCCESS){ MPI_File_close(&fh); PRINTID; printf("File existed. MPI_MODE_DELETE_ON_CLOSE failed.\n"); MPI_Abort(MPI_COMM_WORLD, 1); } /* Verify that MPI_MODE_EXCL works correctly with non-existing file. * It has been reported that this fails in the Panasas parallel filesystem * using the PathScale MPI. (See Bug 1468) */ if ((mpi_err = MPI_File_open(MPI_COMM_WORLD, filename, MPI_MODE_RDWR | MPI_MODE_CREATE | MPI_MODE_EXCL, MPI_INFO_NULL, &fh)) != MPI_SUCCESS){ MPI_Error_string(mpi_err, mpi_err_str, &mpi_err_strlen); PRINTID; printf("MPI_File_open with MPI_MODE_EXCL failed (%s)\n", mpi_err_str); MPI_Abort(MPI_COMM_WORLD, 1); } MPI_File_close(&fh); /* Verify MPI_File_delete works. Only 1 calls, the other waits. */ if (mpi_rank==0){ if ((mpi_err = MPI_File_delete(filename, MPI_INFO_NULL)) != MPI_SUCCESS) MPI_Error_string(mpi_err, mpi_err_str, &mpi_err_strlen); } MPI_Bcast(&mpi_err, 1, MPI_INT, 0, MPI_COMM_WORLD); if (mpi_err != MPI_SUCCESS){ if (mpi_rank==0){ PRINTID; printf("MPI_File_delete failed (%s)\n", mpi_err_str); } MPI_Abort(MPI_COMM_WORLD, 1); } /* Check file no longer exist. */ if ((mpi_err = MPI_File_open(MPI_COMM_WORLD, filename, MPI_MODE_RDWR, MPI_INFO_NULL, &fh)) == MPI_SUCCESS){ MPI_File_close(&fh); PRINTID; printf("File existed. MPI_File_delete failed.\n"); MPI_Abort(MPI_COMM_WORLD, 1); } PRINTID; printf("all tests passed\n"); MPI_Finalize(); return 0; }
