[Pvfs2-users] Test problems with hdf5 and pvfs2

[Tobias Brandvik]

Hi,

I'm having some trouble getting the parallel hdf5 tests to pass using
mpich2 and pvfs2. Below is the result of the following commands which
runs the hdf5 tests:

export HDF5_PARAPREFIX=pvfs2:/mnt/pvfs2
./testphdf5

Testing  -- fapl_mpio duplicate (mpiodup)
Testing  -- fapl_mpiposix duplicate (posixdup)
Testing  -- dataset using split communicators (split)
Testing  -- dataset independent write (idsetw)
Testing  -- dataset independent read (idsetr)
Testing  -- dataset collective write (cdsetw)
Testing  -- dataset collective read (cdsetr)
Testing  -- extendible dataset independent write (eidsetw)
Testing  -- extendible dataset independent read (eidsetr)
Testing  -- extendible dataset collective write (ecdsetw)
Testing  -- extendible dataset collective read (ecdsetr)
Testing  -- extendible dataset independent write #2 (eidsetw2)
Testing  -- chunked dataset with none-selection (selnone)
Testing  -- parallel extend Chunked allocation on serial file (calloc)
Proc 0: *** PHDF5 ERROR ***
        Assertion (H5Fcreate) failed at line  126 in t_chunk_alloc.c
aborting MPI process
Attempting to use an MPI routine after finalizing MPICH



PVFS2 itself seems ok:

pvfs2-ping -m /mnt/pvfs2

(1) Parsing tab file...

(2) Initializing system interface...

(3) Initializing each file system found in tab file: /etc/pvfs2tab...

   PVFS2 servers: tcp://gp-111:3334
   Storage name: pvfs2-fs
   Local mount point: /mnt/pvfs2
   /mnt/pvfs2: Ok

(4) Searching for /mnt/pvfs2 in pvfstab...

   PVFS2 servers: tcp://gp-111:3334
   Storage name: pvfs2-fs
   Local mount point: /mnt/pvfs2

   meta servers:
   tcp://gp-111:3334

   data servers:
   tcp://gp-111:3334

(5) Verifying that all servers are responding...

   meta servers:
   tcp://gp-111:3334 Ok

   data servers:
   tcp://gp-111:3334 Ok

(6) Verifying that fsid 1470828028 is acceptable to all servers...

   Ok; all servers understand fs_id 1470828028

(7) Verifying that root handle is owned by one server...

   Root handle: 1048576
     Ok; root handle is owned by exactly one server.

=============================================================

The PVFS2 filesystem at /mnt/pvfs2 appears to be correctly configured.


My build procedure is as follows:

PVFS2 (2.7.0)
./configure --prefix=/home/tbrandvik/pvfs2

MPICH2 (1.0.6p1)
./configure -prefix=/home/tbrandvik/mpich2
--with-pvfs2=/home/tbrandvik/pvfs2/ --enable-sharedlibs=gcc

HDF5 (1.6.6)
./configure -prefix=/home/tbrandvik/hdf5 --enable-parallel
--enable-shared CC=mpicc CXX=mpicxx

This is all on CentOS 5.

There was a thread on the list a while back dealing with the same
issue, but with different tests failing:
http://www.mail-archive.com/pvfs2-users@beowulf-underground.org/msg00281.html

Does anyone have any ideas about why the tests are failing?

Tobias.