I want to test I/O performance on PVFS2, so I what to know what kind
of benchmark do shall we typically use?

Currently, I am trying the follows, but none of them are working
correctly right now.
1) flash_benchmark_io,
2) mpi_tile_io
3) mpiBLAST

If you are familiar with any of them and are readily to offer some
help, please read on; otherwise pleasing ignore the following messages
to save your precious time. Thanks!

Frankly speaking, I am not quite familiar with any of them currently.
As far as I know/guess, ( I might be wrong here), flash_benchmark_io is
a component of Flash (an adaptive mesh hydrodynamics code for modeling
astrophysical thermonuclear flashes) from University of Chicago. This
is simply a guess because I currently don't have access to the entire
flash software suite.

Here is where I need your help:
1) When I was trying to build the flash_benchmark_io code, the
compiler complained that hdf5.h file is missing. I want to know for
sure if this file is necessary for building the code.
# gmake -f Makefile.linux flash_benchmark_io
mpicc -c -I /usr/include/ -DTFLOPS -DN_DIM=3 h5_file_interface.c
h5_file_interface.c:6:18: hdf5.h: No such file or directory

Can anybody explained to me what is the relationship between HDF and PVFS.
Are they working on different levels or what?

2) I can not run mpi_tile_io correctly, the input and output are like:
# mpirun -np 100 mpi-tile-io --nr_tiles_x 25 --nr_tiles_y 4
--sz_tile_x    100 --sz_tile_y 100 --sz_element 32 --filename
/mnt/pvfs2/foo
problem with execution of mpi-tile-io  on  cse-wang-server.unl.edu: 
[Errno 2] No such file or directory
problem with execution of mpi-tile-io  on  cse-wang05b.unl.edu: 
[Errno 2] No such file or directory
problem with execution of mpi-tile-io  on  cse-wang-server.unl.edu: 
[Errno 2] No such file or directory
...
...
...

I don't what file is missing and was complained by the program by
repeatedly printing out "No Such file or directory".

3) I could not build the DB for mpiBLAST, here is my input and output messages:
# mpiformatdb -N 5 -i yeast.aa
Reading input file
Done, read 46527 lines
Reordering 6298 sequence entries
Database type unspecified, assuming protein
Breaking yeast.aa (2 MB) into 5 fragments
Executing: formatdb -i /tmp/reorderAtVnfq -p T -N 5 -n
/mnt/pvfs2/mpiblast/yeast.aa -o T
[formatdb] FATAL ERROR: /mnt/pvfs2/mpiblast/data/seqcode.valInput

tag mismatch on Seq-code-set

I have no idea what was been complained and how to resolve it.


Thank you in advance for your time and help!

Sincerely
Peng

_______________________________________________
PVFS2-users mailing list
[email protected]
http://www.beowulf-underground.org/mailman/listinfo/pvfs2-users

Reply via email to