[Pvfs2-users] Test problems with hdf5 and pvfs2
robl at mcs.anl.gov
Wed Jan 16 09:25:38 EST 2008
On Wed, Jan 16, 2008 at 01:35:41PM +0000, Tobias Brandvik wrote:
> > Do you happen to have PVFS mounted also?
> I'm relatively new to parallel filesystems (new to filesystems in
> general actually), but I take it this means using PVFS through the VFS
> interface by building the kernel modules and so on? If so, no.
That's right. Excellent. Then I think we understand exactly why
> So HDF5 itself should be ok - it's only the test itself that's buggy?
Yes. We're working with the HDF5 guys to come up with better versions
of these tests. Thanks much for the report!
> I had to skip a few tests to get everything working:
> Skipping -- parallel extend Chunked allocation on serial file (calloc)
> Skipping -- parallel read of dataset written serially with filters (fltread)
> Skipping -- compressed dataset collective read (cmpdsetr)
These are new tests with 1.6.6, and I think we know why these fail.
> Skipping -- big dataset test (bigdset)
> Skipping -- collective irregular contiguous write (ccontw)
> Skipping -- collective irregular contiguous read (ccontr)
I think these tests used to pass in 1.6.5. I'll double check them.
Mathematics and Computer Science Division A215 0178 EA2D B059 8CDF
Argonne National Lab, IL USA B29D F333 664A 4280 315B
More information about the Pvfs2-users