Skip to Content.
Sympa Menu

h5part - Re: [H5part] FYI: H5Part-1.3.2 has been released

h5part AT lists.psi.ch

Subject: H5Part development and discussion

List archive

Re: [H5part] FYI: H5Part-1.3.2 has been released


Chronological Thread 
  • From: Achim Gsell <achim AT cybercity.ch>
  • To: John Biddiscombe <biddisco AT cscs.ch>
  • Cc: h5part AT lists.psi.ch
  • Subject: Re: [H5part] FYI: H5Part-1.3.2 has been released
  • Date: Thu, 19 Apr 2007 19:45:03 +0200
  • List-archive: <https://lists.web.psi.ch/pipermail/h5part/>
  • List-id: H5Part development and discussion <h5part.lists.psi.ch>

On Thursday 19 April 2007 17:53, John Biddiscombe wrote:

> 2) Added option to use INDEPENDENT_IO instead of
> COLLECTIVE_IO, I need this when using it on a system with a
> non-parallel file-system, using collective IO causes too large
> performance drop on our cluster.

INDEPENDENT_IO vs COLLECTIVE_IO in H5Part, good point. A couple
of weeks ago a college found a bug in H5Part concerning
COLLECTIVE_IO (or we understand something completely wrong): The
H5FD_MPIO_COLLECTIVE property is added to the property list
f->xfer_prop, but this property list is not used in I/O calls.
Thus we are using independent I/O. It's the same in version 1.0!
John (Shalf), any idea/comments about this?

> 6) Added a function to query IsTimeStep Present, so
> that I don't overwrite an existing one if redoing the same
> time

For me it is OK to add such a function, but SetStep already
returns an error, if the step exists.

> If I update my copy to work with your 1.3.2 (svn head), can I
> send you a large patch with all of it in, or would you prefer
> smaller patches which address individual issues (much more
> work)

Since I want to review the patches, I prefer a set of smaller
patches.

Achim




Archive powered by MHonArc 2.6.19.

Top of Page