h5part AT lists.psi.ch
Subject: H5Part development and discussion
List archive
- From: John Shalf <JShalf AT lbl.gov>
- To: Andreas Adelmann <andreas.adelmann AT psi.ch>
- Cc: Mark Howison <mark.howison AT gmail.com>, h5part AT lists.psi.ch, Prabhat Prabhat <prabhat AT hpcrd.lbl.gov>
- Subject: [H5part] Re: H5Part Benchmarks for ICAP
- Date: Mon, 24 Aug 2009 16:22:34 -0700
- List-archive: <https://lists.web.psi.ch/pipermail/h5part/>
- List-id: H5Part development and discussion <h5part.lists.psi.ch>
Its a long story, but Mark identified some anomalous interaction between Lustre and the POSIX ftruncate() call that is used by HDF5.
The HDF group has issued a patched release of HDF5 that fixes that problem. Mark is currently testing it. The highest priority right now is to ensure that the patch is validated so that it can be part of the mainstream HDF5 release.
-john
On Aug 24, 2009, at 4:19 PM, Andreas Adelmann wrote:
what is ftruncate() ?
aa
On Aug 25, 2009, at 1:18 AM, John Shalf wrote:
Once the ftruncate() fix is sorted out, we should retry the H5Part synthetic benchmark.
-john
On Aug 24, 2009, at 3:59 PM, Andreas Adelmann wrote:
Dear Colleagues do we have synthetic benchmarks
on H5Part which I can show at the ICAP conference in San Francisco next week?
Attached what I already have, best from los alamos
Andreas
<Picture 1.png>
------
Dr. sc. math. Andreas (Andy) Adelmann
Staff Scientist
Paul Scherrer Institut WLGB/132 CH-5232 Villigen PSI
Phone Office: xx41 56 310 42 33 Fax: xx41 56 310 31 91
Phone Home: xx41 62 891 91 44
-------------------------------------------------------
Wednesday: ETH CAB F 10.1 xx41 44 632 82 76
============================================
The more exotic, the more abstract the knowledge,
the more profound will be its consequences.
Leon Lederman
============================================
------
Dr. sc. math. Andreas (Andy) Adelmann
Staff Scientist
Paul Scherrer Institut WLGB/132 CH-5232 Villigen PSI
Phone Office: xx41 56 310 42 33 Fax: xx41 56 310 31 91
Phone Home: xx41 62 891 91 44
-------------------------------------------------------
Wednesday: ETH CAB F 10.1 xx41 44 632 82 76
============================================
The more exotic, the more abstract the knowledge,
the more profound will be its consequences.
Leon Lederman
============================================
- [H5part] Re: H5Part Benchmarks for ICAP, John Shalf, 08/25/2009
- [H5part] Re: H5Part Benchmarks for ICAP, Andreas Adelmann, 08/25/2009
- [H5part] Re: H5Part Benchmarks for ICAP, John Shalf, 08/25/2009
- [H5part] Re: H5Part Benchmarks for ICAP, Andreas Adelmann, 08/25/2009
Archive powered by MHonArc 2.6.19.