Nice article, but I was hoping that they would have a comparison of features/benefits compared to Lustre, PVFS2/OrangeFS, GPFS, Ceph, etc.
It seems to provide a POSIX interface, but is it complete or does it cut some corners? How does it manage the namespace given multiple metadata servers? Does it provide non-Posix interfaces usable by Hadoop or Amazon REST? On Mon, Jul 15, 2013 at 11:33 AM, Douglas Eadline <[email protected]>wrote: > > Hi everyone, I thought you might like a new article > on ClusterMonkey on FhGFS (Fraunhofer Parallel File System): > > FhGFS: A Fast and Scalable Parallel Filesystem > by Tobias Goetz > http://goo.gl/C3XlK > > And if you visit, please take the one question survey about > Big Data: > > http://goo.gl/2nr7l > > thanks > > -- > Doug > > -- > Mailscanner: Clean > > _______________________________________________ > Beowulf mailing list, [email protected] sponsored by Penguin Computing > To change your subscription (digest mode or unsubscribe) visit > http://www.beowulf.org/mailman/listinfo/beowulf >
_______________________________________________ Beowulf mailing list, [email protected] sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
