[Wien] parallel calc. without NFS

[Stefaan Cottenier]

> Is there any way of running either k-point parallel or MPI versions of 
> Wien2k on a cluster of computers without using NFS? i.e., only using local 
> hard disks of each node.
> 
> Our NFS is agonisingly slow and wien2k reads & writes often hang and data 
> gets corrupted. If anyone has a hack for getting around this I'd 
> appreciate it.

What do you use as $SCRATCH ?  If that is a directory that exists locally on 
every node (e.g. /tmp ), then the large scratch files do not need to go over 
the network, which reduces wien-traffic significantly.

Stefaan