9.2. pNFS

Support for Parallel NFS (pNFS) as part of the NFS v4.1 standard is available starting with Red Hat Enterprise Linux 6.4. The pNFS architecture improves the scalability of NFS, with possible improvements to performance. That is, when a server implements pNFS as well, a client is able to access data through multiple sources concurrently.
To enable this functionality, use the -o v4.1 mount option on mounts from a pNFS-enabled server.
After the server is pNFS-enabled, the nfs_layout_nfsv41_files kernel is automatically loaded on the first mount. If the module is successfully loaded, the following message is logged in the /var/log/messages file:
kernel: nfs4filelayout_init: NFSv4 File Layout Driver Registering...
To verify a successful NFSv4.1 mount, run:
$ mount | grep /proc/mounts


Once server and client negotiate NFS v4.1 or higher, they automatically take advantage of pNFS if available. Both client and server need to support the same "layout type". Possible layout types include files, blocks, objects, flexfiles, and SCSI.
Starting with Red Hat Enterprise Linux 6.4, the client only supports the files layout type and uses pNFS only when the server also supports the files layout type. Red Hat recommends using the files profiles only with Red Hat Enterprise Linux 6.6 and later.
For more information on pNFS, see http://www.pnfs.com.