162306a36Sopenharmony_ci 262306a36Sopenharmony_ci================================== 362306a36Sopenharmony_cipNFS SCSI layout server user guide 462306a36Sopenharmony_ci================================== 562306a36Sopenharmony_ci 662306a36Sopenharmony_ciThis document describes support for pNFS SCSI layouts in the Linux NFS server. 762306a36Sopenharmony_ciWith pNFS SCSI layouts, the NFS server acts as Metadata Server (MDS) for pNFS, 862306a36Sopenharmony_ciwhich in addition to handling all the metadata access to the NFS export, 962306a36Sopenharmony_cialso hands out layouts to the clients so that they can directly access the 1062306a36Sopenharmony_ciunderlying SCSI LUNs that are shared with the client. 1162306a36Sopenharmony_ci 1262306a36Sopenharmony_ciTo use pNFS SCSI layouts with the Linux NFS server, the exported file 1362306a36Sopenharmony_cisystem needs to support the pNFS SCSI layouts (currently just XFS), and the 1462306a36Sopenharmony_cifile system must sit on a SCSI LUN that is accessible to the clients in 1562306a36Sopenharmony_ciaddition to the MDS. As of now the file system needs to sit directly on the 1662306a36Sopenharmony_ciexported LUN, striping or concatenation of LUNs on the MDS and clients 1762306a36Sopenharmony_ciis not supported yet. 1862306a36Sopenharmony_ci 1962306a36Sopenharmony_ciOn a server built with CONFIG_NFSD_SCSI, the pNFS SCSI volume support is 2062306a36Sopenharmony_ciautomatically enabled if the file system is exported using the "pnfs" 2162306a36Sopenharmony_cioption and the underlying SCSI device support persistent reservations. 2262306a36Sopenharmony_ciOn the client make sure the kernel has the CONFIG_PNFS_BLOCK option 2362306a36Sopenharmony_cienabled, and the file system is mounted using the NFSv4.1 protocol 2462306a36Sopenharmony_civersion (mount -o vers=4.1). 25