xref: /OK3568_Linux_fs/kernel/Documentation/admin-guide/nfs/pnfs-scsi-server.rst (revision 4882a59341e53eb6f0b4789bf948001014eff981)
1*4882a593Smuzhiyun
2*4882a593Smuzhiyun==================================
3*4882a593SmuzhiyunpNFS SCSI layout server user guide
4*4882a593Smuzhiyun==================================
5*4882a593Smuzhiyun
6*4882a593SmuzhiyunThis document describes support for pNFS SCSI layouts in the Linux NFS server.
7*4882a593SmuzhiyunWith pNFS SCSI layouts, the NFS server acts as Metadata Server (MDS) for pNFS,
8*4882a593Smuzhiyunwhich in addition to handling all the metadata access to the NFS export,
9*4882a593Smuzhiyunalso hands out layouts to the clients so that they can directly access the
10*4882a593Smuzhiyununderlying SCSI LUNs that are shared with the client.
11*4882a593Smuzhiyun
12*4882a593SmuzhiyunTo use pNFS SCSI layouts with the Linux NFS server, the exported file
13*4882a593Smuzhiyunsystem needs to support the pNFS SCSI layouts (currently just XFS), and the
14*4882a593Smuzhiyunfile system must sit on a SCSI LUN that is accessible to the clients in
15*4882a593Smuzhiyunaddition to the MDS.  As of now the file system needs to sit directly on the
16*4882a593Smuzhiyunexported LUN, striping or concatenation of LUNs on the MDS and clients
17*4882a593Smuzhiyunis not supported yet.
18*4882a593Smuzhiyun
19*4882a593SmuzhiyunOn a server built with CONFIG_NFSD_SCSI, the pNFS SCSI volume support is
20*4882a593Smuzhiyunautomatically enabled if the file system is exported using the "pnfs"
21*4882a593Smuzhiyunoption and the underlying SCSI device support persistent reservations.
22*4882a593SmuzhiyunOn the client make sure the kernel has the CONFIG_PNFS_BLOCK option
23*4882a593Smuzhiyunenabled, and the file system is mounted using the NFSv4.1 protocol
24*4882a593Smuzhiyunversion (mount -o vers=4.1).
25