NFS Services Administrator's Guide

Configuring and Administering NFS Services
NFS Client and Server Transport Connections
Chapter 286
NFS Client and Server Transport Connections
NFS runs over both UDP and TCP transport protocols. The default
transport protocol is TCP. Using the TCP protocol increases the
reliability of NFS filesystems working across WANs and ensures that the
packets are successfully delivered. TCP provides congestion control and
error recovery. NFS over TCP and UDP works with NFS Version 2, and
Version 3.
NOTE TCP is the only transport protocol supported by NFS Version 4.
Supporting 1MB Transfer for TCP mounts
By default, NFS supports 32K transfer sizes across both TCP and UDP
transports.
To enable support of 1MB transfers for TCP mounts, you must first
modify the following tunables:
• nfs3_bsize (for NFS version 3)
This tunable controls the logical block size used by NFSv3 clients.
The block size represents the amount of data the client attempts to
read from or write to the server during an I/O operation.
• nfs4_bsize (for NFS version 4)
This tunable controls the logical block size used by NFSv4 clients.
The block size represents the amount of data the client attempts to
read from or write to the server during an I/O operation.
For information on the nfs3_bsize and nfs4_bsize tunables, see
nfs3_bsize (1M) and nfs4_bsize (1M).
After the tunables have been modified, set the mount option for read and
write size to 1MB, as follows:
mount -F nfs -o rsize=1048576, wsize=1048576