Problem
I want to know how to tune NFS to run an optimum number of
nfsd and biod daemons. I understand that the nfsd daemons
are server-based and provide I/O for the clients by
servicing their RPC requests, while the biod daemons are
client-based and provide read aheads and write behinds on
behalf of the client's RPC requests utilizing the client's
buffer cache. Solution
To tune NFS with respect to the number of nfsd and biod daemons
that it runs, take the following steps. Note: nfsd(NADM) syntax
is slightly different for SCO NFS 2.0.0 running on SCO OpenServer
Release 5 than the syntax for SCO NFS 1.2.1 that runs on earlier
releases.1. At the shell prompt, type:ps -ef | grep <daemon>where <daemon> is:- "nfsd", if this is the NFS file server - "biod", if this is the NFS client
For example:ps -ef | grep nfsd2. Determine which daemons need increasing or decreasing.
If all processes displayed have an accumulated time, you may
want to increase the number of daemons that are started. If one
or more processes show a zero time accumulated, then you may
want to reduce the number of daemons started. An example of the
output to "ps -ef | grep nfsd" is:root 381 379 0 Feb 7 ? 0:11 nfsd 4
root 382 379 0 Feb 7 ? 0:10 nfsd 4
root 383 379 0 Feb 7 ? 0:09 nfsd 4
root 379 1 0 Feb 7 ? 0:09 nfsd 4
root 9421 6121 1 17:55:35 p4 0:00 grep nfsd
^^^^
Notice that each of the nfsd daemons has time accumulated.3. Make the changes as follows:a. Stop NFS with:nfs stopb. Edit /etc/nfs and change the number on the line that starts
the daemon (either nfsd or biod). For example, if the /etc/nfs
file starts the nfsd daemon as:nfsd 4and the "ps -ef | grep nfsd" revealed that all processes had
accumulated time, then change the line to:nfsd 5Note: For SCO NFS 2.0.0 on OpenServer Release 5, the syntax for
the options are slightly different. Also, the nfsd daemons are
started by inetd on an as-needed basis. For example, if the line
that starts the nfsd daemon reads:nfsd -u 4 -t 16 &it means there can be a maximum of 4 nfsd daemons running that use the UDP protocol and 16 nfsd daemons that use the TCP protocol.
c. Restart NFS with:nfs startYou can verify the number of daemons running by repeating step 1
again. Continue to monitor your system periodically to see if
further tuning is necessary. See the SEE ALSO section for
references to Streams, UDP and TCP tuning, along with more detailed
information on nfsd and biod tuning.NOTES: (1) You cannot increase the number of nfsd daemons to an
arbitrarily large value. As the number of nfsd daemons
increases, context switching and scheduling overhead
becomes more of a factor.(2) Increasing the number of biod processes above the default only allows an NFS client to send more RPC requests at one time; it will not improve performance, and often makes it worse, if server request handling bandwidth is a constraint.
See also
SCO OpenServer Networking Guide: Chapter 15, "Configuring the Network File System (NFS)", Sections: "Troubleshooting NF-> Everything works slowly"
Performance Guide: Chapter 6, "Tuning NFS Performance" (includes information on UDP/TCP/Streams/nfsd and biod tuning)
Manual pages: nfs(NADM), nfsd(NADM), biod(NADM)SCO Technical Articles:TA102361, "What is nfsstat (NADM) and what does its output represent?"
TA102393, "How to interpret nfsstat for debugging and performance purposes"
TA102429, "Where can I find information on tuning SCO NFS Release 2.0.0?"