NFS Performance Tuning for HP-UX 11.0 and 11i Systems

nfs performance tuning for hp-ux 11.0 and 11i systems page 40

Notes:

Page 40July 22, 2002

Troubleshooting biods (part 2)

• Poor NFS Application Performance

Ø Monitor nfsstat –c output for potential performance problems

Ø Use nfsstat –m output to monitor smooth round trip times

Ø Look for delays or retransmissions in a network trace

Ø Use tusc utility to look for delays at the system call level

ftp://ftp.cup.hp.com/dist/networking/misc/tusc.shar

Ø Use kernel profiling tools, such as kgmon, to understand where

the client’s kernel is spending the majority of its time

biod

Poor NFS Application Performance

“nfsstat –c” output can reveal if retransmissions, badxids (when a server replies

to the same request multiple times), etc. are occurring. These can indicate that

NFS requests are being dropped by the client, the server, or the network.

“nfsstat –m” output includes the smooth round trip timers maintained for the

various NFS call types (see example on page 105). Examining these values

can reveal which NFS filesystems are experiencing better performance than

others.

A network trace can help determine if application delays are caused by the

client not sending requests quickly enough or the server taking too long to reply.

The tusc utility can show which system calls are experiencing delays. This data

can help developers understand where in the application the delay is occurring.

Kernel profiling information can reveal which functions the kernel is spending

the bulk of its time running. This data can only be collected and analyzed by

qualified HP support personnel.