NFS settings in nsfconf

[Randy Durden]

My HP 11.11 servers keeps bogging and occasionly get NFS server not responding.
My NUM_NFSD is set to 16 in the nsfconf file, but the file states 4 is optimal. Should I change this back to 4?

[Ganesan R]

Hi,

Check this thread...

http://forums13.itrc.hp.com/service/forums/questionanswer.do?admit=109447627+1239199773646+28353475&threadId=123930

[Steven E. Protter]

Shalom,

Check nfsstat when it happens. I' not sure why you are working this angle.

SEP

[Randy Durden]

Here is part of the nfsstat output

Server rpc:
Connection oriented:
calls badcalls nullrecv
0 0 0
badlen xdrcall dupchecks
0 0 0
dupreqs
0
Connectionless oriented:
calls badcalls nullrecv
0 0 0
badlen xdrcall dupchecks
0 0 0
dupreqs
0

Server nfs:
calls badcalls
0 0
Version 2: (0 calls)
null getattr setattr
0 0% 0 0% 0 0%
root lookup readlink
0 0% 0 0% 0 0%
read wrcache write
0 0% 0 0% 0 0%
create remove rename
0 0% 0 0% 0 0%
link symlink mkdir
0 0% 0 0% 0 0%
rmdir readdir statfs
0 0% 0 0% 0 0%
Version 3: (0 calls)
null getattr setattr
0 0% 0 0% 0 0%
lookup access readlink
0 0% 0 0% 0 0%
read write create
0 0% 0 0% 0 0%
mkdir symlink mknod
0 0% 0 0% 0 0%
remove rmdir rename
0 0% 0 0% 0 0%
link readdir readdir+
0 0% 0 0% 0 0%
fsstat fsinfo pathconf
0 0% 0 0% 0 0%
commit
0 0%

Client rpc:
Connection oriented:
calls badcalls badxids
0 0 0
timeouts newcreds badverfs
0 0 0
timers cantconn nomem
0 0 0
interrupts
0
Connectionless oriented:
calls badcalls retrans
43902 1169 2344
badxids timeouts waits
4 3512 0
newcreds badverfs timers
0 0 9
toobig nomem cantsend
0 0 0
bufulocks
0

Client nfs:
calls badcalls clgets
42733 0 42733
cltoomany
0
Version 2: (42733 calls)
null getattr setattr
0 0% 5603 13% 0 0%
root lookup readlink
0 0% 28316 66% 1 0%
read wrcache write
7454 17% 0 0% 0 0%
create remove rename
0 0% 0 0% 0 0%
link symlink mkdir
0 0% 0 0% 0 0%
rmdir readdir statfs
0 0% 1243 2% 116 0%
Version 3: (0 calls)
null getattr setattr
0 0% 0 0% 0 0%
lookup access readlink
0 0% 0 0% 0 0%
read write create
0 0% 0 0% 0 0%
mkdir symlink mknod
0 0% 0 0% 0 0%
remove rmdir rename
0 0% 0 0% 0 0%
link readdir readdir+
0 0% 0 0% 0 0%
fsstat fsinfo pathconf
0 0% 0 0% 0 0%
commit
0 0%

[Pete Randall]

Here is a white paper from Dave Olker, *THE* NFS authority that might offer some guidance:

http://docs.hp.com/en/10388/DesigningaHighPerformanceNFSServer.pdf


Pete

[Dave Olker]

The system you collected the nfsstat output is an NFS client, so NUM_NFSD on this box won't matter.

Looking at the output, you're using NFS version 2 and UDP. The only time I ever see that anymore is when you're using the old legacy automounter.

Depending on your environment, you might get better performance if you switch to NFS v3 and TCP. If you manage your filesystems via the automounter, get the Enhanced AutoFS package from software.hp.com and use it instead of the old legacy automounter.

Dave