Re: Very poor NFS I/O

[mlelstv%serpens.de@localhost (Michael van Elst)]

joel.bertrand%systella.fr@localhost (=?UTF-8?Q?BERTRAND_Jo=c3=abl?=) writes:

>> Th nfsstat command may also reveal some information. On the server,
>> look for 'Server Errors'. On a NetBSD client (maybe FreeBSD too)
>> look for timeouts and retries under 'RPC Info'.

>Server :
>RPC errors          faults
>   4549883               0

This looks much, but it also includes all the operations that
just return an error (like ENOENT or EACCESS).


>Client (Linux) :
>Client rpc stats:
>calls      retrans    authrefrsh
>26296714   259        26320477

That's just a small number of retransmissions.


>Client (FreeBSD) :
>Rpc Info:
>     TimedOut      Invalid    X Replies      Retries     Requests
>            0            0            0            0     28344975

Here is no visible problem.

I'd say, that rules out the NFS layer.


Next is to check your disks. Try read and write operations
(and before reading via NFS, do a touch on the testfile
to invalidate caches).

While the operation is running, run on the server:

iostat -yw 1 $disks

where disks is the list of physical disks affected (e.g. wd0 wd1 wd2).