>>>>> " " == Shane Shrybman <shane@zeke.yi.org> writes:
> I am following up my own post because I found some more info.
> I was using an rsize and wsize of 16384 when mounting that nfs
> (which is on a raid0 md device) any value less than 16384 seems
> to work ok. Also, other nfs mount between the same hosts seem
> to be ok with 16384, it still just the raid0 nfs mount that is
> the problem with rsize and wsize of 16384.
Ah. That explains it. You can't expect NFSv2 to work with any value of
rsize or wsize > 8k: it's a hard limit in the protocol. You'll
probably find that the server is running over some buffer limits and
hence corrupting the reply.
The support for > 8k wsize is really a preparation for NFSv3. I'll be
putting in the necessary checks and hard upper limits for rsize/wsize
later in the 2.3.x series.
Cheers,
Trond
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Mar 23 2000 - 21:00:39 EST