Hello,

I have = a NFS related=20 crash on Suse, I do have a support call in with = Suse,

I = really only want=20 to know if there is any patch add/deletes that was to = fix

a = similar issue to=20 this. We are using 2.6.5-7.139 which is of=20 course

a Suse = patched=20 kernel, that I don't not know exactly what it was=20 patched

with.=20 We are running nfsv3, = with udp, 32k=20 block size.

NFS = did survive=20 several large bonnie runs to the same nfs servers, = with

no = signs similar to=20 these. Also the server seems fine when the=20 event

happens it seems to=20 be a client only problem, other clients can get

to the = server being=20 used just fine.

Below = is the=20 description, I have been looking through the recent = nfs

patches and have=20 came up with the following that look possible, but

I have looked at the code that it patches, and = don't see signs=20 of the

code = it deletes=20 being in the Suse kernel, so I don't think that is = it.

linux-2.6.7-01-write_hang.dif:

NFS: remove the WRITEPAGE_ACTIVATE hack. = It causes=20 crashes.

Customer = untars a 8GB=20 file located on a NFS share back onto the=20 same

NFS share, They have done this on at least 4 = separate=20 (slightly different

configurations) machines, with slightly different = results on=20 each machine.

On 1 of the 4 machines it succeeded, on the other = 3 it failed.=20 Customer

has also experienced similar issues doing nfs = read/writes with=20 applications

other than tar. On the other 3 machines, 1 = machine=20 locked up and required

power removal, 1 machine gave us a kernel panic, = and 1 machine=20 put the

tar process into a permanent unkillable "D" state. = Similar results were

obtained with a user test program, and a 3rd party = application=20 software.

The kernel crash message was:

CPU 0: Machine = Check=20 Exception:          4 Bank = 4:=20 f60da00100000813
  RIP !INEXACT! = 10:<ffffffff8022fae2>=20 {copy_user_generic_c0x8/0x26}
  TSC 3d101af6bf756 ADDR=20 4304010
  Kernel panic: Machine check

We have only = so far=20 got this on one of the machines.

Any ideas on what is happening?=20   All machines are Opteron machines,=20 some

are dual processor machines with one motherboard, = and the=20 other machines

are quad processer models with a different = motherboard, so it=20 does look

like a software issues since there is some = variation of=20 hardware, it also does

not look like a = broken hardware=20 issue, as the machine don't fail on anything but

these = nfs=20 tests.

The = same commands=20 appear to work on local filesystems.

&nbs= p; = ; =