[Lustre-discuss] lctl ping between 1.8.1 1.8.2 protocol error

[Sebastian Reitenbach]

Hi,

in my test system I installed Lustre 1.8.2 from source on a opensuse 10.2 i386 
(2.6.18.8-0.13-xenpaelustre) as a client. Other clients and the servers are 
running 1.8.1 on SLES 11 x86_64 (2.6.27.39-0.3-xen-lustre)
lctl ping to and from the client ends with a protocol error. The 1.8.2 client 
can lctl ping himself, and also can mount the lustre filesystem:

client2:~ # lctl ping 10.0.0.81 at tcp
failed to ping 10.0.0.81 at tcp: Protocol error
client2:~ # mount
/dev/xvda1 on / type ext3 (rw,acl,user_xattr)
proc on /proc type proc (rw)
sysfs on /sys type sysfs (rw)
debugfs on /sys/kernel/debug type debugfs (rw)
udev on /dev type tmpfs (rw)
devpts on /dev/pts type devpts (rw,mode=0620,gid=5)
10.0.0.81 at tcp:/foo on /mnt type lustre (rw)
client2:~ # lsmod | grep lust
lustre                755220  1
lov                   503208  2 lustre
mdc                   197612  2 lustre
osc                   254984  3 lustre
ptlrpc               1066664  6 mgc,lustre,lov,mdc,lquota,osc
obdclass              777336  8 mgc,lustre,lov,mdc,lquota,osc,ptlrpc
lvfs                   61532  8 mgc,lustre,lov,mdc,lquota,osc,ptlrpc,obdclass
lnet                  286040  4 lustre,ksocklnd,ptlrpc,obdclass
libcfs                165148  11 
mgc,lustre,lov,mdc,lquota,osc,ksocklnd,ptlrpc,obdclass,lvfs,lnet

/etc/modprobe.conf.local:
options lnet networks=tcp0(eth0)

anything I am missing? I'd expected this to work.

Sebastian