LAM/MPI logo

LAM/MPI General User's Mailing List Archives

  |   Home   |   Download   |   Documentation   |   FAQ   |   all just in this list

From: Azrael (azrael_at_[hidden])
Date: 2004-12-04 10:20:02


Hello,

i have a problem with the lamgrow command.

I have two linux computers, a client and a server. I am booting on the
server the LAM with a nodefile. In this nodefile is only the server.
Everything is fine.

Now i want to add the client with the lamgrow command and get the
following error message:

[...]
n0<1976> ssi:boot:rsh: found the following hosts:
n0<1976> ssi:boot:rsh: n0 192.168.200.100 (cpu=1)
n0<1976> ssi:boot:rsh: n1 client000C29A7D542 (cpu=1)
n0<1976> ssi:boot:rsh: resolved hosts:
n0<1976> ssi:boot:rsh: n0 192.168.200.100 --> 192.168.200.100 (origin)
n0<1976> ssi:boot:rsh: n1 client000C29A7D542 --> 192.168.200.101
n0<1976> ssi:boot:rsh: starting RTE procs
n0<1976> ssi:boot:base:linear: starting
n0<1976> ssi:boot:base:server: opening server TCP socket
n0<1976> ssi:boot:base:server: opened port 1095
n0<1976> ssi:boot:base:linear: skipping n0 (192.168.200.100); not bootable
n0<1976> ssi:boot:base:linear: booting n1 (client000C29A7D542)
Segmentation fault

The ip addresses and hostnames are:
192.168.200.100 master
192.168.200.101 client000C29A7D542

If the client is in the nodefile, then everything went fine.

I can connect from the client to the server and from the server to the
client with ssh without a password or error message.

I can also boot the LAM on the client with a local nodefile on the
client.

I don´t know what "Segmentation fault" means.

Please help.

Thank you.

Azze