Hi everybody,
after another day installing and configuring lam,
now I can run lamboot successfully, on my three node
cluster, besides master has 6.5.9, compiled with
--with-trillium, and nodes has 6.5.8 rpm.
However I want all machines with same lam version,
and I'm trying to do this with NFS. So, after
uninstalled lam on nodes, I exported my /usr/local to
them. When I'm in slave02 or slave03 (by ssh), all lam
execs are avaliable, but if I try 'rsh slave02 hboot'
(exactly like lamboot does), 'hboot: command not
found' is what I got, even if an command like 'rsh
slave02 ls' is successfully.
I just put /usr/local in my /etc/exports, should I
do anything else? How can I solve this? To run XMPI,
do I really need my lam compiled with --with-trillium
on all nodes or just on the master one? Any suggests?
Thanks,
Luiz Augusto
_______________________________________________________________________
Desafio AntiZona: participe do jogo de perguntas e respostas que vai
dar um Renault Clio, computadores, câmeras digitais, videogames e muito
mais! www.cade.com.br/antizona
|
