Hi Cameron,
Many thanks for your informative reply and your patience with my questions.
I looked at the file /usr/local/mpich-1.2.5/share/machines.LINUX and there
are 5 lines
containing the following:
rene.renelinux.net
This is expected as far as I understand because these are virtual machines.
Now in file /etc/hosts, I corrected the line
"10.162.211.74 rene.renelinux.net .renelinux.net" to simply "10.162.211.74
rene.renelinux.net"
I also corrected the file /etc/hosts.deny and now it has
ALL:ALL as you indicated
I also corrected file /etc/hosts.equiv and now it has the following
rene.renelinux.net
rene.renelinux.net
rene.renelinux.net
rene.renelinux.net
rene.renelinux.net
localhost
I put "rene.renelinux.net" 5 times because the file
/usr/loac/mpich-1.2.5/share/machines.LINUX has
that line 5 times.
in the user account "rene", I tried to start a "rsh" shell with the command
rsh -d rene.renelinux.net
doing a "netstat -at" I got as the first line:
Active Internet connections (servers and established)
Proto Recv-Q Send-Q Local Address Foreign Address State
tcp 0 1 192.168.1.102:1023 rene.renelinux.ne:login SYN_SENT
The documentation of netstat indicates that this means that a foreign
connection is being attemped (state = SYN_SENT)
Note here that 192.168.1.102 is the address given by the router to the
computer
So if I am not able to establish a connection with that local address
192.168.1.102 then there is no way
that MPICH will run properly and that my program would give
with the command:
mpirun -np 1 t_mpi1 (name of sample MPI program is t_mpi1.c)
process 0 of 1.
I tried doing "rsh localhost". It does login but doing "mpirun -np 1 t_mpi1"
gives the same answer
process 0 of 0.
Perharps it is the IP address given by the router "192.168.1.102" that is
causing the problem:
IP address of "rene.renelinux.net" is 10.162.211.74 and the Local IP Address
it is trying to login is
192.168.1.102
Beyond this I do not know what to do. Again, there are things I do not
understand about that rshd so
I will have to read to understand better. Any suggestion ?
Regards
Rene
"Cameron Kerr" <cameron.kerr@paradise.net.nz> wrote in message
news:401dcfc9@news.maxnet.co.nz...
> [Set Followup-To COLN]
> In comp.os.linux.networking Rene Girard <aa@bb.yy> wrote:
>
> > mpirun -np 1 ./t_mpi1 (-np is for the number of processors)
> >
> > I should get the following answer:
> >
> > First MPI program
> > [t_mpi1]: I am 0 of 1
> > Success !: First MPI program
> >
> > meaning I am processor no. "0" of one processor
> >
> > however, I get
> >
> > First MPI program
> > [t_mpi1]: I am 0 of 0 <--- Note the "0" instead of the one.
> > Success !: First MPI program.
>
> That would indicate to me that it seems to think it's only configured
> with 0 processes. I think rsh may not be your problem.
>
> To verify, try the following.
>
> Have a look in /var/log/syslog and /var/log/messages. There should be an
> entry in there for every rsh connection that is accepted, and the
> command that was run.
>
>
> Now, what does your /etc/mpich/machines.LINUX file say? (Yours might not
> be called exactly that). Mine says something like the following (Note,
> I admin a network that some people use for cluster stuff, but I don't
> really know much about MPICH.
>
> csatm1
> csatm2
> csatm3
> csatm4
> csatm5
> csatm6
> csatm7
> csatm8
>
> For a total of eight processes.
>
> > Content of file "/etc/hosts"
> >
> > # /etc/hosts - hostname_to_address mappings for the resolver library
>
> > # LISA or COAS will automatically put the hostname in the right line
> > # for you.
> > # !!! Automatically generated by lizard. Do not edit !!!
>
> > 10.162.211.74 rene.renelinux.net .renelinux.net
>
> That doesn't look good, you should fix that. The last bit should just
> say "rene".
>
> > # hosts.deny This file describes the names of the hosts which are
>
> > swat:ALL EXCEPT 127.0.0.1
>
> You should normally have ALL:ALL in here, but you can fix that later.
>
> --
> Cameron Kerr
> cameron.kerr@paradise.net.nz : http://nzgeeks.org/cameron/
> Empowered by Perl!