[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Condor-users] [MPICH] MPICH1.2.4 _Condor Problem



Hi,

I followed the link and set the ephemeral port range.

But still it uses different port numbers to connect to other machines.

Here are the few ports (source, destination) used.

SPT=50912 DPT=0

SPT=50927 DPT=544

SPT=50928 DPT=544

SPT=1023 DPT=514

 

How to control this source and destination port range, for mpich1.2.4 to connect to other machines.

 

Thanks,

Senthil

 

 


From: Rajeev Thakur [mailto:thakur@xxxxxxxxxxx]
Sent: Wednesday, March 07, 2007 4:37 PM
To: Natarajan, Senthil; 'Condor-Users Mail List'; mpich-discuss@xxxxxxxxxxx
Cc: 'Greg Thain'
Subject: RE: [MPICH] MPICH1.2.4 _Condor Problem

 

MPICH doesn't use a fixed port. It uses ports assigned by the machine's IP stack, which are in the ephemeral port range. See http://www.ncftpd.com/ncftpd/doc/misc/ephemeral_ports.html

 

Rajeev

 


From: owner-mpich-discuss@xxxxxxxxxxx [mailto:owner-mpich-discuss@xxxxxxxxxxx] On Behalf Of Natarajan, Senthil
Sent: Wednesday, March 07, 2007 2:13 PM
To: Condor-Users Mail List; mpich-discuss@xxxxxxxxxxx
Cc: Greg Thain
Subject: [MPICH] MPICH1.2.4 _Condor Problem

Hi,

I am submitting MPI jobs, using MPICH1.2.4 through condor.

I have setup a separate user (something like “condor-user”) to run condor jobs on all the dedicated nodes. I created the certificates and copied to all the nodes.

So the user (“condor-user”) can ssh with out password, within all the nodes and to its own node.

 

But the job fails and complaining about the connection refused to the same machine. (I.e) the job runs on Machine A, couldn’t not connect to Machine A.

 

Here is the error from one of the node.

 

connect to address xxx.xx.xxx.xx: Connection refused

connect to address xxx.xx.xxx.xx: Connection refused

trying normal rsh (/usr/bin/rsh)

MachineA: Connection refused

 

p0_20339:  p4_error: Timeout in making connection to remote process on MachineA: 0

p0_20339: (301.989178) net_send: could not write to fd=4, errno = 32

 

By default MPI jobs (MPICH1.2.4) runs on what port? so that I can setup firewall rules. Even I tried to set the port range like this

MPICH_PORT_RANGE=50001:59999

And allow the above ports in the firewall rule. But still having the connection refused problem.

 

Could you please let me know what might be the problem?

 

Thanks,

Senthil