[Beowulf] Problems with MPI(boot)

[Cheng, Kevin]

What's rhs?
(on master)
-bash-3.00# mpd -h slave -p 34706
^[[A
master_32934: conn error in connect_rhs: Connection refused
master_32934 (connect_rhs 602): failed to connect to rhs at 127.0.0.1 34706
master_32934 (enter_ring 513): rhs connect failed
master_32934 (run 215): failed to enter ring


(on slave)
bash-3.00# slave_34706 (handle_rhs_input 899): lost rhs; re-entering ring
slave_34706 (handle_rhs_input 899): lost rhs; re-entering ring

-----

Following the install.pdf I am able to do the mpdcheck -s, and mpdcheck -c host port. However I can't seem to get mpdboot to work, or mpdcheck -f mpd.hosts -ssh. It says connection refused. Even though both rsh and ssh work fine passwordless:

bash-3.00# mpdcheck -f ~/mpd.hosts -ssh
*** the fq hostname seems to be localhost
*** first ipaddr for this host (via slave) is: 127.0.0.1
** timed out waiting for client on master to produce output
client on master failed to access the server
here is the output:
Traceback (most recent call last):
  File "/usr/local/bin/mpdcheck.py", line 102, in ?
    sock.connect((argv[argidx+1],int(argv[argidx+2])))  # note double parens
  File "<string>", line 1, in connect
socket.error: (111, 'Connection refused')

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.scyld.com/pipermail/beowulf/attachments/20050628/177ee45d/attachment.html