Newsgroups: comp.parallel.pvm
From: sweirich@top.cis.syr.edu (Stephanie Weirich)
Subject: Can't get them to talk to eachother
Organization: Syracuse University CIS Dept.
Date: 19 Jul 1994 03:02:15 GMT
Message-ID: <30ffno$7d9@newstand.syr.edu>


Hi. I'm having problems getting two machines to talk to eachother
with pvm 3.3.2. What I have is an SGI challenge and a DEC alpha 
connected together with FDDI. 

I start the pvm daemon on the challenge (kopernik) and 
the hostfile contains:

	kestrel1.npac.syr.edu dx=/tmp_mnt/home/B6G/terrain/sweirich/pvm3/lib/pvmd

which is the name of the DEC Alpha and the directory that 
the daemon is in.

kopernik 84% pvmd3 hostfile
7f000001:060f

so after this it hangs for a long time. I can suspend it 
and start the console to see......

	kopernik 86% pvm
	pvmd already running.	
	pvm> conf
	2 hosts, 2 data formats
        	            HOST     DTID     ARCH   SPEED
                	kopernik    40000    SGIMP    1000
	   kestrel1.npac.syr.edu    80000    ALPHA    1000
	pvm> mstat kestrel1.npac.syr.edu
   	kestrel1.npac.syr.edu  Host failed

In the tmp file created on the challenge I get:
	[t80040000] ready  3.3.2   Mon Jul 18 22:38:09 1994
	[t80040000] netoutput() timed out sending to kestrel1.npac.syr.edu 
		after 14, 190.000000
	[t80040000]  hd_dump() ref 1 t80000 n "kestrel1.npac.syr.edu" a ""
		 ar "ALPHA"
	[t80040000]            lo "" so "" dx "/tmp_mnt/home/B6G/terrain/
		sweirich/pvm3/lib/pvmd" ep "" bx "" wd "" sp 1000
	[t80040000]            sa 128.230.8.51:2351 mtu 4096 f 0x0 e 0 txq 2
	[t80040000]            tx 2 rx 1 rtt 1.000000
	[t80040000] dm_halt() from (kopernik), halting...
	[t80040000] work() pvmd halting
	[t80040000] pvmbailout(0)



hmmmm.... and looking at the console on the Alpha 
I get:

	<kestrel1.npac.syr.edu>:lib % pvm
	pvmd already running.
	pvm> conf
	2 hosts, 1 data format
        	            HOST     DTID     ARCH   SPEED
                	       ?    40000             1000
       	   kestrel1.npac.syr.edu    80000    ALPHA    1000

and looking at it's tmp file:
	[t80080000] ready  3.3.2   Mon Jul 18 22:37:10 1994
	[t80080000] work() run = STARTUP, timed out waiting for master
	[t80080000] pvmbailout(0)


Hopefully this is enough info to make a diagnostic, as I really don't 
have any idea what it is trying to tell me. There obviously connecting 
somewhat, but somewhere a snag occurs.


Thanks a bunch,
stephanie   


________________________________________________________
sweirich@npac.syr.edu
http://www.npac.syr.edu/REU/reu94/sweirich/homepage.html

