Hi Elliot:

How many nodes are in your cluster (compute nodes) and you cannot ssh to
_all_ of them?

I would get on the console to see what is going on the nodes, (i.e. see
why ssh is failing)

Cheers,

Bernard

> -----Original Message-----
> From: Elliott Cox [mailto:[EMAIL PROTECTED] 
> Sent: Tuesday, April 12, 2005 9:40
> To: Bernard Li
> Cc: [email protected]
> Subject: Re: RE: [Oscar-users] PBS shell test failure
> 
> Bernard,
> 
> It says that there is no route to the nodes when i try SSH 
> from the terminal.  and when it tries the user tests it will 
> get to the point where it looks for free nodes and says not 
> enough free nodes.
> 
> Thanks,
> Elliott
> 
> -----Original Message-----
> From: "Bernard Li" <[EMAIL PROTECTED]>
> To: "Elliott Cox" <[EMAIL PROTECTED]>
> Date: Mon, 11 Apr 2005 19:48:11 -0700
> Subject: RE: [Oscar-users] PBS shell test failure
> 
> Can you provide more details?
>  
> I assume you modified /etc/hosts in your headnode only, right?
>  
> Cheers,
>  
> Bernard
> 
> ________________________________
> 
> From: Elliott Cox [mailto:[EMAIL PROTECTED]
> Sent: Mon 11/04/2005 7:41 PM
> To: Bernard Li
> Cc: [email protected]
> Subject: RE: [Oscar-users] PBS shell test failure
> 
> 
> 
> Bernard,
> 
> I did as you suggested however now ssh won't work at all
> 
> regards,
> Elliott
> 
> -----Original Message-----
> From: "Bernard Li" <[EMAIL PROTECTED]>
> To: "Elliott Cox" <[EMAIL PROTECTED]>
> Date: Sun, 10 Apr 2005 21:58:48 -0700
> Subject: RE: RE: [Oscar-users] PBS shell test failure
> 
> Hi Elliot:
> 
> Modify your /etc/hosts file so it reads:
> 
> 127.0.0.1 cserver.clusterdomain localhost.localdomain localhost
> 
> Then re-start Torque then it should work.
> 
> Cheers,
> 
> Bernard
> 
> ________________________________
> 
> From: Elliott Cox [mailto:[EMAIL PROTECTED]
> Sent: Sun 10/04/2005 9:43 PM
> To: Bernard Li
> Cc: [email protected]
> Subject: Re: RE: [Oscar-users] PBS shell test failure
> 
> 
> 
> Hi Bernard:
> 
> attached is the file you requested, as to your question no I 
> haven't modified the file
> 
> Thanks,
> Elliott
> 
> -----Original Message-----
> From: "Bernard Li" <[EMAIL PROTECTED]>
> To: "Elliott Cox" <[EMAIL PROTECTED]>, 
> <[email protected]>
> Date: Sat, 9 Apr 2005 17:43:56 -0700
> Subject: RE: [Oscar-users] PBS shell test failure
> 
> Hi Elliot:
> 
> Can you post your /etc/hosts file (on the headnode)?
> 
> Also, can you let us know whether you have manually modify 
> that particular file?
> 
> Thanks,
> 
> Bernard
> 
> ________________________________
> 
> From: [EMAIL PROTECTED] on behalf of Elliott Cox
> Sent: Sat 09/04/2005 4:47 PM
> To: [email protected]
> Subject: [Oscar-users] PBS shell test failure
> 
> 
> 
> HI,
> 
> I am installing an oscar test cluster on RH9 however the PBS 
> shell test keeps failing.  I don't think it's a naming issue 
> because I Set the name on install to cserver.clusterdomain.  
> The cluster is on a private 10/100 network with no internet 
> access.  And I installed oscar onto eth0.  I am attaching the 
> gzipped shelltest.out, shelltest.err, and oscarinstall .log.
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 
> 


-------------------------------------------------------
SF email is sponsored by - The IT Product Guide
Read honest & candid reviews on hundreds of IT Products from real users.
Discover which products truly live up to the hype. Start reading now.
http://ads.osdn.com/?ad_ide95&alloc_id396&op=click
_______________________________________________
Oscar-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/oscar-users

Reply via email to