sPHENIX discussion of software

[pinkenburg <pinkenburg AT bnl.gov>]

Hi folks,

it was an old configuration on some nodes from previous sphenix lustre 
tests. Fixed now, I switched us back to direct access. Let me know if 
you encounter problems (where I would need the name/ip of the 
problematic host from the condor log file)

Chris


On 10/13/2022 10:46 AM, pinkenburg via sPHENIX-software-l wrote:
> Hi folks,
>
> a bunch of the nodes in the shared pool have problems accessing 
> lustre, so those jobs have been dying. sdcc is working on this (looks 
> like some subnet is missing from the list which is allowed lustre 
> access). I switched the GSEARCHPATH in our setup scripts which sets 
> the order of protocols to access files back to use xrootd. Since this 
> is sourced in the standard condor scripts, jobs should get their input 
> files now.
>
> Once this is fixed we'll go back (last message sounds like this will 
> happen very soon)
>
> Chris

--
*************************************************************

Christopher H. Pinkenburg       ;    pinkenburg AT bnl.gov
                                ;    http://www.phenix.bnl.gov/~pinkenbu

Brookhaven National Laboratory  ;    phone: (631) 344-5692
Physics Department Bldg 510 C   ;    fax:   (631) 344-3253
Upton, NY 11973-5000

*************************************************************