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

[HTCondor-users] flocking problems... Negotiator



Hi,

I'm trying to enable the [bi-directional] flocking between two HTCondor pools (8.0.6) but I did not work. Here is the output of SchedLog

08/04/14 03:39:36 (pid:974) PERMISSION DENIED to unauthenticated@unmapped from host 192.168.252.1 for command 416 (NEGOTIATE), access level NEGOTIATOR: reason: cached result for NEGOTIATOR; see first case for the full reason
08/04/14 03:39:39 (pid:974) Activity on stashed negotiator socket: <192.168.252.2:40537>
08/04/14 03:39:39 (pid:974) Using negotiation protocol: NEGOTIATE
08/04/14 03:39:39 (pid:974) Negotiating for owner: condor@xxxxxxxxxx
08/04/14 03:39:39 (pid:974) Finished negotiating for condor in local pool: 0 matched, 1 rejected
08/04/14 03:40:36 (pid:974) PERMISSION DENIED to unauthenticated@unmapped from host 192.168.252.1 for command 416 (NEGOTIATE), access level NEGOTIATOR: reason: cached result for NEGOTIATOR; see first case for the full reason
08/04/14 03:40:39 (pid:974) Activity on stashed negotiator socket: <192.168.252.2:40537>
08/04/14 03:40:39 (pid:974) Using negotiation protocol: NEGOTIATE
08/04/14 03:40:39 (pid:974) Negotiating for owner: condor@xxxxxxxxxx
08/04/14 03:40:39 (pid:974) Finished negotiating for condor in local pool: 0 matched, 1 rejected

Both HTCondor [virtual] pools are deployed on top of Ubuntu Precise64 systems and they have their corresponding firewall services down.
The HTCondor pools have the following IP addressing scheme

master01.demo01.org -> 192.168.251.2
wn01.demo01.org -> 192.168.251.3
master02.demo02.org -> 192.168.252.2
wn02.demo02.org -> 192.168.252.3

A task from master02 is sent and it can not be processed locally because (in this particular case) the wn02 node is down. However, pool in demo01.org domain is operational and it can even process tasks sent from master01 node. Since demo01 is operational I expect that tasks in demo02 are forwarded to demo01 but they are not.

Any comments, hints, pointers are welcome.

Thanks a lot,