I fixed the problem it seems. /var/spool/pbs/mom_priv/config had the external interface on the master node defined and not the internal private address. It should have just used pbs_oscar for the hostname but instead used the fqdn of the public interface. Perhaps a bug?
Changed this, restarted pbs_mom on all nodes and now I get what I expect. Thanks -jeremy On Fri, 29 Apr 2005, Bernard Li wrote: > Well notice that according to Torque/PBS - the state of your nodes are > 'unknown/down'. You need to figure out why that's the case and how to > make them become 'available' again. > > Cheers, > > Bernard > > > -----Original Message----- > > From: Jeremy Hansen [mailto:[EMAIL PROTECTED] > > Sent: Friday, April 29, 2005 14:55 > > To: Bernard Li > > Cc: [email protected] > > Subject: RE: [Oscar-users] Not enough free nodes. Tests incomplete. > > > > > > I also noticed this using maui's checkjob > > > > [EMAIL PROTECTED] bin]# ./checkjob 31 > > > > > > checking job 31 > > > > State: Idle (User: oscartst Group: oscartst) > > WallTime: 0:00:00 of INFINITY > > SubmitTime: Fri Apr 29 14:52:46 > > (Time Queued Total: 0:00:23 Eligible: 0:00:00) > > > > Total Tasks: 1 > > > > Req[0] TaskCount: 1 Partition: ALL > > Network: [NONE] Memory >= 0 Disk >= 0 Swap NC 0 > > Opsys: [NONE] Arch: [NONE] Class: [workq 1] Features: [NONE] > > > > > > IWD: [NONE] Executable: [NONE] > > QOS: DEFAULT Bypass: 0 StartCount: 0 > > PartitionMask: [ALL] > > Flags: RESTARTABLE > > > > job is deferred. Reason: NoResources (exceeds available partition > > procs) > > Holds: Defer > > PE: 1.00 StartPriority: 1 > > cannot select job 31 for partition DEFAULT (job hold active) > > > > Job is deferred because there are no resources??? > > > > -jeremy > > > > On Fri, 29 Apr 2005, Bernard Li wrote: > > > > > Hey Jeremy: > > > > > > What does pbsnodes -a give you? > > > > > > Also, try running the PBS/Torque GUI's (like xpbs, xpbsmon) > > and see if > > > the nodes are set up properly... it seems like the qmaster > > is set up > > > but none of the execution nodes are set up... > > > > > > Cheers, > > > > > > Bernard > > > > > > > -----Original Message----- > > > > From: Jeremy Hansen [mailto:[EMAIL PROTECTED] > > > > Sent: Friday, April 29, 2005 13:38 > > > > To: Bernard Li > > > > Cc: [email protected] > > > > Subject: RE: [Oscar-users] Not enough free nodes. Tests > > incomplete. > > > > > > > > On Fri, 29 Apr 2005, Bernard Li wrote: > > > > > > > > > Hi Jeremy: > > > > > > > > > > > on the master node /etc/hosts looks like this: > > > > > > > > > > > > 10.2.6.199 oscar-control.blah.com oscar-control oscar_server > > > > > > nfs_oscar pbs_oscar > > > > > > 172.21.184.192 oscar-control.blah.com oscar-control > > > > > > > > > > > > # These entries are managed by SIS, please don't modify them. > > > > > > 10.2.6.1 node1.blah.com node1 > > > > > > 10.2.6.2 node2.blah.com node2 > > > > > > 10.2.6.3 node3.blah.com node3 > > > > > > 10.2.6.4 node4.blah.com node4 > > > > > > 10.2.6.5 node5.blah.com node5 > > > > > > 10.2.6.6 node6.blah.com node6 > > > > > > 10.2.6.7 node7.blah.com node7 > > > > > > 10.2.6.8 node8.blah.com node8 > > > > > > 10.2.6.9 node9.blah.com node9 > > > > > > 10.2.6.10 node10.blah.com node10 > > > > > > > > > > I don't see a 127.0.0.1... It needs to be there. > > > > > > > > It's in there...just skipped it on the paste. > > > > > > > > > > The *.err files in > > > > > > oscartst are zero length. > > > > > > > > > > > > Where would I find more log files? > > > > > > > > > > Since these are PBS/Torque errors, one place to look > > for logs is > > > > > /var/spool/pbs/server_logs. > > > > > > > > Output from the server_log during the test: > > > > > > > > 04/29/2005 > > > > 13:15:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:16:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:17:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:18:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:19:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:20:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:21:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:22:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:23:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:24:15;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > > > > > > > > > > > > > > > > > 04/29/2005 13:24:23;0002;PBS_Server;Svr;PBS_Server;Server > > > > shutdown completed > > > > 04/29/2005 13:24:23;0002;PBS_Server;Svr;Log;Log closed > > > > 04/29/2005 13:24:23;0002;PBS_Server;Svr;Log;Log opened > > > > 04/29/2005 13:24:23;0006;PBS_Server;Svr;PBS_Server;Server > > > > oscar-control started, initialization type = 1 > > > > 04/29/2005 13:24:23;0002;PBS_Server;Svr;Act;Account file > > > > /var/spool/pbs/server_priv/accounting/20050429 opened > > > > 04/29/2005 13:24:23;0040;PBS_Server;Req;setup_nodes;setup_nodes() > > > > > > > > 04/29/2005 13:24:23;0002;PBS_Server;Svr;PBS_Server;Server > > Ready, pid > > > > = > > > > 4391 > > > > 04/29/2005 > > > > 13:24:23;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command scheduler_first > > > > 04/29/2005 > > > > 13:25:23;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:26:23;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:27:23;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:28:23;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > 04/29/2005 > > > > 13:29:23;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command time > > > > > > > > I don't see anything usual in this log. One thing I've > > noticed, and > > > > perhaps this is just my ignorance on how it functions at > > the moment, > > > > but my submitted jobs do not appear to get scheduled when > > submitted. > > > > Just a simple echo script sits in the queue: > > > > > > > > [EMAIL PROTECTED] oscartst]$ qstat > > > > Job id Name User Time > > Use S Queue > > > > ---------------- ---------------- ---------------- > > -------- - ----- > > > > 21.oscar-control test.sh oscartst > > 0 Q workq > > > > 22.oscar-control test.sh oscartst > > 0 Q workq > > > > > > > > 04/29/2005 > > > > 13:36:59;0040;PBS_Server;Svr;oscar-control;Scheduler > > > > sent command new > > > > > > > > > > > > > Cheers, > > > > > > > > > > Bernard > > > > > > > > > > > > > > > ------------------------------------------------------- > > > > > This SF.Net email is sponsored by: NEC IT Guy Games. > > > > > Get your fingers limbered up and give it your best > > shot. 4 great > > > > > events, 4 opportunities to win big! Highest score > > wins.NEC IT Guy > > > > > Games. Play to win an NEC 61 plasma display. Visit > > > > > http://www.necitguy.com/?r > > > > > _______________________________________________ > > > > > Oscar-users mailing list > > > > > [email protected] > > > > > https://lists.sourceforge.net/lists/listinfo/oscar-users > > > > > > > > > > > > > > > > > > > > > > > ------------------------------------------------------- > This SF.Net email is sponsored by: NEC IT Guy Games. > Get your fingers limbered up and give it your best shot. 4 great events, 4 > opportunities to win big! Highest score wins.NEC IT Guy Games. Play to > win an NEC 61 plasma display. Visit http://www.necitguy.com/?r > _______________________________________________ > Oscar-users mailing list > [email protected] > https://lists.sourceforge.net/lists/listinfo/oscar-users > ------------------------------------------------------- This SF.Net email is sponsored by: NEC IT Guy Games. Get your fingers limbered up and give it your best shot. 4 great events, 4 opportunities to win big! Highest score wins.NEC IT Guy Games. Play to win an NEC 61 plasma display. Visit http://www.necitguy.com/?r=20 _______________________________________________ Oscar-users mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/oscar-users
