[torqueusers] New Nodes
Brett Ellis
ellis at cs.utk.edu
Wed Sep 21 09:27:44 MDT 2005
I'm sending this to torqueusers first because -W attributes specified
in maui.cfg work.
As short a description as I can make it. Let's for this example
say I have a 2 node cluster x86 running debian sarge, specified as
follows in the PBS/server_priv/nodefile
foo01 np=2 x86 foo_cluster
foo02 np=2 x86 foo_cluster
Now I've added another 2 node cluster which are
amd64's running ubuntu, so I've made my
PBS/server_priv/nodefile
foo01 np=2 x86 foo_cluster
foo02 np=2 x86 foo_cluster
bar01 np=2 amd64 bar_cluster
bar02 np=2 amd64 bar_cluster
Restarted torque and maui daemons appropriately.
Now here's what happens
qsub -I -l nodes=bar01:ppn=2+bar02:ppn=2
Works as advertised
qsub -I -l nodes=2:ppn=2:x86
Works as advertised
qsub -I -l nodes=2:ppn=2:amd64
Hangs and goes into Maui's deferred pile.
Maui reports
checking job 314
State: Idle EState: Deferred
Creds: user:joe group:joe class:batch qos:DEFAULT
WallTime: 00:00:00 of 1:00:00
SubmitTime: Wed Sep 21 11:23:36
(Time Queued Total: 00:00:01 Eligible: 00:00:01)
StartDate: 00:00:01 Wed Sep 21 11:23:38
Total Tasks: 2
Req[0] TaskCount: 2 Partition: ALL
Network: [NONE] Memory >= 0 Disk >= 0 Swap >= 0
Opsys: [NONE] Arch: [NONE] Features: [amd64]
IWD: [NONE] Executable: [NONE]
Bypass: 0 StartCount: 0
PartitionMask: [ALL]
Flags: RESTARTABLE
job is deferred. Reason: NoResources (cannot create reservation for
job '314' (intital reservation attempt)
A checknode shows the following feature line
Features: [amd64][bar_cluster]
Can anyone point me in the right direction to troubleshoot this?
Thanks,
Brett
More information about the torqueusers
mailing list