Karin Lagesen
2014-10-17 15:57:32 UTC
Hi!
I am new as a slurm admin, so pardon if my questions are a FAQ somewhere.
I am trying to install slurm on my local computer in anticipation of
installing it on a server. In both cases we thus have one single
machine, both acting as controller and compute node.
I am having problems getting the slurmd daemon to start. This is my
error message:
[***@pcus263]~% slurmd -Dcvvvv
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/topology_none.so
slurmd: topology NONE plugin loaded
slurmd: debug3: Success.
slurmd: Gathering cpu frequency information for 4 cpus
slurmd: debug3: NodeName = pcus263
slurmd: debug3: TopoAddr = pcus263
slurmd: debug3: TopoPattern = node
slurmd: debug3: CacheGroups = 0
slurmd: debug3: ClusterName = cluster
slurmd: debug3: Confile = `/usr/local/etc/slurm.conf'
slurmd: debug3: Debug = 7
slurmd: debug3: CPUs = 4 (CF: 4, HW: 4)
slurmd: debug3: Boards = 1 (CF: 1, HW: 1)
slurmd: debug3: Sockets = 1 (CF: 1, HW: 1)
slurmd: debug3: Cores = 2 (CF: 2, HW: 2)
slurmd: debug3: Threads = 2 (CF: 2, HW: 2)
slurmd: debug3: UpTime = 10317 = 02:51:57
slurmd: debug3: Block Map = 0,1,2,3
slurmd: debug3: Inverse Map = 0,1,2,3
slurmd: debug3: RealMemory = 7848
slurmd: debug3: TmpDisk = 3924
slurmd: debug3: Epilog = `(null)'
slurmd: debug3: Logfile = `(null)'
slurmd: debug3: HealthCheck = `(null)'
slurmd: debug3: NodeName = pcus263
slurmd: debug3: NodeAddr = (null)
slurmd: debug3: Port = 6818
slurmd: debug3: Prolog = `(null)'
slurmd: debug3: TmpFS = `/tmp'
slurmd: debug3: Public Cert = `(null)'
slurmd: debug3: Slurmstepd = `/usr/local/sbin/slurmstepd'
slurmd: debug3: Spool Dir = `/home/karinlag/slurm/slurmd'
slurmd: debug3: Pid File = `/home/karinlag/slurm/run/d.pid'
slurmd: debug3: Slurm UID = 59717
slurmd: debug3: TaskProlog = `(null)'
slurmd: debug3: TaskEpilog = `(null)'
slurmd: debug3: TaskPluginParam = 0
slurmd: debug3: Use PAM = 0
slurmd: debug3: Trying to load plugin
/usr/local/lib/slurm/proctrack_linuxproc.so
slurmd: debug3: Success.
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/task_none.so
slurmd: task NONE plugin loaded
slurmd: debug3: Success.
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/auth_none.so
slurmd: Null authentication plugin loaded
slurmd: debug3: Success.
slurmd: debug: spank: opening plugin stack /usr/local/etc/plugstack.conf
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/crypto_munge.so
slurmd: Munge cryptographic signature plugin loaded
slurmd: debug3: Success.
slurmd: debug3: initializing slurmd spool directory
slurmd: fatal: You are running slurmd as something other than user
root(0). If you want to run as this user add SlurmdUser=karinlag to the
slurm.conf file.
[***@pcus263]~%
My SlurmUser is actually set to karinlag (my user), and I can read/write
the config file, which is why this is so confusing.
Thankyou for any help in advance,
Karin
I am new as a slurm admin, so pardon if my questions are a FAQ somewhere.
I am trying to install slurm on my local computer in anticipation of
installing it on a server. In both cases we thus have one single
machine, both acting as controller and compute node.
I am having problems getting the slurmd daemon to start. This is my
error message:
[***@pcus263]~% slurmd -Dcvvvv
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/topology_none.so
slurmd: topology NONE plugin loaded
slurmd: debug3: Success.
slurmd: Gathering cpu frequency information for 4 cpus
slurmd: debug3: NodeName = pcus263
slurmd: debug3: TopoAddr = pcus263
slurmd: debug3: TopoPattern = node
slurmd: debug3: CacheGroups = 0
slurmd: debug3: ClusterName = cluster
slurmd: debug3: Confile = `/usr/local/etc/slurm.conf'
slurmd: debug3: Debug = 7
slurmd: debug3: CPUs = 4 (CF: 4, HW: 4)
slurmd: debug3: Boards = 1 (CF: 1, HW: 1)
slurmd: debug3: Sockets = 1 (CF: 1, HW: 1)
slurmd: debug3: Cores = 2 (CF: 2, HW: 2)
slurmd: debug3: Threads = 2 (CF: 2, HW: 2)
slurmd: debug3: UpTime = 10317 = 02:51:57
slurmd: debug3: Block Map = 0,1,2,3
slurmd: debug3: Inverse Map = 0,1,2,3
slurmd: debug3: RealMemory = 7848
slurmd: debug3: TmpDisk = 3924
slurmd: debug3: Epilog = `(null)'
slurmd: debug3: Logfile = `(null)'
slurmd: debug3: HealthCheck = `(null)'
slurmd: debug3: NodeName = pcus263
slurmd: debug3: NodeAddr = (null)
slurmd: debug3: Port = 6818
slurmd: debug3: Prolog = `(null)'
slurmd: debug3: TmpFS = `/tmp'
slurmd: debug3: Public Cert = `(null)'
slurmd: debug3: Slurmstepd = `/usr/local/sbin/slurmstepd'
slurmd: debug3: Spool Dir = `/home/karinlag/slurm/slurmd'
slurmd: debug3: Pid File = `/home/karinlag/slurm/run/d.pid'
slurmd: debug3: Slurm UID = 59717
slurmd: debug3: TaskProlog = `(null)'
slurmd: debug3: TaskEpilog = `(null)'
slurmd: debug3: TaskPluginParam = 0
slurmd: debug3: Use PAM = 0
slurmd: debug3: Trying to load plugin
/usr/local/lib/slurm/proctrack_linuxproc.so
slurmd: debug3: Success.
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/task_none.so
slurmd: task NONE plugin loaded
slurmd: debug3: Success.
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/auth_none.so
slurmd: Null authentication plugin loaded
slurmd: debug3: Success.
slurmd: debug: spank: opening plugin stack /usr/local/etc/plugstack.conf
slurmd: debug3: Trying to load plugin /usr/local/lib/slurm/crypto_munge.so
slurmd: Munge cryptographic signature plugin loaded
slurmd: debug3: Success.
slurmd: debug3: initializing slurmd spool directory
slurmd: fatal: You are running slurmd as something other than user
root(0). If you want to run as this user add SlurmdUser=karinlag to the
slurm.conf file.
[***@pcus263]~%
My SlurmUser is actually set to karinlag (my user), and I can read/write
the config file, which is why this is so confusing.
Thankyou for any help in advance,
Karin
--
Karin Lagesen, Ph.D.
Department of Medical Genetics
Oslo University Hospital
http://blog.karinlag.no
Karin Lagesen, Ph.D.
Department of Medical Genetics
Oslo University Hospital
http://blog.karinlag.no