Felix, Can you ping the nodes from the controller and vise versa?
The snippet below looks like a potential firewall issue: [2015-03-16T15:40:02.845] debug2: Error connecting slurm stream socket at ***.***.***.***52:6818: Connection timed out Try telnet'ing from the controller to each node on port 6818 and then telnet'ing from each node to the controller on port 6817. John DeSantis 2015-03-17 11:23 GMT-04:00 Yann Sagon <[email protected]>: > > > 2015-03-17 13:31 GMT+01:00 Felix Willenborg < > [email protected]>: > >> >> Hi there, >> >> first of all, i'm kinda new to slurm, so hopefully i may have missed >> something very basic here. >> >> >> slurmctld.log >> ------------------------------------------------------------ >> ------------------------------------------------------------ >> ------------------------------------ >> [2015-03-16T15:39:54.813] debug: sched: slurmctld starting >> [2015-03-16T15:39:54.817] error: Configured MailProg is invalid >> [2015-03-16T15:39:54.817] debug3: Trying to load plugin >> /usr/lib/slurm/accounting_storage_filetxt.so >> [2015-03-16T15:39:54.817] debug2: slurmdb_init() called >> [2015-03-16T15:39:54.817] Accounting storage FileTxt plugin loaded >> [2015-03-16T15:39:54.818] debug3: Success. >> [2015-03-16T15:39:54.818] debug3: not enforcing associations and no list >> was given so we are giving a blank list >> [2015-03-16T15:39:54.818] debug3: Version in assoc_mgr_state header is 1 >> [2015-03-16T15:39:54.818] slurmctld version 2.6.5 started on cluster >> cluster >> > > As you are new to slurm, I would as first step suggest to try with latest > slurm version. (14.11.4) > > >
