[slurm-users] How do you make --export=NONE the default behavior for our cluster?

2022-06-03 Thread Ransom, Geoffrey M.
Hello We recently added new architectures to our compute and submit nodes and a PATH gets generated based on the type of machine our users log into. Unfortunately, this PATH is architecture dependent but it is getting copied with slurm jobs to the compute nodes which could be a different ar

Re: [slurm-users] slurmctld loose connection with slurmd for no reason after upgrading from 20.11.8 to 21.08.8-2

2022-06-03 Thread Audet, Martin
Sorry everybody, I made a few mistakes concerning Slurm versions in the summary of what's working and not working. Here is the text: 20.11.8 (of course without CommunicationParameters=block_null_hash): working since long 21.08.8-2 with CommunicationParameters=block_null_hash: intermittent proble

Re: [slurm-users] slurmctld loose connection with slurmd for no reason after upgrading from 20.11.8 to 21.08.8-2

2022-06-03 Thread Audet, Martin
Hello Slurm user community, I would like to share my experience concerning the updates I did following the security fixes published last month (May 4th) as it may help other users (and hopefully attract attention of responsible developers). As I explained in my previous message, we were running

Re: [slurm-users] what is the possible reason for secondary slurmctld node not allocate job after takeover?

2022-06-03 Thread Brian Andrus
Offhand, I would suggest double check munge and versions of slurmd/slurmctld. Brian Andrus On 6/3/2022 3:17 AM, taleinterve...@sjtu.edu.cn wrote: Hi, all: Our cluster set up 2 slurm control node and scontrol show config as below: > scontrol show config … SlurmctldHost[0] = slurm1 Slurmct

[slurm-users] what is the possible reason for secondary slurmctld node not allocate job after takeover?

2022-06-03 Thread taleintervenor
Hi, all: Our cluster set up 2 slurm control node and scontrol show config as below: > scontrol show config . SlurmctldHost[0]= slurm1 SlurmctldHost[1]= slurm2 StateSaveLocation = /etc/slurm/state . Of course we have make sure both node has the some slurm conf and mo

Re: [slurm-users] New slurm configuration - multiple jobs per host

2022-06-03 Thread Jake Jellinek
Thanks Lyn – that was exactly the problem. Jake From: slurm-users On Behalf Of Lyn Gerner Sent: 03 June 2022 01:51 To: Slurm User Community List Subject: Re: [slurm-users] New slurm configuration - multiple jobs per host Jake, my hunch is that your jobs are getting hung up on mem allocation,