Go look at that system. Likely it has an old slurmd running that should be removed.

Brian Andrus


On 9/20/2025 5:12 PM, Dhumal, Dr. Nilesh via slurm-users wrote:
Thanks. It resolve the issue. Now slrumcld is commuication to all nodes. 
These nodes are not listed the slurm.conf file. 

error: unpack_header: protocol_version 8960 not supported
[2025-09-20T20:05:03.455] error: destroy_forward: no init
[2025-09-20T20:05:03.461] error: slurm_unpack_received_msg: [192.168.3.119:55650] Incompatible versions of client and server code


192.168.3.119 is not mentioned in the slrum.conf file. 


Nilesh Dhumal  

Associate Professor of Chemistry,

 http://faculty.fgcu.edu/ndhumal/

Coordinator, FGCU Computational Facility, 

https://www.fgcu.edu/cas/facultyresources/computationalfacility/
SH-430; Department of Chemistry and Physics
Florida Gulf Coast University
10501 FGCU Boulevard South
Fort Myers, FL 33965-6565
Phone: (239) 745-4394
Email: ndhumal@fgcu.edu 


From: Renfro, Michael <Renfro@tntech.edu>
Sent: Saturday, September 20, 2025 12:21 PM
To: Dhumal, Dr. Nilesh <ndhumal@fgcu.edu>; Slurm User Community List <slurm-users@lists.schedmd.com>
Subject: Re: Compute node not responding
 

   External Email: Do not click links or attachments unless you recognize the sender and know the content is safe.

Level II: Internal


slurmdbd is not a requirement to get things started [1], but you'll probably want it later.

It’s possible you’ve got host-based firewall rules on either system that are blocking communication. If you’re using firewalld, ufw, or something similar, stop their services, restart the slurmd and slurmctld services, and see if that helps.

[1] https://slurm.schedmd.com/quickstart_admin.html#dbd


Level II: Internal

From: Dhumal, Dr. Nilesh via slurm-users <slurm-users@lists.schedmd.com>
Date: Saturday, September 20, 2025 at 11:02 AM
To: Slurm User Community List <slurm-users@lists.schedmd.com>
Subject: [slurm-users] Compute node not responding

External Email Warning

This email originated from outside the university. Please use caution when opening attachments, clicking links, or responding to requests.

Hello,

Recently, we installed slum 25 on our cluster. We are not monitoring the user's account. We didn't configure the sql database on the head node. We are running slurmcld on head node and slumd on the compute node. 
We are getting the following error 
Head node: compute node not responding. 
Compute node:
2025-09-19T15:30:23.461] error: Unable to register: Unable to contact slurm controller (connect failure)

Do we need to run slumdbd on the head node?  
I checked the network connection by pinging the compute node from the head node. 
Do you have any suggestions to resolve this issue? 

Thanks 
Nilesh