Commit Graph

9 Commits

Author SHA1 Message Date
e03fbe5c14
Increase APT retries and timeouts 2024-08-18 00:18:47 -04:00
1e95dd7b2f
Fix munge key race condition and update docs
- Add sleep to prevent munge.key race condition
- Warn about CPU override conflicts in README
- Update README with CPU config details for minimal setup
- Correct `less` command examples for prime number output
- Force update slurm/cgroups configs in the provision script
2024-08-18 00:00:08 -04:00
b1aee01586
Enhance documentation on configuration flexibility
- Describe .settings.yml usage for global override customization
- Explain nodes.rb for individual node override configuration
- Provide example files demonstrating override usage
- Include guidance for minimal resource configuration
2024-08-16 23:53:11 -04:00
f1bd37b0d8
Use Slurm job array instead of multiple jobs 2024-08-14 22:50:29 -04:00
0a37272620
Increase JOIN_TIMEOUT default to 120s 2024-08-12 23:58:25 -04:00
95c7198280
Add README and prime number finding script 2024-08-12 23:50:29 -04:00
943b64fdcf
Set up a functional cluster for basic operations
- Include cgroup.conf configuration
- Install slurm-client on compute nodes
- Move home dir to /vagrant for result sharing
- Add Makefile for streamlined setup and cleanup
- Fix idempotency issues
2024-08-11 23:23:38 -04:00
9a402948c8
Working Slurm cluster with test job execution
- Fix MUNGE key generation and distribution
- Slurm config using easy version of the config tool
- Ensure JOIN_TIMEOUT is passed to the provisioning script
- Execute hostname command as Slurm job for verification
2024-08-11 13:55:40 -04:00
f5f601af13
Create Vagrant environment with shared MUNGE key 2024-08-09 23:03:55 -04:00