On this page you will learn how to use the BeeOND temporary file system to take advantage of the local SSD storage available on compute nodes for high I/O workloads.

BeeOND Temporary Filesystem

The BeeOND (BeeGFS on Demand) temporary file system allows users to combine the internal SSDs of all allocated compute nodes into a single, parallel file system with a shared namespace. This is particularly beneficial for applications with high I/O performance requirements.

For information about the size and specifications of the internal SSDs, refer to the hardware documentation for CLAIX-2023 or CLAIX-2025.

Key Considerations

Before using BeeOND, keep the following points in mind:

• The amount of allocated storage depends on the type and number of requested nodes.
• Computing jobs that use BeeOND will become exclusive.
• Within the job, the file system path for BeeOND is accessible via the environment variable $BEEOND.
• The storage space on the filesystem is strictly temporary! All files will be automatically deleted after the computing jobs concludes.

Example Slurm Job Script

The following example demonstrates how to request BeeOND, copy input data to the temporary file system, execute the workload, and copy the results back to permanent storage.

#!/usr/bin/zsh

### Request BeeOND
#SBATCH --beeond
### Specify other Slurm commands

### Copy Files to Beeond
cp -r $WORK/yourfiles $BEEOND

### Navigate to Beeond
cd $BEEOND/yourfiles

### Perform your job
echo "hello world" > result

### Afterwards copy results back to your partition
cp -r $BEEOND/yourfiles/result $WORK/yourfiles/