LSDF Online Storage: HPC: Difference between revisions

From Lsdf
Jump to navigationJump to search
No edit summary
No edit summary
Line 94: Line 94:
On the compute nodes, the LSDF usage is indicated to the batch system via "'''#SBATCH --constraint=LSDF'''".
On the compute nodes, the LSDF usage is indicated to the batch system via "'''#SBATCH --constraint=LSDF'''".
* [https://wiki.scc.kit.edu/hpc/index.php/ForHLR_-_SLURM_Batch_Jobs#LSDF_Online_Storage Slurm HPC Workload Manager]
* [https://wiki.scc.kit.edu/hpc/index.php/ForHLR_-_SLURM_Batch_Jobs#LSDF_Online_Storage Slurm HPC Workload Manager]
* [https://wiki.bwhpc.de/e/BwUniCluster_2.0_Slurm_common_Features#LSDF_Online_Storage bwUniCluster]

* [https://wiki.scc.kit.edu/hpc/index.php?title=ForHLR_-_SLURM_Batch_Jobs#LSDF_Online_Storage ForHLR]
<hr>
<hr>
<br>
<br>

Revision as of 12:13, 15 December 2020

LSDF_Online_Storage for HPC Cluster

The LSDF storage is permanently mounted on the login nodes and the data movers.

Both for interactive and for batch use, the environment variables $LSDF, $LSDFHOME and $LSDFPROJECTS are set.


Mount on the login nodes

Limits:
Cpu time limit: 3600s
Virtual memory limit: 8GB

Batch Jobs

On the compute nodes, the LSDF usage is indicated to the batch system via "#SBATCH --constraint=LSDF".