27 March 2020

DAS-4/VU and DAS-4/Delft have been decommisioned. The role of for password updates has been taken over by For access to old data on DAS-4/VU or DAS-4/Delft, mail

5 April 2018

OpenNebula on DAS-4/VU and DAS-4/Delft has been updated to version 5.4.6.

4 April 2018

The DAS-4 clusters have been updated to CentOS 7, and the Nvidia CUDA development kit has been updated to version 8.0 (version 9.1 is also available for recent GPUs). This update makes DAS-4 software-compatible with DAS-5.

6 Jul 2015

DAS-5 is now fully operational! To make room for DAS-5, DAS-4/UvA and DAS-4/ASTRON have been decomissioned, only their headnodes remain available.

DAS-4 Usage Policy

Each DAS-4 cluster consists of a headnode (file/compile server) and a number of compute nodes. The headnode is called fsX (X is 0, 1, 2, 3, 4 or 5 according to the cluster base); the worker nodes are named nodeX[0-9][0-9].

The DAS-4 must be used in the following way:

  • Program development (editing, compiling) is done on the headnodes, i.e., the file/compile servers.
  • Program execution MUST be done on the compute nodes, NEVER on a headnode. The headnodes are usually heavily loaded just carrying out the tasks they are intended for. User programs that run on a headnode harm all other users of that DAS-4 cluster! This rule also holds for sequential runs of parallel programs.
  • Running of jobs on the worker nodes MUST be done via the DAS-4 cluster scheduling system Grid Engine, which offers sufficient abstraction and flexibility for nearly all needs. A full documentation set is available.
  • The user interface of the original DAS scheduler prun has also been ported to the DAS-4 scheduler. For many users this will be the most convenient way to start jobs on one of the clusters.
  • The default run time for jobs scheduled on DAS-4 is 15 minutes, which is also the maximum during working hours, from 08:00 to 20:00. We do not want people to monopolize the clusters for a longer time, since that makes interactively running short jobs on a large number of nodes practically impossible. Also, to get a reasonable spread of the load on DAS-4, preferably use the cluster at your own site, unless it is overloaded and another one happens to be free.
  • DAS-4 is specifically NOT a cluster for doing production work. It is meant for people doing experimental research on parallel and distributed programming. Only during the night and in the weekend, when DAS-4 is regularly idle, it is allowed to run long jobs. In all other cases, you will first have to ask permission in advance from to make sure you are not causing too much trouble for other users.

NOTE: Users who do not obey these usage rules, risk blocking of their account!

See also: DAS-4 User Accounts and DAS-4 Job Execution.