Caliburn and ELF are both in service. Caliburn and ELF account holders can access ELF via SSH (ssh [NetID]@elf.rutgers.edu). Current system status can be checked here.
For further documentation on Caliburn and ELF, access this section of the user guide.
Recent work completed includes:
- All hosted VMs, compute nodes, and login nodes have been upgraded to CentOS 7.7 with GPFS 18.104.22.168, SLURM 18.08.8.
- The firmware for all managed and unmanaged InfiniBand switches has been upgraded.
- Node Health Check has been setup to help with monitoring of the compute nodes.
- Added DNS names such that elf.oarc.rutgers.edu and elf[1-2].oarc.rutgers.edu and elf.rutgers.edu are the names used.
- Same list of packages is now installed on each node of each type (improved consistency among the compute nodes).
- Switched from nslcd (deprecated) to System Security Services Daemon (SSSD) for authentication services.
- The Lmod module system has been upgraded to 8.1.6.
Access to Caliburn is provided through a proposal and allocation process where research proposals from anyone affiliated with a NJ-based organization can submit an allocation request here. Instructions for responding to the call for proposals can be found here: Call for Proposals: Caliburn Allocation Requests [PDF] Successful proposals are granted access to a specified number of service units (SUs, similar to core-hours) and associated storage for a 6-month allocation period. The current allocation period is June 1 through November 30, 2020. The next allocation period will be December 15 through May 14, 2021.Link to this Answer
Users are required to be on the legacy-Rutgers network or (if you’re off-campus) on Rutgers Cisco VPN in order to connect to the server. The Cisco VPN requires 2-factor authentication to be turned on. Those instructions are also provided in the documentation in: https://soc.rutgers.edu/vpn.
Data transfers via SFTP are now allowed via the following endpoint:
Account holders can access home folders and the project, staging, and scratch filesystems.
scratch /gpfs/gpfs/scratch/Link to this Answer
In mid-2019, the management and operations responsibilities for Caliburn were transferred to OARC. At the time of this transition, Caliburn was down for an extended maintenance window between allocation periods with only basic service/administrative systems running (i.e., not operating in production mode). It was found that Caliburn’s power and cooling management systems were not configured for automatically returning to service. This created a situation where recharging of the UPS system generated unabated heat in Caliburn’s data center, demonstrating that upgraded (automated) power and cooling control systems would be required for ongoing operation of the Caliburn system. That very time-consuming upgrade process is now complete and the system has been returned to service. We are in a current allocation period of June 1 through November 30, 2020. The next allocation period will be December 15, 2020 through May 14, 2021.Link to this Answer
For computational work that cannot be accommodated by Caliburn, access to OARC’s Amarel system may serve as a useful alternative. Use of the Amarel cluster is free for all Rutgers students, staff, and faculty. Proposal submission is not required for using Amarel. A brief description of how you plan to use the system is all that is requested when completing our access request form.Link to this Answer
Email firstname.lastname@example.org to reach the OARC Research and Education Facilitator (REF) team. They can generally answer questions about Caliburn’s capabilities related to your specific science needs, and they can loop in the Tech Team (systems administrators) or Business Team as needed.Link to this Answer