High-level Infrastructure Architecture
The Ethernet network is used for cluster management:
1. Console access (iDRAC/BMC)
2. Compute nodes provisioning using xCAT
3. Grid internal communications (scheduling, remote login, naming services, etc.)
Infiniband
InfiniBand is used for storage access and MPI traffic.
Access from HaifaU LAN
All grid components, including compute nodes, are accessible from University of Haifa LAN
Storage
Three BeeGFS nodes providing nearly 115TB usable shared storage space
Servers:
Master node - R620 2 x E5-2620v2 64GB Ram 4*1TB SATA - hosting the SLURM scheduler, BeeGFS and cluster management services, monitoring services
Access node - virtual machine hosted on cluster management node, used by the grid users to access the system and submit jobs to the grid.
Storage Nodes - 4 storage servers with BeeGFS file system - 2x Dell PowerEdge R720XD 2 x E5-2620v2 64GB Ram, 12 x 4TB Storage and 1x HP DL380 2x E5- 2620v3 64GB RAM, 12 x 4TB Storage
Backup Node - RX620 2 x E5-2620v2 64GB Ram 2*300GB - dedicated storage node connected directly to the management node. Used to as backup store for a portion of user data.
| Name | Quanity | Model | CPU's № | RAM | Notes |
| Compute(bee's) | 32 | Dell PowerEdge C6220ii | 20 | 128GB | bee001-032 |
| Compute(bee's) | 30 | HP XL170r | 24 | 128GB | bee033-063 |
| Fat node(queen's) | 1 | Dell PowerEdge R820 | 32 | 760GB | queen01 |
| Fat node(queen's) | 2 | HP DL560 | 56 | 760GB | queen02-03 |
| GPU(vespa's) | 1 | HP XL190r | 28 | 256GB | vespa01, Nvidia K80 GPU |
Operating Systems
Operating system on all grid's nodes are CentOS 6 update 7.
