RACC nodes and partitions (queues)
Service node VMs
cluster-head: batch scheduler (Slurm), cluster head
racc-login: login node load balancing and gate keeping (Gridengine)
racc-cron: user cronjobs
Shared login nodes for interactive work
5 login nodes: racc-login-0-[1-5]
3 blades in FX chassis (chassis shared with NX nodes)
2 servers in DSS7500 chassis + 2 x 150 TB of scratch storage
16+ decent cores, 256 GB RAM
Free partition ‘cluster’
Logical rack 0: compute-0-[0-10]
11 Dell PowerEdge C6220 (3 x 4-way chassis, one blade faulty)
2 x Xeon E5-2650L 1.80GHz
16 cores, 96 GB RAM
Logical rack 1: compute-1-[0-12]
13 1U X8 Supermicro nodes
2 x Xeon E5620 2.40GHz
8 cores, 48 GB RAM
Logical rack 2: vm-2-[0-23]
Nutanix VM nodes – not used anymore
Logical rack 3: compute-3-[0-5]
6 1U X9 Supermicro nodes
2 x Xeon E5-2620 2.00GHz
12 cores, 96 GB RAM
Logical rack 4: compute-4-[0-4]
5 1U X9 Supermicro nodes
2 x Xeon E5-2630 2.30GHz
12 cores, 96 GB RAM
Logical rack 5: compute-5-[0-6]
7 1U X8 Supermicro nodes
2 x Xeon X5690 3.47GHz
12 cores, 96+ GB RAM
Logical rack 6: compute-6-2
1 1U X9 Supermicro nodes, new node, less than 3 years old (other nodes are project partition)
96 GB, 20 cores
Logical rack 8: compute-8-[0-3]
4 4U X9 Supermicro storage servers
2 x Xeon E5-2630 2.30GHz
12 cores, 128 GB RAM
Logical rack 9: compute-9-[0-5]
6 4U X9 Supermicro storage servers
2 x Xeon E5-2695v2 2.40 GHz
24 cores, 128 GB RAM
Logical rack 12: compute-12-[0-5]
6 1U Dell PowerEdge R610 nodes
2 x Xeon X5675 3.0 GHz
12 cores, 96 GB RAM
Free partition ‘gpu’: gpu-0-0
Nutanix VM with 4 GPU devices (1 x Tesla M10)
Free partition ‘limited’
Time limited access to idle project nodes.
Project partition ‘project’ (legacy Met projects, shared)
Logical rack 6: compute-6-[0-1,3-5]
5 1U X9 Supermicro nodes, new nodes, less than 3 years old
16+ cores, 96+ GB, assorted CPUs
Project partition ‘CompBio’ (project exclusive)
Logical rack 7: compute-7-0
1 4U Dell PowerEdge R940xa
4 x Xeon Platinum 8268 2.90GHz + 1 Tesla V100 GPU
96 cores, 768 GB RAM
Project partition ‘polymer’ (project exclusive)
Logical rack 7: gpu-7-[1-2]
2 2U Dell PowerEdge R740
2 x Xeon Silver 4215 2.5 GHz + 3 x Tesla T4 GPU
16 cores, 128 GB RAM
(some maths-cluster GPU nodes will be added)
Planned project partition (shared)
A node will cost around £6900 + VAT, and will be supported for 5 years
1U Dell PowerEdge R6625 (or a 4-blade chassis can be considered, but is more expensive)
2 x AMD EPYC 7402 2.8 GHz
48 cores, 512 GB RAM