Hardware Infrastructure Requirements#

Standard deployment is a 5-node cluster with two or more workers.

picture of deployment architecture

Standard Deployment#

Compact deployment is a 3-node cluster.

picture of deployment architecture

Compact Deployment#

Single Node OpenShift (SNO) is also supported, although it lacks the control plane redundancy recommended for production.

Infrastructure Examples#

The following tables show two example bills of materials for standard and compact clusters for Holoscan for Media using the RTX PRO 6000 Blackwell Server Edition GPU. Depending on the application workloads to be run, the network fabric, the number of worker nodes, and the resources (CPU, RAM, GPU) per worker node may be varied. These examples are for worker nodes based on the NVIDIA-Certified Systems PCIe optimized reference configurations and related Enterprise Reference Architecture. The control plane nodes are based on Red Hat OpenShift recommended control plane node sizing.

Standard deployment, a 5-node cluster made with 2-8-5 systems:

#

Part

Type

Quantity

Recommendation

1

Jump Node

Physical server or virtual machine

1

2 cores, 4 GB RAM, 120 GB boot drive

2

Control Node

Physical server

3

8 cores, 32 GB RAM, 500 GB NVMe boot drive

3

Worker Node

Physical server

2

2x 64 cores, 1024 GB RAM, 1x 1 TB NVMe boot drive, 2x 4 TB NVMe storage (adjust for your use case)

4

Ethernet Switch

Multicast and PTP capable 200G switch

1

5

NIC

ConnectX-7 2x200G

4

Per Worker Node

6

DPU

BlueField-3 2x200G (B3220)

1

Per Worker Node (optional depending on your use case)

7

GPU

RTX PRO 6000 Blackwell Server Edition

8

Per Worker Node

8

Cables

8

Per Worker Node

Compact deployment, a 3-node cluster made with 2-4-3 systems:

#

Part

Type

Quantity

Recommendation

1

Jump Node

Physical server or virtual machine

1

2 cores, 4 GB RAM, 120 GB boot drive

2

Control-Worker Node

Physical server

3

2x 64 cores, 512 GB RAM, 1x 1 TB NVMe boot drive, 2x 4 TB NVMe storage (adjust for your use case)

3

Ethernet Switch

Multicast and PTP capable 200G switch

1

4

NIC

ConnectX-7 2x200G

2

Per Node

5

DPU

BlueField-3 2x200G (B3220)

1

Per Node (optional depending on your use case)

6

GPU

RTX PRO 6000 Blackwell Server Edition

4

Per Node

7

Cables

4

Per Node

Network Fabric Configuration#

An example switch configuration can be provided on request for NVIDIA Mellanox Onyx switches (for example, SN3700).

In the production setup manual installation the following configuration is assumed:

VLAN

Subnet

Purpose

100

10.21.10.0/24

Management

200

192.168.20.0/24

Media A (red)

201

192.168.120.0/24

Media B (blue)

300

172.20.0.0/24

PTP

PTP domain is 127.