Validated Patterns

About OpenShift cluster sizing for the Intel AMX accelerated Multicloud GitOps pattern

The minimum requirements for an OpenShift Container Platform cluster depend on your installation platform, for example:

To understand cluster sizing requirements for the Intel AMX accelerated Multicloud GitOps pattern with Openshift AI, consider the following components that the pattern deploys on the datacenter or the hub OpenShift cluster:

NameKindNamespaceDescription

multicloud-gitops-amx-rhoai-hub

Application

multicloud-gitops-amx-rhoai-hub

Hub GitOps management

Red Hat Advanced Cluster Management

Operator

open-cluster-management

Advance Cluster Management

Red Hat OpenShift GitOps

Operator

openshift-operators

OpenShift GitOps

Node Feature Discovery

Operator

openshift-nfd

Manages the detection and labeling of hardware features and configuration (for example Intel AMX)

Red Hat OpenShift Data Foundation

Operator

openshift-storage

Cloud Native storage solution

The Intel AMX accelerated Multicloud GitOps pattern with Openshift AI also includes the Red Hat Advanced Cluster Management (RHACM) supporting operator that is installed by OpenShift GitOps using Argo CD.

Intel AMX accelerated Multicloud GitOps pattern with Openshift AI with OpenShift clusters sizes

The datacenter hub OpenShift cluster needs to be a bit bigger than the Factory/Edge clusters because this is where the developers will be running pipelines to build and deploy the Intel AMX accelerated Multicloud GitOps pattern with Openshift AI on the cluster. The above cluster sizing is close to a minimum size for a Datacenter HUB cluster. In the next few sections we take some snapshots of the cluster utilization while the Intel AMX accelerated Multicloud GitOps pattern with Openshift AI is running. Keep in mind that resources will have to be added as more developers are working building their applications.

The recommended clusters sizes for datacenter hub and for managed datacenter are the same in this case:

Node typeNumber of nodesCPUMemoryStorage

Control Planes

3

2x 5th Generation Intel Xeon Gold 6526Y (16 cores at 2.8 GHz base with Intel AMX) or better

128 GB (8 x 16 GB DDR5 4800) or more

NVME SSD 3TB or more

Workers

3

2x 5th Generation Intel Xeon Gold 6538Y+ (32 cores at 2.2 GHz base with Intel AMX) or better

256 GB (16 x 16 GB) or 512 GB (16 x 32GB) DDR5-4800

NVME SSD 3TB or more

You might want to add resources when more developers are working on building their applications.

The pattern was tested in the on-premises environment with following hardware configuration (per cluster):

Node typeNumber of nodesCPUMemoryStorage

Control Planes + Workers

3 + 3

2x 5th Generation Intel Xeon Platinum 8568Y+ (48 cores at 2.3 GHz base with Intel AMX)

512 GB (16x32GB DDR5 5600)

4x 3.84TB U.2 NVMe PCIe Gen4