Hardware requirements

Before you install IBM Cloud Pak® for Data, review the hardware requirements for the control plane, the shared cluster components, and the services that you plan to install.

Cloud Pak for Data platform hardware requirements

You must install Cloud Pak for Data on a Red Hat® OpenShift® Container Platform cluster. For information about the supported versions of Red Hat OpenShift Container Platform, see Software requirements.

It is strongly recommended that you deploy Cloud Pak for Data on a highly available cluster.

The following requirements are the minimum recommendations for a small, stable deployment of Cloud Pak for Data. Use the minimum recommended configuration as a starting point for your cluster configuration. If you use fewer resources, you are likely to encounter stability problems.

The following configuration has been tested and validated by IBM®. However, Red Hat OpenShift Container Platform supports other configurations. If the configuration in the following table does not work in your environment, you can adapt the configuration based on the guidance in the Red Hat OpenShift documentation. (Links to the relevant Red Hat OpenShift documentation are available in Software requirements.) In general, Cloud Pak for Data is primarily concerned with the resources that are available on your worker nodes.

Important:
Work with your IBM Sales representative to size your cluster. The size of your cluster depends on:
  • The shared components that you need to install
  • The services that you plan to install

    The sizing requirements for services are available in Service hardware requirements. If you install only a few services with small vCPU and memory requirements, you might not need additional resources. However, if you plan to install multiple services or services with large footprints, add the appropriate amount of vCPU and memory to the minimum recommendations below.

  • The types of workloads that you plan to run

    For example, if you plan to run complex analytics workloads in addition to other resource-intensive workloads, such as ETL jobs, you can expect reduced concurrency levels if you don't add additional computing power to your cluster.

    Because workloads vary based on a number of factors, use measurements from running real workloads with realistic data to size your cluster.

For additional information on sizing your cluster, download the component scaling guidance PDF.

Node role Hardware Number of servers Minimum available vCPU Minimum memory Minimum storage
Master + infra
  • x86-64
  • s390x (z14 or later)
  • ppc64le
 3 master (for high availability) and 3 infrastructure on the same 3 nodes 8 vCPU per node 32 GB RAM per node No additional storage is needed. For sizing guidance, refer to the Red Hat OpenShift Container Platform documentation.
Worker/compute
  • x86-64
  • s390x (z14 or later)
  • ppc64le
 3+ worker/compute nodes 16 vCPU per node
  • 64 GB RAM per node (minimum)
  • 128 GB RAM per node (recommended)
 300 GB of storage space per node for storing container images locally. See Cloud Pak for Data platform storage requirements for details.
Load balancer
  • x86-64
  • s390x (z14 or later)
  • ppc64le
 2 load balancer nodes
  • x86-64: 4 vCPU per node
  • ppc64le: 8 vCPU per node
  • s390x: 4 vCPU per node
 4 GB RAM per node

Add another 4 GB of RAM for access restrictions and security control.

 Add 100 GB of root storage for access restrictions and security control.
Restriction:
Power® hardware
Power is supported on the following versions of Red Hat OpenShift Container Platform:
  • Version 4.8

    4.6.0 - 4.6.2 only

  • Version 4.10

    4.6.x

The Cloud Pak for Data control plane supports POWER9™ and Power10, but does not take advantage of Power10 optimizations.

Not all services support Power. For details, see Service hardware requirements.

On Power hardware the maximum supported configuration for each worker node is:

  • 160 vCPU
  • 512 GB RAM
s390x hardware
s390x is supported on the following versions of Red Hat OpenShift Container Platform:
  • Version 4.8

    4.6.0 - 4.6.2 only

  • Version 4.10

    4.6.x

  • Version 4.12

    4.6.4 or later

Not all services support s390x. For details, see Service hardware requirements.

Load balancer
A load balancer is required when using three master nodes. The load balancer distributes the traffic load of the master and proxy nodes, securely isolates the master and compute node IP addresses, and facilitates external communication, including accessing the management console and API or making other requests to the master and proxy nodes.

Cluster node settings

The time on all of the nodes must be synchronized within 500 ms.

Some services require additional node settings to run correctly. For information about the node settings and the services that require them, see Changing required node settings. You must change the node settings before you install Cloud Pak for Data.

Disk requirements

To prepare your storage disks, ensure that you have good I/O performance, and prepare the disks for encryption.

I/O performance
When I/O performance is not sufficient, services can experience poor performance or cluster instability, such as functional failures with timeouts. This is especially true when you are running a heavy workload.

The I/O performance requirements for Cloud Pak for Data are based on extensive testing in various cloud environments. The tests validate the I/O performance in these environments. The requirements are based on the performance of writing data to representative storage classes using the following block size and thread count combinations:

  • To evaluate disk latency, the I/O tests use a small block (4 KB) with 8 threads
  • To evaluate disk throughput, the I/O tests us a large block (1 GB) with 2 threads

To evaluate the storage performance on the cluster where you plan to install Cloud Pak for Data, run the Cloud Pak for Data storage performance validation playbook. Ensure that the results are comparable to the following recommended minimum values:

Disk latency (4 KB block with 8 threads)
For disk latency tests, 18 MB/s has been found to provide sufficient performance.
Disk throughput (1 GB block with 2 thread)
For disk throughput tests, 226 MB/s has been found to provide sufficient performance.

To ensure sufficient performance, both requirements should be satisfied.

Some storage types might have more stringent I/O requirements. For details, see Storage considerations.

Important: It is recommended that you run the validation playbook several times to account for variations in workloads, access patterns, and network traffic.

In addition, if your storage volumes are remote, network speed can be a key factor in your I/O performance. For good I/O performance, ensure that you have sufficient network speed, as described in Storage considerations.

Encryption with Linux® Unified Key Setup
To ensure that your data within Cloud Pak for Data is stored securely, you can encrypt your disks. If you use Linux Unified Key Setup-on-disk-format (LUKS), you must enable LUKS when you install Red Hat OpenShift Container Platform. For more information, see Encrypting disks during installation in the Red Hat OpenShift Container Platform documentation.

Shared cluster component requirements

Shared cluster components provide underlying functionality for the IBM Cloud Pak for Data control plane and services. For details, see Required components.

Use the following information to determine whether you have the minimum required resources to install each component on your Cloud Pak for Data cluster.

x86-64 hardware
Service vCPU Memory Storage Notes
IBM Cloud Pak foundational services See the IBM Cloud Pak foundational services documentation. See the IBM Cloud Pak foundational services documentation. See the IBM Cloud Pak foundational services documentation. Required.

This software is installed once on the cluster. For details, see Required components.
Scheduling service
Operator pods:
1 vCPU

Catalog pods:
0.01 vCPU

Operand:
0.6 vCPU
Operator pods:
0.54 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
1.9 GB RAM
Persistent storage:
Not applicable

Ephemeral storage:
0.605 GB

Image storage:
Approximately 1690 MB
 Required in some situations, but generally recommended.

This software is installed once on the cluster. For details, see Required components.

Minimum resources for an installation with a single replica per service.
Common core services
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
11 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
18.3 GB RAM
Persistent storage:
500 GB

Ephemeral storage:
100 GB

Image storage:
Approximately 25710 MB
 Required in some situations.

Depending on the services that you install, this software is installed once in each Red Hat OpenShift project where Cloud Pak for Data is installed. For details, see Service software requirements.
Power (ppc64le) hardware

The following services are supported on Power9 and Power10. However, the services do not take advantage of Power10 optimizations.

Service vCPU Memory Storage Notes
IBM Cloud Pak foundational services See the IBM Cloud Pak foundational services documentation. See the IBM Cloud Pak foundational services documentation. See the IBM Cloud Pak foundational services documentation. Required.

This software is installed once on the cluster. For details, see Required components.
Scheduling service
Operator pods:
1 vCPU

Catalog pods:
0.01 vCPU

Operand:
0.6 vCPU
Operator pods:
0.54 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
1.9 GB RAM
Persistent storage:
Not applicable

Ephemeral storage:
0.605 GB

Image storage:
Approximately 1690 MB
 Required in some situations, but generally recommended.

This software is installed once on the cluster. For details, see Required components.

Minimum resources for an installation with a single replica per service.
Z (s390x) hardware
Service vCPU Memory Storage Notes
IBM Cloud Pak foundational services See the IBM Cloud Pak foundational services documentation. See the IBM Cloud Pak foundational services documentation. See the IBM Cloud Pak foundational services documentation. Required.

This software is installed once on the cluster. For details, see Required components.
Common core services
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
11 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
18.3 GB RAM
Persistent storage:
500 GB

Ephemeral storage:
100 GB

Image storage:
Approximately 25710 MB
 Required in some situations.

Depending on the services that you install, this software is installed once in each Red Hat OpenShift project where Cloud Pak for Data is installed. For details, see Service software requirements.

Service hardware requirements

Use the following information to determine whether you have the minimum required resources to install each service that you want to use.

x86-64 hardware
Service vCPU Memory Storage Notes
AI Factsheets
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
0.3 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
0.7 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
1 GB

Image storage:
Approximately 2530 MB

Minimum resources for an installation with a single replica per service.
Anaconda Repository for IBM Cloud Pak for Data

4 vCPU

 8 GB RAM 500 GB This service cannot be installed on your Red Hat OpenShift cluster. For details, see the Anaconda installation requirements.
Analytics Engine Powered by Apache Spark
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
3 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
8 GB RAM
Persistent storage:This information is not currently available.

Ephemeral storage:
50 GB per vCPU request
(SSDs are recommended)

Image storage:
Approximately 41870 MB
 Spark jobs use emptyDir volumes for temporary storage and shuffling. If your Spark jobs use a lot of disk space for temporary storage or shuffling, make sure that you have sufficient space on the local disk where emptyDir volumes are created.
The recommended location is a partition in /var/lib. For details, see Understanding ephemeral storage in the Red Hat OpenShift documentation:

If you don't have sufficient space on the local disk, Spark jobs might run slowly and some of the executors might evict jobs. A minimum of 50 GB of temporary storage for each vCPU request is recommended.

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Cognos® Analytics
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
9.3 vCPU
Operator pods:
1 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
40 GB RAM
Persistent storage:
  • 500 MB for the service
  • 2 GB per instance (smallest instance)
Ephemeral storage:
  • 1 GB for the service
  • 23.6 GB per instance (smallest instance)

Image storage:
Approximately 36180 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

When you provision the Cognos Analytics service, you specify the size of the instance.

The information here is for the smallest instance. For other sizes, see Provisioning the Cognos Analytics service.
Cognos Dashboards
Operator pods:
0.1 vCPU

Catalog pods:
0.5 vCPU

Operand:
3.125 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.256 GB RAM

Operand:
6.8 GB RAM
Persistent storage:
30 GB

Ephemeral storage:
2.55 GB

Image storage:
Approximately 4250 MB

Minimum resources for an installation with a single replica per service.
Data Privacy
Operator pods:
0.1 vCPU

Catalog pods:
0..01 vCPU

Operand:
1 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
3.77 GB RAM
Persistent storage:
Uses the persistent storage provisioned by Watson™ Knowledge
Catalog.

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 4700 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Data Refinery
Operator pods:
0.1 vCPU

Catalog pods:
0.5 vCPU

Operand:
1 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
1 GB RAM

Operand:
4 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
2 GB

Image storage:
Approximately 4670 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

This service is installed when you install Watson Knowledge Catalog or Watson Studio
Data Replication
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
13 vCPU
Operator pods:
0.512 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
14 GB RAM
Persistent storage:
10 GB - 512 GB

Ephemeral storage:
22 GB

Image storage:
Approximately 5110 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
DataStage®
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
8 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
31 GB RAM
Persistent storage:
300 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 16700 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

Local storage in /var/lib/containers
Adjust the amount of local storage per node based on the volume of data you are analyzing. Local storage should be approximately 2 times larger than the amount of data you expect the system to process concurrently.
Db2®
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
1.5 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
5.5 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
2.2 - 5.4 GB

Image storage:
Approximately 3050 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

A dedicated node is recommended for production deployments of Db2. For details, see Setting up dedicated nodes.
Db2 Big SQL
Operator pods:
0.2 vCPU

Catalog pods:
0.1 vCPU

Operand:
10.2 vCPU
Operator pods:
0.3 GB RAM

Catalog pods:
0.2 GB RAM

Operand:
66.7 GB RAM
Persistent storage:
470 GB total (assuming defaults)
  • Head pod:

    200 GB (default)

  • One worker pod:

    200 GB (default)

  • Scheduling pod:

    10 GB

  • Log storage:

    30 GB per pod


Ephemeral storage:
1.4 - 12.2 GB

Image storage:
Approximately 2750 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

When you provision the service, you can specify:

  • The resources (vCPU and RAM) for the head and worker pods
  • The number of worker pods
  • The size of the persistent volume for the head pod and worker pods
Db2 Data Gate
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
2 vCPU per instance
Operator pods:
0.1 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
13 GB RAM per instance
Persistent storage:
50 GB per instance

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 12330 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Db2 Data Management Console
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
5 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
19.31 GB RAM
Persistent storage:
10 GB

Ephemeral storage:
7.5 GB

Image storage:
Approximately 6140 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

For information on sizing the provisioned instance, see Provisioning the service.
Db2 Warehouse
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
SMP: 7 vCPU
MPP: 39 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
SMP: 98 GB RAM
MPP: 610 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
2.2 - 10.8 GB

Image storage:
Approximately 3050 MB

Minimum resources for an installation with a single replica per service.

Use dedicated nodes for:

  • Production SMP deployments (recommended)
  • MPP deployments (required)

For detail, see Setting up dedicated nodes.

Development deployment
  • 1 node for SMP
  • 2 nodes for MPP
Production deployment
  • 1 node for SMP
  • 2-999 nodes for MPP
Recommended configuration

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Decision Optimization
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
0.9 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
1.5 GB RAM
Persistent storage:
12 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 4300 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
EDB Postgres
Operator pods:
IBM: 0.1 vCPU
Third-party: 0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
User-defined
Operator pods:
IBM: 0.256 GB RAM
Third-party: 0.2 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
User-defined
Persistent storage:
100 GB

Ephemeral storage:This information is not currently available.

Image storage:This information is not currently available.

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Execution Engine for Apache Hadoop
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
For each deployment:
0.5 vCPU +  (0.5 vCPU * number of Hadoop registrations) + (0.6 vCPU * number of Hadoop jobs run)
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
For each deployment:
0.5 GB + (0.5 GB * number of Hadoop registrations) + (0.5 GB * number of Hadoop jobs run)
Persistent storage:
2 GB per image pushed

Ephemeral storage:
218 - 436 MB

Image storage:
Approximately 3060 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

Each image that is pushed to the remote Hadoop cluster requires disk space where image tgz file can be stored.

Execution Engine for Apache Hadoop requires an Execution Engine for Hadoop RPM installation on the Apache Hadoop or IBM Spectrum® Conductor cluster. For details, see:
IBM Match 360 with Watson
Operator pods:
2 vCPU

Catalog pods:
1 vCPU

Operand:
42 vCPU
Operator pods:
2 GB RAM

Catalog pods:
2 GB RAM

Operand:
115 GB RAM
Persistent storage:
190 GB

Ephemeral storage:
25 GB

Image storage:
Approximately 24620 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Informix®
Operator pods:
0.1 vCPU

Catalog pods:
0.1 vCPU

Operand:
2 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
2 GB RAM
Persistent storage:
20 GB

Ephemeral storage:
900 MB (default)

Image storage:
Approximately 8530 MB

Minimum resources for an installation with a single replica per service.
MongoDB
Operator pods:
IBM: 0.1 vCPU
Third-party: 0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
User-defined
Operator pods:
IBM: 0.256 GB RAM
Third-party: 0.2 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
User-defined
Persistent storage:
100 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 8720 MB

Minimum resources for an installation with a single replica per service.

Dedicated nodes are recommended. For details, see Setting up dedicated nodes.

Development deployment
3 nodes
Production deployment
3 nodes
Recommended configuration
Refer to the Ops Manager System Requirements to determine the appropriate specifications based on your expected workloads.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
OpenPages®
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:  5 vCPU
Operator pods:
2 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
14.5 GB RAM
Persistent storage:
252 GB

Ephemeral storage:
10.9 GB

Image storage:
Approximately 4730 MB
 When you provision the OpenPages service, you specify the size of the instance and the storage class to use. You also specify whether to use the database that is provided with the OpenPages service or a database that is on an external server.

These values represent the minimum resources for OpenPages with a Db2 database on Cloud Pak for Data.

Using a Db2 database on Cloud Pak for Data

OpenPages uses Db2 as a service, which is different from the Db2 service in the services catalog.

You can optionally provision the Db2 database on dedicated nodes. For details, see Provisioning an instance of OpenPages.

Using a Db2 database outside of Cloud Pak for Data
If you use a database outside of Cloud Pak for Data, the minimum requirements for vCPUs and memory are lower.
Planning Analytics
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
10 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
22 GB RAM
Persistent storage:
20 GB

Ephemeral storage: 50 GB (maximum)
Image storage:
Approximately 21360 MB

Work with IBM Sales to get a more accurate sizing based on your expected workload.

Select the size of your instance when you provision Planning Analytics. For details, see Provisioning the Planning Analytics service.
Product Master
Operator pods:
0.2 vCPU

Catalog pods:
0.2 vCPU

Operand:
16 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
44 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
20 GB

Image storage:
Approximately 19180 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
RStudio® Server Runtimes
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
1 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
8.8 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 27220 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
SPSS® Modeler
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
0.25 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
1 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
3 GB (maximum)

Image storage:
Approximately 9790 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Voice Gateway
Operator pods:
0.2 vCPU

Catalog pods:
0.01 vCPU

Operand:
2 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
8 GB RAM
Persistent storage:
Not applicable

Ephemeral storage:
4 GB

Image storage:
4 GB

Minimum resources for a system that can provide voice-only support for up to 11 concurrent calls.

Dedicated nodes are recommended for production environments.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Watson Assistant
Operator pods:
0.25 vCPU

Catalog pods:
0.01 vCPU

Operand:
20 vCPU
Operator pods:
6 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
150 GB RAM
Persistent storage:
425 GB

Ephemeral storage:
60 - 200 GB

Image storage:
Approximately 42500 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

Your hardware must meet the following additional requirements:
  • CPUs must have a clock speed of 2.4 GHz or higher
  • CPUs must support Linux SSE 4.2
  • CPUs must support the AVX2 instruction set
Watson Discovery
Operator pods:
0.1 vCPU

Catalog pods:
0.05 vCPU

Operand:
15 vCPU
Operator pods:
0.05 GB RAM

Catalog pods:
0.01 GB RAM

Operand:
94 GB RAM
Persistent storage:
538 Gi (Block) + 205 Gi (File) = 743 Gi

Ephemeral storage:
194 GB
Image storage:
Approximately 96350 MB
 Starter deployments are sized for demonstration purposes only. Production deployments are sized for robust use. Be sure to choose the right size for your needs. You cannot change the deployment type after you install the service. If you need to change it later, you must reinstall. These values represent the minimum requirements for a Starter deployment.

CPUs must support the AVX2 instruction set.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

Watson Discovery supports only single-zone OpenShift deployments. You cannot install Watson Discovery on a multi-zone deployment.
Watson Knowledge Catalog
Base
Operator pods:
0.75 vCPU

Catalog pods:
0.05 vCPU

Operand:
32 vCPU
Data quality
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
11 vCPU
Semantic search and lineage
Operator pods:
1.5 vCPU

Catalog pods:
0.05 vCPU

Operand:
5 vCPU
Advanced metadata import
Operator pods:
0.3 vCPU

Catalog pods:
0.05 vCPU

Operand:
6 vCPU
Base
Operator pods:
4 GB RAM

Catalog pods:
0.2 GB RAM

Operand:
128 GB RAM
Data Quality
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
44 GB RAM
Semantic search and lineage
Operator pods:
0.7 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
20 GB RAM
Advanced metadata import
Operator pods:
0.6 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
24 GB RAM
Persistent storage:
900 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 29591 MB with all optional components

The minimum required resources depend on the features that you install.

If Data Refinery is not installed, add the vCPU and memory required for Data Refinery to the information listed for Watson Knowledge Catalog.

Local storage in /var/lib/containers
Adjust the amount of local storage per node based on the volume of data you are analyzing. Local storage should be approximately 2 times larger than the amount of data you expect the system to process concurrently.
Persistent storage
The raw size of shared storage depends on the storage class you use. For example, if you use portworx-shared-gp3, which has 3 replicas, multiply the storage by the number of replicas.
Watson Knowledge Studio
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
7 vCPU
Operator pods:
0.1 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
31 GB RAM
Persistent storage:
360 GB

Ephemeral storage:
Not applicable

Image storage:
Approximately 23320 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Watson Machine Learning
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
6 vCPU
Operator pods:
0.5 GB RAM

Catalog pods:
0.5 GB RAM

Operand:
27 GB RAM
Persistent storage:
150 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 151300 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

AVX2 is recommended but not required for AutoAI experiments.
Watson Machine Learning Accelerator
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
6.5 vCPU
Operator pods:
1GB RAM

Catalog pods:
0.05 GB RAM

Operand:
18 GB RAM
Persistent storage:
120 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 29530 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

GPU support is limited to NVIDIA V100, A100 and T4 GPUs.
Watson OpenScale
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
14 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
72 GB RAM
Persistent storage:
100 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 22090 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Watson Pipelines
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
1.4 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
2.625 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
1.3 GB

Image storage:
Approximately 6390 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Watson Query
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
12 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
38 GB RAM
Persistent storage:
280 GB total (assuming defaults)
  • Head pod:

    50 GB (default)

  • One worker pod:

    50 GB (default)

  • Caching storage:

    100 GB (default)

  • Caching metadata:

    10 GB

  • Scheduling pod:

    10 GB

  • Log storage:

    30 GB per pod


Ephemeral storage:
2.428 - 13GB

Image storage:
Approximately 2970 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

When you provision the service, you can specify:

  • The size of the persistent volume for the head pod
  • The size of the persistent volume for the cache
  • The number of worker pods
  • The size of the persistent volume for the worker pods
Watson Speech services
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:

Speech to Text: 11 vCPU

Text to Speech: 8 vCPU
Operator pods:
0.5 GB RAM

Catalog pods:
0.05 GB RAM

Operand:

Speech to Text: 37 GB RAM

Text to Speech: 17 GB RAM
Persistent storage:
900 GB

Ephemeral storage:
34 GB

Image storage:
Approximately 68020 MB

Minimum resources for an instance with a single replica per service using the default models and voices (US-English). The amount of vCPU, memory, and ephemeral storage that is required increases when you install additional models.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

CPUs must support the AVX2 instruction set.
Watson Studio
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
2 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
8.8 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services. Additional storage is required if you enable Visual Studio Code support.

Ephemeral storage:
5 - 10 GB

Image storage:
Approximately 5340 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

If Data Refinery is not installed, add the vCPU and memory required for Data Refinery to the information listed for Watson Studio.

If you enable the Visual Studio Code extension for Watson Studio, you must allocate a minimum of 500-600 MB of storage per user for installed extensions. For details, see To enable Visual Studio Code in Post-installation tasks for the Watson Studio service.
Watson Studio Runtimes
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
Dictated by the runtimes
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
Dictated by the runtimes
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
Dictated by the runtimes.

Image storage:
Approximately 79940 MB
 Runtimes use on-demand vCPU and memory.
Watson Studio Runtimes includes the following runtimes:
  • Runtime 22.2 with Python 3.10
  • Runtime 22.2 with Python 3.10 for GPU
  • Runtime 22.1 with Python 3.9
  • Runtime 22.1 with Python 3.9 for GPU
  • Runtime 22.1 with R 3.6
  • Runtime 22.2 with R 4.2

The following runtimes have additional hardware requirements:

Runtime 22.1 with Python 3.9 for GPU
At least 1 GPU core is required to use this runtime.
Runtime 22.2 with Python 3.10 for GPU
At least 1 GPU core is required to use this runtime.
Power (ppc64le) hardware

The following services support Power9 and Power10. However, the services do not take advantage of Power10 optimizations.

Service vCPU Memory Storage Notes
Db2 Data Management Console
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
5 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
19.31 GB RAM
Persistent storage:
10 GB

Ephemeral storage:
7.5 GB

Image storage:
Approximately 6140 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

For information on sizing the provisioned instance, see Provisioning the service.

The following services support Power9 and Power10.

It is recommended that you configure Power9 logical partitions to run Power9 compatibility mode, and that you configure Power10 logical partitions to run Power10 compatibility mode.

Service vCPU Memory Storage Notes
Db2
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
1.5 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
5.5 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
2.2 - 5.4 GB

Image storage:
Approximately 3050 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

A dedicated node is recommended for production deployments of Db2. For details, see Setting up dedicated nodes.
Db2 Warehouse
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
SMP: 7 vCPU
MPP: 39 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
SMP: 98 GB RAM
MPP: 610 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
2.2 - 10.8 GB

Image storage:
Approximately 3050 MB

Minimum resources for an installation with a single replica per service.

Use dedicated nodes for:

  • Production SMP deployments (recommended)
  • MPP deployments (required)

For detail, see Setting up dedicated nodes.

Development deployment
  • 1 node for SMP
  • 2 nodes for MPP
Production deployment
  • 1 node for SMP
  • 2-999 nodes for MPP
Recommended configuration

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Z (s390x) hardware
Restriction: The following services have a limited set of features on s390x hardware:
  • Watson Machine Learning
  • Watson Studio
  • Watson Studio Runtimes

For a list of the features that are available on s390x hardware, see Capabilities on IBM Z®

Service vCPU Memory Storage Notes
Analytics Engine Powered by Apache Spark
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
3 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
8 GB RAM
Persistent storage:This information is not currently available.

Ephemeral storage:
50 GB per vCPU request
(SSDs are recommended)

Image storage:
Approximately 41870 MB
 Spark jobs use emptyDir volumes for temporary storage and shuffling. If your Spark jobs use a lot of disk space for temporary storage or shuffling, make sure that you have sufficient space on the local disk where emptyDir volumes are created.
The recommended location is a partition in /var/lib. For details, see Understanding ephemeral storage in the Red Hat OpenShift documentation:

If you don't have sufficient space on the local disk, Spark jobs might run slowly and some of the executors might evict jobs. A minimum of 50 GB of temporary storage for each vCPU request is recommended.

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Data Refinery
Operator pods:
0.1 vCPU

Catalog pods:
0.5 vCPU

Operand:
1 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
1 GB RAM

Operand:
4 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
2 GB

Image storage:
Approximately 4670 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

This service is installed when you install Watson Knowledge Catalog or Watson Studio
Db2
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
1.5 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
5.5 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
2.2 - 5.4 GB

Image storage:
Approximately 3050 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

A dedicated node is recommended for production deployments of Db2. For details, see Setting up dedicated nodes.
Db2 Data Gate
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
2 vCPU per instance
Operator pods:
0.1 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
13 GB RAM per instance
Persistent storage:
50 GB per instance

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 12330 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Db2 Data Management Console
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
5 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
19.31 GB RAM
Persistent storage:
10 GB

Ephemeral storage:
7.5 GB

Image storage:
Approximately 6140 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

For information on sizing the provisioned instance, see Provisioning the service.
Db2 Warehouse
Operator pods:
0.5 vCPU

Catalog pods:
0.01 vCPU

Operand:
SMP: 7 vCPU
MPP: 39 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
SMP: 98 GB RAM
MPP: 610 GB RAM
Persistent storage:
200 GB

Ephemeral storage:
2.2 - 10.8 GB

Image storage:
Approximately 3050 MB

Minimum resources for an installation with a single replica per service.

Use dedicated nodes for:

  • Production SMP deployments (recommended)
  • MPP deployments (required)

For detail, see Setting up dedicated nodes.

Development deployment
  • 1 node for SMP
  • 2 nodes for MPP
Production deployment
  • 1 node for SMP
  • 2-999 nodes for MPP
Recommended configuration

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Execution Engine for Apache Hadoop
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
For each deployment:
0.5 vCPU +  (0.5 vCPU * number of Hadoop registrations) + (0.6 vCPU * number of Hadoop jobs run)
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
For each deployment:
0.5 GB + (0.5 GB * number of Hadoop registrations) + (0.5 GB * number of Hadoop jobs run)
Persistent storage:
2 GB per image pushed

Ephemeral storage:
218 - 436 MB

Image storage:
Approximately 3060 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

Each image that is pushed to the remote Hadoop cluster requires disk space where image tgz file can be stored.

Execution Engine for Apache Hadoop requires an Execution Engine for Hadoop RPM installation on the Apache Hadoop or IBM Spectrum Conductor cluster. For details, see:
Watson Machine Learning
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
6 vCPU
Operator pods:
0.5 GB RAM

Catalog pods:
0.5 GB RAM

Operand:
27 GB RAM
Persistent storage:
150 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 151300 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

AVX2 is recommended but not required for AutoAI experiments.
Watson OpenScale
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
14 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
72 GB RAM
Persistent storage:
100 GB

Ephemeral storage:This information is not currently available.

Image storage:
Approximately 22090 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.
Watson Studio
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
2 vCPU
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
8.8 GB RAM
Persistent storage:
Uses the persistent storage provisioned by the common core services. Additional storage is required if you enable Visual Studio Code support.

Ephemeral storage:
5 - 10 GB

Image storage:
Approximately 5340 MB

Minimum resources for an installation with a single replica per service.

Work with IBM Sales to get a more accurate sizing based on your expected workload.

If Data Refinery is not installed, add the vCPU and memory required for Data Refinery to the information listed for Watson Studio.

If you enable the Visual Studio Code extension for Watson Studio, you must allocate a minimum of 500-600 MB of storage per user for installed extensions. For details, see To enable Visual Studio Code in Post-installation tasks for the Watson Studio service.
Watson Studio Runtimes
Operator pods:
0.1 vCPU

Catalog pods:
0.01 vCPU

Operand:
Dictated by the runtimes
Operator pods:
0.256 GB RAM

Catalog pods:
0.05 GB RAM

Operand:
Dictated by the runtimes
Persistent storage:
Uses the persistent storage provisioned by the common core services.

Ephemeral storage:
Dictated by the runtimes.

Image storage:
Approximately 79940 MB
 Runtimes use on-demand vCPU and memory.
Watson Studio Runtimes includes the following runtimes:
  • Runtime 22.1 with Python 3.9
  • 4.6.3 or later Runtime 22.2 with Python 3.10