Chapter 4. Installing the single-model serving platform
4.1. About the single-model serving platform
For deploying large models such as large language models (LLMs), OpenShift AI includes a single-model serving platform that is based on the KServe component. To install the single-model serving platform, the following components are required:
- KServe: A Kubernetes custom resource definition (CRD) that orchestrates model serving for all types of models. KServe includes model-serving runtimes that implement the loading of given types of model servers. KServe also handles the lifecycle of the deployment object, storage access, and networking setup.
- Red Hat OpenShift Serverless: A cloud-native development model that allows for serverless deployments of models. OpenShift Serverless is based on the open source Knative project.
Red Hat OpenShift Service Mesh: A service mesh networking layer that manages traffic flows and enforces access policies. OpenShift Service Mesh is based on the open source Istio project.
NoteCurrently, only OpenShift Service Mesh v2 is supported. For more information, see Supported Configurations.
You can install the single-model serving platform manually or in an automated fashion:
- Automated installation
-
If you have not already created a
ServiceMeshControlPlane
orKNativeServing
resource on your OpenShift cluster, you can configure the Red Hat OpenShift AI Operator to install KServe and configure its dependencies. For more information, see Configuring automated installation of KServe - Manual installation
-
If you have already created a
ServiceMeshControlPlane
orKNativeServing
resource on your OpenShift cluster, you cannot configure the Red Hat OpenShift AI Operator to install KServe and configure its dependencies. In this situation, you must install KServe manually. For more information, see Manually installing KServe.
4.2. Configuring automated installation of KServe
If you have not already created a ServiceMeshControlPlane
or KNativeServing
resource on your OpenShift cluster, you can configure the Red Hat OpenShift AI Operator to install KServe and configure its dependencies.
If you have created a ServiceMeshControlPlane
or KNativeServing
resource on your cluster, the Red Hat OpenShift AI Operator cannot install KServe and configure its dependencies and the installation does not proceed. In this situation, you must follow the manual installation instructions to install KServe.
Prerequisites
- You have cluster administrator privileges for your OpenShift cluster.
- Your cluster has a node with 4 CPUs and 16 GB memory.
- You have downloaded and installed the OpenShift command-line interface (CLI). For more information, see Installing the OpenShift CLI (OpenShift Dedicated) or Installing the OpenShift CLI (Red Hat OpenShift Service on AWS).
You have installed the Red Hat OpenShift Service Mesh Operator and dependent Operators.
NoteTo enable automated installation of KServe, install only the required Operators for Red Hat OpenShift Service Mesh. Do not perform any additional configuration or create a
ServiceMeshControlPlane
resource.You have installed the Red Hat OpenShift Serverless Operator.
NoteTo enable automated installation of KServe, install only the Red Hat OpenShift Serverless Operator. Do not perform any additional configuration or create a
KNativeServing
resource.-
To add Authorino as an authorization provider so that you can enable token authorization for deployed models, you have installed the
Red Hat - Authorino
Operator. See Installing the Authorino Operator.
Procedure
- Log in to the OpenShift web console as a cluster administrator.
-
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift AI Operator. Install OpenShift Service Mesh as follows:
- Click the DSC Initialization tab.
- Click the default-dsci object.
- Click the YAML tab.
In the
spec
section, validate that the value of themanagementState
field for theserviceMesh
component is set toManaged
, as shown:spec: applicationsNamespace: redhat-ods-applications monitoring: managementState: Managed namespace: redhat-ods-monitoring serviceMesh: controlPlane: metricsCollection: Istio name: data-science-smcp namespace: istio-system managementState: Managed
NoteDo not change the
istio-system
namespace that is specified for theserviceMesh
component by default. Other namespace values are not supported.Click Save.
Based on the configuration you added to the
DSCInitialization
object, the Red Hat OpenShift AI Operator installs OpenShift Service Mesh.
(Red Hat OpenShift Service on AWS only): If your OpenShift cluster is running on Red Hat OpenShift Service on AWS (ROSA Classic), there is an additional setting required to make the service mesh control plane configuration work. To add this setting, edit the
data-science-smcp
service mesh control plane object as follows:-
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift Service Mesh Operator. - Click the Istio Service Mesh Control Plane tab.
- Click the data-science-smcp object.
- Click the YAML tab.
In the
spec.security.identity
section, add a field calledtype
, and set the value toThirdParty
, as shown.security: dataPlane: mtls: true identity: type: ThirdParty
- Click Save.
-
In the web console, click Operators
Install both KServe and OpenShift Serverless as follows:
-
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift AI Operator. - Click the Data Science Cluster tab.
- Click the default-dsc DSC object.
- Click the YAML tab.
In the
spec.components
section, configure thekserve
component as shown.spec: components: kserve: managementState: Managed serving: ingressGateway: certificate: secretName: knative-serving-cert type: OpenshiftDefaultIngress managementState: Managed name: knative-serving
Click Save.
The preceding configuration creates an ingress gateway for OpenShift Serverless to receive traffic from OpenShift Service Mesh. In this configuration, observe the following details:
-
The configuration shown uses the default ingress certificate configured for OpenShift to secure incoming traffic to your OpenShift cluster and stores the certificate in the
knative-serving-cert
secret that is specified in thesecretName
field. -
The
secretName
field can only be set at the time of installation. The default value of thesecretName
field isknative-serving-cert
. Subsequent changes to the certificate secret must be made manually. -
If you did not use the default
secretName
value during installation, create a new secret namedknative-serving-cert
in theistio-system
namespace, and then restart theistiod-datascience-smcp-<suffix>
pod. You can specify the following certificate types by updating the value of the
type
field:-
Provided
-
SelfSigned
-
OpenshiftDefaultIngress
-
To use a self-signed certificate or to provide your own, update the value of the
secretName
field to specify your secret name and change the value of thetype
field toSelfSigned
orProvided
.NoteIf you provide your own certificate, the certificate must specify the domain name used by the ingress controller of your OpenShift cluster. You can check this value by running the following command:
$ oc get ingresses.config.openshift.io cluster -o jsonpath='{.spec.domain}'
-
You must set the value of the
managementState
field toManaged
for both thekserve
andserving
components. Settingkserve.managementState
toManaged
triggers automated installation of KServe. Settingserving.managementState
toManaged
triggers automated installation of OpenShift Serverless. However, installation of OpenShift Serverless will not be triggered ifkserve.managementState
is not also set toManaged
.
-
The configuration shown uses the default ingress certificate configured for OpenShift to secure incoming traffic to your OpenShift cluster and stores the certificate in the
-
In the web console, click Operators
Verification
Verify installation of OpenShift Service Mesh as follows:
-
In the web console, click Workloads
Pods. - From the project list, select istio-system. This is the project in which OpenShift Service Mesh is installed.
Confirm that there are running pods for the service mesh control plane, ingress gateway, and egress gateway. These pods have the naming patterns shown in the following example:
NAME READY STATUS RESTARTS AGE istio-egressgateway-7c46668687-fzsqj 1/1 Running 0 22h istio-ingressgateway-77f94d8f85-fhsp9 1/1 Running 0 22h istiod-data-science-smcp-cc8cfd9b8-2rkg4 1/1 Running 0 22h
-
In the web console, click Workloads
Verify installation of OpenShift Serverless as follows:
-
In the web console, click Workloads
Pods. - From the project list, select knative-serving. This is the project in which OpenShift Serverless is installed.
Confirm that there are numerous running pods in the
knative-serving
project, including activator, autoscaler, controller, and domain mapping pods, as well as pods for the Knative Istio controller (which controls the integration of OpenShift Serverless and OpenShift Service Mesh). An example is shown.NAME READY STATUS RESTARTS AGE activator-7586f6f744-nvdlb 2/2 Running 0 22h activator-7586f6f744-sd77w 2/2 Running 0 22h autoscaler-764fdf5d45-p2v98 2/2 Running 0 22h autoscaler-764fdf5d45-x7dc6 2/2 Running 0 22h autoscaler-hpa-7c7c4cd96d-2lkzg 1/1 Running 0 22h autoscaler-hpa-7c7c4cd96d-gks9j 1/1 Running 0 22h controller-5fdfc9567c-6cj9d 1/1 Running 0 22h controller-5fdfc9567c-bf5x7 1/1 Running 0 22h domain-mapping-56ccd85968-2hjvp 1/1 Running 0 22h domain-mapping-56ccd85968-lg6mw 1/1 Running 0 22h domainmapping-webhook-769b88695c-gp2hk 1/1 Running 0 22h domainmapping-webhook-769b88695c-npn8g 1/1 Running 0 22h net-istio-controller-7dfc6f668c-jb4xk 1/1 Running 0 22h net-istio-controller-7dfc6f668c-jxs5p 1/1 Running 0 22h net-istio-webhook-66d8f75d6f-bgd5r 1/1 Running 0 22h net-istio-webhook-66d8f75d6f-hld75 1/1 Running 0 22h webhook-7d49878bc4-8xjbr 1/1 Running 0 22h webhook-7d49878bc4-s4xx4 1/1 Running 0 22h
-
In the web console, click Workloads
Verify installation of KServe as follows:
-
In the web console, click Workloads
Pods. - From the project list, select redhat-ods-applications.This is the project in which OpenShift AI components are installed, including KServe.
Confirm that the project includes a running pod for the KServe controller manager, similar to the following example:
NAME READY STATUS RESTARTS AGE kserve-controller-manager-7fbb7bccd4-t4c5g 1/1 Running 0 22h odh-model-controller-6c4759cc9b-cftmk 1/1 Running 0 129m odh-model-controller-6c4759cc9b-ngj8b 1/1 Running 0 129m odh-model-controller-6c4759cc9b-vnhq5 1/1 Running 0 129m
-
In the web console, click Workloads
4.3. Manually installing KServe
If you have already installed the Red Hat OpenShift Service Mesh Operator and created a ServiceMeshControlPlane
resource or if you have installed the Red Hat OpenShift Serverless Operator and created a KNativeServing
resource, the Red Hat OpenShift AI Operator cannot install KServe and configure its dependencies. In this situation, you must install KServe manually.
The procedures in this section show how to perform a new installation of KServe and its dependencies and are intended as a complete installation and configuration reference. If you have already installed and configured OpenShift Service Mesh or OpenShift Serverless, you might not need to follow all steps. If you are unsure about what updates to apply to your existing configuration to use KServe, contact Red Hat Support.
4.3.1. Installing KServe dependencies
Before you install KServe, you must install and configure some dependencies. Specifically, you must create Red Hat OpenShift Service Mesh and Knative Serving instances and then configure secure gateways for Knative Serving.
Currently, only OpenShift Service Mesh v2 is supported. For more information, see Supported Configurations.
4.3.2. Creating an OpenShift Service Mesh instance
The following procedure shows how to create a Red Hat OpenShift Service Mesh instance.
Prerequisites
- You have cluster administrator privileges for your OpenShift cluster.
- Your cluster has a node with 4 CPUs and 16 GB memory.
- You have downloaded and installed the OpenShift command-line interface (CLI). See Installing the OpenShift CLI (OpenShift Dedicated) or Installing the OpenShift CLI (Red Hat OpenShift Service on AWS).
- You have installed the Red Hat OpenShift Service Mesh Operator and dependent Operators.
Procedure
In a terminal window, if you are not already logged in to your OpenShift cluster as a cluster administrator, log in to the OpenShift CLI as shown in the following example:
$ oc login <openshift_cluster_url> -u <admin_username> -p <password>
Create the required namespace for Red Hat OpenShift Service Mesh.
$ oc create ns istio-system
You see the following output:
namespace/istio-system created
Define a
ServiceMeshControlPlane
object in a YAML file namedsmcp.yaml
with the following contents:apiVersion: maistra.io/v2 kind: ServiceMeshControlPlane metadata: name: minimal namespace: istio-system spec: tracing: type: None addons: grafana: enabled: false kiali: name: kiali enabled: false prometheus: enabled: false jaeger: name: jaeger security: dataPlane: mtls: true identity: type: ThirdParty techPreview: meshConfig: defaultConfig: terminationDrainDuration: 35s gateways: ingress: service: metadata: labels: knative: ingressgateway proxy: networking: trafficControl: inbound: excludedPorts: - 8444 - 8022
For more information about the values in the YAML file, see the Service Mesh control plane configuration reference.
Create the service mesh control plane.
$ oc apply -f smcp.yaml
Verification
Verify creation of the service mesh instance as follows:
In the OpenShift CLI, enter the following command:
$ oc get pods -n istio-system
The preceding command lists all running pods in the
istio-system
project. This is the project in which OpenShift Service Mesh is installed.Confirm that there are running pods for the service mesh control plane, ingress gateway, and egress gateway. These pods have the following naming patterns:
NAME READY STATUS RESTARTS AGE istio-egressgateway-7c46668687-fzsqj 1/1 Running 0 22h istio-ingressgateway-77f94d8f85-fhsp9 1/1 Running 0 22h istiod-data-science-smcp-cc8cfd9b8-2rkg4 1/1 Running 0 22h
4.3.3. Creating a Knative Serving instance
The following procedure shows how to install Knative Serving and then create an instance.
Prerequisites
- You have cluster administrator privileges for your OpenShift cluster.
- Your cluster has a node with 4 CPUs and 16 GB memory.
- You have downloaded and installed the OpenShift command-line interface (CLI). See Installing the OpenShift CLI (OpenShift Dedicated) or Installing the OpenShift CLI (Red Hat OpenShift Service on AWS).
- You have created a Red Hat OpenShift Service Mesh instance.
- You have installed the Red Hat OpenShift Serverless Operator.
Procedure
In a terminal window, if you are not already logged in to your OpenShift cluster as a cluster administrator, log in to the OpenShift CLI as shown in the following example:
$ oc login <openshift_cluster_url> -u <admin_username> -p <password>
Check whether the required project (that is, namespace) for Knative Serving already exists.
$ oc get ns knative-serving
If the project exists, you see output similar to the following example:
NAME STATUS AGE knative-serving Active 4d20h
If the
knative-serving
project doesn’t already exist, create it.$ oc create ns knative-serving
You see the following output:
namespace/knative-serving created
Define a
ServiceMeshMember
object in a YAML file calleddefault-smm.yaml
with the following contents:apiVersion: maistra.io/v1 kind: ServiceMeshMember metadata: name: default namespace: knative-serving spec: controlPlaneRef: namespace: istio-system name: minimal
Create the
ServiceMeshMember
object in theistio-system
namespace.$ oc apply -f default-smm.yaml
You see the following output:
servicemeshmember.maistra.io/default created
Define a
KnativeServing
object in a YAML file calledknativeserving-istio.yaml
with the following contents:apiVersion: operator.knative.dev/v1beta1 kind: KnativeServing metadata: name: knative-serving namespace: knative-serving annotations: serverless.openshift.io/default-enable-http2: "true" spec: workloads: - name: net-istio-controller env: - container: controller envVars: - name: ENABLE_SECRET_INFORMER_FILTERING_BY_CERT_UID value: 'true' - annotations: sidecar.istio.io/inject: "true" 1 sidecar.istio.io/rewriteAppHTTPProbers: "true" 2 name: activator - annotations: sidecar.istio.io/inject: "true" sidecar.istio.io/rewriteAppHTTPProbers: "true" name: autoscaler ingress: istio: enabled: true config: features: kubernetes.podspec-affinity: enabled kubernetes.podspec-nodeselector: enabled kubernetes.podspec-tolerations: enabled
The preceding file defines a custom resource (CR) for a
KnativeServing
object. The CR also adds the following actions to each of the activator and autoscaler pods:NoteIf you configure a custom domain for a Knative service, you can use a TLS certificate to secure the mapped service. To do this, you must create a TLS secret, and then update the
DomainMapping
CR to use the TLS secret that you have created. For more information, see Securing a mapped service using a TLS certificate in the Red Hat OpenShift Serverless documentation.Create the
KnativeServing
object in the specifiedknative-serving
namespace.$ oc apply -f knativeserving-istio.yaml
You see the following output:
knativeserving.operator.knative.dev/knative-serving created
Verification
Review the default
ServiceMeshMemberRoll
object in theistio-system
namespace.$ oc describe smmr default -n istio-system
In the description of the
ServiceMeshMemberRoll
object, locate theStatus.Members
field and confirm that it includes theknative-serving
namespace.Verify creation of the Knative Serving instance as follows:
In the OpenShift CLI, enter the following command:
$ oc get pods -n knative-serving
The preceding command lists all running pods in the
knative-serving
project. This is the project in which you created the Knative Serving instance.Confirm that there are numerous running pods in the
knative-serving
project, including activator, autoscaler, controller, and domain mapping pods, as well as pods for the Knative Istio controller, which controls the integration of OpenShift Serverless and OpenShift Service Mesh. An example is shown.NAME READY STATUS RESTARTS AGE activator-7586f6f744-nvdlb 2/2 Running 0 22h activator-7586f6f744-sd77w 2/2 Running 0 22h autoscaler-764fdf5d45-p2v98 2/2 Running 0 22h autoscaler-764fdf5d45-x7dc6 2/2 Running 0 22h autoscaler-hpa-7c7c4cd96d-2lkzg 1/1 Running 0 22h autoscaler-hpa-7c7c4cd96d-gks9j 1/1 Running 0 22h controller-5fdfc9567c-6cj9d 1/1 Running 0 22h controller-5fdfc9567c-bf5x7 1/1 Running 0 22h domain-mapping-56ccd85968-2hjvp 1/1 Running 0 22h domain-mapping-56ccd85968-lg6mw 1/1 Running 0 22h domainmapping-webhook-769b88695c-gp2hk 1/1 Running 0 22h domainmapping-webhook-769b88695c-npn8g 1/1 Running 0 22h net-istio-controller-7dfc6f668c-jb4xk 1/1 Running 0 22h net-istio-controller-7dfc6f668c-jxs5p 1/1 Running 0 22h net-istio-webhook-66d8f75d6f-bgd5r 1/1 Running 0 22h net-istio-webhook-66d8f75d6f-hld75 1/1 Running 0 22h webhook-7d49878bc4-8xjbr 1/1 Running 0 22h webhook-7d49878bc4-s4xx4 1/1 Running 0 22h
4.3.4. Creating secure gateways for Knative Serving
To secure traffic between your Knative Serving instance and the service mesh, you must create secure gateways for your Knative Serving instance.
The following procedure shows how to use OpenSSL to generate a wildcard certificate and key and then use them to create local and ingress gateways for Knative Serving.
If you have your own wildcard certificate and key to specify when configuring the gateways, you can skip to step 11 of this procedure.
Prerequisites
- You have cluster administrator privileges for your OpenShift cluster.
- You have downloaded and installed the OpenShift command-line interface (CLI). See Installing the OpenShift CLI (OpenShift Dedicated) or Installing the OpenShift CLI (Red Hat OpenShift Service on AWS).
- You have created a Red Hat OpenShift Service Mesh instance.
- You have created a Knative Serving instance.
- If you intend to generate a wildcard certificate and key, you have downloaded and installed OpenSSL.
Procedure
In a terminal window, if you are not already logged in to your OpenShift cluster as a cluster administrator, log in to the OpenShift CLI as shown in the following example:
$ oc login <openshift_cluster_url> -u <admin_username> -p <password>
ImportantIf you have your own wildcard certificate and key to specify when configuring the gateways, skip to step 11 of this procedure.
Set environment variables to define base directories for generation of a wildcard certificate and key for the gateways.
$ export BASE_DIR=/tmp/kserve $ export BASE_CERT_DIR=${BASE_DIR}/certs
Set an environment variable to define the common name used by the ingress controller of your OpenShift cluster.
$ export COMMON_NAME=$(oc get ingresses.config.openshift.io cluster -o jsonpath='{.spec.domain}' | awk -F'.' '{print $(NF-1)"."$NF}')
Set an environment variable to define the domain name used by the ingress controller of your OpenShift cluster.
$ export DOMAIN_NAME=$(oc get ingresses.config.openshift.io cluster -o jsonpath='{.spec.domain}')
Create the required base directories for the certificate generation, based on the environment variables that you previously set.
$ mkdir ${BASE_DIR} $ mkdir ${BASE_CERT_DIR}
Create the OpenSSL configuration for generation of a wildcard certificate.
$ cat <<EOF> ${BASE_DIR}/openssl-san.config [ req ] distinguished_name = req [ san ] subjectAltName = DNS:*.${DOMAIN_NAME} EOF
Generate a root certificate.
$ openssl req -x509 -sha256 -nodes -days 3650 -newkey rsa:2048 \ -subj "/O=Example Inc./CN=${COMMON_NAME}" \ -keyout $BASE_DIR/root.key \ -out $BASE_DIR/root.crt
Generate a wildcard certificate signed by the root certificate.
$ openssl req -x509 -newkey rsa:2048 \ -sha256 -days 3560 -nodes \ -subj "/CN=${COMMON_NAME}/O=Example Inc." \ -extensions san -config ${BASE_DIR}/openssl-san.config \ -CA $BASE_DIR/root.crt \ -CAkey $BASE_DIR/root.key \ -keyout $BASE_DIR/wildcard.key \ -out $BASE_DIR/wildcard.crt $ openssl x509 -in ${BASE_DIR}/wildcard.crt -text
Verify the wildcard certificate.
$ openssl verify -CAfile ${BASE_DIR}/root.crt ${BASE_DIR}/wildcard.crt
Export the wildcard key and certificate that were created by the script to new environment variables.
$ export TARGET_CUSTOM_CERT=${BASE_CERT_DIR}/wildcard.crt $ export TARGET_CUSTOM_KEY=${BASE_CERT_DIR}/wildcard.key
Optional: To export your own wildcard key and certificate to new environment variables, enter the following commands:
$ export TARGET_CUSTOM_CERT=<path_to_certificate> $ export TARGET_CUSTOM_KEY=<path_to_key>
NoteIn the certificate that you provide, you must specify the domain name used by the ingress controller of your OpenShift cluster. You can check this value by running the following command:
$ oc get ingresses.config.openshift.io cluster -o jsonpath='{.spec.domain}'
Create a TLS secret in the
istio-system
namespace using the environment variables that you set for the wildcard certificate and key.$ oc create secret tls wildcard-certs --cert=${TARGET_CUSTOM_CERT} --key=${TARGET_CUSTOM_KEY} -n istio-system
Create a
gateways.yaml
YAML file with the following contents:apiVersion: v1 kind: Service 1 metadata: labels: experimental.istio.io/disable-gateway-port-translation: "true" name: knative-local-gateway namespace: istio-system spec: ports: - name: http2 port: 80 protocol: TCP targetPort: 8081 selector: knative: ingressgateway type: ClusterIP --- apiVersion: networking.istio.io/v1beta1 kind: Gateway metadata: name: knative-ingress-gateway 2 namespace: knative-serving spec: selector: knative: ingressgateway servers: - hosts: - '*' port: name: https number: 443 protocol: HTTPS tls: credentialName: wildcard-certs mode: SIMPLE --- apiVersion: networking.istio.io/v1beta1 kind: Gateway metadata: name: knative-local-gateway 3 namespace: knative-serving spec: selector: knative: ingressgateway servers: - port: number: 8081 name: https protocol: HTTPS tls: mode: ISTIO_MUTUAL hosts: - "*"
- 1
- Defines a service in the
istio-system
namespace for the Knative local gateway. - 2
- Defines an ingress gateway in the
knative-serving namespace
. The gateway uses the TLS secret you created earlier in this procedure. The ingress gateway handles external traffic to Knative. - 3
- Defines a local gateway for Knative in the
knative-serving
namespace.
Apply the
gateways.yaml
file to create the defined resources.$ oc apply -f gateways.yaml
You see the following output:
service/knative-local-gateway created gateway.networking.istio.io/knative-ingress-gateway created gateway.networking.istio.io/knative-local-gateway created
Verification
Review the gateways that you created.
$ oc get gateway --all-namespaces
Confirm that you see the local and ingress gateways that you created in the
knative-serving
namespace, as shown in the following example:NAMESPACE NAME AGE knative-serving knative-ingress-gateway 69s knative-serving knative-local-gateway 2m
4.3.5. Installing KServe
To complete manual installation of KServe, you must install the Red Hat OpenShift AI Add-on, which installs the Red Hat OpenShift AI Operator. Then, you can use the Operator to install KServe.
Prerequisites
- You have cluster administrator privileges for your OpenShift cluster.
- Your cluster has a node with 4 CPUs and 16 GB memory.
- You have downloaded and installed the OpenShift command-line interface (CLI). See Installing the OpenShift CLI (OpenShift Dedicated) or Installing the OpenShift CLI (Red Hat OpenShift Service on AWS).
- You have created a Red Hat OpenShift Service Mesh instance.
- You have created a Knative Serving instance.
- You have created secure gateways for Knative Serving.
-
You have installed the Red Hat OpenShift AI Add-on in your OpenShift cluster. This installs the Red Hat OpenShift AI Operator and creates a default
DataScienceCluster
object.
Procedure
- Log in to the OpenShift web console as a cluster administrator.
-
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift AI Operator. For installation of KServe, configure the OpenShift Service Mesh component as follows:
- Click the DSC Initialization tab.
- Click the default-dsci object.
- Click the YAML tab.
In the
spec
section, add and configure theserviceMesh
component as shown:spec: serviceMesh: managementState: Unmanaged
- Click Save.
For installation of KServe, configure the KServe and OpenShift Serverless components as follows:
-
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift AI Operator. - Click the Data Science Cluster tab.
- Click the default-dsc DSC object.
- Click the YAML tab.
In the
spec.components
section, configure thekserve
component as shown:spec: components: kserve: managementState: Managed
Within the
kserve
component, add theserving
component, and configure it as shown:spec: components: kserve: managementState: Managed serving: managementState: Unmanaged
- Click Save.
-
In the web console, click Operators
4.3.6. Disabling KServe dependencies
If you have not enabled the KServe component (that is, you set the value of the managementState
field to Removed
), you must also disable the dependent Service Mesh component to avoid errors.
Prerequisites
- You have used the OpenShift command-line interface (CLI) or web console to disable the KServe component.
Procedure
- Log in to the OpenShift web console as a cluster administrator.
-
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift AI Operator. Disable the OpenShift Service Mesh component as follows:
- Click the DSC Initialization tab.
- Click the default-dsci object.
- Click the YAML tab.
In the
spec
section, add theserviceMesh
component (if it is not already present) and configure themanagementState
field as shown:spec: serviceMesh: managementState: Removed
- Click Save.
Verification
In the web console, click Operators
Installed Operators and then click the Red Hat OpenShift AI Operator. The Operator details page opens.
- In the Conditions section, confirm that there is no ReconcileComplete condition with a status value of Unknown.
4.4. Adding an authorization provider for the single-model serving platform
You can add Authorino as an authorization provider for the single-model serving platform. Adding an authorization provider allows you to enable token authorization for models that you deploy on the platform, which ensures that only authorized parties can make inference requests to the models.
The method that you use to add Authorino as an authorization provider depends on how you install the single-model serving platform. The installation options for the platform are described as follows:
- Automated installation
If you have not already created a
ServiceMeshControlPlane
orKNativeServing
resource on your OpenShift cluster, you can configure the Red Hat OpenShift AI Operator to install KServe and its dependencies. You can include Authorino as part of the automated installation process.For more information about automated installation, including Authorino, see Configuring automated installation of KServe.
- Manual installation
If you have already created a
ServiceMeshControlPlane
orKNativeServing
resource on your OpenShift cluster, you cannot configure the Red Hat OpenShift AI Operator to install KServe and its dependencies. In this situation, you must install KServe manually. You must also manually configure Authorino.For more information about manual installation, including Authorino, see Manually installing KServe.
4.4.1. Manually adding an authorization provider
You can add Authorino as an authorization provider for the single-model serving platform. Adding an authorization provider allows you to enable token authorization for models that you deploy on the platform, which ensures that only authorized parties can make inference requests to the models.
To manually add Authorino as an authorization provider, you must install the Red Hat - Authorino
Operator, create an Authorino instance, and then configure the OpenShift Service Mesh and KServe components to use the instance.
To manually add an authorization provider, you must make configuration updates to your OpenShift Service Mesh instance. To ensure that your OpenShift Service Mesh instance remains in a supported state, make only the updates shown in this section.
Prerequisites
- You have reviewed the options for adding Authorino as an authorization provider and identified manual installation as the appropriate option. See Adding an authorization provider.
- You have manually installed KServe and its dependencies, including OpenShift Service Mesh. See Manually installing KServe.
-
When you manually installed KServe, you set the value of the
managementState
field for theserviceMesh
component toUnmanaged
. This setting is required for manually adding Authorino. See Installing KServe.
4.4.2. Installing the Red Hat Authorino Operator
Before you can add Autorino as an authorization provider, you must install the Red Hat - Authorino
Operator on your OpenShift cluster.
Prerequisites
- You have cluster administrator privileges for your OpenShift cluster.
Procedure
- Log in to the OpenShift web console as a cluster administrator.
-
In the web console, click Operators
OperatorHub. - On the OperatorHub page, in the Filter by keyword field, type Red Hat - Authorino.
- Click the Red Hat - Authorino Operator.
- On the Red Hat - Authorino Operator page, review the Operator information and then click Install.
- On the Install Operator page, keep the default values for Update channel, Version, Installation mode, Installed Namespace and Update Approval.
- Click Install.
Verification
In the OpenShift web console, click Operators
Installed Operators and confirm that the Red Hat - Authorino
Operator shows one of the following statuses:-
Installing
- installation is in progress; wait for this to change toSucceeded
. This might take several minutes. -
Succeeded
- installation is successful.
-
4.4.3. Creating an Authorino instance
When you have installed the Red Hat - Authorino
Operator on your OpenShift cluster, you must create an Authorino instance.
Prerequisites
-
You have installed the
Red Hat - Authorino
Operator. You have privileges to add resources to the project in which your OpenShift Service Mesh instance was created. See Creating an OpenShift Service Mesh instance.
For more information about OpenShift permissions, see Using RBAC to define and apply permissions (Red Hat OpenShift Dedicated) or Using RBAC to define and apply permissions (Red Hat OpenShift Service on AWS).
Procedure
- Open a new terminal window.
Log in to the OpenShift command-line interface (CLI) as follows:
$ oc login <openshift_cluster_url> -u <username> -p <password>
Create a namespace to install the Authorino instance.
$ oc new-project <namespace_for_authorino_instance>
NoteThe automated installation process creates a namespace called
redhat-ods-applications-auth-provider
for the Authorino instance. Consider using the same namespace name for the manual installation.To enroll the new namespace for the Authorino instance in your existing OpenShift Service Mesh instance, create a new YAML file with the following contents:
apiVersion: maistra.io/v1 kind: ServiceMeshMember metadata: name: default namespace: <namespace_for_authorino_instance> spec: controlPlaneRef: namespace: <namespace_for_service_mesh_instance> name: <name_of_service_mesh_instance>
- Save the YAML file.
Create the
ServiceMeshMember
resource on your cluster.$ oc create -f <file_name>.yaml
To configure an Authorino instance, create a new YAML file as shown in the following example:
apiVersion: operator.authorino.kuadrant.io/v1beta1 kind: Authorino metadata: name: authorino namespace: <namespace_for_authorino_instance> spec: authConfigLabelSelectors: security.opendatahub.io/authorization-group=default clusterWide: true listener: tls: enabled: false oidcServer: tls: enabled: false
- Save the YAML file.
Create the
Authorino
resource on your cluster.$ oc create -f <file_name>.yaml
Patch the Authorino deployment to inject an Istio sidecar, which makes the Authorino instance part of your OpenShift Service Mesh instance.
$ oc patch deployment <name_of_authorino_instance> -n <namespace_for_authorino_instance> -p '{"spec": {"template":{"metadata":{"labels":{"sidecar.istio.io/inject":"true"}}}} }'
Verification
Confirm that the Authorino instance is running as follows:
Check the pods (and containers) that are running in the namespace that you created for the Authorino instance, as shown in the following example:
$ oc get pods -n redhat-ods-applications-auth-provider -o="custom-columns=NAME:.metadata.name,STATUS:.status.phase,CONTAINERS:.spec.containers[*].name"
Confirm that the output resembles the following example:
NAME STATUS CONTAINERS authorino-6bc64bd667-kn28z Running authorino,istio-proxy
As shown in the example, there is a single running pod for the Authorino instance. The pod has containers for Authorino and for the Istio sidecar that you injected.
4.4.4. Configuring an OpenShift Service Mesh instance to use Authorino
When you have created an Authorino instance, you must configure your OpenShift Service Mesh instance to use Authorino as an authorization provider.
To ensure that your OpenShift Service Mesh instance remains in a supported state, make only the configuration updates shown in the following procedure.
Prerequisites
- You have created an Authorino instance and enrolled the namespace for the Authorino instance in your OpenShift Service Mesh instance.
- You have privileges to modify the OpenShift Service Mesh instance. See Creating an OpenShift Service Mesh instance.
Procedure
In a terminal window, if you are not already logged in to your OpenShift cluster as a user that has privileges to update the OpenShift Service Mesh instance, log in to the OpenShift CLI as shown in the following example:
$ oc login <openshift_cluster_url> -u <username> -p <password>
Create a new YAML file with the following contents:
spec: techPreview: meshConfig: extensionProviders: - name: redhat-ods-applications-auth-provider envoyExtAuthzGrpc: service: <name_of_authorino_instance>-authorino-authorization.<namespace_for_authorino_instance>.svc.cluster.local port: 50051
- Save the YAML file.
Use the
oc patch
command to apply the YAML file to your OpenShift Service Mesh instance.$ oc patch smcp <name_of_service_mesh_instance> --type merge -n <namespace_for_service_mesh_instance> --patch-file <file_name>.yaml
ImportantYou can apply the configuration shown as a patch only if you have not already specified other extension providers in your OpenShift Service Mesh instance. If you have already specified other extension providers, you must manually edit your
ServiceMeshControlPlane
resource to add the configuration.
Verification
Verify that your Authorino instance has been added as an extension provider in your OpenShift Service Mesh configuration as follows:
Inspect the
ConfigMap
object for your OpenShift Service Mesh instance:$ oc get configmap istio-<name_of_service_mesh_instance> -n <namespace_for_service_mesh_instance> --output=jsonpath={.data.mesh}
Confirm that you see output similar to the following example, which shows that the Authorino instance has been successfully added as an extension provider.
defaultConfig: discoveryAddress: istiod-data-science-smcp.istio-system.svc:15012 proxyMetadata: ISTIO_META_DNS_AUTO_ALLOCATE: "true" ISTIO_META_DNS_CAPTURE: "true" PROXY_XDS_VIA_AGENT: "true" terminationDrainDuration: 35s tracing: {} dnsRefreshRate: 300s enablePrometheusMerge: true extensionProviders: - envoyExtAuthzGrpc: port: 50051 service: authorino-authorino-authorization.opendatahub-auth-provider.svc.cluster.local name: opendatahub-auth-provider ingressControllerMode: "OFF" rootNamespace: istio-system trustDomain: null%
4.4.5. Configuring authorization for KServe
To configure the single-model serving platform to use Authorino, you must create a global AuthorizationPolicy
resource that is applied to the KServe predictor pods that are created when you deploy a model. In addition, to account for the multiple network hops that occur when you make an inference request to a model, you must create an EnvoyFilter
resource that continually resets the HTTP host header to the one initially included in the inference request.
Prerequisites
- You have created an Authorino instance and configured your OpenShift Service Mesh to use it.
- You have privileges to update the KServe deployment on your cluster.
- You have privileges to add resources to the project in which your OpenShift Service Mesh instance was created. See Creating an OpenShift Service Mesh instance.
Procedure
In a terminal window, if you are not already logged in to your OpenShift cluster as a user that has privileges to update the KServe deployment, log in to the OpenShift CLI as shown in the following example:
$ oc login <openshift_cluster_url> -u <username> -p <password>
Create a new YAML file with the following contents:
apiVersion: security.istio.io/v1beta1 kind: AuthorizationPolicy metadata: name: kserve-predictor spec: action: CUSTOM provider: name: redhat-ods-applications-auth-provider 1 rules: - to: - operation: notPaths: - /healthz - /debug/pprof/ - /metrics - /wait-for-drain selector: matchLabels: component: predictor
- 1
- The name that you specify must match the name of the extension provider that you added to your OpenShift Service Mesh instance.
- Save the YAML file.
Create the
AuthorizationPolicy
resource in the namespace for your OpenShift Service Mesh instance.$ oc create -n <namespace_for_service_mesh_instance> -f <file_name>.yaml
Create another new YAML file with the following contents:
apiVersion: networking.istio.io/v1alpha3 kind: EnvoyFilter metadata: name: activator-host-header spec: priority: 20 workloadSelector: labels: component: predictor configPatches: - applyTo: HTTP_FILTER match: listener: filterChain: filter: name: envoy.filters.network.http_connection_manager patch: operation: INSERT_BEFORE value: name: envoy.filters.http.lua typed_config: '@type': type.googleapis.com/envoy.extensions.filters.http.lua.v3.Lua inlineCode: | function envoy_on_request(request_handle) local headers = request_handle:headers() if not headers then return end local original_host = headers:get("k-original-host") if original_host then port_seperator = string.find(original_host, ":", 7) if port_seperator then original_host = string.sub(original_host, 0, port_seperator-1) end headers:replace('host', original_host) end end
The
EnvoyFilter
resource shown continually resets the HTTP host header to the one initially included in any inference request.Create the
EnvoyFilter
resource in the namespace for your OpenShift Service Mesh instance.$ oc create -n <namespace_for_service_mesh_instance> -f <file_name>.yaml
Verification
Check that the
AuthorizationPolicy
resource was successfully created.$ oc get authorizationpolicies -n <namespace_for_service_mesh_instance>
Confirm that you see output similar to the following example:
NAME AGE kserve-predictor 28h
Check that the
EnvoyFilter
resource was successfully created.$ oc get envoyfilter -n <namespace_for_service_mesh_instance>
Confirm that you see output similar to the following example:
NAME AGE activator-host-header 28h