update: test all functions (#93)

.yamllint

@@ -23,4 +23,4 @@ rules:
 ignore:
   - "scratch/*"
   - "components/containers/web-terminal/src/*"
-  - "components/operators/gpu-operator-certified/instance/components/console-plugin-helm/*"
+  - "components/operators/gpu-operator-certified/operator/components/console-plugin-helm/*"

README.md

@@ -6,7 +6,7 @@
 This project is a catalog of configurations used to provision infrastructure, on
 OpenShift, that supports machine learning (ML) and artificial intelligence (AI) workloads.
 
-The intention of this repository is to help support practical use of OpenShift for AI / ML workloads.
+The intention of this repository is to help support practical use of OpenShift for AI / ML workloads and provide a catalog of configurations / demos / workshops.
 
 Please look at the [GitOps Catalog](https://github.com/redhat-cop/gitops-catalog) if you only need to automate an operator install.
 
@@ -16,12 +16,14 @@ In this repo, look at various [kustomized configs](components/configs) and [argo
 
 ## Prerequisites
 
-- OpenShift 4.8+
+- OpenShift 4.14+
   - role: `cluster-admin` - for all [demo](demos) or [cluster](clusters) configs
   - role: `self-provisioner` - for namespaced components
 
 [Red Hat Demo Platform](https://demo.redhat.com) Options (Tested)
 
+NOTE: node sizes below are the **recommended minimum** to select for provisioning
+
 - <a href="https://demo.redhat.com/catalog?item=babylon-catalog-prod/sandboxes-gpte.sandbox-ocp.prod&utm_source=webapp&utm_medium=share-link" target="_blank">AWS with OpenShift Open Environment</a>
   - 1 x Control Plane - `m6a.2xlarge`
   - 0 x Workers - `m6a.2xlarge`

components/operators/ack-system/base/user-config-cm.yaml

@@ -11,3 +11,4 @@ data:
   AWS_ENDPOINT_URL: ""
   ENABLE_LEADER_ELECTION: "true"
   LEADER_ELECTION_NAMESPACE: ""
+  RECONCILE_DEFAULT_MAX_CONCURRENT_SYNCS: "1"

components/operators/ack-system/scripts/setup.sh

@@ -31,7 +31,7 @@ ocp_aws_get_key(){
 }
 
 # create secrets for ack controllers
-aws_setup_ack_system(){
+ocp_aws_setup_ack_system(){
   NAMESPACE=ack-system
 
   ocp_aws_get_key
@@ -56,4 +56,4 @@ aws_setup_ack_system(){
   done
 }
 
-aws_setup_ack_system
+ocp_aws_setup_ack_system

components/operators/gpu-operator-certified/operator/components/console-plugin/configmap.yaml

@@ -5,6 +5,9 @@ kind: ConfigMap
 metadata:
   name: console-plugin-nvidia-gpu
   namespace: nvidia-gpu-operator
+  annotations:
+    meta.helm.sh/release-name: console-plugin-nvidia-gpu
+    meta.helm.sh/release-namespace: nvidia-gpu-operator
   labels:
     helm.sh/chart: console-plugin-nvidia-gpu-0.2.4
     app.kubernetes.io/name: console-plugin-nvidia-gpu

components/operators/gpu-operator-certified/operator/components/console-plugin/consoleplugin.yaml

@@ -5,6 +5,9 @@ kind: ConsolePlugin
 metadata:
   name: console-plugin-nvidia-gpu
   namespace: nvidia-gpu-operator
+  annotations:
+    meta.helm.sh/release-name: console-plugin-nvidia-gpu
+    meta.helm.sh/release-namespace: nvidia-gpu-operator
   labels:
     helm.sh/chart: console-plugin-nvidia-gpu-0.2.4
     app.kubernetes.io/name: console-plugin-nvidia-gpu

components/operators/gpu-operator-certified/operator/components/console-plugin/deployment.yaml

@@ -5,6 +5,9 @@ kind: Deployment
 metadata:
   name: console-plugin-nvidia-gpu
   namespace: nvidia-gpu-operator
+  annotations:
+    meta.helm.sh/release-name: console-plugin-nvidia-gpu
+    meta.helm.sh/release-namespace: nvidia-gpu-operator
   labels:
     helm.sh/chart: console-plugin-nvidia-gpu-0.2.4
     app.kubernetes.io/name: console-plugin-nvidia-gpu

components/operators/gpu-operator-certified/operator/components/console-plugin/service.yaml

@@ -5,6 +5,10 @@ kind: Service
 metadata:
   name: console-plugin-nvidia-gpu
   namespace: nvidia-gpu-operator
+  annotations:
+    meta.helm.sh/release-name: console-plugin-nvidia-gpu
+    meta.helm.sh/release-namespace: nvidia-gpu-operator
+    service.alpha.openshift.io/serving-cert-secret-name: plugin-serving-cert
   labels:
     helm.sh/chart: console-plugin-nvidia-gpu-0.2.4
     app.kubernetes.io/name: console-plugin-nvidia-gpu
@@ -13,8 +17,6 @@ metadata:
     app.kubernetes.io/component: console-plugin-nvidia-gpu
     app.kubernetes.io/instance: console-plugin-nvidia-gpu
     app.kubernetes.io/part-of: console-plugin-nvidia-gpu
-  annotations:
-    service.alpha.openshift.io/serving-cert-secret-name: plugin-serving-cert
 spec:
   ports:
   - name: 9443-tcp

components/operators/web-terminal/instance/overlays/enhanced/web-terminal-tooling.yaml

@@ -11,18 +11,13 @@ metadata:
 spec:
   components:
     - container:
-        env:
-          - name: YOLO_URL
-            value: https://raw.githubusercontent.com/redhat-na-ssa/demo-ai-gitops-catalog/main/scripts/library/term.sh
         args:
           - "/bin/bash"
           - "-c"
           - |
             #!/bin/bash
-            # set -x
 
-            . <(curl -s "${YOLO_URL}" | tee /tmp/yolo.sh)
-            term_init
+            . /home/user/.bashrc
 
             sleep infinity  # just in case