Publish to stable

.github/workflows/release.yaml

@@ -2,6 +2,7 @@ name: Release
 on:
   milestone:
     types: [closed]
+  workflow_dispatch: {}
 
 permissions:
   id-token: write

.github/workflows/test-util-ci.yml

@@ -6,7 +6,7 @@ on:
     branches:
       - main
     paths:
-      - test/util/**
+      - testing/util/**
 
 jobs:
   test:
@@ -22,16 +22,16 @@ jobs:
           node-version: ${{ env.node_version }}
           registry-url: "https://registry.npmjs.org"
       - name: Install NPM packages
-        working-directory: test/util
+        working-directory: testing/util
         run: npm ci
       - name: Build
-        working-directory: test/util
+        working-directory: testing/util
         run: npm run build
       - name: Run unit tests
-        working-directory: test/util
+        working-directory: testing/util
         run: |
           npm test
       - name: Run test content
-        working-directory: test/util
+        working-directory: testing/util
         run: |
           npm run exec -- test ./test-content

.mergify.yml

@@ -0,0 +1,7 @@
+pull_request_rules:
+  - name: Automatically approve Renovate PRs
+    conditions:
+      - author = renovate[bot]
+    actions:
+      review:
+        type: APPROVE

.spelling

@@ -126,4 +126,5 @@ mehta
 sheetal
 joshi
 keda
-AIML
+AIML
+DCGM

README.md

@@ -60,13 +60,6 @@ There are several tools that are required to run the workshop such as `kubectl`
 - Governance model: [governance/model.md](governance/model.md)
 - Tenets: [governance/tenets.md](governance/tenets.md)
 
-### Meetings
-
-2nd Thursday every month at 8am PT (3pm UTC)
-
-- Meeting link: [Chime Web Meeting Link](https://chime.aws/8607878433)
-- Agenda, Notes, and calendar invites: [Google Doc](https://docs.google.com/document/d/1hYjhBhPvLVMf7gunooM-kE0wptMjMIORCmI2BOedCWI/edit?usp=sharing)
-
 ## Security
 
 See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.

docs/authoring_content.md

@@ -167,7 +167,7 @@ See `lab/Dockerfile` and `lab/scripts/installer.sh` to configure the installed u
 
 If Terraform is needed it should be created at `./manifests/modules/<yourpath>/.workshop/terraform`. This Terraform will be automatically applied when the user runs `prepare-environment` and destroyed when they move to the next lab.
 
-You can use the directory `manifests/template/.workshop/terraform` as a starter example. The Terraform is treated as a module and the variables in that directory must match exactly in order to meet the "contract" with the rest of the framework. See `vars.tf` and `outputs.tf`.
+You can use the directory `templates/lab-manifests/.workshop/terraform` as a starter example. The Terraform is treated as a module and the variables in that directory must match exactly in order to meet the "contract" with the rest of the framework. See `vars.tf` and `outputs.tf`.
 
 ### Variables
 

docs/style_guide.md

@@ -42,6 +42,18 @@ sidebar_custom_props: {"info": true}
 ---
 ```
 
+To mark your module as external content, which at the moment is only used for other AWS workshops, place the following in the header of your markdown file:
+
+```
+---
+...
+sidebar_custom_props:
+  {
+    "explore": "https://<external link here>"
+  }
+---
+```
+
 ### Navigating the AWS console
 
 There are instances where the user needs to navigate to specific screens in the AWS console. It is preferable to provide a link to the exact screen if possible, or a close as can be done.

hack/run-tests.sh

@@ -37,7 +37,7 @@ container_image='eks-workshop-test'
 
 (cd $SCRIPT_DIR/../lab && $CONTAINER_CLI build -q -t eks-workshop-environment .)
 
-(cd $SCRIPT_DIR/../test && $CONTAINER_CLI build -q -t $container_image .)
+(cd $SCRIPT_DIR/../testing && $CONTAINER_CLI build -q -t $container_image .)
 
 source $SCRIPT_DIR/lib/generate-aws-creds.sh
 

lab/bin/reset-environment

@@ -1,5 +1,8 @@
 #!/bin/bash
 
+# Make sure we run from a consistent directory
+cd ~
+
 mkdir -p /eks-workshop/logs
 log_file=/eks-workshop/logs/action-$(date +%s).log
 
@@ -121,6 +124,11 @@ rm -rf /eks-workshop/terraform
 mkdir -p /eks-workshop/terraform
 cp -R $manifests_path/.workshop/terraform/* /eks-workshop/terraform
 
+# Use a separate directory for .terraform directory
+# Allows us to wipe the TF configuration every time but retain providers installed
+mkdir -p /eks-workshop/terraform-data
+export TF_DATA_DIR="/eks-workshop/terraform-data"
+
 export TF_VAR_eks_cluster_id="$EKS_CLUSTER_NAME"
 
 RESOURCES_PRECREATED=${RESOURCES_PRECREATED:-"false"}
@@ -226,6 +234,7 @@ fi
 # Recycle workload pods in case stateful pods got restarted
 kubectl delete pod -l app.kubernetes.io/created-by=eks-workshop -l app.kubernetes.io/component=service -A
 
+# Wait for the workload pods previously recycled
 kubectl wait --for=condition=Ready --timeout=240s pods -l app.kubernetes.io/created-by=eks-workshop -A
 
 # Finished

lab/iam/policies/base.yaml

@@ -71,13 +71,14 @@ Statement:
     Resource: ["*"]
     Condition:
       StringLike:
-        kms:RequestAlias: "alias/${Env}*"
+        kms:RequestAlias: ["alias/${Env}*", "alias/eks/${Env}*"]
   - Effect: Allow
     Action:
       - kms:CreateAlias
       - kms:DeleteAlias
     Resource:
       - !Sub arn:aws:kms:${AWS::Region}:${AWS::AccountId}:alias/${Env}*
+      - !Sub arn:aws:kms:${AWS::Region}:${AWS::AccountId}:alias/eks/${Env}*
       - !Sub arn:aws:kms:${AWS::Region}:${AWS::AccountId}:key/*
   - Effect: Allow
     Action:

lab/iam/policies/labs2.yaml

@@ -34,6 +34,7 @@ Statement:
     Resource:
       - !Sub arn:aws:events:${AWS::Region}:${AWS::AccountId}:rule/${Env}*
       - !Sub arn:aws:events:${AWS::Region}:${AWS::AccountId}:rule/eks-workshop*
+      - !Sub arn:aws:events:${AWS::Region}:${AWS::AccountId}:rule/Karpenter*
   - Effect: Allow
     Action:
       - vpc-lattice:List*

lab/scripts/installer.sh

@@ -3,27 +3,27 @@
 set -e
 
 # renovate: depName=kubernetes/kubernetes
-kubectl_version='1.30.3'
+kubectl_version='1.30.4'
 
 # renovate: depName=helm/helm
-helm_version='3.15.3'
+helm_version='3.15.4'
 
 # renovate: depName=eksctl-io/eksctl
-eksctl_version='0.188.0'
+eksctl_version='0.190.0'
 
 kubeseal_version='0.18.4'
 
 # renovate: depName=mikefarah/yq
-yq_version='4.44.2'
+yq_version='4.44.3'
 
 # renovate: depName=fluxcd/flux2
 flux_version='2.3.0'
 
 # renovate: depName=argoproj/argo-cd
-argocd_version='2.11.7'
+argocd_version='2.12.3'
 
 # renovate: depName=hashicorp/terraform
-terraform_version='1.9.3'
+terraform_version='1.9.5'
 
 # renovate: depName=aws/amazon-ec2-instance-selector
 ec2_instance_selector_version='2.4.1'

manifests/.workshop/terraform/base.tf

@@ -4,15 +4,15 @@ terraform {
   required_providers {
     aws = {
       source  = "hashicorp/aws"
-      version = "5.61.0"
+      version = "5.66.0"
     }
     kubernetes = {
       source  = "hashicorp/kubernetes"
-      version = "2.31.0"
+      version = "2.32.0"
     }
     helm = {
       source  = "hashicorp/helm"
-      version = "2.14.0"
+      version = "2.15.0"
     }
     kubectl = {
       source  = "gavinbunney/kubectl"

manifests/base-application/carts/deployment.yaml

@@ -44,12 +44,18 @@ spec:
             readOnlyRootFilesystem: true
             runAsNonRoot: true
             runAsUser: 1000
-          image: "public.ecr.aws/aws-containers/retail-store-sample-cart:0.7.0"
+          image: "public.ecr.aws/aws-containers/retail-store-sample-cart:0.8.0"
           imagePullPolicy: IfNotPresent
           ports:
             - name: http
               containerPort: 8080
               protocol: TCP
+          readinessProbe:
+            httpGet:
+              path: /actuator/health/readiness
+              port: 8080
+            initialDelaySeconds: 15
+            periodSeconds: 3
           livenessProbe:
             httpGet:
               path: /actuator/health/liveness

manifests/modules/aiml/chatbot/.workshop/cleanup.sh

@@ -2,43 +2,30 @@
 
 set -e
 
-logmessage "Deleting AIML resources..."
-
 logmessage "Deleting Gradio-UI Components..."
 
-kubectl delete -k /eks-workshop/manifests/modules/aiml/chatbot/gradio --ignore-not-found=true
+kubectl delete -k /eks-workshop/manifests/modules/aiml/chatbot/gradio --ignore-not-found
 
 logmessage "Deleting Llama2 pods..."
 
-kubectl delete -f https://raw.githubusercontent.com/aws-neuron/aws-neuron-sdk/v2.19.1/src/k8/k8s-neuron-device-plugin-rbac.yml --ignore-not-found
-kubectl delete -f https://raw.githubusercontent.com/aws-neuron/aws-neuron-sdk/v2.19.1/src/k8/k8s-neuron-device-plugin.yml --ignore-not-found
+kubectl delete -k /eks-workshop/manifests/modules/aiml/chatbot/ray-service-llama2-chatbot --ignore-not-found
 
 logmessage "Deleting Neuron Device Plugin..."
 
-kubectl delete -k /eks-workshop/manifests/modules/aiml/chatbot/neuron-device-plugin --ignore-not-found=true
+kubectl delete -f https://raw.githubusercontent.com/aws-neuron/aws-neuron-sdk/v2.19.1/src/k8/k8s-neuron-device-plugin-rbac.yml --ignore-not-found
+kubectl delete -f https://raw.githubusercontent.com/aws-neuron/aws-neuron-sdk/v2.19.1/src/k8/k8s-neuron-device-plugin.yml --ignore-not-found
 
 logmessage "Un-installing kuberay operator..."
 
-helm uninstall kuberay-operator
-
-kubectl delete namespace llama2 --ignore-not-found
-
-kubectl delete namespace gradio-llama2-inf2 --ignore-not-found
+helm uninstall kuberay-operator --ignore-not-found
 
-logmessage "Deleting Karpenter NodePool and EC2NodeClass..."
+logmessage "Deleting Karpenter resources..."
 
-delete-all-if-crd-exists nodepools.karpenter.sh
-delete-all-if-crd-exists ec2nodeclasses.karpenter.k8s.aws
+kubectl kustomize ~/environment/eks-workshop/modules/aiml/chatbot/nodepool \
+  | envsubst | kubectl delete -f-
 
-logmessage "Waiting for Karpenter nodes to be removed..."
+logmessage "Deleting llama2 and gradio-llama2-inf2 namespaces..."
 
-EXIT_CODE=0
-
-timeout --foreground -s TERM 30 bash -c \
-    'while [[ $(kubectl get nodes --selector=type=karpenter -o json | jq -r ".items | length") -gt 0 ]];\
-    do sleep 5;\
-    done' || EXIT_CODE=$?
+kubectl delete namespace llama2 --ignore-not-found
 
-if [ $EXIT_CODE -ne 0 ]; then
-  logmessage "Warning: Karpenter nodes did not clean up"
-fi
+kubectl delete namespace gradio-llama2-inf2 --ignore-not-found