feat: add docs on cycling out ec2 nodes

docs/infrastructure/kubernetes.version.md

@@ -69,4 +69,24 @@ Resources
 
 **Version bump deployments can take 10+ minutes**
 
-6. Cycle out EC2 Nodes to the new version.
+## Cycle out EC2 Nodes to the new version.
+
+1. Find the nodegroup name for the cluster
+
+```bash
+aws eks list-nodegroups --cluster-name Workflows
+```
+
+2. Describe the nodegroup to validate the versions
+
+By describing the node group you can check the current version, or you can use `k get nodes` to see what version is currently running
+
+```bash
+aws eks describe-nodegroup --cluster-name Workflows --nodegroup-name EksWorkflowsNodegroupCluste
+```
+
+3. Update the version to match
+
+```bash
+aws eks update-nodegroup-version --cluster-name Workflows --nodegroup-name EksWorkflowsNodegroupCluste-OWsXxRuVz2B7
+```

infra/README.md

@@ -110,3 +110,8 @@ The deployment of the K8s config is managed by GithubActions in [main](../.githu
 ## Troubleshoot
 
 - [DNS](../docs/dns.configuration.md)
+
+## Upgrading Kubernetes Versions
+
+Kubernetes upgrades very frequently to deploy a new version follow the
+[Version Upgrade Guide](../docs/infrastructure/kubernetes.version.md)

infra/eks/cluster.ts

@@ -1,4 +1,4 @@
-import { KubectlV27Layer } from '@aws-cdk/lambda-layer-kubectl-v27';
+import { KubectlV28Layer } from '@aws-cdk/lambda-layer-kubectl-v28';
 import { Aws, CfnOutput, Duration, RemovalPolicy, Stack, StackProps } from 'aws-cdk-lib';
 import { InstanceType, IVpc, SubnetType, Vpc } from 'aws-cdk-lib/aws-ec2';
 import { Cluster, ClusterLoggingTypes, IpFamily, KubernetesVersion, NodegroupAmiType } from 'aws-cdk-lib/aws-eks';
@@ -25,7 +25,7 @@ export class LinzEksCluster extends Stack {
   /* Cluster ID */
   id: string;
   /** Version of EKS to use, this must be aligned to the `kubectlLayer` */
-  version = KubernetesVersion.V1_27;
+  version = { version: '1.27' } as KubernetesVersion;
   /** Argo needs a temporary bucket to store objects */
   tempBucket: Bucket;
   /* Bucket where read/write roles config files are stored */
@@ -65,7 +65,7 @@ export class LinzEksCluster extends Stack {
       defaultCapacity: 0,
       vpcSubnets: [{ subnetType: SubnetType.PRIVATE_WITH_EGRESS }],
       /** This must align to Cluster version: {@link version} */
-      kubectlLayer: new KubectlV27Layer(this, 'KubeCtlLayer'),
+      kubectlLayer: new KubectlV28Layer(this, 'KubeCtlLayer'),
       /** To prevent IP exhaustion when running huge workflows run using ipv6 */
       ipFamily: IpFamily.IP_V6,
       clusterLogging: [ClusterLoggingTypes.API, ClusterLoggingTypes.CONTROLLER_MANAGER, ClusterLoggingTypes.SCHEDULER],

package.json

@@ -24,7 +24,7 @@
     "@aws-sdk/client-cloudformation": "3.429.0",
     "@aws-sdk/client-eks": "3.429.0",
     "@aws-sdk/client-ssm": "3.429.0",
-    "@aws-cdk/lambda-layer-kubectl-v27": "^2.0.0",
+    "@aws-cdk/lambda-layer-kubectl-v28": "^2.0.0",
     "@linzjs/style": "^5.0.0",
     "aws-cdk": "2.93.x",
     "aws-cdk-lib": "2.93.x",