feat: Add enhanced node repair configuration support

examples/44-enhanced-node-repair.yaml

@@ -0,0 +1,103 @@
+# An example ClusterConfig that demonstrates the enhanced node repair configuration
+# for EKS managed nodegroups with comprehensive parameters and custom overrides.
+
+apiVersion: eksctl.io/v1alpha5
+kind: ClusterConfig
+
+metadata:
+  name: enhanced-node-repair-cluster
+  region: us-west-2
+
+managedNodeGroups:
+  # Example 1: Basic node repair with percentage-based thresholds
+  - name: basic-repair-ng
+    instanceType: m5.large
+    desiredCapacity: 3
+    minSize: 1
+    maxSize: 5
+    nodeRepairConfig:
+      enabled: true
+      # Stop repair actions when 20% of nodes are unhealthy
+      maxUnhealthyNodeThresholdPercentage: 20
+      # Repair at most 15% of unhealthy nodes in parallel
+      maxParallelNodesRepairedPercentage: 15
+
+  # Example 2: Node repair with count-based thresholds
+  - name: count-based-repair-ng
+    instanceType: m5.xlarge
+    desiredCapacity: 10
+    minSize: 5
+    maxSize: 20
+    nodeRepairConfig:
+      enabled: true
+      # Stop repair actions when 3 nodes are unhealthy
+      maxUnhealthyNodeThresholdCount: 3
+      # Repair at most 2 unhealthy nodes in parallel
+      maxParallelNodesRepairedCount: 2
+
+  # Example 3: Comprehensive configuration with custom overrides
+  - name: comprehensive-repair-ng
+    instanceType: g4dn.xlarge  # GPU instance for ML workloads
+    desiredCapacity: 4
+    minSize: 2
+    maxSize: 8
+    nodeRepairConfig:
+      enabled: true
+      # Stop repair actions when 25% of nodes are unhealthy
+      maxUnhealthyNodeThresholdPercentage: 25
+      # Repair at most 1 unhealthy node at a time to maintain workload availability
+      maxParallelNodesRepairedCount: 1
+      # Custom repair behavior for specific failure scenarios
+      nodeRepairConfigOverrides:
+        # Handle GPU-related failures with immediate termination
+        - nodeMonitoringCondition: "AcceleratedInstanceNotReady"
+          nodeUnhealthyReason: "NvidiaXID13Error"
+          minRepairWaitTimeMins: 5
+          repairAction: "Terminate"
+        # Handle network issues with restart first, then terminate
+        - nodeMonitoringCondition: "NetworkNotReady"
+          nodeUnhealthyReason: "InterfaceNotUp"
+          minRepairWaitTimeMins: 15
+          repairAction: "Restart"
+
+  # Example 4: Conservative repair settings for critical workloads
+  - name: critical-workload-ng
+    instanceType: c5.2xlarge
+    desiredCapacity: 6
+    minSize: 3
+    maxSize: 12
+    nodeRepairConfig:
+      enabled: true
+      # Very conservative settings - stop repair actions when only 10% of nodes are unhealthy
+      maxUnhealthyNodeThresholdPercentage: 10
+      # Repair only 1 unhealthy node at a time for critical workloads
+      maxParallelNodesRepairedCount: 1
+      nodeRepairConfigOverrides:
+        # For critical workloads, wait longer before taking action
+        - nodeMonitoringCondition: "AcceleratedInstanceNotReady"
+          nodeUnhealthyReason: "NvidiaXID13Error"
+          minRepairWaitTimeMins: 30
+          repairAction: "Terminate"
+        - nodeMonitoringCondition: "NetworkNotReady"
+          nodeUnhealthyReason: "InterfaceNotUp"
+          minRepairWaitTimeMins: 45
+          repairAction: "Restart"
+
+  # Example 5: Disabled node repair (for comparison)
+  - name: no-repair-ng
+    instanceType: t3.medium
+    desiredCapacity: 2
+    minSize: 1
+    maxSize: 4
+    nodeRepairConfig:
+      enabled: false
+
+# Additional cluster configuration
+vpc:
+  cidr: "10.0.0.0/16"
+  autoAllocateIPv6: false
+
+# Enable logging for monitoring node repair activities
+cloudWatch:
+  clusterLogging:
+    enableTypes: ["api", "audit", "authenticator", "controllerManager", "scheduler"]

go.mod

@@ -8,23 +8,23 @@ require (
 	github.com/Masterminds/semver/v3 v3.4.0
 	github.com/aws/amazon-ec2-instance-selector/v3 v3.1.1-0.20250224180552-36eea73b44c2
 	github.com/aws/aws-sdk-go v1.55.7
-	github.com/aws/aws-sdk-go-v2 v1.38.3
+	github.com/aws/aws-sdk-go-v2 v1.39.0
 	github.com/aws/aws-sdk-go-v2/config v1.29.14
-	github.com/aws/aws-sdk-go-v2/credentials v1.17.67
-	github.com/aws/aws-sdk-go-v2/service/autoscaling v1.58.2
-	github.com/aws/aws-sdk-go-v2/service/cloudformation v1.66.0
-	github.com/aws/aws-sdk-go-v2/service/cloudtrail v1.53.2
-	github.com/aws/aws-sdk-go-v2/service/cloudwatchlogs v1.57.2
+	github.com/aws/aws-sdk-go-v2/credentials v1.18.11
+	github.com/aws/aws-sdk-go-v2/service/autoscaling v1.59.0
+	github.com/aws/aws-sdk-go-v2/service/cloudformation v1.66.1
+	github.com/aws/aws-sdk-go-v2/service/cloudtrail v1.53.3
+	github.com/aws/aws-sdk-go-v2/service/cloudwatchlogs v1.57.3
 	github.com/aws/aws-sdk-go-v2/service/cognitoidentityprovider v1.51.3
 	github.com/aws/aws-sdk-go-v2/service/ec2 v1.210.1
-	github.com/aws/aws-sdk-go-v2/service/eks v1.73.1
-	github.com/aws/aws-sdk-go-v2/service/elasticloadbalancing v1.33.2
-	github.com/aws/aws-sdk-go-v2/service/elasticloadbalancingv2 v1.50.2
-	github.com/aws/aws-sdk-go-v2/service/iam v1.47.3
+	github.com/aws/aws-sdk-go-v2/service/eks v1.74.0
+	github.com/aws/aws-sdk-go-v2/service/elasticloadbalancing v1.33.3
+	github.com/aws/aws-sdk-go-v2/service/elasticloadbalancingv2 v1.50.3
+	github.com/aws/aws-sdk-go-v2/service/iam v1.47.4
 	github.com/aws/aws-sdk-go-v2/service/kms v1.38.3
-	github.com/aws/aws-sdk-go-v2/service/outposts v1.56.2
-	github.com/aws/aws-sdk-go-v2/service/ssm v1.64.2
-	github.com/aws/aws-sdk-go-v2/service/sts v1.33.19
+	github.com/aws/aws-sdk-go-v2/service/outposts v1.56.3
+	github.com/aws/aws-sdk-go-v2/service/ssm v1.64.3
+	github.com/aws/aws-sdk-go-v2/service/sts v1.38.3
 	github.com/aws/smithy-go v1.23.0
 	github.com/awslabs/amazon-eks-ami/nodeadm v0.0.0-20250219002025-c3b5cd3d2fd9
 	github.com/benjamintf1/unmarshalledmatchers v1.0.0
@@ -129,22 +129,22 @@ require (
 	github.com/ashanbrown/makezero v1.2.0 // indirect
 	github.com/atotto/clipboard v0.1.4 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.1 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.30 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.6 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.6 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.7 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.7 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.7 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.3 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/v4a v1.3.33 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.7 // indirect
 	github.com/aws/aws-sdk-go-v2/service/eventbridge v1.36.12 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.3 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.6.1 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.15 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.14 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.1 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.8.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.7 // indirect
 	github.com/aws/aws-sdk-go-v2/service/pricing v1.32.17 // indirect
 	github.com/aws/aws-sdk-go-v2/service/route53 v1.48.8 // indirect
 	github.com/aws/aws-sdk-go-v2/service/s3 v1.77.1 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sqs v1.37.15 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.25.3 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.30.1 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.29.2 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.34.3 // indirect
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/bkielbasa/cyclop v1.2.3 // indirect