CNTRLPLANE-2262: Add Azure scale-from-zero support

api/hypershift/v1beta1/nodepool_types.go

@@ -106,7 +106,7 @@ type NodePool struct {
 // +kubebuilder:validation:XValidation:rule="!has(self.replicas) || !has(self.autoScaling)", message="Both replicas or autoScaling should not be set"
 // +kubebuilder:validation:XValidation:rule="self.arch != 's390x' || has(self.platform.kubevirt)", message="s390x is only supported on KubeVirt platform"
 // +kubebuilder:validation:XValidation:rule="!has(self.platform.aws) || !has(self.platform.aws.imageType) || self.platform.aws.imageType != 'Windows' || self.arch == 'amd64'", message="ImageType 'Windows' requires arch 'amd64' (AWS only)"
-// +kubebuilder:validation:XValidation:rule="!has(self.autoScaling) || self.autoScaling.min > 0 || self.platform.type == 'AWS'", message="Scale-from-zero (autoScaling.min=0) is currently only supported for AWS platform"
+// +kubebuilder:validation:XValidation:rule="!has(self.autoScaling) || self.autoScaling.min > 0 || self.platform.type == 'AWS' || self.platform.type == 'Azure'", message="Scale-from-zero (autoScaling.min=0) is currently only supported for AWS and Azure platforms"
 type NodePoolSpec struct {
 	// clusterName is the name of the HostedCluster this NodePool belongs to.
 	// If a HostedCluster with this name doesn't exist, the controller will no-op until it exists.
@@ -501,7 +501,7 @@ type NodePoolManagement struct {
 // +kubebuilder:validation:XValidation:rule="self.max >= self.min", message="max must be equal or greater than min"
 type NodePoolAutoScaling struct {
 	// min is the minimum number of nodes to maintain in the pool.
-	// Can be set to 0 for scale-from-zero for AWS platform.
+	// Can be set to 0 for scale-from-zero for AWS and Azure platforms.
 	// Must be >= 0 and <= .Max.
 	//
 	// +kubebuilder:validation:Minimum=0

api/hypershift/v1beta1/zz_generated.featuregated-crd-manifests/nodepools.hypershift.openshift.io/AAA_ungated.yaml

@@ -108,7 +108,7 @@ spec:
                   min:
                     description: |-
                       min is the minimum number of nodes to maintain in the pool.
-                      Can be set to 0 for scale-from-zero for AWS platform.
+                      Can be set to 0 for scale-from-zero for AWS and Azure platforms.
                       Must be >= 0 and <= .Max.
                     format: int32
                     minimum: 0
@@ -1518,9 +1518,9 @@ spec:
               rule: '!has(self.platform.aws) || !has(self.platform.aws.imageType)
                 || self.platform.aws.imageType != ''Windows'' || self.arch == ''amd64'''
             - message: Scale-from-zero (autoScaling.min=0) is currently only supported
-                for AWS platform
+                for AWS and Azure platforms
               rule: '!has(self.autoScaling) || self.autoScaling.min > 0 || self.platform.type
-                == ''AWS'''
+                == ''AWS'' || self.platform.type == ''Azure'''
           status:
             description: status is the latest observed status of the NodePool.
             properties:

api/hypershift/v1beta1/zz_generated.featuregated-crd-manifests/nodepools.hypershift.openshift.io/GCPPlatform.yaml

@@ -108,7 +108,7 @@ spec:
                   min:
                     description: |-
                       min is the minimum number of nodes to maintain in the pool.
-                      Can be set to 0 for scale-from-zero for AWS platform.
+                      Can be set to 0 for scale-from-zero for AWS and Azure platforms.
                       Must be >= 0 and <= .Max.
                     format: int32
                     minimum: 0
@@ -1787,9 +1787,9 @@ spec:
               rule: '!has(self.platform.aws) || !has(self.platform.aws.imageType)
                 || self.platform.aws.imageType != ''Windows'' || self.arch == ''amd64'''
             - message: Scale-from-zero (autoScaling.min=0) is currently only supported
-                for AWS platform
+                for AWS and Azure platforms
               rule: '!has(self.autoScaling) || self.autoScaling.min > 0 || self.platform.type
-                == ''AWS'''
+                == ''AWS'' || self.platform.type == ''Azure'''
           status:
             description: status is the latest observed status of the NodePool.
             properties:

api/hypershift/v1beta1/zz_generated.featuregated-crd-manifests/nodepools.hypershift.openshift.io/OpenStack.yaml

@@ -108,7 +108,7 @@ spec:
                   min:
                     description: |-
                       min is the minimum number of nodes to maintain in the pool.
-                      Can be set to 0 for scale-from-zero for AWS platform.
+                      Can be set to 0 for scale-from-zero for AWS and Azure platforms.
                       Must be >= 0 and <= .Max.
                     format: int32
                     minimum: 0
@@ -1705,9 +1705,9 @@ spec:
               rule: '!has(self.platform.aws) || !has(self.platform.aws.imageType)
                 || self.platform.aws.imageType != ''Windows'' || self.arch == ''amd64'''
             - message: Scale-from-zero (autoScaling.min=0) is currently only supported
-                for AWS platform
+                for AWS and Azure platforms
               rule: '!has(self.autoScaling) || self.autoScaling.min > 0 || self.platform.type
-                == ''AWS'''
+                == ''AWS'' || self.platform.type == ''Azure'''
           status:
             description: status is the latest observed status of the NodePool.
             properties:

cmd/install/assets/crds/hypershift-operator/tests/nodepools.hypershift.openshift.io/stable.nodepools.autoscaling.testsuite.yaml

@@ -31,7 +31,7 @@ tests:
               id: "subnet-01234567"
           type: AWS
 
-  - name: when autoScaling min=0 on Azure platform it should fail
+  - name: when autoScaling min=0 on Azure platform it should pass
     initial: |
       apiVersion: hypershift.openshift.io/v1beta1
       kind: NodePool
@@ -56,7 +56,6 @@ tests:
               diskStorageAccountType: Premium_LRS
             subnetID: "/subscriptions/12345678-1234-5678-9012-123456789012/resourceGroups/test-rg/providers/Microsoft.Network/virtualNetworks/test-vnet/subnets/test-subnet"
           type: Azure
-    expectedError: "Scale-from-zero (autoScaling.min=0) is currently only supported for AWS platform"
 
   - name: when autoScaling min=0 on Agent platform it should fail
     initial: |
@@ -77,7 +76,7 @@ tests:
           agent: {}
           type: Agent
 
-    expectedError: "Scale-from-zero (autoScaling.min=0) is currently only supported for AWS platform"
+    expectedError: "Scale-from-zero (autoScaling.min=0) is currently only supported for AWS and Azure platforms"
 
   - name: when autoScaling min=0 on KubeVirt platform it should fail
     initial: |
@@ -101,7 +100,7 @@ tests:
               persistent:
                 size: 32Gi
           type: KubeVirt
-    expectedError: "Scale-from-zero (autoScaling.min=0) is currently only supported for AWS platform"
+    expectedError: "Scale-from-zero (autoScaling.min=0) is currently only supported for AWS and Azure platforms"
 
   - name: when autoScaling min=1 on Azure platform it should pass
     initial: |

cmd/install/install.go

@@ -291,18 +291,15 @@ func (o *Options) validateScaleFromZeroConfig() []error {
 		return nil
 	}
 	var errs []error
-	supportedProviders := set.New("aws")
-	// Check mutual exclusivity - only one of file or secret should be provided
+	supportedProviders := set.New("aws", "azure")
 	if len(o.ScaleFromZeroCreds) != 0 && len(o.ScaleFromZeroCredentialsSecret) != 0 {
 		errs = append(errs, fmt.Errorf("only one of --scale-from-zero-creds or --scale-from-zero-secret is supported"))
 	}
-	// Provider is required when using scale-from-zero credentials
 	if len(o.ScaleFromZeroProvider) == 0 {
 		errs = append(errs, fmt.Errorf("--scale-from-zero-provider is required when using scale-from-zero credentials"))
 	} else if !supportedProviders.Has(o.ScaleFromZeroProvider) {
 		errs = append(errs, fmt.Errorf("invalid --scale-from-zero-provider: %s (must be one of: %v)", o.ScaleFromZeroProvider, supportedProviders.UnsortedList()))
 	}
-	// Validate credentials file exists and is accessible if provided
 	if len(o.ScaleFromZeroCreds) > 0 {
 		if _, err := os.Stat(o.ScaleFromZeroCreds); err != nil {
 			if os.IsNotExist(err) {
@@ -435,7 +432,7 @@ func NewCommand() *cobra.Command {
 	cmd.PersistentFlags().StringSliceVar(&opts.PlatformsToInstall, "limit-crd-install", opts.PlatformsToInstall, "Used to limit the CRDs that are installed to a per platform basis (example: --limit-crd-install=AWS,Azure). If this flag is not specified, all CRDs for all platforms will be installed. Valid, case-insensitive values are: AWS, Azure, IBMCloud, KubeVirt, Agent, OpenStack, GCP.")
 	cmd.PersistentFlags().StringToStringVar(&opts.AdditionalOperatorEnvVars, "additional-operator-env-vars", opts.AdditionalOperatorEnvVars, "Set of additional environment variables to be set on the HyperShift Operator deployment.")
 	cmd.PersistentFlags().BoolVar(&opts.EnableAuditLogPersistence, "enable-audit-log-persistence", opts.EnableAuditLogPersistence, "If true, enables persistent audit logs with automatic snapshots for kube-apiserver pods")
-	cmd.PersistentFlags().StringVar(&opts.ScaleFromZeroProvider, "scale-from-zero-provider", opts.ScaleFromZeroProvider, "Platform type for scale-from-zero autoscaling (aws)")
+	cmd.PersistentFlags().StringVar(&opts.ScaleFromZeroProvider, "scale-from-zero-provider", opts.ScaleFromZeroProvider, "Platform type for scale-from-zero autoscaling (aws, azure)")
 	cmd.PersistentFlags().StringVar(&opts.ScaleFromZeroCreds, "scale-from-zero-creds", opts.ScaleFromZeroCreds, "Path to credentials file for scale-from-zero instance type queries")
 	cmd.PersistentFlags().StringVar(&opts.ScaleFromZeroCredentialsSecret, "scale-from-zero-secret", opts.ScaleFromZeroCredentialsSecret, "Name of existing secret containing scale-from-zero credentials (alternative to --scale-from-zero-creds)")
 	cmd.PersistentFlags().StringVar(&opts.ScaleFromZeroCredentialsSecretKey, "scale-from-zero-secret-key", opts.ScaleFromZeroCredentialsSecretKey, "Key within the scale-from-zero credentials secret (default: credentials)")

go.mod

@@ -6,6 +6,7 @@ require (
 	github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.1
 	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1
 	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/authorization/armauthorization/v2 v2.2.0
+	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/compute/armcompute/v5 v5.7.0
 	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/dns/armdns v1.2.0
 	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/msi/armmsi v1.3.0
 	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/network/armnetwork/v5 v5.2.0
@@ -137,7 +138,6 @@ require (
 	cloud.google.com/go/compute/metadata v0.9.0 // indirect
 	cyphar.com/go-pathrs v0.2.1 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/internal v1.12.0 // indirect
-	github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/compute/armcompute/v5 v5.7.0 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/azsecrets v1.4.0 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/security/keyvault/internal v1.2.0 // indirect
 	github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c // indirect

hypershift-operator/controllers/nodepool/capi.go

@@ -51,7 +51,8 @@ const (
 // and let nodepool, hostedcluster, and client be fields of CAPI / interface methods.
 type CAPI struct {
 	*Token
-	capiClusterName string
+	capiClusterName       string
+	scaleFromZeroPlatform hyperv1.PlatformType
 	upsert.ApplyProvider
 }
 
@@ -472,7 +473,7 @@ func (c *CAPI) reconcileMachineDeployment(ctx context.Context, log logr.Logger,
 		}
 	}
 
-	setMachineDeploymentReplicas(nodePool, machineDeployment)
+	setMachineDeploymentReplicas(nodePool, machineDeployment, c.scaleFromZeroPlatform)
 
 	if updated := c.propagateVersionAndTemplate(log, machineDeployment, machineTemplateCR); updated {
 		return nil
@@ -756,7 +757,7 @@ func (c *CAPI) reconcileMachineHealthCheck(ctx context.Context,
 
 // setMachineDeploymentReplicas sets wanted replicas:
 // If autoscaling is enabled we reconcile min/max annotations and leave replicas untouched.
-func setMachineDeploymentReplicas(nodePool *hyperv1.NodePool, machineDeployment *capiv1.MachineDeployment) {
+func setMachineDeploymentReplicas(nodePool *hyperv1.NodePool, machineDeployment *capiv1.MachineDeployment, scaleFromZeroPlatform hyperv1.PlatformType) {
 	if machineDeployment.Annotations == nil {
 		machineDeployment.Annotations = make(map[string]string)
 	}
@@ -773,7 +774,7 @@ func setMachineDeploymentReplicas(nodePool *hyperv1.NodePool, machineDeployment
 		// NodePools from being permanently stuck at 0 replicas on platforms that don't support
 		// scale-from-zero metadata.
 		effectiveMin := ptr.Deref(nodePool.Spec.AutoScaling.Min, 0)
-		if effectiveMin == 0 && nodePool.Spec.Platform.Type != hyperv1.AWSPlatform {
+		if effectiveMin == 0 && nodePool.Spec.Platform.Type != hyperv1.AWSPlatform && nodePool.Spec.Platform.Type != scaleFromZeroPlatform {
 			effectiveMin = 1
 		}
 
@@ -957,7 +958,7 @@ func (c *CAPI) reconcileMachineSet(ctx context.Context,
 	}
 	machineSet.Spec.Template.Annotations[nodePoolAnnotationTaints] = taintsInJSON
 
-	setMachineSetReplicas(nodePool, machineSet)
+	setMachineSetReplicas(nodePool, machineSet, c.scaleFromZeroPlatform)
 
 	isUpdating := false
 	// Propagate version and userData Secret to the MachineSet.
@@ -1064,7 +1065,7 @@ func machineSetInPlaceRolloutIsComplete(machineSet *capiv1.MachineSet) bool {
 
 // setMachineSetReplicas sets wanted replicas:
 // If autoscaling is enabled we reconcile min/max annotations and leave replicas untouched.
-func setMachineSetReplicas(nodePool *hyperv1.NodePool, machineSet *capiv1.MachineSet) {
+func setMachineSetReplicas(nodePool *hyperv1.NodePool, machineSet *capiv1.MachineSet, scaleFromZeroPlatform hyperv1.PlatformType) {
 	if machineSet.Annotations == nil {
 		machineSet.Annotations = make(map[string]string)
 	}
@@ -1081,7 +1082,7 @@ func setMachineSetReplicas(nodePool *hyperv1.NodePool, machineSet *capiv1.Machin
 		// NodePools from being permanently stuck at 0 replicas on platforms that don't support
 		// scale-from-zero metadata.
 		effectiveMin := ptr.Deref(nodePool.Spec.AutoScaling.Min, 0)
-		if effectiveMin == 0 && nodePool.Spec.Platform.Type != hyperv1.AWSPlatform {
+		if effectiveMin == 0 && nodePool.Spec.Platform.Type != hyperv1.AWSPlatform && nodePool.Spec.Platform.Type != scaleFromZeroPlatform {
 			effectiveMin = 1
 		}