Merge branch 'kubernetes:master' into prachigandhi/azure-getvmss-spot

cluster-autoscaler/FAQ.md

@@ -1183,9 +1183,11 @@ sub-library. It can be used with custom kubernetes fork, by default it uses
 Example execution looks like this:
 
 ```
-./hack/update-vendor.sh 1.20.0-alpha.1 [email protected]:kubernetes/kubernetes.git
+./hack/update-deps.sh v1.30.2 v1.30.2 [email protected]:kubernetes/kubernetes.git
 ```
 
+The first of two versions denotes k8s dependency of Cluster Autoscaler, the second one refers to the apis/ submodule.
+
 If you need to update vendor to an unreleased commit of Kubernetes, you can use the breakglass script:
 
 ```

cluster-autoscaler/README.md

@@ -90,12 +90,12 @@ target ETA and the actual releases.
 
 | Date       | Maintainer Preparing Release | Backup Maintainer | Type  |
 |------------|------------------------------|-------------------|-------|
-| 2024-01-17 | MaciekPytel                  | gjtempleton       | patch |
-| 2024-03-13 | gjtempleton                  | BigDarkClown      | patch |
-| 2024-04-17 | towca                        | BigDarkClown      | 1.30  |
-| 2024-05-22 | BigDarkClown                 | x13n              | patch |
-| 2024-07-24 | x13n                         | MaciekPytel       | patch |
+| 2024-07-18 | x13n                         | MaciekPytel       | patch |
 | 2024-08-21 | MaciekPytel                  | gjtempleton       | 1.31  |
+| 2024-09-18 | gjtempleton                  | towca             | patch |
+| 2024-11-20 | towca                        | BigDarkClown      | patch |
+| 2024-12-18 | BigDarkClown                 | x13n              | 1.32  |
+| 2025-01-22 | x13n                         | MaciekPytel       | patch |
 
 Additional patch releases may happen outside of the schedule in case of critical
 bugs or vulnerabilities.

cluster-autoscaler/cloudprovider/aws/README.md

@@ -48,7 +48,6 @@ should be updated to restrict the resources/add conditionals:
         "autoscaling:DescribeAutoScalingInstances",
         "autoscaling:DescribeLaunchConfigurations",
         "autoscaling:DescribeScalingActivities",
-        "autoscaling:DescribeTags",
         "ec2:DescribeImages",
         "ec2:DescribeInstanceTypes",
         "ec2:DescribeLaunchTemplateVersions",

cluster-autoscaler/cloudprovider/aws/ec2_instance_types.go

@@ -28,7 +28,7 @@ type InstanceType struct {
 }
 
 // StaticListLastUpdateTime is a string declaring the last time the static list was updated.
-var StaticListLastUpdateTime = "2024-04-08"
+var StaticListLastUpdateTime = "2024-07-15"
 
 // InstanceTypes is a map of ec2 resources
 var InstanceTypes = map[string]*InstanceType{
@@ -1110,6 +1110,13 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "arm64",
 	},
+	"c7gd.metal": {
+		InstanceType: "c7gd.metal",
+		VCPU:         64,
+		MemoryMb:     131072,
+		GPU:          0,
+		Architecture: "arm64",
+	},
 	"c7gd.xlarge": {
 		InstanceType: "c7gd.xlarge",
 		VCPU:         4,
@@ -1166,6 +1173,13 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "arm64",
 	},
+	"c7gn.metal": {
+		InstanceType: "c7gn.metal",
+		VCPU:         64,
+		MemoryMb:     131072,
+		GPU:          0,
+		Architecture: "arm64",
+	},
 	"c7gn.xlarge": {
 		InstanceType: "c7gn.xlarge",
 		VCPU:         4,
@@ -1376,20 +1390,6 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "amd64",
 	},
-	"g2.2xlarge": {
-		InstanceType: "g2.2xlarge",
-		VCPU:         8,
-		MemoryMb:     15360,
-		GPU:          1,
-		Architecture: "amd64",
-	},
-	"g2.8xlarge": {
-		InstanceType: "g2.8xlarge",
-		VCPU:         32,
-		MemoryMb:     61440,
-		GPU:          4,
-		Architecture: "amd64",
-	},
 	"g3.16xlarge": {
 		InstanceType: "g3.16xlarge",
 		VCPU:         64,
@@ -3315,6 +3315,13 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "arm64",
 	},
+	"m7gd.metal": {
+		InstanceType: "m7gd.metal",
+		VCPU:         64,
+		MemoryMb:     262144,
+		GPU:          0,
+		Architecture: "arm64",
+	},
 	"m7gd.xlarge": {
 		InstanceType: "m7gd.xlarge",
 		VCPU:         4,
@@ -3441,13 +3448,27 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "amd64",
 	},
+	"mac2-m1ultra.metal": {
+		InstanceType: "mac2-m1ultra.metal",
+		VCPU:         20,
+		MemoryMb:     131072,
+		GPU:          0,
+		Architecture: "amd64",
+	},
 	"mac2-m2.metal": {
 		InstanceType: "mac2-m2.metal",
 		VCPU:         8,
 		MemoryMb:     24576,
 		GPU:          0,
 		Architecture: "amd64",
 	},
+	"mac2-m2pro.metal": {
+		InstanceType: "mac2-m2pro.metal",
+		VCPU:         12,
+		MemoryMb:     32768,
+		GPU:          0,
+		Architecture: "amd64",
+	},
 	"mac2.metal": {
 		InstanceType: "mac2.metal",
 		VCPU:         8,
@@ -4662,7 +4683,7 @@ var InstanceTypes = map[string]*InstanceType{
 	"r7gd.12xlarge": {
 		InstanceType: "r7gd.12xlarge",
 		VCPU:         48,
-		MemoryMb:     262144,
+		MemoryMb:     393216,
 		GPU:          0,
 		Architecture: "arm64",
 	},
@@ -4690,7 +4711,7 @@ var InstanceTypes = map[string]*InstanceType{
 	"r7gd.8xlarge": {
 		InstanceType: "r7gd.8xlarge",
 		VCPU:         32,
-		MemoryMb:     196608,
+		MemoryMb:     262144,
 		GPU:          0,
 		Architecture: "arm64",
 	},
@@ -4708,6 +4729,13 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "arm64",
 	},
+	"r7gd.metal": {
+		InstanceType: "r7gd.metal",
+		VCPU:         64,
+		MemoryMb:     524288,
+		GPU:          0,
+		Architecture: "arm64",
+	},
 	"r7gd.xlarge": {
 		InstanceType: "r7gd.xlarge",
 		VCPU:         4,
@@ -4862,6 +4890,90 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "amd64",
 	},
+	"r8g.12xlarge": {
+		InstanceType: "r8g.12xlarge",
+		VCPU:         48,
+		MemoryMb:     393216,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.16xlarge": {
+		InstanceType: "r8g.16xlarge",
+		VCPU:         64,
+		MemoryMb:     524288,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.24xlarge": {
+		InstanceType: "r8g.24xlarge",
+		VCPU:         96,
+		MemoryMb:     786432,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.2xlarge": {
+		InstanceType: "r8g.2xlarge",
+		VCPU:         8,
+		MemoryMb:     65536,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.48xlarge": {
+		InstanceType: "r8g.48xlarge",
+		VCPU:         192,
+		MemoryMb:     1572864,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.4xlarge": {
+		InstanceType: "r8g.4xlarge",
+		VCPU:         16,
+		MemoryMb:     131072,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.8xlarge": {
+		InstanceType: "r8g.8xlarge",
+		VCPU:         32,
+		MemoryMb:     262144,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.large": {
+		InstanceType: "r8g.large",
+		VCPU:         2,
+		MemoryMb:     16384,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.medium": {
+		InstanceType: "r8g.medium",
+		VCPU:         1,
+		MemoryMb:     8192,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.metal-24xl": {
+		InstanceType: "r8g.metal-24xl",
+		VCPU:         96,
+		MemoryMb:     786432,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.metal-48xl": {
+		InstanceType: "r8g.metal-48xl",
+		VCPU:         192,
+		MemoryMb:     1572864,
+		GPU:          0,
+		Architecture: "arm64",
+	},
+	"r8g.xlarge": {
+		InstanceType: "r8g.xlarge",
+		VCPU:         4,
+		MemoryMb:     32768,
+		GPU:          0,
+		Architecture: "arm64",
+	},
 	"t1.micro": {
 		InstanceType: "t1.micro",
 		VCPU:         1,
@@ -5135,6 +5247,34 @@ var InstanceTypes = map[string]*InstanceType{
 		GPU:          0,
 		Architecture: "amd64",
 	},
+	"u7i-12tb.224xlarge": {
+		InstanceType: "u7i-12tb.224xlarge",
+		VCPU:         896,
+		MemoryMb:     12582912,
+		GPU:          0,
+		Architecture: "amd64",
+	},
+	"u7in-16tb.224xlarge": {
+		InstanceType: "u7in-16tb.224xlarge",
+		VCPU:         896,
+		MemoryMb:     16777216,
+		GPU:          0,
+		Architecture: "amd64",
+	},
+	"u7in-24tb.224xlarge": {
+		InstanceType: "u7in-24tb.224xlarge",
+		VCPU:         896,
+		MemoryMb:     25165824,
+		GPU:          0,
+		Architecture: "amd64",
+	},
+	"u7in-32tb.224xlarge": {
+		InstanceType: "u7in-32tb.224xlarge",
+		VCPU:         896,
+		MemoryMb:     33554432,
+		GPU:          0,
+		Architecture: "amd64",
+	},
 	"vt1.24xlarge": {
 		InstanceType: "vt1.24xlarge",
 		VCPU:         96,

cluster-autoscaler/cloudprovider/azure/azure_util.go

@@ -25,6 +25,7 @@ import (
 	"io/ioutil"
 	"net/http"
 	"net/url"
+	"os"
 	"regexp"
 	"sort"
 	"strconv"
@@ -244,7 +245,8 @@ func decodePkcs12(pkcs []byte, password string) (*x509.Certificate, *rsa.Private
 }
 
 func getUserAgentExtension() string {
-	return fmt.Sprintf("cluster-autoscaler/v%s", version.ClusterAutoscalerVersion)
+	suffix := os.Getenv("AZURE_CLUSTER_AUTOSCALER_USER_AGENT_SUFFIX")
+	return fmt.Sprintf("cluster-autoscaler%s/v%s", suffix, version.ClusterAutoscalerVersion)
 }
 
 func configureUserAgent(client *autorest.Client) {

cluster-autoscaler/cloudprovider/azure/test/Makefile

@@ -16,9 +16,9 @@ ARTIFACTS?=_artifacts
 .PHONY: test-e2e
 test-e2e: build-e2e
 	go run github.com/onsi/ginkgo/v2/ginkgo -v --trace --output-dir "$(ARTIFACTS)" --junit-report="junit.e2e_suite.1.xml" e2e -- \
-		-resource-group="$$(KUBECONFIG= kubectl get managedclusters -o jsonpath='{.items[0].status.nodeResourceGroup}')" \
-		-cluster-name="$$(KUBECONFIG= kubectl get cluster -o jsonpath='{.items[0].metadata.name}')" \
-		-client-id="$$(KUBECONFIG= kubectl get userassignedidentities -o jsonpath='{.items[0].status.clientId}')" \
+		-resource-group="$$(KUBECONFIG= kubectl get managedclusters -n default -o jsonpath='{.items[0].status.nodeResourceGroup}')" \
+		-cluster-name="$$(KUBECONFIG= kubectl get cluster -n default -o jsonpath='{.items[0].metadata.name}')" \
+		-client-id="$$(KUBECONFIG= kubectl get userassignedidentities -n default -o jsonpath='{.items[0].status.clientId}')" \
 		-cas-namespace="$(CLUSTER_AUTOSCALER_NAMESPACE)" \
 		-cas-serviceaccount-name="$(CLUSTER_AUTOSCALER_SERVICEACCOUNT_NAME)" \
 		-cas-image-repository="$(IMAGE)-$(GOARCH)" \

cluster-autoscaler/cloudprovider/azure/test/templates/cluster-template-prow-aks-aso-cluster-autoscaler.yaml

@@ -266,6 +266,7 @@ apiVersion: v1
 kind: Secret
 metadata:
   name: ${ASO_CREDENTIAL_SECRET_NAME}
+  namespace: default
 stringData:
   AZURE_SUBSCRIPTION_ID: ${AZURE_SUBSCRIPTION_ID}
   AZURE_TENANT_ID:       ${AZURE_TENANT_ID}
@@ -276,6 +277,7 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole
 metadata:
   name: capz-${CLUSTER_NAME}
+  namespace: default
   labels:
     cluster.x-k8s.io/aggregate-to-capz-manager: "true"
 rules:

cluster-autoscaler/cloudprovider/clusterapi/clusterapi_controller.go

@@ -19,6 +19,7 @@ package clusterapi
 import (
 	"fmt"
 	"os"
+	"path"
 	"strings"
 	"sync"
 
@@ -144,6 +145,7 @@ func indexNodeByProviderID(obj interface{}) ([]string, error) {
 	return []string{}, nil
 }
 
+// findMachine looks up a machine by the ID which is stored in the index as <namespace>/<name>.
 func (c *machineController) findMachine(id string) (*unstructured.Unstructured, error) {
 	return c.findResourceByKey(c.machineInformer.Informer().GetStore(), id)
 }
@@ -333,7 +335,8 @@ func (c *machineController) findMachineByProviderID(providerID normalizedProvide
 	}
 
 	machineID := node.Annotations[machineAnnotationKey]
-	return c.findMachine(machineID)
+	ns := node.Annotations[clusterNamespaceAnnotationKey]
+	return c.findMachine(path.Join(ns, machineID))
 }
 
 func isPendingMachineProviderID(providerID normalizedProviderID) bool {

cluster-autoscaler/cloudprovider/clusterapi/clusterapi_controller_test.go

@@ -458,7 +458,9 @@ func makeLinkedNodeAndMachine(i int, namespace, clusterName string, owner metav1
 		ObjectMeta: metav1.ObjectMeta{
 			Name: fmt.Sprintf("%s-%s-node-%d", namespace, owner.Name, i),
 			Annotations: map[string]string{
-				machineAnnotationKey: fmt.Sprintf("%s/%s-%s-machine-%d", namespace, namespace, owner.Name, i),
+				clusterNameAnnotationKey:      clusterName,
+				clusterNamespaceAnnotationKey: namespace,
+				machineAnnotationKey:          fmt.Sprintf("%s-%s-machine-%d", namespace, owner.Name, i),
 			},
 		},
 		Spec: corev1.NodeSpec{

cluster-autoscaler/cloudprovider/clusterapi/clusterapi_provider.go

@@ -18,6 +18,7 @@ package clusterapi
 
 import (
 	"fmt"
+	"path"
 	"reflect"
 
 	corev1 "k8s.io/api/core/v1"
@@ -81,8 +82,9 @@ func (p *provider) NodeGroupForNode(node *corev1.Node) (cloudprovider.NodeGroup,
 // HasInstance returns whether a given node has a corresponding instance in this cloud provider
 func (p *provider) HasInstance(node *corev1.Node) (bool, error) {
 	machineID := node.Annotations[machineAnnotationKey]
+	ns := node.Annotations[clusterNamespaceAnnotationKey]
 
-	machine, err := p.controller.findMachine(machineID)
+	machine, err := p.controller.findMachine(path.Join(ns, machineID))
 	if machine != nil {
 		return true, nil
 	}