Add csinode limit awareness in cluster-autoscaler

cluster-autoscaler/Dockerfile

@@ -11,7 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-FROM --platform=$BUILDPLATFORM golang:1.24 AS builder
+FROM --platform=$BUILDPLATFORM golang:1.25 AS builder
 
 WORKDIR /workspace
 

cluster-autoscaler/apis/go.mod

@@ -1,61 +1,60 @@
 module k8s.io/autoscaler/cluster-autoscaler/apis
 
-go 1.24.0
+go 1.25.0
 
 require (
-	github.com/onsi/ginkgo/v2 v2.21.0
-	github.com/onsi/gomega v1.35.1
-	k8s.io/apimachinery v0.34.1
-	k8s.io/client-go v0.34.1
-	k8s.io/code-generator v0.34.1
+	github.com/onsi/ginkgo/v2 v2.27.2
+	github.com/onsi/gomega v1.38.2
+	k8s.io/apimachinery v0.35.0-beta.0
+	k8s.io/client-go v0.35.0-beta.0
+	k8s.io/code-generator v0.35.0-beta.0
 	sigs.k8s.io/structured-merge-diff/v6 v6.3.0
 )
 
 require (
+	github.com/Masterminds/semver/v3 v3.4.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/emicklei/go-restful/v3 v3.12.2 // indirect
 	github.com/fxamacker/cbor/v2 v2.9.0 // indirect
-	github.com/go-logr/logr v1.4.2 // indirect
+	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-openapi/jsonpointer v0.21.0 // indirect
 	github.com/go-openapi/jsonreference v0.20.2 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
 	github.com/go-task/slim-sprig/v3 v3.0.0 // indirect
-	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/google/gnostic-models v0.7.0 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
-	github.com/google/pprof v0.0.0-20241029153458-d1b30febd7db // indirect
+	github.com/google/pprof v0.0.0-20250403155104-27863c87afa6 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
-	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
-	github.com/spf13/pflag v1.0.6 // indirect
+	github.com/spf13/pflag v1.0.9 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
-	go.yaml.in/yaml/v2 v2.4.2 // indirect
+	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
-	golang.org/x/mod v0.21.0 // indirect
-	golang.org/x/net v0.38.0 // indirect
-	golang.org/x/oauth2 v0.27.0 // indirect
-	golang.org/x/sync v0.12.0 // indirect
-	golang.org/x/sys v0.31.0 // indirect
-	golang.org/x/term v0.30.0 // indirect
-	golang.org/x/text v0.23.0 // indirect
+	golang.org/x/mod v0.28.0 // indirect
+	golang.org/x/net v0.43.0 // indirect
+	golang.org/x/oauth2 v0.30.0 // indirect
+	golang.org/x/sync v0.17.0 // indirect
+	golang.org/x/sys v0.37.0 // indirect
+	golang.org/x/term v0.36.0 // indirect
+	golang.org/x/text v0.29.0 // indirect
 	golang.org/x/time v0.9.0 // indirect
-	golang.org/x/tools v0.26.0 // indirect
-	google.golang.org/protobuf v1.36.5 // indirect
-	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
+	golang.org/x/tools v0.36.0 // indirect
+	google.golang.org/protobuf v1.36.8 // indirect
+	gopkg.in/evanphx/json-patch.v4 v4.13.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	k8s.io/api v0.34.1 // indirect
-	k8s.io/gengo/v2 v2.0.0-20250604051438-85fd79dbfd9f // indirect
+	k8s.io/api v0.35.0-beta.0 // indirect
+	k8s.io/gengo/v2 v2.0.0-20250922181213-ec3ebc5fd46b // indirect
 	k8s.io/klog/v2 v2.130.1 // indirect
-	k8s.io/kube-openapi v0.0.0-20250710124328-f3f2b991d03b // indirect
-	k8s.io/utils v0.0.0-20250604170112-4c0f3b243397 // indirect
-	sigs.k8s.io/json v0.0.0-20241014173422-cfa47c3a1cc8 // indirect
+	k8s.io/kube-openapi v0.0.0-20250910181357-589584f1c912 // indirect
+	k8s.io/utils v0.0.0-20251002143259-bc988d571ff4 // indirect
+	sigs.k8s.io/json v0.0.0-20250730193827-2d320260d730 // indirect
 	sigs.k8s.io/randfill v1.0.0 // indirect
 	sigs.k8s.io/yaml v1.6.0 // indirect
 )

cluster-autoscaler/cloudprovider/azure/test/go.sum

@@ -484,4 +484,4 @@ sigs.k8s.io/randfill v1.0.0/go.mod h1:XeLlZ/jmk4i1HRopwe7/aU3H5n1zNUcX6TM94b3QxO
 sigs.k8s.io/structured-merge-diff/v4 v4.7.0 h1:qPeWmscJcXP0snki5IYF79Z8xrl8ETFxgMd7wez1XkI=
 sigs.k8s.io/structured-merge-diff/v4 v4.7.0/go.mod h1:dDy58f92j70zLsuZVuUX5Wp9vtxXpaZnkPGWeqDfCps=
 sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
-sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=
+sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=

cluster-autoscaler/cloudprovider/clusterapi/README.md

@@ -307,6 +307,30 @@ metadata:
 > Please see the [Cluster API Book chapter on Metadata propagation](https://cluster-api.sigs.k8s.io/reference/api/metadata-propagation)
 > for more information.
 
+
+#### Pre-defined csi driver information on nodes scaled from zero
+
+To provide CSI driver information for scale from zero, the optional
+capacity annotation may be supplied as a comma separated list of driver name
+and volume limit key/value pairs, as demonstrated in the example below:
+
+```yaml
+apiVersion: cluster.x-k8s.io/v1alpha4
+kind: MachineDeployment
+metadata:
+  annotations:
+    cluster.x-k8s.io/cluster-api-autoscaler-node-group-max-size: "5"
+    cluster.x-k8s.io/cluster-api-autoscaler-node-group-min-size: "0"
+    capacity.cluster-autoscaler.kubernetes.io/memory: "128G"
+    capacity.cluster-autoscaler.kubernetes.io/cpu: "16"
+    capacity.cluster-autoscaler.kubernetes.io/csi-driver: "ebs.csi.aws.com=25,efs.csi.aws.com=16"
+```
+
+> Note: The CSI driver information supplied through the capacity annotation
+> specifies which CSI drivers will be installed on nodes scaled from zero, along
+> with their respective volume limits. The format is `driver-name=volume-limit`
+> with multiple drivers separated by commas.
+
 #### Per-NodeGroup autoscaling options
 
 Custom autoscaling options per node group (MachineDeployment/MachinePool/MachineSet) can be specified as annoations with a common prefix:
@@ -328,14 +352,14 @@ metadata:
     cluster.x-k8s.io/autoscaling-options-maxnodeprovisiontime: "20m0s"
 ```
 
-#### CPU Architecture awareness for single-arch clusters 
+#### CPU Architecture awareness for single-arch clusters
 
-Users of single-arch non-amd64 clusters who are using scale from zero 
+Users of single-arch non-amd64 clusters who are using scale from zero
 support should also set the `CAPI_SCALE_ZERO_DEFAULT_ARCH` environment variable
 to set the architecture of the nodes they want to default the node group templates to.
-The autoscaler will default to `amd64` if it is not set, and the node 
-group templates may not match the nodes' architecture, specifically when 
-the workload triggering the scale-up uses a node affinity predicate checking 
+The autoscaler will default to `amd64` if it is not set, and the node
+group templates may not match the nodes' architecture, specifically when
+the workload triggering the scale-up uses a node affinity predicate checking
 for the node's architecture.
 
 ## Specifying a Custom Resource Group

cluster-autoscaler/cloudprovider/clusterapi/clusterapi_nodegroup.go

@@ -380,8 +380,12 @@ func (ng *nodegroup) TemplateNodeInfo() (*framework.NodeInfo, error) {
 	if err != nil {
 		return nil, err
 	}
+	csiNode := ng.scalableResource.InstanceCSINode()
 
 	nodeInfo := framework.NewNodeInfo(&node, resourceSlices, &framework.PodInfo{Pod: cloudprovider.BuildKubeProxy(ng.scalableResource.Name())})
+	if csiNode != nil {
+		nodeInfo.AddCSINode(csiNode)
+	}
 	return nodeInfo, nil
 }
 

cluster-autoscaler/cloudprovider/clusterapi/clusterapi_nodegroup_test.go

@@ -27,13 +27,15 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	corev1 "k8s.io/api/core/v1"
+	storagev1 "k8s.io/api/storage/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/apis/meta/v1/unstructured"
 	"k8s.io/apimachinery/pkg/util/wait"
 	"k8s.io/autoscaler/cluster-autoscaler/cloudprovider"
 	"k8s.io/autoscaler/cluster-autoscaler/config"
 	gpuapis "k8s.io/autoscaler/cluster-autoscaler/utils/gpu"
 	"k8s.io/client-go/tools/cache"
+	"k8s.io/utils/ptr"
 )
 
 const (
@@ -1500,6 +1502,7 @@ func TestNodeGroupTemplateNodeInfo(t *testing.T) {
 		expectedCapacity      map[corev1.ResourceName]int64
 		expectedNodeLabels    map[string]string
 		expectedResourceSlice testResourceSlice
+		expectedCSINode       *storagev1.CSINode
 	}
 
 	testCases := []struct {
@@ -1650,6 +1653,49 @@ func TestNodeGroupTemplateNodeInfo(t *testing.T) {
 				},
 			},
 		},
+		{
+			name: "When the NodeGroup can scale from zero and CSI driver annotations are present, it creates CSINode with driver information",
+			nodeGroupAnnotations: map[string]string{
+				memoryKey:    "2048Mi",
+				cpuKey:       "2",
+				csiDriverKey: "ebs.csi.aws.com=25,efs.csi.aws.com=16",
+			},
+			config: testCaseConfig{
+				expectedErr: nil,
+				nodeLabels: map[string]string{
+					"kubernetes.io/os":   "linux",
+					"kubernetes.io/arch": "amd64",
+				},
+				expectedCapacity: map[corev1.ResourceName]int64{
+					corev1.ResourceCPU:    2,
+					corev1.ResourceMemory: 2048 * 1024 * 1024,
+					corev1.ResourcePods:   110,
+				},
+				expectedNodeLabels: map[string]string{
+					"kubernetes.io/os":       "linux",
+					"kubernetes.io/arch":     "amd64",
+					"kubernetes.io/hostname": "random value",
+				},
+				expectedCSINode: &storagev1.CSINode{
+					Spec: storagev1.CSINodeSpec{
+						Drivers: []storagev1.CSINodeDriver{
+							{
+								Name: "ebs.csi.aws.com",
+								Allocatable: &storagev1.VolumeNodeResources{
+									Count: ptr.To(int32(25)),
+								},
+							},
+							{
+								Name: "efs.csi.aws.com",
+								Allocatable: &storagev1.VolumeNodeResources{
+									Count: ptr.To(int32(16)),
+								},
+							},
+						},
+					},
+				},
+			},
+		},
 	}
 
 	test := func(t *testing.T, testConfig *TestConfig, config testCaseConfig) {
@@ -1726,6 +1772,55 @@ func TestNodeGroupTemplateNodeInfo(t *testing.T) {
 				}
 			}
 		}
+
+		// Validate CSINode if expected
+		if config.expectedCSINode != nil {
+			if nodeInfo.CSINode == nil {
+				t.Errorf("Expected CSINode to be set, but got nil")
+			} else {
+				expectedDrivers := config.expectedCSINode.Spec.Drivers
+				gotDrivers := nodeInfo.CSINode.Spec.Drivers
+				if len(expectedDrivers) != len(gotDrivers) {
+					t.Errorf("Expected %d CSI drivers, but got %d", len(expectedDrivers), len(gotDrivers))
+				} else {
+					for i, expectedDriver := range expectedDrivers {
+						if i >= len(gotDrivers) {
+							t.Errorf("Expected driver at index %d but got only %d drivers", i, len(gotDrivers))
+							break
+						}
+						gotDriver := gotDrivers[i]
+						if expectedDriver.Name != gotDriver.Name {
+							t.Errorf("Expected CSI driver name at index %d to be %s, but got %s", i, expectedDriver.Name, gotDriver.Name)
+						}
+						if expectedDriver.Allocatable == nil {
+							if gotDriver.Allocatable != nil {
+								t.Errorf("Expected CSI driver Allocatable at index %d to be nil, but got non-nil", i)
+							}
+						} else {
+							if gotDriver.Allocatable == nil {
+								t.Errorf("Expected CSI driver Allocatable at index %d to be non-nil, but got nil", i)
+							} else {
+								if expectedDriver.Allocatable.Count == nil {
+									if gotDriver.Allocatable.Count != nil {
+										t.Errorf("Expected CSI driver Count at index %d to be nil, but got %d", i, *gotDriver.Allocatable.Count)
+									}
+								} else {
+									if gotDriver.Allocatable.Count == nil {
+										t.Errorf("Expected CSI driver Count at index %d to be %d, but got nil", i, *expectedDriver.Allocatable.Count)
+									} else if *expectedDriver.Allocatable.Count != *gotDriver.Allocatable.Count {
+										t.Errorf("Expected CSI driver Count at index %d to be %d, but got %d", i, *expectedDriver.Allocatable.Count, *gotDriver.Allocatable.Count)
+									}
+								}
+							}
+						}
+					}
+				}
+			}
+		} else {
+			if nodeInfo.CSINode != nil {
+				t.Errorf("Expected CSINode to be nil, but got non-nil with %d drivers", len(nodeInfo.CSINode.Spec.Drivers))
+			}
+		}
 	}
 
 	for _, tc := range testCases {