Merge pull request #585 from nearora-msft/implement-distributed-snapshotting

Implement distributed snapshotting

README.md

@@ -109,6 +109,20 @@ Read more about how to install the example webhook [here](deploy/kubernetes/webh
 
 * `--port`: Secure port that the webhook listens on (default 443)
 
+### Distributed Snapshotting
+
+The distributed snapshotting feature is provided to handle snapshot operations for local volumes. To use this functionality, the snapshotter sidecar should be deployed along with the csi driver on each node so that every node manages the snapshot operations only for the volumes local to that node. This feature can be enabled by setting the following command line options to true:
+
+#### Snapshot controller option
+
+* `--enable-distributed-snapshotting`: This option lets the snapshot controller know that distributed snapshotting is enabled and the snapshotter sidecar will be running on each node. Off by default. 
+
+#### CSI external snapshotter sidecar option
+
+* `--node-deployment`: Enables the snapshotter sidecar to handle snapshot operations for the volumes local to the node on which it is deployed. Off by default. 
+
+Other than this, the NODE_NAME environment variable must be set where the CSI snapshotter sidecar is deployed. The value of NODE_NAME should be the name of the node where the sidecar is running.
+
 ### Snapshot controller command line options
 
 #### Important optional arguments that are highly recommended to be used
@@ -134,7 +148,9 @@ Read more about how to install the example webhook [here](deploy/kubernetes/webh
 
 * `--retry-interval-start`: Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default value is 1 second.
 
-*`--retry-interval-max`: Maximum retry interval of failed volume snapshot creation or deletion. Default value is 5 minutes.
+* `--retry-interval-max`: Maximum retry interval of failed volume snapshot creation or deletion. Default value is 5 minutes.
+
+* `--enable-distributed-snapshotting` : Enables each node to handle snapshots for the volumes local to that node. Off by default. It should be set to true only if `--node-deployment` parameter for the csi external snapshotter sidecar is set to true. See https://github.com/kubernetes-csi/external-snapshotter/blob/master/README.md#distributed-snapshotting for details.
 
 #### Other recognized arguments
 * `--kubeconfig <path>`: Path to Kubernetes client configuration that the snapshot controller uses to connect to Kubernetes API server. When omitted, default token provided by Kubernetes will be used. This option is useful only when the snapshot controller does not run as a Kubernetes pod, e.g. for debugging.
@@ -172,9 +188,11 @@ Read more about how to install the example webhook [here](deploy/kubernetes/webh
 
 * `--worker-threads`: Number of worker threads for running create snapshot and delete snapshot operations. Default value is 10.
 
+* `--node-deployment`: Enables deploying the sidecar controller together with a CSI driver on nodes to manage node-local volumes. Off by default. This should be set to true along with the `--enable-distributed-snapshotting` in the snapshot controller parameters to make use of distributed snapshotting. See https://github.com/kubernetes-csi/external-snapshotter/blob/master/README.md#distributed-snapshotting for details.
+
 * `--retry-interval-start`: Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default value is 1 second.
 
-*`--retry-interval-max`: Maximum retry interval of failed volume snapshot creation or deletion. Default value is 5 minutes.
+* `--retry-interval-max`: Maximum retry interval of failed volume snapshot creation or deletion. Default value is 5 minutes.
 #### Other recognized arguments
 * `--kubeconfig <path>`: Path to Kubernetes client configuration that the CSI external-snapshotter uses to connect to Kubernetes API server. When omitted, default token provided by Kubernetes will be used. This option is useful only when the external-snapshotter does not run as a Kubernetes pod, e.g. for debugging.
 

cmd/csi-snapshotter/main.go

@@ -26,8 +26,12 @@ import (
 	"strings"
 	"time"
 
+	utils "github.com/kubernetes-csi/external-snapshotter/v4/pkg/utils"
+
 	"google.golang.org/grpc"
 
+	v1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/apimachinery/pkg/labels"
 	"k8s.io/client-go/kubernetes"
 	"k8s.io/client-go/kubernetes/scheme"
 	"k8s.io/client-go/rest"
@@ -75,11 +79,12 @@ var (
 	kubeAPIQPS   = flag.Float64("kube-api-qps", 5, "QPS to use while communicating with the kubernetes apiserver. Defaults to 5.0.")
 	kubeAPIBurst = flag.Int("kube-api-burst", 10, "Burst to use while communicating with the kubernetes apiserver. Defaults to 10.")
 
-	metricsAddress     = flag.String("metrics-address", "", "(deprecated) The TCP network address where the prometheus metrics endpoint will listen (example: `:8080`). The default is empty string, which means metrics endpoint is disabled. Only one of `--metrics-address` and `--http-endpoint` can be set.")
-	httpEndpoint       = flag.String("http-endpoint", "", "The TCP network address where the HTTP server for diagnostics, including metrics and leader election health check, will listen (example: `:8080`). The default is empty string, which means the server is disabled. Only one of `--metrics-address` and `--http-endpoint` can be set.")
-	metricsPath        = flag.String("metrics-path", "/metrics", "The HTTP path where prometheus metrics will be exposed. Default is `/metrics`.")
-	retryIntervalStart = flag.Duration("retry-interval-start", time.Second, "Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default is 1 second.")
-	retryIntervalMax   = flag.Duration("retry-interval-max", 5*time.Minute, "Maximum retry interval of failed volume snapshot creation or deletion. Default is 5 minutes.")
+	metricsAddress       = flag.String("metrics-address", "", "(deprecated) The TCP network address where the prometheus metrics endpoint will listen (example: `:8080`). The default is empty string, which means metrics endpoint is disabled. Only one of `--metrics-address` and `--http-endpoint` can be set.")
+	httpEndpoint         = flag.String("http-endpoint", "", "The TCP network address where the HTTP server for diagnostics, including metrics and leader election health check, will listen (example: `:8080`). The default is empty string, which means the server is disabled. Only one of `--metrics-address` and `--http-endpoint` can be set.")
+	metricsPath          = flag.String("metrics-path", "/metrics", "The HTTP path where prometheus metrics will be exposed. Default is `/metrics`.")
+	retryIntervalStart   = flag.Duration("retry-interval-start", time.Second, "Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default is 1 second.")
+	retryIntervalMax     = flag.Duration("retry-interval-max", 5*time.Minute, "Maximum retry interval of failed volume snapshot creation or deletion. Default is 5 minutes.")
+	enableNodeDeployment = flag.Bool("node-deployment", false, "Enables deploying the sidecar controller together with a CSI driver on nodes to manage snapshots for node-local volumes.")
 )
 
 var (
@@ -98,6 +103,12 @@ func main() {
 	}
 	klog.Infof("Version: %s", version)
 
+	// If distributed snapshotting is enabled and leaderElection is also set to true, return
+	if *enableNodeDeployment && *leaderElection {
+		klog.Error("Leader election cannot happen when node-deployment is set to true")
+		os.Exit(1)
+	}
+
 	// Create the client config. Use kubeconfig if given, otherwise assume in-cluster.
 	config, err := buildConfig(*kubeconfig)
 	if err != nil {
@@ -122,6 +133,19 @@ func main() {
 
 	factory := informers.NewSharedInformerFactory(snapClient, *resyncPeriod)
 	coreFactory := coreinformers.NewSharedInformerFactory(kubeClient, *resyncPeriod)
+	var snapshotContentfactory informers.SharedInformerFactory
+	if *enableNodeDeployment {
+		node := os.Getenv("NODE_NAME")
+		if node == "" {
+			klog.Fatal("The NODE_NAME environment variable must be set when using --enable-node-deployment.")
+		}
+		snapshotContentfactory = informers.NewSharedInformerFactoryWithOptions(snapClient, *resyncPeriod, informers.WithTweakListOptions(func(lo *v1.ListOptions) {
+			lo.LabelSelector = labels.Set{utils.VolumeSnapshotContentManagedByLabel: node}.AsSelector().String()
+		}),
+		)
+	} else {
+		snapshotContentfactory = factory
+	}
 
 	// Add Snapshot types to the default Kubernetes so events can be logged for them
 	snapshotscheme.AddToScheme(scheme.Scheme)
@@ -202,7 +226,7 @@ func main() {
 		snapClient,
 		kubeClient,
 		driverName,
-		factory.Snapshot().V1().VolumeSnapshotContents(),
+		snapshotContentfactory.Snapshot().V1().VolumeSnapshotContents(),
 		factory.Snapshot().V1().VolumeSnapshotClasses(),
 		snapShotter,
 		*csiTimeout,
@@ -216,6 +240,7 @@ func main() {
 	run := func(context.Context) {
 		// run...
 		stopCh := make(chan struct{})
+		snapshotContentfactory.Start(stopCh)
 		factory.Start(stopCh)
 		coreFactory.Start(stopCh)
 		go ctrl.Run(*threads, stopCh)

cmd/snapshot-controller/main.go

@@ -27,6 +27,7 @@ import (
 	"sync"
 	"time"
 
+	v1 "k8s.io/client-go/informers/core/v1"
 	"k8s.io/client-go/kubernetes"
 	"k8s.io/client-go/kubernetes/scheme"
 	"k8s.io/client-go/rest"
@@ -64,10 +65,11 @@ var (
 	kubeAPIQPS   = flag.Float64("kube-api-qps", 5, "QPS to use while communicating with the kubernetes apiserver. Defaults to 5.0.")
 	kubeAPIBurst = flag.Int("kube-api-burst", 10, "Burst to use while communicating with the kubernetes apiserver. Defaults to 10.")
 
-	httpEndpoint       = flag.String("http-endpoint", "", "The TCP network address where the HTTP server for diagnostics, including metrics, will listen (example: :8080). The default is empty string, which means the server is disabled.")
-	metricsPath        = flag.String("metrics-path", "/metrics", "The HTTP path where prometheus metrics will be exposed. Default is `/metrics`.")
-	retryIntervalStart = flag.Duration("retry-interval-start", time.Second, "Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default is 1 second.")
-	retryIntervalMax   = flag.Duration("retry-interval-max", 5*time.Minute, "Maximum retry interval of failed volume snapshot creation or deletion. Default is 5 minutes.")
+	httpEndpoint                  = flag.String("http-endpoint", "", "The TCP network address where the HTTP server for diagnostics, including metrics, will listen (example: :8080). The default is empty string, which means the server is disabled.")
+	metricsPath                   = flag.String("metrics-path", "/metrics", "The HTTP path where prometheus metrics will be exposed. Default is `/metrics`.")
+	retryIntervalStart            = flag.Duration("retry-interval-start", time.Second, "Initial retry interval of failed volume snapshot creation or deletion. It doubles with each failure, up to retry-interval-max. Default is 1 second.")
+	retryIntervalMax              = flag.Duration("retry-interval-max", 5*time.Minute, "Maximum retry interval of failed volume snapshot creation or deletion. Default is 5 minutes.")
+	enableDistributedSnapshotting = flag.Bool("enable-distributed-snapshotting", false, "Enables each node to handle snapshotting for the local volumes created on that node")
 )
 
 var (
@@ -147,6 +149,11 @@ func main() {
 
 	factory := informers.NewSharedInformerFactory(snapClient, *resyncPeriod)
 	coreFactory := coreinformers.NewSharedInformerFactory(kubeClient, *resyncPeriod)
+	var nodeInformer v1.NodeInformer
+
+	if *enableDistributedSnapshotting {
+		nodeInformer = coreFactory.Core().V1().Nodes()
+	}
 
 	// Create and register metrics manager
 	metricsManager := metrics.NewMetricsManager()
@@ -174,10 +181,12 @@ func main() {
 		factory.Snapshot().V1().VolumeSnapshotContents(),
 		factory.Snapshot().V1().VolumeSnapshotClasses(),
 		coreFactory.Core().V1().PersistentVolumeClaims(),
+		nodeInformer,
 		metricsManager,
 		*resyncPeriod,
 		workqueue.NewItemExponentialFailureRateLimiter(*retryIntervalStart, *retryIntervalMax),
 		workqueue.NewItemExponentialFailureRateLimiter(*retryIntervalStart, *retryIntervalMax),
+		*enableDistributedSnapshotting,
 	)
 
 	if err := ensureCustomResourceDefinitionsExist(snapClient); err != nil {

deploy/kubernetes/snapshot-controller/rbac-snapshot-controller.yaml

@@ -44,7 +44,10 @@ rules:
   - apiGroups: ["snapshot.storage.k8s.io"]
     resources: ["volumesnapshots/status"]
     verbs: ["update", "patch"]
-
+  # Enable this RBAC rule only when using distributed snapshotting, i.e. when the enable-distributed-snapshotting flag is set to true
+  # - apiGroups: [""]
+  #   resources: ["nodes"]
+  #   verbs: ["get", "list", "watch"]
 ---
 kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1

go.mod

@@ -24,6 +24,7 @@ require (
 	k8s.io/apimachinery v0.23.0
 	k8s.io/client-go v0.23.0
 	k8s.io/component-base v0.23.0
+	k8s.io/component-helpers v0.23.0
 	k8s.io/klog/v2 v2.30.0
 	k8s.io/kubernetes v1.23.0
 )

go.sum

@@ -1100,6 +1100,7 @@ k8s.io/cluster-bootstrap v0.23.0/go.mod h1:VltEnKWfrRTiKgOXp3ts3vh7yqNlH6KFKFflo
 k8s.io/code-generator v0.23.0/go.mod h1:vQvOhDXhuzqiVfM/YHp+dmg10WDZCchJVObc9MvowsE=
 k8s.io/component-base v0.23.0 h1:UAnyzjvVZ2ZR1lF35YwtNY6VMN94WtOnArcXBu34es8=
 k8s.io/component-base v0.23.0/go.mod h1:DHH5uiFvLC1edCpvcTDV++NKULdYYU6pR9Tt3HIKMKI=
+k8s.io/component-helpers v0.23.0 h1:qNbqN10QTefiWcCOPkHL/0nn81sdKVv6ZgEXcSyot/U=
 k8s.io/component-helpers v0.23.0/go.mod h1:liXMh6FZS4qamKtMJQ7uLHnFe3tlC86RX5mJEk/aerg=
 k8s.io/controller-manager v0.23.0/go.mod h1:6/IKItSv6p9FY3mSbHgsOYmt4y+HDxiC5hEFg9rJVc8=
 k8s.io/cri-api v0.23.0/go.mod h1:2edENu3/mkyW3c6fVPPPaVGEFbLRacJizBbSp7ZOLOo=

pkg/common-controller/framework_test.go

@@ -838,10 +838,12 @@ func newTestController(kubeClient kubernetes.Interface, clientset clientset.Inte
 		informerFactory.Snapshot().V1().VolumeSnapshotContents(),
 		informerFactory.Snapshot().V1().VolumeSnapshotClasses(),
 		coreFactory.Core().V1().PersistentVolumeClaims(),
+		nil,
 		metricsManager,
 		60*time.Second,
 		workqueue.NewItemExponentialFailureRateLimiter(1*time.Millisecond, 1*time.Minute),
 		workqueue.NewItemExponentialFailureRateLimiter(1*time.Millisecond, 1*time.Minute),
+		false,
 	)
 
 	ctrl.eventRecorder = record.NewFakeRecorder(1000)

pkg/common-controller/snapshot_controller.go

@@ -29,6 +29,7 @@ import (
 	"k8s.io/apimachinery/pkg/labels"
 	"k8s.io/client-go/kubernetes/scheme"
 	ref "k8s.io/client-go/tools/reference"
+	corev1helpers "k8s.io/component-helpers/scheduling/corev1"
 	klog "k8s.io/klog/v2"
 
 	crdv1 "github.com/kubernetes-csi/external-snapshotter/client/v4/apis/volumesnapshot/v1"
@@ -671,6 +672,18 @@ func (ctrl *csiSnapshotCommonController) createSnapshotContent(snapshot *crdv1.V
 		},
 	}
 
+	if ctrl.enableDistributedSnapshotting {
+		nodeName, err := ctrl.getManagedByNode(volume)
+		if err != nil {
+			return nil, err
+		}
+		if nodeName != "" {
+			snapshotContent.Labels = map[string]string{
+				utils.VolumeSnapshotContentManagedByLabel: nodeName,
+			}
+		}
+	}
+
 	// Set AnnDeletionSecretRefName and AnnDeletionSecretRefNamespace
 	if snapshotterSecretRef != nil {
 		klog.V(5).Infof("createSnapshotContent: set annotation [%s] on content [%s].", utils.AnnDeletionSecretRefName, snapshotContent.Name)
@@ -1655,3 +1668,27 @@ func (ctrl *csiSnapshotCommonController) checkAndSetInvalidSnapshotLabel(snapsho
 
 	return updatedSnapshot, nil
 }
+
+func (ctrl *csiSnapshotCommonController) getManagedByNode(pv *v1.PersistentVolume) (string, error) {
+	if pv.Spec.NodeAffinity == nil {
+		klog.V(5).Infof("NodeAffinity not set for pv %s", pv.Name)
+		return "", nil
+	}
+	nodeSelectorTerms := pv.Spec.NodeAffinity.Required
+
+	nodes, err := ctrl.nodeLister.List(labels.Everything())
+	if err != nil {
+		klog.Errorf("failed to get the list of nodes: %q", err)
+		return "", err
+	}
+
+	for _, node := range nodes {
+		match, _ := corev1helpers.MatchNodeSelectorTerms(node, nodeSelectorTerms)
+		if match {
+			return node.Name, nil
+		}
+	}
+
+	klog.Errorf("failed to find nodes that match the node affinity requirements for pv[%s]", pv.Name)
+	return "", nil
+}

pkg/common-controller/snapshot_controller_base.go

@@ -57,6 +57,8 @@ type csiSnapshotCommonController struct {
 	classListerSynced    cache.InformerSynced
 	pvcLister            corelisters.PersistentVolumeClaimLister
 	pvcListerSynced      cache.InformerSynced
+	nodeLister           corelisters.NodeLister
+	nodeListerSynced     cache.InformerSynced
 
 	snapshotStore cache.Store
 	contentStore  cache.Store
@@ -64,6 +66,8 @@ type csiSnapshotCommonController struct {
 	metricsManager metrics.MetricsManager
 
 	resyncPeriod time.Duration
+
+	enableDistributedSnapshotting bool
 }
 
 // NewCSISnapshotController returns a new *csiSnapshotCommonController
@@ -74,10 +78,12 @@ func NewCSISnapshotCommonController(
 	volumeSnapshotContentInformer storageinformers.VolumeSnapshotContentInformer,
 	volumeSnapshotClassInformer storageinformers.VolumeSnapshotClassInformer,
 	pvcInformer coreinformers.PersistentVolumeClaimInformer,
+	nodeInformer coreinformers.NodeInformer,
 	metricsManager metrics.MetricsManager,
 	resyncPeriod time.Duration,
 	snapshotRateLimiter workqueue.RateLimiter,
 	contentRateLimiter workqueue.RateLimiter,
+	enableDistributedSnapshotting bool,
 ) *csiSnapshotCommonController {
 	broadcaster := record.NewBroadcaster()
 	broadcaster.StartLogging(klog.Infof)
@@ -125,6 +131,13 @@ func NewCSISnapshotCommonController(
 	ctrl.classLister = volumeSnapshotClassInformer.Lister()
 	ctrl.classListerSynced = volumeSnapshotClassInformer.Informer().HasSynced
 
+	ctrl.enableDistributedSnapshotting = enableDistributedSnapshotting
+
+	if enableDistributedSnapshotting {
+		ctrl.nodeLister = nodeInformer.Lister()
+		ctrl.nodeListerSynced = nodeInformer.Informer().HasSynced
+	}
+
 	return ctrl
 }
 
@@ -135,7 +148,12 @@ func (ctrl *csiSnapshotCommonController) Run(workers int, stopCh <-chan struct{}
 	klog.Infof("Starting snapshot controller")
 	defer klog.Infof("Shutting snapshot controller")
 
-	if !cache.WaitForCacheSync(stopCh, ctrl.snapshotListerSynced, ctrl.contentListerSynced, ctrl.classListerSynced, ctrl.pvcListerSynced) {
+	informersSynced := []cache.InformerSynced{ctrl.snapshotListerSynced, ctrl.contentListerSynced, ctrl.classListerSynced, ctrl.pvcListerSynced}
+	if ctrl.enableDistributedSnapshotting {
+		informersSynced = append(informersSynced, ctrl.nodeListerSynced)
+	}
+
+	if !cache.WaitForCacheSync(stopCh, informersSynced...) {
 		klog.Errorf("Cannot sync caches")
 		return
 	}

pkg/common-controller/snapshot_controller_test.go

@@ -21,11 +21,28 @@ import (
 
 	crdv1 "github.com/kubernetes-csi/external-snapshotter/client/v4/apis/volumesnapshot/v1"
 	"github.com/kubernetes-csi/external-snapshotter/v4/pkg/utils"
+	v1 "k8s.io/api/core/v1"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/apimachinery/pkg/labels"
 	"k8s.io/client-go/tools/cache"
 )
 
 var deletionPolicy = crdv1.VolumeSnapshotContentDelete
 
+type FakeNodeLister struct {
+	NodeList []*v1.Node
+}
+
+// List lists all Nodes in the indexer.
+// Objects returned here must be treated as read-only.
+func (l FakeNodeLister) List(selector labels.Selector) (ret []*v1.Node, err error) {
+	return l.NodeList, nil
+}
+
+func (l FakeNodeLister) Get(name string) (*v1.Node, error) {
+	return nil, nil
+}
+
 func storeVersion(t *testing.T, prefix string, c cache.Store, version string, expectedReturn bool) {
 	content := newContent("contentName", "snapuid1-1", "snap1-1", "sid1-1", classGold, "", "pv-handle-1-1", deletionPolicy, nil, nil, false, true)
 	content.ResourceVersion = version
@@ -92,3 +109,71 @@ func TestControllerCacheParsingError(t *testing.T) {
 		t.Errorf("Expected parsing error, got nil instead")
 	}
 }
+
+func TestGetManagedByNode(t *testing.T) {
+
+	// Test that a matching node is found
+
+	node1 := &v1.Node{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:   "node1",
+			Labels: map[string]string{"key1": "value1"},
+		},
+	}
+
+	node2 := &v1.Node{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:   "node2",
+			Labels: map[string]string{"key2": "value2"},
+		},
+	}
+
+	ctrl := &csiSnapshotCommonController{
+		nodeLister: FakeNodeLister{NodeList: []*v1.Node{node1, node2}},
+	}
+
+	pv := &v1.PersistentVolume{
+		Spec: v1.PersistentVolumeSpec{
+			NodeAffinity: &v1.VolumeNodeAffinity{
+				Required: &v1.NodeSelector{
+					NodeSelectorTerms: []v1.NodeSelectorTerm{
+						{
+							MatchExpressions: []v1.NodeSelectorRequirement{
+								{
+									Key:      "key1",
+									Operator: v1.NodeSelectorOpIn,
+									Values:   []string{"value1"},
+								},
+							},
+						},
+					},
+				},
+			},
+		},
+	}
+
+	nodeName, err := ctrl.getManagedByNode(pv)
+	if err != nil {
+		t.Errorf("Unexpected error occurred: %v", err)
+	}
+	if nodeName != "node1" {
+		t.Errorf("Expected node:%s , Found node: %s instead", "node1", nodeName)
+	}
+
+	// Test that no matching node is found
+
+	node1 = &v1.Node{
+		ObjectMeta: metav1.ObjectMeta{
+			Name: "node1",
+		},
+	}
+
+	ctrl = &csiSnapshotCommonController{
+		nodeLister: FakeNodeLister{NodeList: []*v1.Node{node1}},
+	}
+
+	nodeName, _ = ctrl.getManagedByNode(pv)
+	if nodeName != "" {
+		t.Errorf("Expected no node, Found node(%s)", nodeName)
+	}
+}

pkg/utils/util.go

@@ -107,6 +107,9 @@ const (
 	// VolumeSnapshotInvalidLabel is applied to invalid snapshot as a label key. The value does not matter.
 	// See https://github.com/kubernetes/enhancements/blob/master/keps/sig-storage/177-volume-snapshot/tighten-validation-webhook-crd.md#automatic-labelling-of-invalid-objects
 	VolumeSnapshotInvalidLabel = "snapshot.storage.kubernetes.io/invalid-snapshot-resource"
+	// VolumeSnapshotContentManagedByLabel is applied by the snapshot controller to the VolumeSnapshotContent object in case distributed snapshotting is enabled.
+	// The value contains the name of the node that handles the snapshot for the volume local to that node.
+	VolumeSnapshotContentManagedByLabel = "snapshot.storage.kubernetes.io/managed-by"
 )
 
 var SnapshotterSecretParams = secretParamsMap{

vendor/k8s.io/component-helpers/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   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.

vendor/k8s.io/component-helpers/scheduling/corev1/doc.go

@@ -0,0 +1,23 @@
+/*
+Copyright 2020 The Kubernetes Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+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.
+*/
+
+// Package corev1 defines functions which should satisfy one of the following:
+//
+// - Be used by more than one core component (kube-scheduler, kubelet, kube-apiserver, etc.)
+// - Be used by a core component and another kubernetes project (cluster-autoscaler, descheduler)
+//
+// And be a scheduling feature.
+package corev1 // import "k8s.io/component-helpers/scheduling/corev1"

vendor/k8s.io/component-helpers/scheduling/corev1/helpers.go

@@ -0,0 +1,101 @@
+/*
+Copyright 2020 The Kubernetes Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+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.
+*/
+
+package corev1
+
+import (
+	"encoding/json"
+
+	v1 "k8s.io/api/core/v1"
+	"k8s.io/component-helpers/scheduling/corev1/nodeaffinity"
+)
+
+// PodPriority returns priority of the given pod.
+func PodPriority(pod *v1.Pod) int32 {
+	if pod.Spec.Priority != nil {
+		return *pod.Spec.Priority
+	}
+	// When priority of a running pod is nil, it means it was created at a time
+	// that there was no global default priority class and the priority class
+	// name of the pod was empty. So, we resolve to the static default priority.
+	return 0
+}
+
+// MatchNodeSelectorTerms checks whether the node labels and fields match node selector terms in ORed;
+// nil or empty term matches no objects.
+func MatchNodeSelectorTerms(
+	node *v1.Node,
+	nodeSelector *v1.NodeSelector,
+) (bool, error) {
+	if node == nil {
+		return false, nil
+	}
+	return nodeaffinity.NewLazyErrorNodeSelector(nodeSelector).Match(node)
+}
+
+// GetAvoidPodsFromNodeAnnotations scans the list of annotations and
+// returns the pods that needs to be avoided for this node from scheduling
+func GetAvoidPodsFromNodeAnnotations(annotations map[string]string) (v1.AvoidPods, error) {
+	var avoidPods v1.AvoidPods
+	if len(annotations) > 0 && annotations[v1.PreferAvoidPodsAnnotationKey] != "" {
+		err := json.Unmarshal([]byte(annotations[v1.PreferAvoidPodsAnnotationKey]), &avoidPods)
+		if err != nil {
+			return avoidPods, err
+		}
+	}
+	return avoidPods, nil
+}
+
+// TolerationsTolerateTaint checks if taint is tolerated by any of the tolerations.
+func TolerationsTolerateTaint(tolerations []v1.Toleration, taint *v1.Taint) bool {
+	for i := range tolerations {
+		if tolerations[i].ToleratesTaint(taint) {
+			return true
+		}
+	}
+	return false
+}
+
+type taintsFilterFunc func(*v1.Taint) bool
+
+// FindMatchingUntoleratedTaint checks if the given tolerations tolerates
+// all the filtered taints, and returns the first taint without a toleration
+// Returns true if there is an untolerated taint
+// Returns false if all taints are tolerated
+func FindMatchingUntoleratedTaint(taints []v1.Taint, tolerations []v1.Toleration, inclusionFilter taintsFilterFunc) (v1.Taint, bool) {
+	filteredTaints := getFilteredTaints(taints, inclusionFilter)
+	for _, taint := range filteredTaints {
+		if !TolerationsTolerateTaint(tolerations, &taint) {
+			return taint, true
+		}
+	}
+	return v1.Taint{}, false
+}
+
+// getFilteredTaints returns a list of taints satisfying the filter predicate
+func getFilteredTaints(taints []v1.Taint, inclusionFilter taintsFilterFunc) []v1.Taint {
+	if inclusionFilter == nil {
+		return taints
+	}
+	filteredTaints := []v1.Taint{}
+	for _, taint := range taints {
+		if !inclusionFilter(&taint) {
+			continue
+		}
+		filteredTaints = append(filteredTaints, taint)
+	}
+	return filteredTaints
+}

vendor/k8s.io/component-helpers/scheduling/corev1/nodeaffinity/nodeaffinity.go

@@ -0,0 +1,324 @@
+/*
+Copyright 2020 The Kubernetes Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+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.
+*/
+
+package nodeaffinity
+
+import (
+	v1 "k8s.io/api/core/v1"
+	"k8s.io/apimachinery/pkg/fields"
+	"k8s.io/apimachinery/pkg/labels"
+	"k8s.io/apimachinery/pkg/selection"
+	"k8s.io/apimachinery/pkg/util/errors"
+	"k8s.io/apimachinery/pkg/util/validation/field"
+)
+
+// NodeSelector is a runtime representation of v1.NodeSelector.
+type NodeSelector struct {
+	lazy LazyErrorNodeSelector
+}
+
+// LazyErrorNodeSelector is a runtime representation of v1.NodeSelector that
+// only reports parse errors when no terms match.
+type LazyErrorNodeSelector struct {
+	terms []nodeSelectorTerm
+}
+
+// NewNodeSelector returns a NodeSelector or aggregate parsing errors found.
+func NewNodeSelector(ns *v1.NodeSelector, opts ...field.PathOption) (*NodeSelector, error) {
+	lazy := NewLazyErrorNodeSelector(ns, opts...)
+	var errs []error
+	for _, term := range lazy.terms {
+		if len(term.parseErrs) > 0 {
+			errs = append(errs, term.parseErrs...)
+		}
+	}
+	if len(errs) != 0 {
+		return nil, errors.Flatten(errors.NewAggregate(errs))
+	}
+	return &NodeSelector{lazy: *lazy}, nil
+}
+
+// NewLazyErrorNodeSelector creates a NodeSelector that only reports parse
+// errors when no terms match.
+func NewLazyErrorNodeSelector(ns *v1.NodeSelector, opts ...field.PathOption) *LazyErrorNodeSelector {
+	p := field.ToPath(opts...)
+	parsedTerms := make([]nodeSelectorTerm, 0, len(ns.NodeSelectorTerms))
+	path := p.Child("nodeSelectorTerms")
+	for i, term := range ns.NodeSelectorTerms {
+		// nil or empty term selects no objects
+		if isEmptyNodeSelectorTerm(&term) {
+			continue
+		}
+		p := path.Index(i)
+		parsedTerms = append(parsedTerms, newNodeSelectorTerm(&term, p))
+	}
+	return &LazyErrorNodeSelector{
+		terms: parsedTerms,
+	}
+}
+
+// Match checks whether the node labels and fields match the selector terms, ORed;
+// nil or empty term matches no objects.
+func (ns *NodeSelector) Match(node *v1.Node) bool {
+	// parse errors are reported in NewNodeSelector.
+	match, _ := ns.lazy.Match(node)
+	return match
+}
+
+// Match checks whether the node labels and fields match the selector terms, ORed;
+// nil or empty term matches no objects.
+// Parse errors are only returned if no terms matched.
+func (ns *LazyErrorNodeSelector) Match(node *v1.Node) (bool, error) {
+	if node == nil {
+		return false, nil
+	}
+	nodeLabels := labels.Set(node.Labels)
+	nodeFields := extractNodeFields(node)
+
+	var errs []error
+	for _, term := range ns.terms {
+		match, tErrs := term.match(nodeLabels, nodeFields)
+		if len(tErrs) > 0 {
+			errs = append(errs, tErrs...)
+			continue
+		}
+		if match {
+			return true, nil
+		}
+	}
+	return false, errors.Flatten(errors.NewAggregate(errs))
+}
+
+// PreferredSchedulingTerms is a runtime representation of []v1.PreferredSchedulingTerms.
+type PreferredSchedulingTerms struct {
+	terms []preferredSchedulingTerm
+}
+
+// NewPreferredSchedulingTerms returns a PreferredSchedulingTerms or all the parsing errors found.
+// If a v1.PreferredSchedulingTerm has a 0 weight, its parsing is skipped.
+func NewPreferredSchedulingTerms(terms []v1.PreferredSchedulingTerm, opts ...field.PathOption) (*PreferredSchedulingTerms, error) {
+	p := field.ToPath(opts...)
+	var errs []error
+	parsedTerms := make([]preferredSchedulingTerm, 0, len(terms))
+	for i, term := range terms {
+		path := p.Index(i)
+		if term.Weight == 0 || isEmptyNodeSelectorTerm(&term.Preference) {
+			continue
+		}
+		parsedTerm := preferredSchedulingTerm{
+			nodeSelectorTerm: newNodeSelectorTerm(&term.Preference, path),
+			weight:           int(term.Weight),
+		}
+		if len(parsedTerm.parseErrs) > 0 {
+			errs = append(errs, parsedTerm.parseErrs...)
+		} else {
+			parsedTerms = append(parsedTerms, parsedTerm)
+		}
+	}
+	if len(errs) != 0 {
+		return nil, errors.Flatten(errors.NewAggregate(errs))
+	}
+	return &PreferredSchedulingTerms{terms: parsedTerms}, nil
+}
+
+// Score returns a score for a Node: the sum of the weights of the terms that
+// match the Node.
+func (t *PreferredSchedulingTerms) Score(node *v1.Node) int64 {
+	var score int64
+	nodeLabels := labels.Set(node.Labels)
+	nodeFields := extractNodeFields(node)
+	for _, term := range t.terms {
+		// parse errors are reported in NewPreferredSchedulingTerms.
+		if ok, _ := term.match(nodeLabels, nodeFields); ok {
+			score += int64(term.weight)
+		}
+	}
+	return score
+}
+
+func isEmptyNodeSelectorTerm(term *v1.NodeSelectorTerm) bool {
+	return len(term.MatchExpressions) == 0 && len(term.MatchFields) == 0
+}
+
+func extractNodeFields(n *v1.Node) fields.Set {
+	f := make(fields.Set)
+	if len(n.Name) > 0 {
+		f["metadata.name"] = n.Name
+	}
+	return f
+}
+
+type nodeSelectorTerm struct {
+	matchLabels labels.Selector
+	matchFields fields.Selector
+	parseErrs   []error
+}
+
+func newNodeSelectorTerm(term *v1.NodeSelectorTerm, path *field.Path) nodeSelectorTerm {
+	var parsedTerm nodeSelectorTerm
+	var errs []error
+	if len(term.MatchExpressions) != 0 {
+		p := path.Child("matchExpressions")
+		parsedTerm.matchLabels, errs = nodeSelectorRequirementsAsSelector(term.MatchExpressions, p)
+		if errs != nil {
+			parsedTerm.parseErrs = append(parsedTerm.parseErrs, errs...)
+		}
+	}
+	if len(term.MatchFields) != 0 {
+		p := path.Child("matchFields")
+		parsedTerm.matchFields, errs = nodeSelectorRequirementsAsFieldSelector(term.MatchFields, p)
+		if errs != nil {
+			parsedTerm.parseErrs = append(parsedTerm.parseErrs, errs...)
+		}
+	}
+	return parsedTerm
+}
+
+func (t *nodeSelectorTerm) match(nodeLabels labels.Set, nodeFields fields.Set) (bool, []error) {
+	if t.parseErrs != nil {
+		return false, t.parseErrs
+	}
+	if t.matchLabels != nil && !t.matchLabels.Matches(nodeLabels) {
+		return false, nil
+	}
+	if t.matchFields != nil && len(nodeFields) > 0 && !t.matchFields.Matches(nodeFields) {
+		return false, nil
+	}
+	return true, nil
+}
+
+// nodeSelectorRequirementsAsSelector converts the []NodeSelectorRequirement api type into a struct that implements
+// labels.Selector.
+func nodeSelectorRequirementsAsSelector(nsm []v1.NodeSelectorRequirement, path *field.Path) (labels.Selector, []error) {
+	if len(nsm) == 0 {
+		return labels.Nothing(), nil
+	}
+	var errs []error
+	selector := labels.NewSelector()
+	for i, expr := range nsm {
+		p := path.Index(i)
+		var op selection.Operator
+		switch expr.Operator {
+		case v1.NodeSelectorOpIn:
+			op = selection.In
+		case v1.NodeSelectorOpNotIn:
+			op = selection.NotIn
+		case v1.NodeSelectorOpExists:
+			op = selection.Exists
+		case v1.NodeSelectorOpDoesNotExist:
+			op = selection.DoesNotExist
+		case v1.NodeSelectorOpGt:
+			op = selection.GreaterThan
+		case v1.NodeSelectorOpLt:
+			op = selection.LessThan
+		default:
+			errs = append(errs, field.NotSupported(p.Child("operator"), expr.Operator, nil))
+			continue
+		}
+		r, err := labels.NewRequirement(expr.Key, op, expr.Values, field.WithPath(p))
+		if err != nil {
+			errs = append(errs, err)
+		} else {
+			selector = selector.Add(*r)
+		}
+	}
+	if len(errs) != 0 {
+		return nil, errs
+	}
+	return selector, nil
+}
+
+var validFieldSelectorOperators = []string{
+	string(v1.NodeSelectorOpIn),
+	string(v1.NodeSelectorOpNotIn),
+}
+
+// nodeSelectorRequirementsAsFieldSelector converts the []NodeSelectorRequirement core type into a struct that implements
+// fields.Selector.
+func nodeSelectorRequirementsAsFieldSelector(nsr []v1.NodeSelectorRequirement, path *field.Path) (fields.Selector, []error) {
+	if len(nsr) == 0 {
+		return fields.Nothing(), nil
+	}
+	var errs []error
+
+	var selectors []fields.Selector
+	for i, expr := range nsr {
+		p := path.Index(i)
+		switch expr.Operator {
+		case v1.NodeSelectorOpIn:
+			if len(expr.Values) != 1 {
+				errs = append(errs, field.Invalid(p.Child("values"), expr.Values, "must have one element"))
+			} else {
+				selectors = append(selectors, fields.OneTermEqualSelector(expr.Key, expr.Values[0]))
+			}
+
+		case v1.NodeSelectorOpNotIn:
+			if len(expr.Values) != 1 {
+				errs = append(errs, field.Invalid(p.Child("values"), expr.Values, "must have one element"))
+			} else {
+				selectors = append(selectors, fields.OneTermNotEqualSelector(expr.Key, expr.Values[0]))
+			}
+
+		default:
+			errs = append(errs, field.NotSupported(p.Child("operator"), expr.Operator, validFieldSelectorOperators))
+		}
+	}
+
+	if len(errs) != 0 {
+		return nil, errs
+	}
+	return fields.AndSelectors(selectors...), nil
+}
+
+type preferredSchedulingTerm struct {
+	nodeSelectorTerm
+	weight int
+}
+
+type RequiredNodeAffinity struct {
+	labelSelector labels.Selector
+	nodeSelector  *LazyErrorNodeSelector
+}
+
+// GetRequiredNodeAffinity returns the parsing result of pod's nodeSelector and nodeAffinity.
+func GetRequiredNodeAffinity(pod *v1.Pod) RequiredNodeAffinity {
+	var selector labels.Selector
+	if len(pod.Spec.NodeSelector) > 0 {
+		selector = labels.SelectorFromSet(pod.Spec.NodeSelector)
+	}
+	// Use LazyErrorNodeSelector for backwards compatibility of parsing errors.
+	var affinity *LazyErrorNodeSelector
+	if pod.Spec.Affinity != nil &&
+		pod.Spec.Affinity.NodeAffinity != nil &&
+		pod.Spec.Affinity.NodeAffinity.RequiredDuringSchedulingIgnoredDuringExecution != nil {
+		affinity = NewLazyErrorNodeSelector(pod.Spec.Affinity.NodeAffinity.RequiredDuringSchedulingIgnoredDuringExecution)
+	}
+	return RequiredNodeAffinity{labelSelector: selector, nodeSelector: affinity}
+}
+
+// Match checks whether the pod is schedulable onto nodes according to
+// the requirements in both nodeSelector and nodeAffinity.
+func (s RequiredNodeAffinity) Match(node *v1.Node) (bool, error) {
+	if s.labelSelector != nil {
+		if !s.labelSelector.Matches(labels.Set(node.Labels)) {
+			return false, nil
+		}
+	}
+	if s.nodeSelector != nil {
+		return s.nodeSelector.Match(node)
+	}
+	return true, nil
+}

vendor/modules.txt

@@ -638,6 +638,10 @@ k8s.io/client-go/util/workqueue
 ## explicit; go 1.16
 k8s.io/component-base/metrics
 k8s.io/component-base/version
+# k8s.io/component-helpers v0.23.0 => k8s.io/component-helpers v0.23.0
+## explicit; go 1.16
+k8s.io/component-helpers/scheduling/corev1
+k8s.io/component-helpers/scheduling/corev1/nodeaffinity
 # k8s.io/klog v1.0.0
 ## explicit; go 1.12
 k8s.io/klog