Add Status.Version for KThreesControlPlane

controlplane/api/v1beta1/conversion.go

@@ -71,6 +71,10 @@ func Convert_v1beta2_KThreesConfigSpec_To_v1beta1_KThreesConfigSpec(in *bootstra
 	return bootstrapv1beta1.Convert_v1beta2_KThreesConfigSpec_To_v1beta1_KThreesConfigSpec(in, out, s)
 }
 
+func Convert_v1beta2_KThreesControlPlaneStatus_To_v1beta1_KThreesControlPlaneStatus(in *controlplanev1beta2.KThreesControlPlaneStatus, out *KThreesControlPlaneStatus, s conversion.Scope) error { //nolint: stylecheck
+	return autoConvert_v1beta2_KThreesControlPlaneStatus_To_v1beta1_KThreesControlPlaneStatus(in, out, s)
+}
+
 // ConvertTo converts the v1beta1 KThreesControlPlane receiver to a v1beta2 KThreesControlPlane.
 func (in *KThreesControlPlane) ConvertTo(dstRaw ctrlconversion.Hub) error {
 	dst := dstRaw.(*controlplanev1beta2.KThreesControlPlane)
@@ -91,6 +95,7 @@ func (in *KThreesControlPlane) ConvertTo(dstRaw ctrlconversion.Hub) error {
 	dst.Spec.KThreesConfigSpec.ServerConfig.DisableCloudController = restored.Spec.KThreesConfigSpec.ServerConfig.DisableCloudController
 	dst.Spec.MachineTemplate.NodeVolumeDetachTimeout = restored.Spec.MachineTemplate.NodeVolumeDetachTimeout
 	dst.Spec.MachineTemplate.NodeDeletionTimeout = restored.Spec.MachineTemplate.NodeDeletionTimeout
+	dst.Status.Version = restored.Status.Version
 	return nil
 }
 

controlplane/api/v1beta2/kthreescontrolplane_types.go

@@ -171,6 +171,11 @@ type KThreesControlPlaneStatus struct {
 	// +optional
 	Replicas int32 `json:"replicas,omitempty"`
 
+	// Version represents the minimum Kubernetes version for the control plane machines
+	// in the cluster.
+	// +optional
+	Version *string `json:"version,omitempty"`
+
 	// Total number of non-terminated machines targeted by this control plane
 	// that have the desired template spec.
 	// +optional

controlplane/config/crd/bases/controlplane.cluster.x-k8s.io_kthreescontrolplanes.yaml

@@ -1111,6 +1111,11 @@ spec:
                   that have the desired template spec.
                 format: int32
                 type: integer
+              version:
+                description: |-
+                  Version represents the minimum Kubernetes version for the control plane machines
+                  in the cluster.
+                type: string
             type: object
         type: object
     served: true

controlplane/controllers/kthreescontrolplane_controller.go

@@ -49,6 +49,7 @@ import (
 	controlplanev1 "github.com/k3s-io/cluster-api-k3s/controlplane/api/v1beta2"
 	k3s "github.com/k3s-io/cluster-api-k3s/pkg/k3s"
 	"github.com/k3s-io/cluster-api-k3s/pkg/kubeconfig"
+	"github.com/k3s-io/cluster-api-k3s/pkg/machinefilters"
 	"github.com/k3s-io/cluster-api-k3s/pkg/secret"
 	"github.com/k3s-io/cluster-api-k3s/pkg/token"
 )
@@ -159,13 +160,23 @@ func (r *KThreesControlPlaneReconciler) Reconcile(ctx context.Context, req ctrl.
 		err = kerrors.NewAggregate([]error{err, patchErr})
 	}
 
-	// TODO: remove this as soon as we have a proper remote cluster cache in place.
-	// Make KCP to requeue in case status is not ready, so we can check for node status without waiting for a full resync (by default 10 minutes).
-	// Only requeue if we are not going in exponential backoff due to error, or if we are not already re-queueing, or if the object has a deletion timestamp.
-	if err == nil && !res.Requeue && !(res.RequeueAfter > 0) && kcp.ObjectMeta.DeletionTimestamp.IsZero() {
+	// Only requeue if there is no error, Requeue or RequeueAfter and the object does not have a deletion timestamp.
+	if err == nil && res.IsZero() && kcp.ObjectMeta.DeletionTimestamp.IsZero() {
+		// Make KCP requeue in case node status is not ready, so we can check for node status without waiting for a full
+		// resync (by default 10 minutes).
+		// The alternative solution would be to watch the control plane nodes in the Cluster - similar to how the
+		// MachineSet and MachineHealthCheck controllers watch the nodes under their control.
 		if !kcp.Status.Ready {
 			res = ctrl.Result{RequeueAfter: 20 * time.Second}
 		}
+
+		// Make KCP requeue if ControlPlaneComponentsHealthyCondition is false so we can check for control plane component
+		// status without waiting for a full resync (by default 10 minutes).
+		// Otherwise this condition can lead to a delay in provisioning MachineDeployments when MachineSet preflight checks are enabled.
+		// The alternative solution to this requeue would be watching the relevant pods inside each workload cluster which would be very expensive.
+		if conditions.IsFalse(kcp, controlplanev1.ControlPlaneComponentsHealthyCondition) {
+			res = ctrl.Result{RequeueAfter: 20 * time.Second}
+		}
 	}
 
 	return res, err
@@ -364,6 +375,12 @@ func (r *KThreesControlPlaneReconciler) updateStatus(ctx context.Context, kcp *c
 		return nil
 	}
 
+	machinesWithAgentHealthy := controlPlane.Machines.Filter(machinefilters.AgentHealthy())
+	lowestVersion := machinesWithAgentHealthy.LowestVersion()
+	if lowestVersion != nil {
+		controlPlane.KCP.Status.Version = lowestVersion
+	}
+
 	switch {
 	// We are scaling up
 	case replicas < desiredReplicas:

pkg/machinefilters/machine_filters.go

@@ -22,6 +22,7 @@ import (
 	"k8s.io/apimachinery/pkg/apis/meta/v1/unstructured"
 	clusterv1 "sigs.k8s.io/cluster-api/api/v1beta1"
 	"sigs.k8s.io/cluster-api/util/collections"
+	"sigs.k8s.io/cluster-api/util/conditions"
 
 	bootstrapv1 "github.com/k3s-io/cluster-api-k3s/bootstrap/api/v1beta2"
 	controlplanev1 "github.com/k3s-io/cluster-api-k3s/controlplane/api/v1beta2"
@@ -112,3 +113,14 @@ func MatchesKThreesBootstrapConfig(machineConfigs map[string]*bootstrapv1.KThree
 		return reflect.DeepEqual(&machineConfig.Spec, kcpConfig)
 	}
 }
+
+// AgentHealthy returns a filter to find all machines that have an AgentHealthy
+// set to true.
+func AgentHealthy() Func {
+	return func(machine *clusterv1.Machine) bool {
+		if machine == nil {
+			return false
+		}
+		return conditions.IsTrue(machine, controlplanev1.MachineAgentHealthyCondition)
+	}
+}