$ ll pkg/scheduler/framework/plugins
defaultbinder/
defaultpreemption/
dynamicresources/
feature/
imagelocality/
interpodaffinity/
names/
nodeaffinity/
nodename/
nodeports/
noderesources/
nodeunschedulable/
nodevolumelimits/
podtopologyspread/
queuesort/
schedulinggates/
selectorspread/
tainttoleration/
volumebinding/
volumerestrictions/
volumezone/

// https://github.com/kubernetes/kubernetes/blob/v1.28.4/pkg/scheduler/framework/interface.go#L349-L367

// PreFilterPlugin is an interface that must be implemented by "PreFilter" plugins.
// These plugins are called at the beginning of the scheduling cycle.
type PreFilterPlugin interface {
    // PreFilter is called at the beginning of the scheduling cycle. All PreFilter
    // plugins must return success or the pod will be rejected. PreFilter could optionally
    // return a PreFilterResult to influence which nodes to evaluate downstream. This is useful
    // for cases where it is possible to determine the subset of nodes to process in O(1) time.
    // When it returns Skip status, returned PreFilterResult and other fields in status are just ignored,
    // and coupled Filter plugin/PreFilterExtensions() will be skipped in this scheduling cycle.
    PreFilter(ctx , state *CycleState, p *v1.Pod) (*PreFilterResult, *Status)

    // PreFilterExtensions returns a PreFilterExtensions interface if the plugin implements one,
    // or nil if it does not. A Pre-filter plugin can provide extensions to incrementally
    // modify its pre-processed info. The framework guarantees that the extensions
    // AddPod/RemovePod will only be called after PreFilter, possibly on a cloned
    // CycleState, and may call those functions more than once before calling
    // Filter again on a specific node.
    PreFilterExtensions() PreFilterExtensions
}

// https://github.com/kubernetes/kubernetes/blob/v1.28.4/pkg/scheduler/framework/interface.go#L349C1-L367C2

// FilterPlugin is an interface for Filter plugins. These plugins are called at the
// filter extension point for filtering out hosts that cannot run a pod.
// This concept used to be called 'predicate' in the original scheduler.
// These plugins should return "Success", "Unschedulable" or "Error" in Status.code.
// However, the scheduler accepts other valid codes as well.
// Anything other than "Success" will lead to exclusion of the given host from running the pod.
type FilterPlugin interface {
    Plugin
    // Filter is called by the scheduling framework.
    // All FilterPlugins should return "Success" to declare that
    // the given node fits the pod. If Filter doesn't return "Success",
    // it will return "Unschedulable", "UnschedulableAndUnresolvable" or "Error".
    // For the node being evaluated, Filter plugins should look at the passed
    // nodeInfo reference for this particular node's information (e.g., pods
    // considered to be running on the node) instead of looking it up in the
    // NodeInfoSnapshot because we don't guarantee that they will be the same.
    // For example, during preemption, we may pass a copy of the original
    // nodeInfo object that has some pods removed from it to evaluate the
    // possibility of preempting them to schedule the target pod.
    Filter(ctx , state *CycleState, pod *v1.Pod, nodeInfo *NodeInfo) *Status
}

// https://github.com/kubernetes/kubernetes/blob/v1.28.4/pkg/scheduler/framework/interface.go#L392C1-L407C2

// PostFilterPlugin is an interface for "PostFilter" plugins. These plugins are called after a pod cannot be scheduled.
type PostFilterPlugin interface {
    // A PostFilter plugin should return one of the following statuses:
    // - Unschedulable: the plugin gets executed successfully but the pod cannot be made schedulable.
    // - Success: the plugin gets executed successfully and the pod can be made schedulable.
    // - Error: the plugin aborts due to some internal error.
    //
    // Informational plugins should be configured ahead of other ones, and always return Unschedulable status.
    // Optionally, a non-nil PostFilterResult may be returned along with a Success status. For example,
    // a preemption plugin may choose to return nominatedNodeName, so that framework can reuse that to update the
    // preemptor pod's .spec.status.nominatedNodeName field.
    PostFilter(ctx , state *CycleState, pod *v1.Pod, filteredNodeStatusMap NodeToStatusMap) (*PostFilterResult, *Status)
}

// https://github.com/kubernetes/kubernetes/blob/v1.28.4/pkg/scheduler/framework/interface.go#L444C1-L462C2

// ReservePlugin is an interface for plugins with Reserve and Unreserve
// methods. These are meant to update the state of the plugin. This concept
// used to be called 'assume' in the original scheduler. These plugins should
// return only Success or Error in Status.code. However, the scheduler accepts
// other valid codes as well. Anything other than Success will lead to
// rejection of the pod.
type ReservePlugin interface {
    // Reserve is called by the scheduling framework when the scheduler cache is
    // updated. If this method returns a failed Status, the scheduler will call
    // the Unreserve method for all enabled ReservePlugins.
    Reserve(ctx , state *CycleState, p *v1.Pod, nodeName string) *Status
    // Unreserve is called by the scheduling framework when a reserved pod was
    // rejected, an error occurred during reservation of subsequent plugins, or
    // in a later phase. The Unreserve method implementation must be idempotent
    // and may be called by the scheduler even if the corresponding Reserve
    // method for the same plugin was not called.
    Unreserve(ctx , state *CycleState, p *v1.Pod, nodeName string)
}

// PermitPlugin is an interface that must be implemented by "Permit" plugins.
// These plugins are called before a pod is bound to a node.
type PermitPlugin interface {
    // Permit is called before binding a pod (and before prebind plugins). Permit
    // plugins are used to prevent or delay the binding of a Pod. A permit plugin
    // must return success or wait with timeout duration, or the pod will be rejected.
    // The pod will also be rejected if the wait timeout or the pod is rejected while
    // waiting. Note that if the plugin returns "wait", the framework will wait only
    // after running the remaining plugins given that no other plugin rejects the pod.
    Permit(ctx , state *CycleState, p *v1.Pod, nodeName string) (*Status, time.Duration)
}

// PreBindPlugin is an interface that must be implemented by "PreBind" plugins.
// These plugins are called before a pod being scheduled.
type PreBindPlugin interface {
    // PreBind is called before binding a pod. All prebind plugins must return
    // success or the pod will be rejected and won't be sent for binding.
    PreBind(ctx , state *CycleState, p *v1.Pod, nodeName string) *Status
}

// https://github.com/kubernetes/kubernetes/blob/v1.28.4/pkg/scheduler/framework/interface.go#L497

// Bind plugins are used to bind a pod to a Node.
type BindPlugin interface {
    // Bind plugins will not be called until all pre-bind plugins have completed. Each
    // bind plugin is called in the configured order. A bind plugin may choose whether
    // or not to handle the given Pod. If a bind plugin chooses to handle a Pod, the
    // remaining bind plugins are skipped. When a bind plugin does not handle a pod,
    // it must return Skip in its Status code. If a bind plugin returns an Error, the
    // pod is rejected and will not be bound.
    Bind(ctx , state *CycleState, p *v1.Pod, nodeName string) *Status
}

// https://github.com/kubernetes/kubernetes/blob/v1.28.4/pkg/scheduler/framework/interface.go#L473

// PostBindPlugin is an interface that must be implemented by "PostBind" plugins.
// These plugins are called after a pod is successfully bound to a node.
type PostBindPlugin interface {
    // PostBind is called after a pod is successfully bound. These plugins are informational.
    // A common application of this extension point is for cleaning
    // up. If a plugin needs to clean-up its state after a pod is scheduled and
    // bound, PostBind is the extension point that it should register.
    PostBind(ctx , state *CycleState, p *v1.Pod, nodeName string)
}

// PreFilter invoked at the preFilter extension point.
func (pl *StickyVM) PreFilter(ctx , state *framework.CycleState, pod *v1.Pod) (*framework.PreFilterResult, *framework.Status) {
    s := stickyState{false, ""}

    // Get pod owner reference
    podOwnerRef := getPodOwnerRef(pod)
    if podOwnerRef == nil {
        return nil, framework.NewStatus(framework.Success, "Pod owner ref not found, return")
    }

    // Get VMI
    vmiName := podOwnerRef.Name
    ns := pod.Namespace

    vmi := pl.kubevirtClient.VirtualMachineInstances(ns).Get(context.TODO(), vmiName, metav1.GetOptions{ResourceVersion: "0"})
    if err != nil {
        return nil, framework.NewStatus(framework.Error, "get vmi failed")
    }

    vmiOwnerRef := getVMIOwnerRef(vmi)
    if vmiOwnerRef == nil {
        return nil, framework.NewStatus(framework.Success, "VMI owner ref not found, return")
    }

    // Get VM
    vmName := vmiOwnerRef.Name
    vm := pl.kubevirtClient.VirtualMachines(ns).Get(context.TODO(), vmName, metav1.GetOptions{ResourceVersion: "0"})
    if err != nil {
        return nil, framework.NewStatus(framework.Error, "get vmi failed")
    }

    // Annotate sticky node to VM
    s.node, s.nodeExists = vm.Annotations[stickyAnnotationKey]
    return nil, framework.NewStatus(framework.Success, "Check pod/vmi/vm finish, return")
}

// For a given pod
for node in selectedNodes:
    for pl in plugins:
        pl.Filter(ctx, customState, pod, node)

func (pl *StickyVM) Filter(ctx , state *framework.CycleState, pod *v1.Pod, nodeInfo *framework.NodeInfo) *framework.Status {
    s := state.Read(stateKey)
    if err != nil {
        return framework.NewStatus(framework.Error, fmt.Sprintf("read preFilter state fail: %v", err))
    }

    r, ok := s.(*stickyState)
    if !ok {
        return framework.NewStatus(framework.Error, fmt.Sprintf("convert %+v to stickyState fail", s))
    }
    if !r.nodeExists {
        return nil
    }

    if r.node != nodeInfo.Node().Name {
        // returning "framework.Error" will prevent process on other nodes
        return framework.NewStatus(framework.Unschedulable, "already stick to another node")
    }

    return nil
}

func (pl *StickyVM) PostBind(ctx , state *framework.CycleState, pod *v1.Pod, nodeName string) {
    s := state.Read(stateKey)
    if err != nil {
        return
    }

    r, ok := s.(*stickyState)
    if !ok {
        klog.Errorf("PostBind: pod %s/%s: convert failed", pod.Namespace, pod.Name)
        return
    }

    if r.nodeExists {
        klog.Errorf("PostBind: VM already has sticky annotation, return")
        return
    }

    // Get pod owner reference
    podOwnerRef := getPodOwnerRef(pod)
    if podOwnerRef == nil {
        return
    }

    // Get VMI owner reference
    vmiName := podOwnerRef.Name
    ns := pod.Namespace

    vmi := pl.kubevirtClient.VirtualMachineInstances(ns).Get(context.TODO(), vmiName, metav1.GetOptions{ResourceVersion: "0"})
    if err != nil {
        return
    }

    vmiOwnerRef := getVMIOwnerRef(vmi)
    if vmiOwnerRef == nil {
        return
    }

    // Add sticky node to VM annotations
    retry.RetryOnConflict(retry.DefaultRetry, func() error {
        vmName := vmiOwnerRef.Name
        vm := pl.kubevirtClient.VirtualMachines(ns).Get(context.TODO(), vmName, metav1.GetOptions{ResourceVersion: "0"})
        if err != nil {
            return err
        }

        if vm.Annotations == nil {
            vm.Annotations = make(map[string]string)
        }

        vm.Annotations[stickyAnnotationKey] = nodeName
        if _ = pl.kubevirtClient.VirtualMachines(pod.Namespace).Update(ctx, vm, metav1.UpdateOptions{}); err != nil {
            return err
        }
        return nil
    })
}

apiVersion: kubescheduler.config.k8s.io/v1
kind: KubeSchedulerConfiguration
clientConnection:
  kubeconfig: "/etc/kubernetes/scheduler.kubeconfig"
profiles:
- schedulerName: stickyvm
  plugins:
    preFilter:
      enabled:
      - name: StickyVM
      disabled:
      - name: NodeResourceFit
    filter:
      enabled:
      - name: StickyVM
      disabled:
      - name: NodePorts
      # - name: "*"
    reserve:
      disabled:
      - name: "*"
    preBind:
      disabled:
      - name: "*"
    postBind:
      enabled:
      - name: StickyVM
      disabled:
      - name: "*"

$ ./bin/stickyvm-scheduler --leader-elect=false --config ksc.yaml
Creating StickyVM scheduling plugin
Creating kubevirt clientset
Create kubevirt clientset successful
Create StickyVM scheduling plugin successful
Starting Kubernetes Scheduler" version="v0.0.20231122"
Golang settings" GOGC="" GOMAXPROCS="" GOTRACEBACK=""
Serving securely on [::]:10259
"Starting DynamicServingCertificateController"

Prefilter: start
Prefilter: processing pod default/virt-launcher-kubevirt-smoke-fedora-nd4hp
PreFilter: parent is VirtualMachineInstance kubevirt-smoke-fedora
PreFilter: found corresponding VMI
PreFilter: found corresponding VM
PreFilter: VM has no sticky node, skip to write to scheduling context
Prefilter: finish
Filter: start
Filter: pod default/virt-launcher-kubevirt-smoke-fedora-nd4hp, sticky node not exist, got node-1, return success
PostBind: start: pod default/virt-launcher-kubevirt-smoke-fedora-nd4hp
PostBind: annotating selected node node-1 to VM
PostBind: parent is VirtualMachineInstance kubevirt-smoke-fedora
PostBind: found corresponding VMI
PostBind: found corresponding VM
PostBind: annotating node node-1 to VM: kubevirt-smoke-fedora

Prefilter: start
Prefilter: processing pod default/virt-launcher-kubevirt-smoke-fedora-m8f7v
PreFilter: parent is VirtualMachineInstance kubevirt-smoke-fedora
PreFilter: found corresponding VMI
PreFilter: found corresponding VM
PreFilter: VM already sticky to node node-1, write to scheduling context
Prefilter: finish
Filter: start
Filter: default/virt-launcher-kubevirt-smoke-fedora-m8f7v, already stick to node-1, skip node-2
Filter: start
Filter: default/virt-launcher-kubevirt-smoke-fedora-m8f7v, given node is sticky node node-1, return success
Filter: finish
Filter: start
Filter: default/virt-launcher-kubevirt-smoke-fedora-m8f7v, already stick to node-1, skip node-3
PostBind: start: pod default/virt-launcher-kubevirt-smoke-fedora-m8f7v
PostBind: VM already has sticky annotation, return