v1alpha1

type AffinityTerm struct {
	Namespaces  sets.String
	Selector    labels.Selector
	TopologyKey string
}

type BindPlugin interface {
	Plugin
	// 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 context.Context, state *CycleState, p *v1.Pod, nodeName string) *Status
}

type Code int

type CycleState struct {
	// contains filtered or unexported fields
}

type Extender interface {
	// Name returns a unique name that identifies the extender.
	Name() string

	// Filter based on extender-implemented predicate functions. The filtered list is
	// expected to be a subset of the supplied list. failedNodesMap optionally contains
	// the list of failed nodes and failure reasons.
	Filter(pod *v1.Pod, nodes []*v1.Node) (filteredNodes []*v1.Node, failedNodesMap extenderv1.FailedNodesMap, err error)

	// Prioritize based on extender-implemented priority functions. The returned scores & weight
	// are used to compute the weighted score for an extender. The weighted scores are added to
	// the scores computed by Kubernetes scheduler. The total scores are used to do the host selection.
	Prioritize(pod *v1.Pod, nodes []*v1.Node) (hostPriorities *extenderv1.HostPriorityList, weight int64, err error)

	// Bind delegates the action of binding a pod to a node to the extender.
	Bind(binding *v1.Binding) error

	// IsBinder returns whether this extender is configured for the Bind method.
	IsBinder() bool

	// IsInterested returns true if at least one extended resource requested by
	// this pod is managed by this extender.
	IsInterested(pod *v1.Pod) bool

	// ProcessPreemption returns nodes with their victim pods processed by extender based on
	// given:
	//   1. Pod to schedule
	//   2. Candidate nodes and victim pods (nodeNameToVictims) generated by previous scheduling process.
	// The possible changes made by extender may include:
	//   1. Subset of given candidate nodes after preemption phase of extender.
	//   2. A different set of victim pod for every given candidate node after preemption phase of extender.
	ProcessPreemption(
		pod *v1.Pod,
		nodeNameToVictims map[string]*extenderv1.Victims,
		nodeInfos NodeInfoLister,
	) (map[string]*extenderv1.Victims, error)

	// SupportsPreemption returns if the scheduler extender support preemption or not.
	SupportsPreemption() bool

	// IsIgnorable returns true indicates scheduling should not fail when this extender
	// is unavailable. This gives scheduler ability to fail fast and tolerate non-critical extenders as well.
	IsIgnorable() bool
}

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",
	// please refer scheduler/algorithm/predicates/error.go
	// to set error message.
	// 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 context.Context, state *CycleState, pod *v1.Pod, nodeInfo *NodeInfo) *Status
}

type Framework interface {
	FrameworkHandle
	// QueueSortFunc returns the function to sort pods in scheduling queue
	QueueSortFunc() LessFunc

	// RunPreFilterPlugins runs the set of configured prefilter plugins. It returns
	// *Status and its code is set to non-success if any of the plugins returns
	// anything but Success. If a non-success status is returned, then the scheduling
	// cycle is aborted.
	RunPreFilterPlugins(ctx context.Context, state *CycleState, pod *v1.Pod) *Status

	// RunFilterPlugins runs the set of configured filter plugins for pod on
	// the given node. Note that for the node being evaluated, the passed nodeInfo
	// reference could be different from the one in NodeInfoSnapshot map (e.g., pods
	// considered to be running on the node could be different). 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.
	RunFilterPlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodeInfo *NodeInfo) PluginToStatus

	// RunPostFilterPlugins runs the set of configured PostFilter plugins.
	// PostFilter plugins can either be informational, in which case should be configured
	// to execute first and return Unschedulable status, or ones that try to change the
	// cluster state to make the pod potentially schedulable in a future scheduling cycle.
	RunPostFilterPlugins(ctx context.Context, state *CycleState, pod *v1.Pod, filteredNodeStatusMap NodeToStatusMap) (*PostFilterResult, *Status)

	// RunPreFilterExtensionAddPod calls the AddPod interface for the set of configured
	// PreFilter plugins. It returns directly if any of the plugins return any
	// status other than Success.
	RunPreFilterExtensionAddPod(ctx context.Context, state *CycleState, podToSchedule *v1.Pod, podToAdd *v1.Pod, nodeInfo *NodeInfo) *Status

	// RunPreFilterExtensionRemovePod calls the RemovePod interface for the set of configured
	// PreFilter plugins. It returns directly if any of the plugins return any
	// status other than Success.
	RunPreFilterExtensionRemovePod(ctx context.Context, state *CycleState, podToSchedule *v1.Pod, podToAdd *v1.Pod, nodeInfo *NodeInfo) *Status

	// RunPreScorePlugins runs the set of configured pre-score plugins. If any
	// of these plugins returns any status other than "Success", the given pod is rejected.
	RunPreScorePlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodes []*v1.Node) *Status

	// RunScorePlugins runs the set of configured scoring plugins. It returns a map that
	// stores for each scoring plugin name the corresponding NodeScoreList(s).
	// It also returns *Status, which is set to non-success if any of the plugins returns
	// a non-success status.
	RunScorePlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodes []*v1.Node) (PluginToNodeScores, *Status)

	// RunPreBindPlugins runs the set of configured prebind plugins. It returns
	// *Status and its code is set to non-success if any of the plugins returns
	// anything but Success. If the Status code is "Unschedulable", it is
	// considered as a scheduling check failure, otherwise, it is considered as an
	// internal error. In either case the pod is not going to be bound.
	RunPreBindPlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodeName string) *Status

	// RunPostBindPlugins runs the set of configured postbind plugins.
	RunPostBindPlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodeName string)

	// RunReservePluginsReserve runs the Reserve method of the set of
	// configured reserve plugins. If any of these calls returns an error, it
	// does not continue running the remaining ones and returns the error. In
	// such case, pod will not be scheduled.
	RunReservePluginsReserve(ctx context.Context, state *CycleState, pod *v1.Pod, nodeName string) *Status

	// RunReservePluginsUnreserve runs the Unreserve method of the set of
	// configured reserve plugins.
	RunReservePluginsUnreserve(ctx context.Context, state *CycleState, pod *v1.Pod, nodeName string)

	// RunPermitPlugins runs the set of configured permit plugins. If any of these
	// plugins returns a status other than "Success" or "Wait", it does not continue
	// running the remaining plugins and returns an error. Otherwise, if any of the
	// plugins returns "Wait", then this function will create and add waiting pod
	// to a map of currently waiting pods and return status with "Wait" code.
	// Pod will remain waiting pod for the minimum duration returned by the permit plugins.
	RunPermitPlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodeName string) *Status

	// WaitOnPermit will block, if the pod is a waiting pod, until the waiting pod is rejected or allowed.
	WaitOnPermit(ctx context.Context, pod *v1.Pod) *Status

	// RunBindPlugins runs the set of configured bind plugins. A bind plugin may choose
	// whether or not to handle the given Pod. If a bind plugin chooses to skip the
	// binding, it should return code=5("skip") status. Otherwise, it should return "Error"
	// or "Success". If none of the plugins handled binding, RunBindPlugins returns
	// code=5("skip") status.
	RunBindPlugins(ctx context.Context, state *CycleState, pod *v1.Pod, nodeName string) *Status

	// HasFilterPlugins returns true if at least one filter plugin is defined.
	HasFilterPlugins() bool

	// HasPostFilterPlugins returns true if at least one postFilter plugin is defined.
	HasPostFilterPlugins() bool

	// HasScorePlugins returns true if at least one score plugin is defined.
	HasScorePlugins() bool

	// ListPlugins returns a map of extension point name to list of configured Plugins.
	ListPlugins() map[string][]config.Plugin
}

type FrameworkHandle interface {
	// SnapshotSharedLister returns listers from the latest NodeInfo Snapshot. The snapshot
	// is taken at the beginning of a scheduling cycle and remains unchanged until
	// a pod finishes "Permit" point. There is no guarantee that the information
	// remains unchanged in the binding phase of scheduling, so plugins in the binding
	// cycle (pre-bind/bind/post-bind/un-reserve plugin) should not use it,
	// otherwise a concurrent read/write error might occur, they should use scheduler
	// cache instead.
	SnapshotSharedLister() SharedLister

	// IterateOverWaitingPods acquires a read lock and iterates over the WaitingPods map.
	IterateOverWaitingPods(callback func(WaitingPod))

	// GetWaitingPod returns a waiting pod given its UID.
	GetWaitingPod(uid types.UID) WaitingPod

	// RejectWaitingPod rejects a waiting pod given its UID.
	RejectWaitingPod(uid types.UID)

	// ClientSet returns a kubernetes clientSet.
	ClientSet() clientset.Interface

	// EventRecorder returns an event recorder.
	EventRecorder() events.EventRecorder

	SharedInformerFactory() informers.SharedInformerFactory

	// TODO: unroll the wrapped interfaces to FrameworkHandle.
	PreemptHandle() PreemptHandle
}

type HostPortInfo map[string]map[ProtocolPort]struct{}

type ImageStateSummary struct {
	// Size of the image
	Size int64
	// Used to track how many nodes have this image
	NumNodes int
}

type LessFunc func(podInfo1, podInfo2 *QueuedPodInfo) bool

type NodeInfo struct {

	// Pods running on the node.
	Pods []*PodInfo

	// The subset of pods with affinity.
	PodsWithAffinity []*PodInfo

	// The subset of pods with required anti-affinity.
	PodsWithRequiredAntiAffinity []*PodInfo

	// Ports allocated on the node.
	UsedPorts HostPortInfo

	// Total requested resources of all pods on this node. This includes assumed
	// pods, which scheduler has sent for binding, but may not be scheduled yet.
	Requested *Resource
	// Total requested resources of all pods on this node with a minimum value
	// applied to each container's CPU and memory requests. This does not reflect
	// the actual resource requests for this node, but is used to avoid scheduling
	// many zero-request pods onto one node.
	NonZeroRequested *Resource
	// We store allocatedResources (which is Node.Status.Allocatable.*) explicitly
	// as int64, to avoid conversions and accessing map.
	Allocatable *Resource

	// ImageStates holds the entry of an image if and only if this image is on the node. The entry can be used for
	// checking an image's existence and advanced usage (e.g., image locality scheduling policy) based on the image
	// state information.
	ImageStates map[string]*ImageStateSummary

	// TransientInfo holds the information pertaining to a scheduling cycle. This will be destructed at the end of
	// scheduling cycle.
	// TODO: @ravig. Remove this once we have a clear approach for message passing across predicates and priorities.
	TransientInfo *TransientSchedulerInfo

	// Whenever NodeInfo changes, generation is bumped.
	// This is used to avoid cloning it if the object didn't change.
	Generation int64
	// contains filtered or unexported fields
}

type NodeInfoLister interface {
	// Returns the list of NodeInfos.
	List() ([]*NodeInfo, error)
	// Returns the list of NodeInfos of nodes with pods with affinity terms.
	HavePodsWithAffinityList() ([]*NodeInfo, error)
	// Returns the list of NodeInfos of nodes with pods with required anti-affinity terms.
	HavePodsWithRequiredAntiAffinityList() ([]*NodeInfo, error)
	// Returns the NodeInfo of the given node name.
	Get(nodeName string) (*NodeInfo, error)
}

type NodeScore struct {
	Name  string
	Score int64
}

type NodeScoreList []NodeScore

type NodeToStatusMap map[string]*Status

type PermitPlugin interface {
	Plugin
	// 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 context.Context, state *CycleState, p *v1.Pod, nodeName string) (*Status, time.Duration)
}

type Plugin interface {
	Name() string
}

type PluginToNodeScores map[string]NodeScoreList

type PluginToStatus map[string]*Status

type PluginsRunner interface {
	// RunFilterPlugins runs the set of configured filter plugins for pod on the given node.
	RunFilterPlugins(context.Context, *CycleState, *v1.Pod, *NodeInfo) PluginToStatus
	// RunPreFilterExtensionAddPod calls the AddPod interface for the set of configured PreFilter plugins.
	RunPreFilterExtensionAddPod(ctx context.Context, state *CycleState, podToSchedule *v1.Pod, podToAdd *v1.Pod, nodeInfo *NodeInfo) *Status
	// RunPreFilterExtensionRemovePod calls the RemovePod interface for the set of configured PreFilter plugins.
	RunPreFilterExtensionRemovePod(ctx context.Context, state *CycleState, podToSchedule *v1.Pod, podToRemove *v1.Pod, nodeInfo *NodeInfo) *Status
}

type PodInfo struct {
	Pod                        *v1.Pod
	RequiredAffinityTerms      []AffinityTerm
	RequiredAntiAffinityTerms  []AffinityTerm
	PreferredAffinityTerms     []WeightedAffinityTerm
	PreferredAntiAffinityTerms []WeightedAffinityTerm
	ParseError                 error
}

type PodNominator interface {
	// AddNominatedPod adds the given pod to the nominated pod map or
	// updates it if it already exists.
	AddNominatedPod(pod *v1.Pod, nodeName string)
	// DeleteNominatedPodIfExists deletes nominatedPod from internal cache. It's a no-op if it doesn't exist.
	DeleteNominatedPodIfExists(pod *v1.Pod)
	// UpdateNominatedPod updates the <oldPod> with <newPod>.
	UpdateNominatedPod(oldPod, newPod *v1.Pod)
	// NominatedPodsForNode returns nominatedPods on the given node.
	NominatedPodsForNode(nodeName string) []*v1.Pod
}

type PostBindPlugin interface {
	Plugin
	// 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 context.Context, state *CycleState, p *v1.Pod, nodeName string)
}

type PostFilterPlugin interface {
	Plugin
	// PostFilter is called by the scheduling framework.
	// 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 context.Context, state *CycleState, pod *v1.Pod, filteredNodeStatusMap NodeToStatusMap) (*PostFilterResult, *Status)
}

type PostFilterResult struct {
	NominatedNodeName string
}

type PreBindPlugin interface {
	Plugin
	// 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 context.Context, state *CycleState, p *v1.Pod, nodeName string) *Status
}

type PreFilterExtensions interface {
	// AddPod is called by the framework while trying to evaluate the impact
	// of adding podToAdd to the node while scheduling podToSchedule.
	AddPod(ctx context.Context, state *CycleState, podToSchedule *v1.Pod, podToAdd *v1.Pod, nodeInfo *NodeInfo) *Status
	// RemovePod is called by the framework while trying to evaluate the impact
	// of removing podToRemove from the node while scheduling podToSchedule.
	RemovePod(ctx context.Context, state *CycleState, podToSchedule *v1.Pod, podToRemove *v1.Pod, nodeInfo *NodeInfo) *Status
}

type PreFilterPlugin interface {
	Plugin
	// PreFilter is called at the beginning of the scheduling cycle. All PreFilter
	// plugins must return success or the pod will be rejected.
	PreFilter(ctx context.Context, state *CycleState, p *v1.Pod) *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
}

type PreScorePlugin interface {
	Plugin
	// PreScore is called by the scheduling framework after a list of nodes
	// passed the filtering phase. All prescore plugins must return success or
	// the pod will be rejected
	PreScore(ctx context.Context, state *CycleState, pod *v1.Pod, nodes []*v1.Node) *Status
}

type PreemptHandle interface {
	// PodNominator abstracts operations to maintain nominated Pods.
	PodNominator
	// PluginsRunner abstracts operations to run some plugins.
	PluginsRunner
	// Extenders returns registered scheduler extenders.
	Extenders() []Extender
}

type ProtocolPort struct {
	Protocol string
	Port     int32
}

type QueueSortPlugin interface {
	Plugin
	// Less are used to sort pods in the scheduling queue.
	Less(*QueuedPodInfo, *QueuedPodInfo) bool
}

type QueuedPodInfo struct {
	Pod *v1.Pod
	// The time pod added to the scheduling queue.
	Timestamp time.Time
	// Number of schedule attempts before successfully scheduled.
	// It's used to record the # attempts metric.
	Attempts int
	// The time when the pod is added to the queue for the first time. The pod may be added
	// back to the queue multiple times before it's successfully scheduled.
	// It shouldn't be updated once initialized. It's used to record the e2e scheduling
	// latency for a pod.
	InitialAttemptTimestamp time.Time
}

type ReservePlugin interface {
	Plugin
	// 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 context.Context, 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 context.Context, state *CycleState, p *v1.Pod, nodeName string)
}

type Resource struct {
	MilliCPU         int64
	Memory           int64
	EphemeralStorage int64
	// We store allowedPodNumber (which is Node.Status.Allocatable.Pods().Value())
	// explicitly as int, to avoid conversions and improve performance.
	AllowedPodNumber int
	// ScalarResources
	ScalarResources map[v1.ResourceName]int64
}

type ScoreExtensions interface {
	// NormalizeScore is called for all node scores produced by the same plugin's "Score"
	// method. A successful run of NormalizeScore will update the scores list and return
	// a success status.
	NormalizeScore(ctx context.Context, state *CycleState, p *v1.Pod, scores NodeScoreList) *Status
}

type ScorePlugin interface {
	Plugin
	// Score is called on each filtered node. It must return success and an integer
	// indicating the rank of the node. All scoring plugins must return success or
	// the pod will be rejected.
	Score(ctx context.Context, state *CycleState, p *v1.Pod, nodeName string) (int64, *Status)

	// ScoreExtensions returns a ScoreExtensions interface if it implements one, or nil if does not.
	ScoreExtensions() ScoreExtensions
}

type SharedLister interface {
	NodeInfos() NodeInfoLister
}

type StateData interface {
	// Clone is an interface to make a copy of StateData. For performance reasons,
	// clone should make shallow copies for members (e.g., slices or maps) that are not
	// impacted by PreFilter's optional AddPod/RemovePod methods.
	Clone() StateData
}

type StateKey string

type Status struct {
	// contains filtered or unexported fields
}

type TransientSchedulerInfo struct {
	TransientLock sync.Mutex
	// NodeTransInfo holds the information related to nodeTransientInformation. NodeName is the key here.
	TransNodeInfo nodeTransientInfo
}

type WaitingPod interface {
	// GetPod returns a reference to the waiting pod.
	GetPod() *v1.Pod
	// GetPendingPlugins returns a list of pending permit plugin's name.
	GetPendingPlugins() []string
	// Allow declares the waiting pod is allowed to be scheduled by plugin pluginName.
	// If this is the last remaining plugin to allow, then a success signal is delivered
	// to unblock the pod.
	Allow(pluginName string)
	// Reject declares the waiting pod unschedulable.
	Reject(msg string)
}

type WeightedAffinityTerm struct {
	AffinityTerm
	Weight int32
}