Kubernetes 调度器实现原理

// pkg/scheduler/framework/plugins/registry.go

// NewInTreeRegistry 使用所有内部插件构建注册表。
// 外部插件可以通过 WithFrameworkOutOfTreeRegistry 选项注册额外的插件。
func NewInTreeRegistry() runtime.Registry {
 fts := plfeature.Features{
  EnableDynamicResourceAllocation:              feature.DefaultFeatureGate.Enabled(features.DynamicResourceAllocation),
  EnableReadWriteOncePod:                       feature.DefaultFeatureGate.Enabled(features.ReadWriteOncePod),
  EnableVolumeCapacityPriority:                 feature.DefaultFeatureGate.Enabled(features.VolumeCapacityPriority),
  EnableMinDomainsInPodTopologySpread:          feature.DefaultFeatureGate.Enabled(features.MinDomainsInPodTopologySpread),
  EnableNodeInclusionPolicyInPodTopologySpread: feature.DefaultFeatureGate.Enabled(features.NodeInclusionPolicyInPodTopologySpread),
  EnableMatchLabelKeysInPodTopologySpread:      feature.DefaultFeatureGate.Enabled(features.MatchLabelKeysInPodTopologySpread),
  EnablePodSchedulingReadiness:                 feature.DefaultFeatureGate.Enabled(features.PodSchedulingReadiness),
 }

 registry := runtime.Registry{
  dynamicresources.Name:                runtime.FactoryAdapter(fts, dynamicresources.New),
  selectorspread.Name:                  selectorspread.New,
  imagelocality.Name:                   imagelocality.New,
  tainttoleration.Name:                 tainttoleration.New,
  nodename.Name:                        nodename.New,
  nodeports.Name:                       nodeports.New,
  nodeaffinity.Name:                    nodeaffinity.New,
  podtopologyspread.Name:               runtime.FactoryAdapter(fts, podtopologyspread.New),
  nodeunschedulable.Name:               nodeunschedulable.New,
  noderesources.Name:                   runtime.FactoryAdapter(fts, noderesources.NewFit),
  noderesources.BalancedAllocationName: runtime.FactoryAdapter(fts, noderesources.NewBalancedAllocation),
  volumebinding.Name:                   runtime.FactoryAdapter(fts, volumebinding.New),
  volumerestrictions.Name:              runtime.FactoryAdapter(fts, volumerestrictions.New),
  volumezone.Name:                      volumezone.New,
  nodevolumelimits.CSIName:             runtime.FactoryAdapter(fts, nodevolumelimits.NewCSI),
  nodevolumelimits.EBSName:             runtime.FactoryAdapter(fts, nodevolumelimits.NewEBS),
  nodevolumelimits.GCEPDName:           runtime.FactoryAdapter(fts, nodevolumelimits.NewGCEPD),
  nodevolumelimits.AzureDiskName:       runtime.FactoryAdapter(fts, nodevolumelimits.NewAzureDisk),
  nodevolumelimits.CinderName:          runtime.FactoryAdapter(fts, nodevolumelimits.NewCinder),
  interpodaffinity.Name:                interpodaffinity.New,
  queuesort.Name:                       queuesort.New,
  defaultbinder.Name:                   defaultbinder.New,
  defaultpreemption.Name:               runtime.FactoryAdapter(fts, defaultpreemption.New),
  schedulinggates.Name:                 runtime.FactoryAdapter(fts, schedulinggates.New),
 }

 return registry
}
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.
42.
43.
44.

// Plugin is the parent type for all the scheduling framework plugins.
type Plugin interface {
 Name() string
}

// PreEnqueuePlugin is an interface that must be implemented by "PreEnqueue" plugins.
// These plugins are called prior to adding Pods to activeQ.
// Note: an preEnqueue plugin is expected to be lightweight and efficient, so it's not expected to
// involve expensive calls like accessing external endpoints; otherwise it'd block other
// Pods' enqueuing in event handlers.
type PreEnqueuePlugin interface {
 Plugin
 // PreEnqueue is called prior to adding Pods to activeQ.
 PreEnqueue(ctx context.Context, p *v1.Pod) *Status
}

// LessFunc is the function to sort pod info
type LessFunc func(podInfo1, podInfo2 *QueuedPodInfo) bool

// QueueSortPlugin is an interface that must be implemented by "QueueSort" plugins.
// These plugins are used to sort pods in the scheduling queue. Only one queue sort
// plugin may be enabled at a time.
type QueueSortPlugin interface {
 Plugin
 // Less are used to sort pods in the scheduling queue.
 Less(*QueuedPodInfo, *QueuedPodInfo) bool
}

// EnqueueExtensions is an optional interface that plugins can implement to efficiently
// move unschedulable Pods in internal scheduling queues. Plugins
// that fail pod scheduling (e.g., Filter plugins) are expected to implement this interface.
type EnqueueExtensions interface {
 // EventsToRegister returns a series of possible events that may cause a Pod
 // failed by this plugin schedulable.
 // The events will be registered when instantiating the internal scheduling queue,
 // and leveraged to build event handlers dynamically.
 // Note: the returned list needs to be static (not depend on configuration parameters);
 // otherwise it would lead to undefined behavior.
 EventsToRegister() []ClusterEvent
}

// PreFilterExtensions is an interface that is included in plugins that allow specifying
// callbacks to make incremental updates to its supposedly pre-calculated
// state.
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, podInfoToAdd *PodInfo, 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, podInfoToRemove *PodInfo, nodeInfo *NodeInfo) *Status
}

// 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 {
 Plugin
 // 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.
 PreFilter(ctx context.Context, 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
}

// 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 context.Context, state *CycleState, pod *v1.Pod, nodeInfo *NodeInfo) *Status
}

// PostFilterPlugin is an interface for "PostFilter" plugins. These plugins are called
// after a pod cannot be scheduled.
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)
}

// PreScorePlugin is an interface for "PreScore" plugin. PreScore is an
// informational extension point. Plugins will be called with a list of nodes
// that passed the filtering phase. A plugin may use this data to update internal
// state or to generate logs/metrics.
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
}

// ScoreExtensions is an interface for Score extended functionality.
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
}

// ScorePlugin is an interface that must be implemented by "Score" plugins to rank
// nodes that passed the filtering phase.
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
}

// 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 {
 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)
}

// PreBindPlugin is an interface that must be implemented by "PreBind" plugins.
// These plugins are called before a pod being scheduled.
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
}

// 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 {
 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)
}

// 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 {
 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)
}

// BindPlugin is an interface that must be implemented by "Bind" plugins. Bind
// plugins are used to bind a pod to a Node.
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
}
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.
42.
43.
44.
45.
46.
47.
48.
49.
50.
51.
52.
53.
54.
55.
56.
57.
58.
59.
60.
61.
62.
63.
64.
65.
66.
67.
68.
69.
70.
71.
72.
73.
74.
75.
76.
77.
78.
79.
80.
81.
82.
83.
84.
85.
86.
87.
88.
89.
90.
91.
92.
93.
94.
95.
96.
97.
98.
99.
100.
101.
102.
103.
104.
105.
106.
107.
108.
109.
110.
111.
112.
113.
114.
115.
116.
117.
118.
119.
120.
121.
122.
123.
124.
125.
126.
127.
128.
129.
130.
131.
132.
133.
134.
135.
136.
137.
138.
139.
140.
141.
142.
143.
144.
145.
146.
147.
148.
149.
150.
151.
152.
153.
154.
155.
156.
157.
158.
159.
160.
161.
162.
163.
164.
165.
166.
167.
168.
169.
170.
171.
172.
173.
174.
175.
176.
177.
178.
179.
180.
181.
182.
183.
184.
185.
186.
187.
188.
189.
190.
191.
192.
193.
194.
195.
196.
197.
198.
199.
200.
201.
202.
203.
204.
205.
206.
207.
208.
209.

apiVersion: kubescheduler.config.k8s.io/v1
kind: KubeSchedulerConfiguration

---
plugins:
  reserve:
    enabled:
      - name: foo
      - name: bar
    disabled:
      - name: baz
  preBind:
    enabled:
      - name: foo
    disabled:
      - name: baz

pluginConfig:
  - name: foo
    args: >
      foo插件可以解析的任意内容
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.

apiVersion: kubescheduler.config.k8s.io/v1
kind: KubeSchedulerConfiguration

---
profiles:
  - plugins:
      reserve:
        enabled:
          - name: bar
          - name: foo
        disabled:
          - name: foo
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.

// pkg/scheduler/algorithmprovider/registry.go
func NewRegistry() Registry {
 return Registry{
  // FactoryMap:
  // New plugins are registered here.
  // example:
  // {
  //  stateful_plugin.Name: stateful.NewStatefulMultipointExample,
  //  fooplugin.Name: fooplugin.New,
  // }
 }
}
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.

// Option configures a framework.Registry.
type Option func(framework.Registry) error

// NewSchedulerCommand creates a *cobra.Command object with default parameters and registryOptions
func NewSchedulerCommand(registryOptions ...Option) *cobra.Command {
  ......
}
1.
2.
3.
4.
5.
6.
7.

func WithPlugin(name string, factory runtime.PluginFactory) Option {
 return func(registry runtime.Registry) error {
  return registry.Register(name, factory)
 }
}
1.
2.
3.
4.
5.

package main

import (
 "k8s.io/component-base/cli"
 "k8s.io/kubernetes/cmd/kube-scheduler/app"
 "math/rand"
 "os"
 // Ensure scheme package is initialized.
 _ "simple-scheduler/pkg/scheduler/apis/config/schema"
 "simple-scheduler/pkg/scheduler/framework/plugins"
 "time"
)

func main() {
 rand.Seed(time.Now().UTC().UnixNano())
 command := app.NewSchedulerCommand(
  app.WithPlugin(plugins.Name, plugins.New))
 code := cli.Run(command)
 os.Exit(code)
}
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.

type PluginFactory = func(configuration runtime.Object, f framework.Handle) (framework.Plugin, error)
1.

package plugins

import (
 "context"
 "fmt"
 v1 "k8s.io/api/core/v1"
 "k8s.io/apimachinery/pkg/runtime"
 "k8s.io/klog/v2"
 "k8s.io/kubernetes/pkg/scheduler/framework"
 "simple-scheduler/pkg/scheduler/apis/config"
 "simple-scheduler/pkg/scheduler/apis/config/validation"
)

const Name = "sample-plugin"

type Sample struct {
 args   *config.SampleArgs
 handle framework.Handle
}

func (s *Sample) Name() string {
 return Name
}

func (s *Sample) PreFilter(ctx context.Context, cycleState *framework.CycleState, pod *v1.Pod) (*framework.PreFilterResult, *framework.Status) {
 klog.V(3).Infof("prefilter pod: %v", pod.Name)
 return nil, nil
}

func (s *Sample) Filter(ctx context.Context, cycleState *framework.CycleState, pod *v1.Pod, nodeInfo *framework.NodeInfo) *framework.Status {
 klog.V(3).Infof("filter pod: %v, node: %v", pod.Name, nodeInfo.Node().Name)
 return framework.NewStatus(framework.Success, "")
}

func (s *Sample) PreBind(ctx context.Context, state *framework.CycleState, pod *v1.Pod, nodeName string) *framework.Status {
 if nodeInfo, err := s.handle.SnapshotSharedLister().NodeInfos().Get(nodeName); err != nil {
  return framework.NewStatus(framework.Error, fmt.Sprintf("prebind get node: %s info error: %s", nodeName, err.Error()))
 } else {
  klog.V(3).Infof("prebind node info: %+v", nodeInfo.Node())
  return framework.NewStatus(framework.Success, "")
 }
}

func New(fpArgs runtime.Object, fh framework.Handle) (framework.Plugin, error) {
 args, ok := fpArgs.(*config.SampleArgs)
 if !ok {
  return nil, fmt.Errorf("got args of type %T, want *SampleArgs", fpArgs)
 }
 if err := validation.ValidateSamplePluginArgs(*args); err != nil {
  return nil, err
 }
 return &Sample{
  args:   args,
  handle: fh,
 }, nil
}
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.
42.
43.
44.
45.
46.
47.
48.
49.
50.
51.
52.
53.
54.
55.
56.

// +k8s:deepcopy-gen:interfaces=k8s.io/apimachinery/pkg/runtime.Object

type SampleArgs struct {
 metav1.TypeMeta
 FavoriteColor  string `json:"favorite_color,omitempty"`
 FavoriteNumber int    `json:"favorite_number,omitempty"`
 ThanksTo       string `json:"thanks_to,omitempty"`
}
1.
2.
3.
4.
5.
6.
7.
8.

# sample-scheduler.yaml
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: sample-scheduler-clusterrole
rules:
  - apiGroups:
      - ""
    resources:
      - endpoints
      - events
    verbs:
      - create
      - get
      - update
  - apiGroups:
      - ""
    resources:
      - nodes
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - ""
    resources:
      - pods
    verbs:
      - delete
      - get
      - list
      - watch
      - update
  - apiGroups:
      - ""
    resources:
      - bindings
      - pods/binding
    verbs:
      - create
  - apiGroups:
      - ""
    resources:
      - pods/status
    verbs:
      - patch
      - update
  - apiGroups:
      - ""
    resources:
      - replicationcontrollers
      - services
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - apps
      - extensions
    resources:
      - replicasets
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - apps
    resources:
      - statefulsets
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - policy
    resources:
      - poddisruptionbudgets
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - ""
    resources:
      - persistentvolumeclaims
      - persistentvolumes
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - ""
    resources:
      - configmaps
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - "storage.k8s.io"
    resources:
      - storageclasses
      - csinodes
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - "coordination.k8s.io"
    resources:
      - leases
    verbs:
      - create
      - get
      - list
      - update
  - apiGroups:
      - "events.k8s.io"
    resources:
      - events
    verbs:
      - create
      - patch
      - update
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: sample-scheduler-sa
  namespace: kube-system
---
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
  name: sample-scheduler-clusterrolebinding
  namespace: kube-system
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: sample-scheduler-clusterrole
subjects:
  - kind: ServiceAccount
    name: sample-scheduler-sa
    namespace: kube-system
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: scheduler-config
  namespace: kube-system
data:
  scheduler-config.yaml: |
    apiVersion: kubescheduler.config.k8s.io/v1
    kind: KubeSchedulerConfiguration
    leaderElection:
      leaderElect: true
      leaseDuration: 15s
      renewDeadline: 10s
      resourceLock: endpointsleases
      resourceName: sample-scheduler
      resourceNamespace: kube-system
      retryPeriod: 2s
    profiles:
      - schedulerName: sample-scheduler
        plugins:
          preFilter:
            enabled:
              - name: "sample-plugin"
          filter:
            enabled:
              - name: "sample-plugin"
        pluginConfig:
          - name: sample-plugin
            args:  # runtime.Object
              favorColor: "#326CE5"
              favorNumber: 7
              thanksTo: "Kubernetes"---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: sample-scheduler
  namespace: kube-system
  labels:
    component: sample-scheduler
spec:
  selector:
    matchLabels:
      component: sample-scheduler
  template:
    metadata:
      labels:
        component: sample-scheduler
    spec:
      serviceAccountName: sample-scheduler-sa
      priorityClassName: system-cluster-critical
      volumes:
        - name: scheduler-config
          configMap:
            name: scheduler-config
      containers:
        - name: scheduler
          image: cnych/sample-scheduler:v0.26.4
          imagePullPolicy: IfNotPresent
          command:
            - sample-scheduler
            - --config=/etc/kubernetes/scheduler-config.yaml
            - --v=3
          volumeMounts:
            - name: scheduler-config
              mountPath: /etc/kubernetes
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.
42.
43.
44.
45.
46.
47.
48.
49.
50.
51.
52.
53.
54.
55.
56.
57.
58.
59.
60.
61.
62.
63.
64.
65.
66.
67.
68.
69.
70.
71.
72.
73.
74.
75.
76.
77.
78.
79.
80.
81.
82.
83.
84.
85.
86.
87.
88.
89.
90.
91.
92.
93.
94.
95.
96.
97.
98.
99.
100.
101.
102.
103.
104.
105.
106.
107.
108.
109.
110.
111.
112.
113.
114.
115.
116.
117.
118.
119.
120.
121.
122.
123.
124.
125.
126.
127.
128.
129.
130.
131.
132.
133.
134.
135.
136.
137.
138.
139.
140.
141.
142.
143.
144.
145.
146.
147.
148.
149.
150.
151.
152.
153.
154.
155.
156.
157.
158.
159.
160.
161.
162.
163.
164.
165.
166.
167.
168.
169.
170.
171.
172.
173.
174.
175.
176.
177.
178.
179.
180.
181.
182.
183.
184.
185.
186.
187.
188.
189.
190.
191.
192.
193.
194.
195.
196.
197.
198.
199.
200.
201.
202.
203.
204.
205.
206.
207.
208.
209.
210.

# test-scheduler.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: test-scheduler
spec:
  selector:
    matchLabels:
      app: test-scheduler
  template:
    metadata:
      labels:
        app: test-scheduler
    spec:
      schedulerName: sample-scheduler # 指定使用的调度器，不指定使用默认的default-scheduler
      containers:
        - image: nginx:1.7.9
          imagePullPolicy: IfNotPresent
          name: nginx
          ports:
            - containerPort: 80
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.

➜ kubectl get pods -n kube-system -l component=sample-scheduler
NAME                               READY   STATUS    RESTARTS   AGE
sample-scheduler-896658cd7-k7vcl   1/1     Running   0          57s
➜ kubectl logs -f sample-scheduler-896658cd7-k7vcl -n kube-system
I0114 09:14:18.878613       1 eventhandlers.go:173] add event for unscheduled pod default/test-scheduler-6486fd49fc-zjhcx
I0114 09:14:18.878670       1 scheduler.go:464] Attempting to schedule pod: default/test-scheduler-6486fd49fc-zjhcx
I0114 09:14:18.878706       1 sample.go:77] "Start PreFilter Pod" pod="test-scheduler-6486fd49fc-zjhcx"
I0114 09:14:18.878802       1 sample.go:93] "Start Filter Pod" pod="test-scheduler-6486fd49fc-zjhcx" node="node2" preFilterState=&{Resource:{MilliCPU:0 Memory:0 EphemeralStorage:0 AllowedPodNumber:0 ScalarResources:map[]}}
I0114 09:14:18.878835       1 sample.go:93] "Start Filter Pod" pod="test-scheduler-6486fd49fc-zjhcx" node="node1" preFilterState=&{Resource:{MilliCPU:0 Memory:0 EphemeralStorage:0 AllowedPodNumber:0 ScalarResources:map[]}}
I0114 09:14:18.879043       1 default_binder.go:51] Attempting to bind default/test-scheduler-6486fd49fc-zjhcx to node1
I0114 09:14:18.886360       1 scheduler.go:609] "Successfully bound pod to node" pod="default/test-scheduler-6486fd49fc-zjhcx" node="node1" evaluatedNodes=3 feasibleNodes=2
I0114 09:14:18.887426       1 eventhandlers.go:205] delete event for unscheduled pod default/test-scheduler-6486fd49fc-zjhcx
I0114 09:14:18.887475       1 eventhandlers.go:225] add event for scheduled pod default/test-scheduler-6486fd49fc-zjhcx
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.

➜ kubectl get pods
NAME                              READY   STATUS    RESTARTS       AGE
test-scheduler-6486fd49fc-zjhcx   1/1     Running   0              35s
➜ kubectl get pod test-scheduler-6486fd49fc-zjhcx -o yaml
......
restartPolicy: Always
schedulerName: sample-scheduler
securityContext: {}
serviceAccount: default
......
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.