kubernets中负责pod调度的重要模块是kube-schduler。kube-scheduler就是调度安排Pod到具体的Node，，kube-scheduler通过API Server提供的接口监听Pod任务列表，获取待调度pod，然后根据一系列的预选策略和优选策略给各个Node节点打分，然后将Pod发送到得分最高的Node节点上，同时将绑定信息写入etcd.
node节点上的kubelet通过kuber-apiserver的监听，获取kube-scheduler产生的绑定事件，获取pod清单，下载镜像，启动容器。
调度策略
Kubernetes的调度策略分为Predicates（预选策略）和Priorites（优选策略），整个调度过程分为两步：
预选策略，Predicates是强制性规则，遍历所有的Node节点，按照具体的预选策略筛选出符合要求的Node列表，如没有Node符合Predicates策略规则，那该Pod就会被挂起，直到有Node能够满足。
优选策略，在第一步筛选的基础上，按照优选策略为待选Node打分排序，获取最优者。
- 源码位置：
predicates包为k8s支持的所有预选策略
priorites包为k8s支持的所有优选策略
algorithmprovider包下的defaults包为默认的预选和优选策略
Predicates 预选策略
v1.7支持15个策略，Kubernetes（v1.7）中可用的Predicates策略有：
- MatchNodeSelector：检查spec.nodeSelector是否包含Node节点的label定义
- PodFitsResources：检查主机的资源(cpu和内存)是否满足Pod的需求，根据实际已经分配（Limit）的资源量做调度
- PodFitsHostPorts：检查Pod内每一个容器所需的HostPort是否已被其它容器占用，如果有所需的HostPort不满足需求，那么Pod不能调度到这个主机上
- HostName：检查主机名称是不是Pod指定的NodeName
- NoDiskConflict：根据pod.spec.volumes检查在此主机上是否存在卷冲突。如果这个主机已经挂载了卷，其它同样使用这个卷的Pod不能调度到这个主机上，不同的存储后端具体规则不同
- NoVolumeZoneConflict：检查给定的zone限制前提下，检查如果在此主机上部署Pod是否存在卷冲突
- PodToleratesNodeTaints：确保pod定义的tolerates能接纳node定义的taints
- CheckNodeMemoryPressure：检查pod是否可以调度到已经报告了主机内存压力过大的节点
- CheckNodeDiskPressure：检查pod是否可以调度到已经报告了主机的存储压力过大的节点
- MaxEBSVolumeCount：确保已挂载的EBS存储卷不超过设置的最大值，默认39
- MaxGCEPDVolumeCount：确保已挂载的GCE存储卷不超过设置的最大值，默认16
- MaxAzureDiskVolumeCount：确保已挂载的Azure存储卷不超过设置的最大值，默认16
- MatchInterPodAffinity：检查pod和其他pod是否符合亲和性规则
- GeneralPredicates：检查pod与主机上kubernetes相关组件是否匹配
- NoVolumeNodeConflict：检查给定的Node限制前提下，检查如果在此主机上部署Pod是否存在卷冲突
Priorites 优选策略
Kubernetes（v1.7）中可用的Priorites策略有：
- EqualPriority：所有节点同样优先级
- ImageLocalityPriority：根据主机上是否已具备Pod运行的环境来打分，得分计算：不存在所需镜像，返回0分，存在镜像，镜像越大得分越高
- LeastRequestedPriority：计算Pods需要的CPU和内存在当前节点可用资源的百分比，具有最小百分比的节点就是最优，得分计算公式
cpu((capacity – sum(requested)) * 10 / capacity) + memory((capacity – sum(requested)) * 10 / capacity) / 2
- BalancedResourceAllocation：节点上各项资源（CPU、内存）使用率最均衡的为最优，得分计算公式
10 – abs(totalCpu/cpuNodeCapacity-totalMemory/memoryNodeCapacity)*10
- SelectorSpreadPriority：按Service和Replicaset归属计算Node上分布最少的同类Pod数量，得分计算：数量越少得分越高
- NodePreferAvoidPodsPriority：判断alpha.kubernetes.io/preferAvoidPods属性，设置权重为10000，覆盖其他策略
- NodeAffinityPriority：节点亲和性选择策略，提供两种选择器支持：requiredDuringSchedulingIgnoredDuringExecution（保证所选的主机必须满足所有Pod对主机的规则要求）、preferresDuringSchedulingIgnoredDuringExecution（调度器会尽量但不保证满足NodeSelector的所有要求）
- TaintTolerationPriority：类似于Predicates策略中的PodToleratesNodeTaints，优先调度到标记了Taint的节点
- InterPodAffinityPriority：pod亲和性选择策略，类似NodeAffinityPriority，提供两种选择器支持：requiredDuringSchedulingIgnoredDuringExecution（保证所选的主机必须满足所有Pod对主机的规则要求）、preferresDuringSchedulingIgnoredDuringExecution（调度器会尽量但不保证满足NodeSelector的所有要求）
- MostRequestedPriority：动态伸缩集群环境比较适用，会优先调度pod到使用率最高的主机节点，这样在伸缩集群时，就会腾出空闲机器，从而进行停机处理。
默认策略
默认预选策略
func defaultPredicates() sets.String {
predSet := sets.NewString(
factory.RegisterFitPredicateFactory(
"NoVolumeZoneConflict",
func(args factory.PluginFactoryArgs) algorithm.FitPredicate {
return predicates.NewVolumeZonePredicate(args.PVInfo, args.PVCInfo)
},
),
factory.RegisterFitPredicateFactory(
"MaxEBSVolumeCount",
func(args factory.PluginFactoryArgs) algorithm.FitPredicate {
// TODO: allow for generically parameterized scheduler predicates, because this is a bit ugly
maxVols := getMaxVols(aws.DefaultMaxEBSVolumes)
return predicates.NewMaxPDVolumeCountPredicate(predicates.EBSVolumeFilter, maxVols, args.PVInfo, args.PVCInfo)
},
),
factory.RegisterFitPredicateFactory(
"MaxGCEPDVolumeCount",
func(args factory.PluginFactoryArgs) algorithm.FitPredicate {
// TODO: allow for generically parameterized scheduler predicates, because this is a bit ugly
maxVols := getMaxVols(DefaultMaxGCEPDVolumes)
return predicates.NewMaxPDVolumeCountPredicate(predicates.GCEPDVolumeFilter, maxVols, args.PVInfo, args.PVCInfo)
},
),
factory.RegisterFitPredicateFactory(
"MaxAzureDiskVolumeCount",
func(args factory.PluginFactoryArgs) algorithm.FitPredicate {
// TODO: allow for generically parameterized scheduler predicates, because this is a bit ugly
maxVols := getMaxVols(DefaultMaxAzureDiskVolumes)
return predicates.NewMaxPDVolumeCountPredicate(predicates.AzureDiskVolumeFilter, maxVols, args.PVInfo, args.PVCInfo)
},
),
factory.RegisterFitPredicateFactory(
predicates.MatchInterPodAffinity,
func(args factory.PluginFactoryArgs) algorithm.FitPredicate {
return predicates.NewPodAffinityPredicate(args.NodeInfo, args.PodLister)
},
),
factory.RegisterFitPredicate("NoDiskConflict", predicates.NoDiskConflict),
factory.RegisterFitPredicate("GeneralPredicates", predicates.GeneralPredicates),
factory.RegisterFitPredicate("CheckNodeMemoryPressure", predicates.CheckNodeMemoryPressurePredicate),
factory.RegisterFitPredicate("CheckNodeDiskPressure", predicates.CheckNodeDiskPressurePredicate),
factory.RegisterFitPredicateFactory(
"NoVolumeNodeConflict",
func(args factory.PluginFactoryArgs) algorithm.FitPredicate {
return predicates.NewVolumeNodePredicate(args.PVInfo, args.PVCInfo, nil)
},
),
)
if utilfeature.DefaultFeatureGate.Enabled(features.TaintNodesByCondition) {
predSet.Insert(factory.RegisterMandatoryFitPredicate("PodToleratesNodeTaints", predicates.PodToleratesNodeTaints))
glog.Warningf("TaintNodesByCondition is enabled, PodToleratesNodeTaints predicate is mandatory")
} else {
predSet.Insert(factory.RegisterMandatoryFitPredicate("CheckNodeCondition", predicates.CheckNodeConditionPredicate))
predSet.Insert(factory.RegisterFitPredicate("PodToleratesNodeTaints", predicates.PodToleratesNodeTaints))
}
return predSet
}
默认优选策略
func defaultPriorities() sets.String {
return sets.NewString(
factory.RegisterPriorityConfigFactory(
"SelectorSpreadPriority",
factory.PriorityConfigFactory{
Function: func(args factory.PluginFactoryArgs) algorithm.PriorityFunction {
return priorities.NewSelectorSpreadPriority(args.ServiceLister, args.ControllerLister, args.ReplicaSetLister, args.StatefulSetLister)
},
Weight: 1,
},
),
factory.RegisterPriorityConfigFactory(
"InterPodAffinityPriority",
factory.PriorityConfigFactory{
Function: func(args factory.PluginFactoryArgs) algorithm.PriorityFunction {
return priorities.NewInterPodAffinityPriority(args.NodeInfo, args.NodeLister, args.PodLister, args.HardPodAffinitySymmetricWeight)
},
Weight: 1,
},
),
factory.RegisterPriorityFunction2("LeastRequestedPriority", priorities.LeastRequestedPriorityMap, nil, 1),
factory.RegisterPriorityFunction2("BalancedResourceAllocation", priorities.BalancedResourceAllocationMap, nil, 1),
factory.RegisterPriorityFunction2("NodePreferAvoidPodsPriority", priorities.CalculateNodePreferAvoidPodsPriorityMap, nil, 10000),
factory.RegisterPriorityFunction2("NodeAffinityPriority", priorities.CalculateNodeAffinityPriorityMap, priorities.CalculateNodeAffinityPriorityReduce, 1),
factory.RegisterPriorityFunction2("TaintTolerationPriority", priorities.ComputeTaintTolerationPriorityMap, priorities.ComputeTaintTolerationPriorityReduce, 1),
)
}
默认注册但不加载的策略
预选策略
// Registers predicates and priorities that are not enabled by default, but user can pick when creating his
// own set of priorities/predicates.
factory.RegisterFitPredicate("PodFitsPorts", predicates.PodFitsHostPorts)
factory.RegisterFitPredicate("PodFitsHostPorts", predicates.PodFitsHostPorts)
factory.RegisterFitPredicate("PodFitsResources", predicates.PodFitsResources)
factory.RegisterFitPredicate("HostName", predicates.PodFitsHost)
factory.RegisterFitPredicate("MatchNodeSelector", predicates.PodMatchNodeSelector)
优选策略
factory.RegisterPriorityFunction2("EqualPriority", core.EqualPriorityMap, nil, 1)
factory.RegisterPriorityFunction2("ImageLocalityPriority", priorities.ImageLocalityPriorityMap, nil, 1)
factory.RegisterPriorityFunction2("MostRequestedPriority", priorities.MostRequestedPriorityMap, nil, 1)
