// Calculates host priority based on the amount of unused resources.
// 'node' has information about the resources on the node.
// 'pods' is a list of pods currently scheduled on the node.
// TODO: Use Node() from nodeInfo instead of passing it.
func calculateUnusedPriority(pod *api.Pod, podRequests *schedulercache.Resource, node *api.Node, nodeInfo *schedulercache.NodeInfo) schedulerapi.HostPriority {
allocatableResources := nodeInfo.AllocatableResource()
totalResources := *podRequests
totalResources.MilliCPU += nodeInfo.NonZeroRequest().MilliCPU
totalResources.Memory += nodeInfo.NonZeroRequest().Memory
cpuScore := calculateUnusedScore(totalResources.MilliCPU, allocatableResources.MilliCPU, node.Name)
memoryScore := calculateUnusedScore(totalResources.Memory, allocatableResources.Memory, node.Name)
if glog.V(10) {
// We explicitly don't do glog.V(10).Infof() to avoid computing all the parameters if this is
// not logged. There is visible performance gain from it.
glog.V(10).Infof(
"%v -> %v: Least Requested Priority, capacity %d millicores %d memory bytes, total request %d millicores %d memory bytes, score %d CPU %d memory",
pod.Name, node.Name,
allocatableResources.MilliCPU, allocatableResources.Memory,
totalResources.MilliCPU, totalResources.Memory,
cpuScore, memoryScore,
)
}
return schedulerapi.HostPriority{
Host: node.Name,
Score: int((cpuScore + memoryScore) / 2),
}
}
func PodFitsResources(pod *api.Pod, meta interface{}, nodeInfo *schedulercache.NodeInfo) (bool, []algorithm.PredicateFailureReason, error) {
node := nodeInfo.Node()
if node == nil {
return false, nil, fmt.Errorf("node not found")
}
var predicateFails []algorithm.PredicateFailureReason
allowedPodNumber := nodeInfo.AllowedPodNumber()
if len(nodeInfo.Pods())+1 > allowedPodNumber {
predicateFails = append(predicateFails, NewInsufficientResourceError(api.ResourcePods, 1, int64(len(nodeInfo.Pods())), int64(allowedPodNumber)))
}
var podRequest *schedulercache.Resource
if predicateMeta, ok := meta.(*predicateMetadata); ok {
podRequest = predicateMeta.podRequest
} else {
// We couldn't parse metadata - fallback to computing it.
podRequest = GetResourceRequest(pod)
}
if podRequest.MilliCPU == 0 && podRequest.Memory == 0 && podRequest.NvidiaGPU == 0 && len(podRequest.OpaqueIntResources) == 0 {
return len(predicateFails) == 0, predicateFails, nil
}
allocatable := nodeInfo.AllocatableResource()
if allocatable.MilliCPU < podRequest.MilliCPU+nodeInfo.RequestedResource().MilliCPU {
predicateFails = append(predicateFails, NewInsufficientResourceError(api.ResourceCPU, podRequest.MilliCPU, nodeInfo.RequestedResource().MilliCPU, allocatable.MilliCPU))
}
if allocatable.Memory < podRequest.Memory+nodeInfo.RequestedResource().Memory {
predicateFails = append(predicateFails, NewInsufficientResourceError(api.ResourceMemory, podRequest.Memory, nodeInfo.RequestedResource().Memory, allocatable.Memory))
}
if allocatable.NvidiaGPU < podRequest.NvidiaGPU+nodeInfo.RequestedResource().NvidiaGPU {
predicateFails = append(predicateFails, NewInsufficientResourceError(api.ResourceNvidiaGPU, podRequest.NvidiaGPU, nodeInfo.RequestedResource().NvidiaGPU, allocatable.NvidiaGPU))
}
for rName, rQuant := range podRequest.OpaqueIntResources {
if allocatable.OpaqueIntResources[rName] < rQuant+nodeInfo.RequestedResource().OpaqueIntResources[rName] {
predicateFails = append(predicateFails, NewInsufficientResourceError(rName, podRequest.OpaqueIntResources[rName], nodeInfo.RequestedResource().OpaqueIntResources[rName], allocatable.OpaqueIntResources[rName]))
}
}
if glog.V(10) {
// We explicitly don't do glog.V(10).Infof() to avoid computing all the parameters if this is
// not logged. There is visible performance gain from it.
glog.Infof("Schedule Pod %+v on Node %+v is allowed, Node is running only %v out of %v Pods.",
podName(pod), node.Name, len(nodeInfo.Pods()), allowedPodNumber)
}
return len(predicateFails) == 0, predicateFails, nil
}
func PodFitsResources(pod *api.Pod, meta interface{}, nodeInfo *schedulercache.NodeInfo) (bool, error) {
node := nodeInfo.Node()
if node == nil {
return false, fmt.Errorf("node not found")
}
allowedPodNumber := nodeInfo.AllowedPodNumber()
if len(nodeInfo.Pods())+1 > allowedPodNumber {
return false,
newInsufficientResourceError(podCountResourceName, 1, int64(len(nodeInfo.Pods())), int64(allowedPodNumber))
}
var podRequest *schedulercache.Resource
if predicateMeta, ok := meta.(*predicateMetadata); ok {
podRequest = predicateMeta.podRequest
} else {
// We couldn't parse metadata - fallback to computing it.
podRequest = getResourceRequest(pod)
}
if podRequest.MilliCPU == 0 && podRequest.Memory == 0 && podRequest.NvidiaGPU == 0 {
return true, nil
}
allocatable := nodeInfo.AllocatableResource()
if allocatable.MilliCPU < podRequest.MilliCPU+nodeInfo.RequestedResource().MilliCPU {
return false,
newInsufficientResourceError(cpuResourceName, podRequest.MilliCPU, nodeInfo.RequestedResource().MilliCPU, allocatable.MilliCPU)
}
if allocatable.Memory < podRequest.Memory+nodeInfo.RequestedResource().Memory {
return false,
newInsufficientResourceError(memoryResourceName, podRequest.Memory, nodeInfo.RequestedResource().Memory, allocatable.Memory)
}
if allocatable.NvidiaGPU < podRequest.NvidiaGPU+nodeInfo.RequestedResource().NvidiaGPU {
return false,
newInsufficientResourceError(nvidiaGpuResourceName, podRequest.NvidiaGPU, nodeInfo.RequestedResource().NvidiaGPU, allocatable.NvidiaGPU)
}
if glog.V(10) {
// We explicitly don't do glog.V(10).Infof() to avoid computing all the parameters if this is
// not logged. There is visible performance gain from it.
glog.Infof("Schedule Pod %+v on Node %+v is allowed, Node is running only %v out of %v Pods.",
podName(pod), node.Name, len(nodeInfo.Pods()), allowedPodNumber)
}
return true, nil
}
func calculateBalancedResourceAllocation(pod *api.Pod, podRequests *schedulercache.Resource, nodeInfo *schedulercache.NodeInfo) (schedulerapi.HostPriority, error) {
node := nodeInfo.Node()
if node == nil {
return schedulerapi.HostPriority{}, fmt.Errorf("node not found")
}
allocatableResources := nodeInfo.AllocatableResource()
totalResources := *podRequests
totalResources.MilliCPU += nodeInfo.NonZeroRequest().MilliCPU
totalResources.Memory += nodeInfo.NonZeroRequest().Memory
cpuFraction := fractionOfCapacity(totalResources.MilliCPU, allocatableResources.MilliCPU)
memoryFraction := fractionOfCapacity(totalResources.Memory, allocatableResources.Memory)
score := int(0)
if cpuFraction >= 1 || memoryFraction >= 1 {
// if requested >= capacity, the corresponding host should never be preferred.
score = 0
} else {
// Upper and lower boundary of difference between cpuFraction and memoryFraction are -1 and 1
// respectively. Multilying the absolute value of the difference by 10 scales the value to
// 0-10 with 0 representing well balanced allocation and 10 poorly balanced. Subtracting it from
// 10 leads to the score which also scales from 0 to 10 while 10 representing well balanced.
diff := math.Abs(cpuFraction - memoryFraction)
score = int(10 - diff*10)
}
if glog.V(10) {
// We explicitly don't do glog.V(10).Infof() to avoid computing all the parameters if this is
// not logged. There is visible performance gain from it.
glog.V(10).Infof(
"%v -> %v: Balanced Resource Allocation, capacity %d millicores %d memory bytes, total request %d millicores %d memory bytes, score %d",
pod.Name, node.Name,
allocatableResources.MilliCPU, allocatableResources.Memory,
totalResources.MilliCPU, totalResources.Memory,
score,
)
}
return schedulerapi.HostPriority{
Host: node.Name,
Score: score,
}, nil
}
