// GetContainerOOMAdjust returns the amount by which the OOM score of all processes in the
// container should be adjusted.
// The OOM score of a process is the percentage of memory it consumes
// multiplied by 10 (barring exceptional cases) + a configurable quantity which is between -1000
// and 1000. Containers with higher OOM scores are killed if the system runs out of memory.
// See https://lwn.net/Articles/391222/ for more information.
func GetContainerOOMScoreAdjust(pod *v1.Pod, container *v1.Container, memoryCapacity int64) int {
if kubetypes.IsCriticalPod(pod) {
return CriticalPodOOMAdj
}
switch GetPodQOS(pod) {
case Guaranteed:
// Guaranteed containers should be the last to get killed.
return guaranteedOOMScoreAdj
case BestEffort:
return besteffortOOMScoreAdj
}
// Burstable containers are a middle tier, between Guaranteed and Best-Effort. Ideally,
// we want to protect Burstable containers that consume less memory than requested.
// The formula below is a heuristic. A container requesting for 10% of a system's
// memory will have an OOM score adjust of 900. If a process in container Y
// uses over 10% of memory, its OOM score will be 1000. The idea is that containers
// which use more than their request will have an OOM score of 1000 and will be prime
// targets for OOM kills.
// Note that this is a heuristic, it won't work if a container has many small processes.
memoryRequest := container.Resources.Requests.Memory().Value()
oomScoreAdjust := 1000 - (1000*memoryRequest)/memoryCapacity
// A guaranteed pod using 100% of memory can have an OOM score of 10. Ensure
// that burstable pods have a higher OOM score adjustment.
if int(oomScoreAdjust) < (1000 + guaranteedOOMScoreAdj) {
return (1000 + guaranteedOOMScoreAdj)
}
// Give burstable pods a higher chance of survival over besteffort pods.
if int(oomScoreAdjust) == besteffortOOMScoreAdj {
return int(oomScoreAdjust - 1)
}
return int(oomScoreAdjust)
}
// Admit rejects a pod if its not safe to admit for node stability.
func (m *managerImpl) Admit(attrs *lifecycle.PodAdmitAttributes) lifecycle.PodAdmitResult {
m.RLock()
defer m.RUnlock()
if len(m.nodeConditions) == 0 {
return lifecycle.PodAdmitResult{Admit: true}
}
// the node has memory pressure, admit if not best-effort
if hasNodeCondition(m.nodeConditions, v1.NodeMemoryPressure) {
notBestEffort := v1.PodQOSBestEffort != qos.GetPodQOS(attrs.Pod)
if notBestEffort || kubetypes.IsCriticalPod(attrs.Pod) {
return lifecycle.PodAdmitResult{Admit: true}
}
}
// reject pods when under memory pressure (if pod is best effort), or if under disk pressure.
glog.Warningf("Failed to admit pod %v - %s", format.Pod(attrs.Pod), "node has conditions: %v", m.nodeConditions)
return lifecycle.PodAdmitResult{
Admit: false,
Reason: reason,
Message: fmt.Sprintf(message, m.nodeConditions),
}
}
