深入理解Kubernetes - 基于OOMKill的QoS的设计

1
2

printf 'PID\tOOM Score\tOOM Adj\tCommand\n'
while read -r pid comm; do [ -f /proc/$pid/oom_score ] && [ $(cat /proc/$pid/oom_score) != 0 ] && printf '%d\t%d\t\t%d\t%s\n' "$pid" "$(cat /proc/$pid/oom_score)" "$(cat /proc/$pid/oom_score_adj)" "$comm"; done < <(ps -e -o pid= -o comm=) | sort -k 2nr

1

my_process invoked oom-killer: gfp_mask=0x201da, order=0, oom_score_adj=0

1
2
3
4
5
6
7
8

const (
	// KubeletOOMScoreAdj is the OOM score adjustment for Kubelet
	KubeletOOMScoreAdj int = -999
	// KubeProxyOOMScoreAdj is the OOM score adjustment for kube-proxy
	KubeProxyOOMScoreAdj  int = -999
	guaranteedOOMScoreAdj int = -998
	besteffortOOMScoreAdj int = 1000
)

 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

func GetContainerOOMScoreAdjust(pod *v1.Pod, container *v1.Container, memoryCapacity int64) int {
	if types.IsNodeCriticalPod(pod) {
		// Only node critical pod should be the last to get killed.
		return guaranteedOOMScoreAdj
	}

	switch v1qos.GetPodQOS(pod) {
	case v1.PodQOSGuaranteed:
		// Guaranteed containers should be the last to get killed.
		return guaranteedOOMScoreAdj
	case v1.PodQOSBestEffort:
		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()
	if utilfeature.DefaultFeatureGate.Enabled(features.InPlacePodVerticalScaling) {
		if cs, ok := podutil.GetContainerStatus(pod.Status.ContainerStatuses, container.Name); ok {
			memoryRequest = cs.AllocatedResources.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)
}