k8s 缩容时待删除pod的选择

// pkg/controller/replicaset/replicaset.go


// func() syncReplicaSet

if rsNeedsSync && rs.DeletionTimestamp == nil {
		manageReplicasErr = rsc.manageReplicas(ctx, filteredPods, rs)
	}

// func() manageReplicas
} else if diff > 0 {
		if diff > rsc.burstReplicas {
			diff = rsc.burstReplicas
		}
		klog.V(2).InfoS("Too many replicas", "replicaSet", klog.KObj(rs), "need", *(rs.Spec.Replicas), "deleting", diff)

		relatedPods, err := rsc.getIndirectlyRelatedPods(rs)
		utilruntime.HandleError(err)

		// Choose which Pods to delete, preferring those in earlier phases of startup.
		podsToDelete := getPodsToDelete(filteredPods, relatedPods, diff)

func getPodsToDelete(filteredPods, relatedPods []*v1.Pod, diff int) []*v1.Pod {
	// No need to sort pods if we are about to delete all of them.
	// diff will always be <= len(filteredPods), so not need to handle > case.
	if diff < len(filteredPods) {
		podsWithRanks := getPodsRankedByRelatedPodsOnSameNode(filteredPods, relatedPods)
		sort.Sort(podsWithRanks)
		reportSortingDeletionAgeRatioMetric(filteredPods, diff)
	}
	return filteredPods[:diff]
}

/*getPodsRankedByRelatedPodsOnSameNode returns an ActivePodsWithRanks value
that wraps podsToRank and assigns each pod a rank equal to the number of
active pods in relatedPods that are colocated on the same node with the pod.
relatedPods generally should be a superset of podsToRank.
*/
func getPodsRankedByRelatedPodsOnSameNode(podsToRank, relatedPods []*v1.Pod) controller.ActivePodsWithRanks {
	podsOnNode := make(map[string]int)
	for _, pod := range relatedPods {
		if controller.IsPodActive(pod) {
			podsOnNode[pod.Spec.NodeName]++
		}
	}
	ranks := make([]int, len(podsToRank))
	for i, pod := range podsToRank {
		ranks[i] = podsOnNode[pod.Spec.NodeName]
	}
	return controller.ActivePodsWithRanks{Pods: podsToRank, Rank: ranks, Now: metav1.Now()}
}

func (s ActivePodsWithRanks) Less(i, j int) bool {
	// 1. Unassigned < assigned
	// If only one of the pods is unassigned, the unassigned one is smaller
	if s.Pods[i].Spec.NodeName != s.Pods[j].Spec.NodeName && (len(s.Pods[i].Spec.NodeName) == 0 || len(s.Pods[j].Spec.NodeName) == 0) {
		return len(s.Pods[i].Spec.NodeName) == 0
	}
	// 2. PodPending < PodUnknown < PodRunning
	if podPhaseToOrdinal[s.Pods[i].Status.Phase] != podPhaseToOrdinal[s.Pods[j].Status.Phase] {
		return podPhaseToOrdinal[s.Pods[i].Status.Phase] < podPhaseToOrdinal[s.Pods[j].Status.Phase]
	}
	// 3. Not ready < ready
	// If only one of the pods is not ready, the not ready one is smaller
	if podutil.IsPodReady(s.Pods[i]) != podutil.IsPodReady(s.Pods[j]) {
		return !podutil.IsPodReady(s.Pods[i])
	}

	// 4. lower pod-deletion-cost < higher pod-deletion cost
	if utilfeature.DefaultFeatureGate.Enabled(features.PodDeletionCost) {
		pi, _ := helper.GetDeletionCostFromPodAnnotations(s.Pods[i].Annotations)
		pj, _ := helper.GetDeletionCostFromPodAnnotations(s.Pods[j].Annotations)
		if pi != pj {
			return pi < pj
		}
	}

	// 5. Doubled up < not doubled up
	// If one of the two pods is on the same node as one or more additional
	// ready pods that belong to the same replicaset, whichever pod has more
	// colocated ready pods is less
	if s.Rank[i] != s.Rank[j] {
		return s.Rank[i] > s.Rank[j]
	}
	// TODO: take availability into account when we push minReadySeconds information from deployment into pods,
	//       see https://github.com/kubernetes/kubernetes/issues/22065
	// 6. Been ready for empty time < less time < more time
	// If both pods are ready, the latest ready one is smaller
	if podutil.IsPodReady(s.Pods[i]) && podutil.IsPodReady(s.Pods[j]) {
		readyTime1 := podReadyTime(s.Pods[i])
		readyTime2 := podReadyTime(s.Pods[j])
		if !readyTime1.Equal(readyTime2) {
			if !utilfeature.DefaultFeatureGate.Enabled(features.LogarithmicScaleDown) {
				return afterOrZero(readyTime1, readyTime2)
			} else {
				if s.Now.IsZero() || readyTime1.IsZero() || readyTime2.IsZero() {
					return afterOrZero(readyTime1, readyTime2)
				}
				rankDiff := logarithmicRankDiff(*readyTime1, *readyTime2, s.Now)
				if rankDiff == 0 {
					return s.Pods[i].UID < s.Pods[j].UID
				}
				return rankDiff < 0
			}
		}
	}
	// 7. Pods with containers with higher restart counts < lower restart counts
	if maxContainerRestarts(s.Pods[i]) != maxContainerRestarts(s.Pods[j]) {
		return maxContainerRestarts(s.Pods[i]) > maxContainerRestarts(s.Pods[j])
	}
	// 8. Empty creation time pods < newer pods < older pods
	if !s.Pods[i].CreationTimestamp.Equal(&s.Pods[j].CreationTimestamp) {
		if !utilfeature.DefaultFeatureGate.Enabled(features.LogarithmicScaleDown) {
			return afterOrZero(&s.Pods[i].CreationTimestamp, &s.Pods[j].CreationTimestamp)
		} else {
			if s.Now.IsZero() || s.Pods[i].CreationTimestamp.IsZero() || s.Pods[j].CreationTimestamp.IsZero() {
				return afterOrZero(&s.Pods[i].CreationTimestamp, &s.Pods[j].CreationTimestamp)
			}
			rankDiff := logarithmicRankDiff(s.Pods[i].CreationTimestamp, s.Pods[j].CreationTimestamp, s.Now)
			if rankDiff == 0 {
				return s.Pods[i].UID < s.Pods[j].UID
			}
			return rankDiff < 0
		}
	}
	return false
}