K8S中Eviction Manager如何实现Pod驱逐

func (m *managerImpl) synchronize(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc, capacityProvider CapacityProvider) []*v1.Pod {

   // 1. 从配置中读取所有Thresholds

   thresholds := m.config.Thresholds

   if len(thresholds) == 0 {

      return nil

   }

   ....

   // 2. 初始化rank funcs/reclaim funcs等

   if m.dedicatedImageFs == nil {

      hasImageFs, ok := diskInfoProvider.HasDedicatedImageFs()

      if ok != nil {

         return nil

      }

      m.dedicatedImageFs = &hasImageFs

      m.resourceToRankFunc = buildResourceToRankFunc(hasImageFs)

      m.resourceToNodeReclaimFuncs = buildResourceToNodeReclaimFuncs(m.imageGC, m.containerGC, hasImageFs)

   }

   // 3. 通过初始化传入的func获取Pods

   activePods := podFunc()

   // 4. 通过summary provider获得当前资源使用情况

   observations, statsFunc, err := makeSignalObservations(m.summaryProvider, capacityProvider, activePods)

   ....

   // 5. 通过memcg加速内存占用通知，只在notifiersInitialized 为false时进入

   if m.config.KernelMemcgNotification && !m.notifiersInitialized {

      ....

      m.notifiersInitialized = true  // 初始化完成 

     err = startMemoryThresholdNotifier(m.config.Thresholds, observations, true, func(desc string) {

         // 回调函数，memcg的通知会立即触发synchronize函数

        glog.Infof("hard memory eviction threshold crossed at %s", desc)

         m.synchronize(diskInfoProvider, podFunc, capacityProvider)

      })

      ....

   }

   ....

}

func (m *managerImpl) synchronize(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc, capacityProvider CapacityProvider) []*v1.Pod {

    ....

    // 1. 根据配置的thresholds参数以及当前资源使用情况，计算出超出的thresholds

    thresholds = thresholdsMet(thresholds, observations, false)

    // 2. 合并上次计算的thresholds结果

    if len(m.thresholdsMet) > 0 {

        thresholdsNotYetResolved := thresholdsMet(m.thresholdsMet, observations, true)

        thresholds = mergeThresholds(thresholds, thresholdsNotYetResolved)

    }

    // 3. 过滤未真正激活的soft thresholds

    now := m.clock.Now()

    thresholdsFirstObservedAt := thresholdsFirstObservedAt(thresholds, m.thresholdsFirstObservedAt, now)

    ....

    thresholds = thresholdsMetGracePeriod(thresholdsFirstObservedAt, now)

    // 4. 更新计算结果

    m.Lock()

    m.nodeConditions = nodeConditions

    m.thresholdsFirstObservedAt = thresholdsFirstObservedAt

    m.nodeConditionsLastObservedAt = nodeConditionsLastObservedAt

    m.thresholdsMet = thresholds

    // determine the set of thresholds whose stats have been updated since the last sync

    thresholds = thresholdsUpdatedStats(thresholds, observations, m.lastObservations)

    debugLogThresholdsWithObservation("thresholds - updated stats", thresholds, observations)

    m.lastObservations = observations

    m.Unlock()

   ...

}

func (m *managerImpl) synchronize(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc, capacityProvider CapacityProvider) []*v1.Pod {

    ....

    // 1. 收集当前所有发生紧缺的resource类型

    starvedResources := getStarvedResources(thresholds)

    if len(starvedResources) == 0 {

        glog.V(3).Infof("eviction manager: no resources are starved")

        return nil

    }

    // 2. 排序并选择其中一种resource

    sort.Sort(byEvictionPriority(starvedResources))

    resourceToReclaim := starvedResources[0]

    // determine if this is a soft or hard eviction associated with the resource

    softEviction := isSoftEvictionThresholds(thresholds, resourceToReclaim)

    .....

    // 3. 根据选中Resource的使用量来排序Pods

    rank, ok := m.resourceToRankFunc[resourceToReclaim]

    ....

    rank(activePods, statsFunc)

    ....

}

func (m *managerImpl) synchronize(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc, capacityProvider CapacityProvider) []*v1.Pod {

    ....

    for i := range activePods {

        pod := activePods[i]

        ...

        status := v1.PodStatus{

            Phase:   v1.PodFailed,

            Message: fmt.Sprintf(message, resourceToReclaim),

            Reason:  reason,

        }

        ....

        gracePeriodOverride := int64(0)

        if softEviction {

            gracePeriodOverride = m.config.MaxPodGracePeriodSeconds

        }

        // 真正KillPod

        err := m.killPodFunc(pod, status, &gracePeriodOverride)

        if err != nil {

            glog.Warningf("eviction manager: error while evicting pod %s: %v", format.Pod(pod), err)

        }

        return []*v1.Pod{pod}

    }

    glog.Infof("eviction manager: unable to evict any pods from the node")

    return nil

}