Exemple #1
0
// synchronize is the main control loop that enforces eviction thresholds.
func (m *managerImpl) synchronize(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc) {
	// if we have nothing to do, just return
	thresholds := m.config.Thresholds
	if len(thresholds) == 0 {
		return
	}

	// build the ranking functions (if not yet known)
	// TODO: have a function in cadvisor that lets us know if global housekeeping has completed
	if len(m.resourceToRankFunc) == 0 || len(m.resourceToNodeReclaimFuncs) == 0 {
		// this may error if cadvisor has yet to complete housekeeping, so we will just try again in next pass.
		hasDedicatedImageFs, err := diskInfoProvider.HasDedicatedImageFs()
		if err != nil {
			return
		}
		m.resourceToRankFunc = buildResourceToRankFunc(hasDedicatedImageFs)
		m.resourceToNodeReclaimFuncs = buildResourceToNodeReclaimFuncs(m.imageGC, hasDedicatedImageFs)
	}

	// make observations and get a function to derive pod usage stats relative to those observations.
	observations, statsFunc, err := makeSignalObservations(m.summaryProvider)
	if err != nil {
		glog.Errorf("eviction manager: unexpected err: %v", err)
		return
	}

	// attempt to create a threshold notifier to improve eviction response time
	if !m.notifiersInitialized {
		m.notifiersInitialized = true
		// start soft memory notification
		err = startMemoryThresholdNotifier(m.config.Thresholds, observations, false, func(desc string) {
			glog.Infof("soft memory eviction threshold crossed at %s", desc)
			// TODO wait grace period for soft memory limit
			m.synchronize(diskInfoProvider, podFunc)
		})
		if err != nil {
			glog.Warningf("eviction manager: failed to create hard memory threshold notifier: %v", err)
		}
		// start hard memory notification
		err = startMemoryThresholdNotifier(m.config.Thresholds, observations, true, func(desc string) {
			glog.Infof("hard memory eviction threshold crossed at %s", desc)
			m.synchronize(diskInfoProvider, podFunc)
		})
		if err != nil {
			glog.Warningf("eviction manager: failed to create soft memory threshold notifier: %v", err)
		}
	}

	// determine the set of thresholds met independent of grace period
	thresholds = thresholdsMet(thresholds, observations, false)

	// determine the set of thresholds previously met that have not yet satisfied the associated min-reclaim
	if len(m.thresholdsMet) > 0 {
		thresholdsNotYetResolved := thresholdsMet(m.thresholdsMet, observations, true)
		thresholds = mergeThresholds(thresholds, thresholdsNotYetResolved)
	}

	// determine the set of thresholds whose stats have been updated since the last sync
	thresholds = thresholdsUpdatedStats(thresholds, observations, m.lastObservations)

	// track when a threshold was first observed
	now := m.clock.Now()
	thresholdsFirstObservedAt := thresholdsFirstObservedAt(thresholds, m.thresholdsFirstObservedAt, now)

	// the set of node conditions that are triggered by currently observed thresholds
	nodeConditions := nodeConditions(thresholds)

	// track when a node condition was last observed
	nodeConditionsLastObservedAt := nodeConditionsLastObservedAt(nodeConditions, m.nodeConditionsLastObservedAt, now)

	// node conditions report true if it has been observed within the transition period window
	nodeConditions = nodeConditionsObservedSince(nodeConditionsLastObservedAt, m.config.PressureTransitionPeriod, now)

	// determine the set of thresholds we need to drive eviction behavior (i.e. all grace periods are met)
	thresholds = thresholdsMetGracePeriod(thresholdsFirstObservedAt, now)

	// update internal state
	m.Lock()
	m.nodeConditions = nodeConditions
	m.thresholdsFirstObservedAt = thresholdsFirstObservedAt
	m.nodeConditionsLastObservedAt = nodeConditionsLastObservedAt
	m.thresholdsMet = thresholds
	m.lastObservations = observations
	m.Unlock()

	// determine the set of resources under starvation
	starvedResources := getStarvedResources(thresholds)
	if len(starvedResources) == 0 {
		glog.V(3).Infof("eviction manager: no resources are starved")
		return
	}

	// rank the resources to reclaim by eviction priority
	sort.Sort(byEvictionPriority(starvedResources))
	resourceToReclaim := starvedResources[0]
	glog.Warningf("eviction manager: attempting to reclaim %v", resourceToReclaim)

	// determine if this is a soft or hard eviction associated with the resource
	softEviction := isSoftEvictionThresholds(thresholds, resourceToReclaim)

	// record an event about the resources we are now attempting to reclaim via eviction
	m.recorder.Eventf(m.nodeRef, v1.EventTypeWarning, "EvictionThresholdMet", "Attempting to reclaim %s", resourceToReclaim)

	// check if there are node-level resources we can reclaim to reduce pressure before evicting end-user pods.
	if m.reclaimNodeLevelResources(resourceToReclaim, observations) {
		glog.Infof("eviction manager: able to reduce %v pressure without evicting pods.", resourceToReclaim)
		return
	}

	glog.Infof("eviction manager: must evict pod(s) to reclaim %v", resourceToReclaim)

	// rank the pods for eviction
	rank, ok := m.resourceToRankFunc[resourceToReclaim]
	if !ok {
		glog.Errorf("eviction manager: no ranking function for resource %s", resourceToReclaim)
		return
	}

	// the only candidates viable for eviction are those pods that had anything running.
	activePods := podFunc()
	if len(activePods) == 0 {
		glog.Errorf("eviction manager: eviction thresholds have been met, but no pods are active to evict")
		return
	}

	// rank the running pods for eviction for the specified resource
	rank(activePods, statsFunc)

	glog.Infof("eviction manager: pods ranked for eviction: %s", format.Pods(activePods))

	// we kill at most a single pod during each eviction interval
	for i := range activePods {
		pod := activePods[i]
		status := v1.PodStatus{
			Phase:   v1.PodFailed,
			Message: fmt.Sprintf(message, resourceToReclaim),
			Reason:  reason,
		}
		// record that we are evicting the pod
		m.recorder.Eventf(pod, v1.EventTypeWarning, reason, fmt.Sprintf(message, resourceToReclaim))
		gracePeriodOverride := int64(0)
		if softEviction {
			gracePeriodOverride = m.config.MaxPodGracePeriodSeconds
		}
		// this is a blocking call and should only return when the pod and its containers are killed.
		err := m.killPodFunc(pod, status, &gracePeriodOverride)
		if err != nil {
			glog.Infof("eviction manager: pod %s failed to evict %v", format.Pod(pod), err)
			continue
		}
		// success, so we return until the next housekeeping interval
		glog.Infof("eviction manager: pod %s evicted successfully", format.Pod(pod))
		return
	}
	glog.Infof("eviction manager: unable to evict any pods from the node")
}
// synchronize is the main control loop that enforces eviction thresholds.
func (m *managerImpl) synchronize(podFunc ActivePodsFunc) {
	// if we have nothing to do, just return
	thresholds := m.config.Thresholds
	if len(thresholds) == 0 {
		return
	}

	// make observations and get a function to derive pod usage stats relative to those observations.
	observations, statsFunc, err := makeSignalObservations(m.summaryProvider)
	if err != nil {
		glog.Errorf("eviction manager: unexpected err: %v", err)
		return
	}

	// find the list of thresholds that are met independent of grace period
	now := m.clock.Now()

	// determine the set of thresholds met independent of grace period
	thresholds = thresholdsMet(thresholds, observations)

	// track when a threshold was first observed
	thresholdsFirstObservedAt := thresholdsFirstObservedAt(thresholds, m.thresholdsFirstObservedAt, now)

	// the set of node conditions that are triggered by currently observed thresholds
	nodeConditions := nodeConditions(thresholds)

	// track when a node condition was last observed
	nodeConditionsLastObservedAt := nodeConditionsLastObservedAt(nodeConditions, m.nodeConditionsLastObservedAt, now)

	// node conditions report true if it has been observed within the transition period window
	nodeConditions = nodeConditionsObservedSince(nodeConditionsLastObservedAt, m.config.PressureTransitionPeriod, now)

	// determine the set of thresholds we need to drive eviction behavior (i.e. all grace periods are met)
	thresholds = thresholdsMetGracePeriod(thresholdsFirstObservedAt, now)

	// update internal state
	m.Lock()
	m.nodeConditions = nodeConditions
	m.thresholdsFirstObservedAt = thresholdsFirstObservedAt
	m.nodeConditionsLastObservedAt = nodeConditionsLastObservedAt
	m.Unlock()

	// determine the set of resources under starvation
	starvedResources := reclaimResources(thresholds)
	if len(starvedResources) == 0 {
		glog.V(3).Infof("eviction manager: no resources are starved")
		return
	}

	// rank the resources to reclaim by eviction priority
	sort.Sort(byEvictionPriority(starvedResources))
	resourceToReclaim := starvedResources[0]
	glog.Warningf("eviction manager: attempting to reclaim %v", resourceToReclaim)

	// determine if this is a soft or hard eviction associated with the resource
	softEviction := isSoftEviction(thresholds, resourceToReclaim)

	// record an event about the resources we are now attempting to reclaim via eviction
	m.recorder.Eventf(m.nodeRef, api.EventTypeWarning, "EvictionThresholdMet", "Attempting to reclaim %s", resourceToReclaim)

	// rank the pods for eviction
	rank, ok := resourceToRankFunc[resourceToReclaim]
	if !ok {
		glog.Errorf("eviction manager: no ranking function for resource %s", resourceToReclaim)
		return
	}

	// the only candidates viable for eviction are those pods that had anything running.
	activePods := podFunc()
	if len(activePods) == 0 {
		glog.Errorf("eviction manager: eviction thresholds have been met, but no pods are active to evict")
		return
	}

	// rank the running pods for eviction for the specified resource
	rank(activePods, statsFunc)

	glog.Infof("eviction manager: pods ranked for eviction: %s", format.Pods(activePods))

	// we kill at most a single pod during each eviction interval
	for i := range activePods {
		pod := activePods[i]
		status := api.PodStatus{
			Phase:   api.PodFailed,
			Message: message,
			Reason:  reason,
		}
		// record that we are evicting the pod
		m.recorder.Eventf(pod, api.EventTypeWarning, reason, message)
		gracePeriodOverride := int64(0)
		if softEviction {
			gracePeriodOverride = m.config.MaxPodGracePeriodSeconds
		}
		// this is a blocking call and should only return when the pod and its containers are killed.
		err := m.killPodFunc(pod, status, &gracePeriodOverride)
		if err != nil {
			glog.Infof("eviction manager: pod %s failed to evict %v", format.Pod(pod), err)
			continue
		}
		// success, so we return until the next housekeeping interval
		glog.Infof("eviction manager: pod %s evicted successfully", format.Pod(pod))
		return
	}
	glog.Infof("eviction manager: unable to evict any pods from the node")
}