kubernetes的eviction机制

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
func (nc *NodeController) ComputeZoneState(nodeReadyConditions []*v1.NodeCondition) (int, zoneState) {
    readyNodes := 0
    notReadyNodes := 0
    for i := range nodeReadyConditions {
        if nodeReadyConditions[i] != nil && nodeReadyConditions[i].Status == v1.ConditionTrue {
            readyNodes++
        } else {
            notReadyNodes++
        }
    }       
    switch {    
    case readyNodes == 0 && notReadyNodes > 0:
        return notReadyNodes, stateFullDisruption
    case notReadyNodes > 2 && float32(notReadyNodes)/float32(notReadyNodes+readyNodes) >= nc.unhealthyZoneThreshold:
        return notReadyNodes, statePartialDisruption
    default:
        return notReadyNodes, stateNormal
    }
}

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 (nc *NodeController) setLimiterInZone(zone string, zoneSize int, state zoneState) {
    switch state {
    case stateNormal:
        if nc.useTaintBasedEvictions {
            nc.zoneNotReadyOrUnreachableTainer[zone].SwapLimiter(nc.evictionLimiterQPS)
        } else {
            nc.zonePodEvictor[zone].SwapLimiter(nc.evictionLimiterQPS)
        }    
    case statePartialDisruption:
        if nc.useTaintBasedEvictions {
            nc.zoneNotReadyOrUnreachableTainer[zone].SwapLimiter(
                nc.enterPartialDisruptionFunc(zoneSize))
        } else {
            nc.zonePodEvictor[zone].SwapLimiter(
                nc.enterPartialDisruptionFunc(zoneSize))
        }    
    case stateFullDisruption:
        if nc.useTaintBasedEvictions {
            nc.zoneNotReadyOrUnreachableTainer[zone].SwapLimiter(
                nc.enterFullDisruptionFunc(zoneSize))
        } else {
            nc.zonePodEvictor[zone].SwapLimiter(
                nc.enterFullDisruptionFunc(zoneSize))
        }    
    }    
}

其中enterPartialDisruptionFunc就是函数ReducedQPSFunc
func (nc *NodeController) ReducedQPSFunc(nodeNum int) float32 {
    if int32(nodeNum) > nc.largeClusterThreshold {
        return nc.secondaryEvictionLimiterQPS
    }
    return 0
} 

而enterFullDisruptionFunc是函数HealthyQPSFunc
func (nc *NodeController) HealthyQPSFunc(nodeNum int) float32 {
    return nc.evictionLimiterQPS 
}   

1
2
3
4
5
6
7
if nc.useTaintBasedEvictions {

    go wait.Until(nc.doTaintingPass, nodeEvictionPeriod, wait.NeverStop)
} else {
    go wait.Until(nc.doEvictionPass, nodeEvictionPeriod, wait.NeverStop)
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
func (nc *NodeController) doEvictionPass() {
    nc.evictorLock.Lock()
    defer nc.evictorLock.Unlock()
    for k := range nc.zonePodEvictor {
        nc.zonePodEvictor[k].Try(func(value TimedValue) (bool, time.Duration) {
            node, err := nc.nodeLister.Get(value.Value)
            ...
            nodeUid, _ := value.UID.(string)
            remaining, err := deletePods(nc.kubeClient, nc.recorder, value.Value, nodeUid, nc.daemonSetStore)
            ...
            if remaining {
                glog.Infof("Pods awaiting deletion due to NodeController eviction")
            }
            return true, 0
        })  
    }
}

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
41
42
func deletePods(kubeClient clientset.Interface, recorder record.EventRecorder, nodeName, nodeUID string, daemonStore extensionslisters.DaemonSetLister) (bool, error) {
    remaining := false
    selector := fields.OneTermEqualSelector(api.PodHostField, nodeName).String()
    options := metav1.ListOptions{FieldSelector: selector}
    pods, err := kubeClient.Core().Pods(metav1.NamespaceAll).List(options)
    var updateErrList []error
    
    ...

    for _, pod := range pods.Items {
        // Defensive check, also needed for tests.
        if pod.Spec.NodeName != nodeName {
            continue
        }

        // 设置Pod终止理由
        if _, err = setPodTerminationReason(kubeClient, &pod, nodeName); err != nil {
            if errors.IsConflict(err) {
                updateErrList = append(updateErrList,
                    fmt.Errorf("update status failed for pod %q: %v", format.Pod(&pod), err))
                continue
            }
        }
        // 该Pod正在被删除，忽略
        if pod.DeletionGracePeriodSeconds != nil {
            remaining = true
            continue
        }
        // 假如该节点是又daemonset管理，则忽略
        _, err := daemonStore.GetPodDaemonSets(&pod)
        if err == nil {
            continue
        }
        if err := kubeClient.Core().Pods(pod.Namespace).Delete(pod.Name, nil); err != nil {
            return false, err
        }
        remaining = true
    }
    ...
    return remaining, nil
}

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
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
// Run starts NoExecuteTaintManager which will run in loop until `stopCh` is closed.
func (tc *NoExecuteTaintManager) Run(stopCh <-chan struct{}) {   
    go func(stopCh <-chan struct{}) {
        for {            
            item, shutdown := tc.nodeUpdateQueue.Get()
            if shutdown {
                break    
            }            
            nodeUpdate := item.(*nodeUpdateItem) 
            select {     
            case <-stopCh:            
                break    
            case tc.nodeUpdateChannel <- nodeUpdate:
            }
        }
    }(stopCh)            

    go func(stopCh <-chan struct{}) {
        for {
            item, shutdown := tc.podUpdateQueue.Get()
            if shutdown {
                break
            }
            podUpdate := item.(*podUpdateItem)
            select {     
            case <-stopCh:            
                break
            case tc.podUpdateChannel <- podUpdate:
            }
        }
    }(stopCh)
    
    for {                
        select {         
        case <-stopCh:   
            break        
        case nodeUpdate := <-tc.nodeUpdateChannel:
            tc.handleNodeUpdate(nodeUpdate)
        case podUpdate := <-tc.podUpdateChannel: 
            // If we found a Pod update we need to empty Node queue first.
        priority:
            for {        
                select {
                case nodeUpdate := <-tc.nodeUpdateChannel:
                    tc.handleNodeUpdate(nodeUpdate)
                default:
                    break priority            
                }
            }
            // After Node queue is emptied we process podUpdate.
            tc.handlePodUpdate(podUpdate)
        }
    }
}

func deletePodHandler(c clientset.Interface, emitEventFunc func(types.NamespacedName)) func(args *WorkArgs) error {
    return func(args *WorkArgs) error {
        ns := args.NamespacedName.Namespace
        name := args.NamespacedName.Name
        glog.V(0).Infof("NoExecuteTaintManager is deleting Pod: %v", args.NamespacedName.String())
        if emitEventFunc != nil { 
            emitEventFunc(args.NamespacedName)
        }
        var err error    
        for i := 0; i < retries; i++ {
            err = c.Core().Pods(ns).Delete(name, &metav1.DeleteOptions{})
            if err == nil {           
                break
            }
            time.Sleep(10 * time.Millisecond)
        }
        return err
    }                    
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
func (m *managerImpl) Start(diskInfoProvider DiskInfoProvider, podFunc ActivePodsFunc, podCleanedUpFunc PodCleanedUpFunc, nodeProvider NodeProvider, monitoringInterval time.Duration) {
    // start the eviction manager monitoring
    go func() {
        for {
            if evictedPods := m.synchronize(diskInfoProvider, podFunc, nodeProvider); evictedPods != nil {
                glog.Infof("eviction manager: pods %s evicted, waiting for pod to be cleaned up", format.Pods(evictedPods))
                m.waitForPodsCleanup(podCleanedUpFunc, evictedPods)
            } else {
                time.Sleep(monitoringInterval)
            }       
        }       
    }()     
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
if m.config.KernelMemcgNotification && !m.notifiersInitialized { 
        glog.Infof("eviction manager attempting to integrate with kernel memcg notification api")
        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, nodeProvider)
        })
        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, nodeProvider)
        })
        if err != nil {
            glog.Warningf("eviction manager: failed to create soft memory threshold notifier: %v", err)
        }
    } 

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
// rankMemoryPressure orders the input pods for eviction in response to memory pressure.
func rankMemoryPressure(pods []*v1.Pod, stats statsFunc) {
    orderedBy(qosComparator, memory(stats)).Sort(pods)
}

// qosComparator compares pods by QoS (BestEffort < Burstable < Guaranteed)
func qosComparator(p1, p2 *v1.Pod) int {
    qosP1 := v1qos.GetPodQOS(p1)
    qosP2 := v1qos.GetPodQOS(p2)
    // its a tie
    if qosP1 == qosP2 {
        return 0
    }   
    // if p1 is best effort, we know p2 is burstable or guaranteed
    if qosP1 == v1.PodQOSBestEffort {
        return -1
    }
    // we know p1 and p2 are not besteffort, so if p1 is burstable, p2 must be guaranteed
    if qosP1 == v1.PodQOSBurstable {
        if qosP2 == v1.PodQOSGuaranteed {  
            return -1
        }
        return 1
    }
    // ok, p1 must be guaranteed.
    return 1
}

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
// we kill at most a single pod during each eviction interval
    for i := range activePods {
        pod := activePods[i]      
        // If the pod is marked as critical and static, and support for critical pod annotations is enabled,
        // do not evict such pods. Static pods are not re-admitted after evictions.
        // https://github.com/kubernetes/kubernetes/issues/40573 has more details.
        if utilfeature.DefaultFeatureGate.Enabled(features.ExperimentalCriticalPodAnnotation) &&
            kubelettypes.IsCriticalPod(pod) && kubepod.IsStaticPod(pod) {
            continue     
        }
        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.Warningf("eviction manager: error while evicting pod %s: %v", format.Pod(pod), err)
        }                
        return []*v1.Pod{pod}     
    }