分析kubernetes中的事件机制

apiVersion: v1
count: 1
eventTime: null
firstTimestamp: "2020-03-02T13:08:22Z"
involvedObject:
  apiVersion: v1
  kind: Pod
  name: example-foo-d75d8587c-xsf64
  namespace: default
  resourceVersion: "429837"
  uid: ce611c62-6c1a-4bd8-9029-136a1adf7de4
kind: Event
lastTimestamp: "2020-03-02T13:08:22Z"
message: Pod sandbox changed, it will be killed and re-created.
metadata:
  creationTimestamp: "2020-03-02T13:08:30Z"
  name: example-foo-d75d8587c-xsf64.15f87ea1df862b64
  namespace: default
  resourceVersion: "479466"
  selfLink: /api/v1/namespaces/default/events/example-foo-d75d8587c-xsf64.15f87ea1df862b64
  uid: 9fe6f72a-341d-4c49-960b-e185982d331a
reason: SandboxChanged
reportingComponent: ""
reportingInstance: ""
source:
  component: kubelet
  host: minikube
type: Normal

// makeEventRecorder sets up kubeDeps.Recorder if it's nil. It's a no-op otherwise.
func makeEventRecorder(kubeDeps *kubelet.Dependencies, nodeName types.NodeName) {
	if kubeDeps.Recorder != nil {
		return
	}
    //事件广播
	eventBroadcaster := record.NewBroadcaster()
    //创建EventRecorder
	kubeDeps.Recorder = eventBroadcaster.NewRecorder(legacyscheme.Scheme, v1.EventSource{Component: componentKubelet, Host: string(nodeName)})
	//发送event至log输出
    eventBroadcaster.StartLogging(klog.V(3).Infof)
	if kubeDeps.EventClient != nil {
		klog.V(4).Infof("Sending events to api server.")
        //发送event至apiserver
		eventBroadcaster.StartRecordingToSink(&v1core.EventSinkImpl{Interface: kubeDeps.EventClient.Events("")})
	} else {
		klog.Warning("No api server defined - no events will be sent to API server.")
	}
}

// EventBroadcaster knows how to receive events and send them to any EventSink, watcher, or log.
type EventBroadcaster interface {
    //
	StartEventWatcher(eventHandler func(*v1.Event)) watch.Interface
	StartRecordingToSink(sink EventSink) watch.Interface
	StartLogging(logf func(format string, args ...interface{})) watch.Interface
	NewRecorder(scheme *runtime.Scheme, source v1.EventSource) EventRecorder

	Shutdown()
}

// EventRecorder knows how to record events on behalf of an EventSource.
type EventRecorder interface {
	// Event constructs an event from the given information and puts it in the queue for sending.
	// 'object' is the object this event is about. Event will make a reference-- or you may also
	// pass a reference to the object directly.
	// 'type' of this event, and can be one of Normal, Warning. New types could be added in future
	// 'reason' is the reason this event is generated. 'reason' should be short and unique; it
	// should be in UpperCamelCase format (starting with a capital letter). "reason" will be used
	// to automate handling of events, so imagine people writing switch statements to handle them.
	// You want to make that easy.
	// 'message' is intended to be human readable.
	//
	// The resulting event will be created in the same namespace as the reference object.
	Event(object runtime.Object, eventtype, reason, message string)

	// Eventf is just like Event, but with Sprintf for the message field.
	Eventf(object runtime.Object, eventtype, reason, messageFmt string, args ...interface{})

	// PastEventf is just like Eventf, but with an option to specify the event's 'timestamp' field.
	PastEventf(object runtime.Object, timestamp metav1.Time, eventtype, reason, messageFmt string, args ...interface{})

	// AnnotatedEventf is just like eventf, but with annotations attached
	AnnotatedEventf(object runtime.Object, annotations map[string]string, eventtype, reason, messageFmt string, args ...interface{})
}

func (recorder *recorderImpl) generateEvent(object runtime.Object, annotations map[string]string, timestamp metav1.Time, eventtype, reason, message string) {
    .....
	event := recorder.makeEvent(ref, annotations, eventtype, reason, message)
	event.Source = recorder.source
	go func() {
		// NOTE: events should be a non-blocking operation
		defer utilruntime.HandleCrash()
		recorder.Action(watch.Added, event)
	}()
}

func (recorder *recorderImpl) makeEvent(ref *v1.ObjectReference, annotations map[string]string, eventtype, reason, message string) *v1.Event {
	t := metav1.Time{Time: recorder.clock.Now()}
	namespace := ref.Namespace
	if namespace == "" {
		namespace = metav1.NamespaceDefault
	}
	return &v1.Event{
		ObjectMeta: metav1.ObjectMeta{
			Name:        fmt.Sprintf("%v.%x", ref.Name, t.UnixNano()),
			Namespace:   namespace,
			Annotations: annotations,
		},
		InvolvedObject: *ref,
		Reason:         reason,
		Message:        message,
		FirstTimestamp: t,
		LastTimestamp:  t,
		Count:          1,
		Type:           eventtype,
	}
}

// Action distributes the given event among all watchers.
func (m *Broadcaster) Action(action EventType, obj runtime.Object) {
	m.incoming <- Event{action, obj}
}

func (e *eventBroadcasterImpl) StartEventWatcher(eventHandler func(*v1.Event)) watch.Interface {
	watcher := e.Watch()
	go func() {
		defer utilruntime.HandleCrash()
		for watchEvent := range watcher.ResultChan() {
			event, ok := watchEvent.Object.(*v1.Event)
			if !ok {
				// This is all local, so there's no reason this should
				// ever happen.
				continue
			}
			eventHandler(event)
		}
	}()
	return watcher
}

func recordToSink(sink EventSink, event *v1.Event, eventCorrelator *EventCorrelator, sleepDuration time.Duration) {
	// Make a copy before modification, because there could be multiple listeners.
	// Events are safe to copy like this.
	eventCopy := *event
	event = &eventCopy
	result, err := eventCorrelator.EventCorrelate(event)
	if err != nil {
		utilruntime.HandleError(err)
	}
	if result.Skip {
		return
	}
	tries := 0
	for {
		if recordEvent(sink, result.Event, result.Patch, result.Event.Count > 1, eventCorrelator) {
			break
		}
		tries++
		if tries >= maxTriesPerEvent {
			klog.Errorf("Unable to write event '%#v' (retry limit exceeded!)", event)
			break
		}
		// Randomize the first sleep so that various clients won't all be
		// synced up if the master goes down.
        // 第一次重试增加随机性，防止 apiserver 重启的时候所有的事件都在同一时间发送事件
		if tries == 1 {
			time.Sleep(time.Duration(float64(sleepDuration) * rand.Float64()))
		} else {
			time.Sleep(sleepDuration)
		}
	}
}

// EventCorrelate filters, aggregates, counts, and de-duplicates all incoming events
func (c *EventCorrelator) EventCorrelate(newEvent *v1.Event) (*EventCorrelateResult, error) {
	if newEvent == nil {
		return nil, fmt.Errorf("event is nil")
	}
	aggregateEvent, ckey := c.aggregator.EventAggregate(newEvent)
	observedEvent, patch, err := c.logger.eventObserve(aggregateEvent, ckey)
	if c.filterFunc(observedEvent) {
		return &EventCorrelateResult{Skip: true}, nil
	}
	return &EventCorrelateResult{Event: observedEvent, Patch: patch}, err
}

func (e *EventAggregator) EventAggregate(newEvent *v1.Event) (*v1.Event, string) {
	now := metav1.NewTime(e.clock.Now())
	var record aggregateRecord
	// eventKey is the full cache key for this event
    //eventKey 是将除了时间戳外所有字段结合在一起
	eventKey := getEventKey(newEvent)
	// aggregateKey is for the aggregate event, if one is needed.
    //aggregateKey 是除了message和时间戳外的字段结合在一起，localKey 是message
	aggregateKey, localKey := e.keyFunc(newEvent)

	// Do we have a record of similar events in our cache?
	e.Lock()
	defer e.Unlock()
    //从cache中根据aggregateKey查询是否存在，如果是相同或者相类似的事件会被放入cache中
	value, found := e.cache.Get(aggregateKey)
	if found {
		record = value.(aggregateRecord)
	}

    //判断上次事件产生的时间是否超过10分钟，如何操作则重新生成一个localKeys集合（集合中存放message）
	maxInterval := time.Duration(e.maxIntervalInSeconds) * time.Second
	interval := now.Time.Sub(record.lastTimestamp.Time)
	if interval > maxInterval {
		record = aggregateRecord{localKeys: sets.NewString()}
	}

	// Write the new event into the aggregation record and put it on the cache
    //将locakKey也就是message放入集合中，如果message相同就是覆盖了
	record.localKeys.Insert(localKey)
	record.lastTimestamp = now
	e.cache.Add(aggregateKey, record)

	// If we are not yet over the threshold for unique events, don't correlate them
	//判断localKeys集合中存放的类似事件是否超过10个，
    if uint(record.localKeys.Len()) < e.maxEvents {
		return newEvent, eventKey
	}

	// do not grow our local key set any larger than max
	record.localKeys.PopAny()

	// create a new aggregate event, and return the aggregateKey as the cache key
	// (so that it can be overwritten.)
	eventCopy := &v1.Event{
		ObjectMeta: metav1.ObjectMeta{
			Name:      fmt.Sprintf("%v.%x", newEvent.InvolvedObject.Name, now.UnixNano()),
			Namespace: newEvent.Namespace,
		},
		Count:          1,
		FirstTimestamp: now,
		InvolvedObject: newEvent.InvolvedObject,
		LastTimestamp:  now,
        //这里会对message加个前缀：(combined from similar events):
		Message:        e.messageFunc(newEvent),
		Type:           newEvent.Type,
		Reason:         newEvent.Reason,
		Source:         newEvent.Source,
	}
	return eventCopy, aggregateKey
}