Kubernetes惊天地泣鬼神之大bug

 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

// watchHandler watches w and keeps *resourceVersion up to date.
func (r *Reflector) watchHandler(w watch.Interface, resourceVersion *string, errc chan error, stopCh <-chan struct{}) error {
	start := r.clock.Now()
	eventCount := 0

	// Stopping the watcher should be idempotent and if we return from this function there's no way
	// we're coming back in with the same watch interface.
	defer w.Stop()
	// update metrics
	defer func() {
		r.metrics.numberOfItemsInWatch.Observe(float64(eventCount))
		r.metrics.watchDuration.Observe(time.Since(start).Seconds())
	}()

loop:
	for {
		select {
		case <-stopCh:
			return errorStopRequested
		case err := <-errc:
			return err
		case event, ok := <-w.ResultChan():
			if !ok {
				break loop
			}
			if event.Type == watch.Error {
				return apierrs.FromObject(event.Object)
			}
			if e, a := r.expectedType, reflect.TypeOf(event.Object); e != nil && e != a {
				utilruntime.HandleError(fmt.Errorf("%s: expected type %v, but watch event object had type %v", r.name, e, a))
				continue
			}
			meta, err := meta.Accessor(event.Object)
			if err != nil {
				utilruntime.HandleError(fmt.Errorf("%s: unable to understand watch event %#v", r.name, event))
				continue
			}
			newResourceVersion := meta.GetResourceVersion()
			switch event.Type {
			case watch.Added:
				err := r.store.Add(event.Object)
				if err != nil {
					utilruntime.HandleError(fmt.Errorf("%s: unable to add watch event object (%#v) to store: %v", r.name, event.Object, err))
				}
			case watch.Modified:
				err := r.store.Update(event.Object)
				if err != nil {
					utilruntime.HandleError(fmt.Errorf("%s: unable to update watch event object (%#v) to store: %v", r.name, event.Object, err))
				}
			case watch.Deleted:
				// TODO: Will any consumers need access to the "last known
				// state", which is passed in event.Object? If so, may need
				// to change this.
				err := r.store.Delete(event.Object)
				if err != nil {
					utilruntime.HandleError(fmt.Errorf("%s: unable to delete watch event object (%#v) from store: %v", r.name, event.Object, err))
				}
			default:
				utilruntime.HandleError(fmt.Errorf("%s: unable to understand watch event %#v", r.name, event))
			}
			*resourceVersion = newResourceVersion
			r.setLastSyncResourceVersion(newResourceVersion)
			eventCount++
		}
	}

	watchDuration := r.clock.Now().Sub(start)
	if watchDuration < 1*time.Second && eventCount == 0 {
		r.metrics.numberOfShortWatches.Inc()
		return fmt.Errorf("very short watch: %s: Unexpected watch close - watch lasted less than a second and no items received", r.name)
	}
	glog.V(4).Infof("%s: Watch close - %v total %v items received", r.name, r.expectedType, eventCount)
	return 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
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111

// ListAndWatch first lists all items and get the resource version at the moment of call,
// and then use the resource version to watch.
// It returns error if ListAndWatch didn't even try to initialize watch.
func (r *Reflector) ListAndWatch(stopCh <-chan struct{}) error {
	glog.V(3).Infof("Listing and watching %v from %s", r.expectedType, r.name)
	var resourceVersion string

	// Explicitly set "0" as resource version - it's fine for the List()
	// to be served from cache and potentially be delayed relative to
	// etcd contents. Reflector framework will catch up via Watch() eventually.
	options := metav1.ListOptions{ResourceVersion: "0"}
	r.metrics.numberOfLists.Inc()
	start := r.clock.Now()
	list, err := r.listerWatcher.List(options)
	if err != nil {
		return fmt.Errorf("%s: Failed to list %v: %v", r.name, r.expectedType, err)
	}
	r.metrics.listDuration.Observe(time.Since(start).Seconds())
	listMetaInterface, err := meta.ListAccessor(list)
	if err != nil {
		return fmt.Errorf("%s: Unable to understand list result %#v: %v", r.name, list, err)
	}
	resourceVersion = listMetaInterface.GetResourceVersion()
	items, err := meta.ExtractList(list)
	if err != nil {
		return fmt.Errorf("%s: Unable to understand list result %#v (%v)", r.name, list, err)
	}
	r.metrics.numberOfItemsInList.Observe(float64(len(items)))
	if err := r.syncWith(items, resourceVersion); err != nil {
		return fmt.Errorf("%s: Unable to sync list result: %v", r.name, err)
	}
	r.setLastSyncResourceVersion(resourceVersion)

	resyncerrc := make(chan error, 1)
	cancelCh := make(chan struct{})
	defer close(cancelCh)
	go func() {
		resyncCh, cleanup := r.resyncChan()
		defer func() {
			cleanup() // Call the last one written into cleanup
		}()
		for {
			select {
			case <-resyncCh:
			case <-stopCh:
				return
			case <-cancelCh:
				return
			}
			if r.ShouldResync == nil || r.ShouldResync() {
				glog.V(4).Infof("%s: forcing resync", r.name)
				if err := r.store.Resync(); err != nil {
					resyncerrc <- err
					return
				}
			}
			cleanup()
			resyncCh, cleanup = r.resyncChan()
		}
	}()

	for {
		// give the stopCh a chance to stop the loop, even in case of continue statements further down on errors
		select {
		case <-stopCh:
			return nil
		default:
		}

		timeoutSeconds := int64(minWatchTimeout.Seconds() * (rand.Float64() + 1.0))
		options = metav1.ListOptions{
			ResourceVersion: resourceVersion,
			// We want to avoid situations of hanging watchers. Stop any wachers that do not
			// receive any events within the timeout window.
			TimeoutSeconds: &timeoutSeconds,
		}

		r.metrics.numberOfWatches.Inc()
		w, err := r.listerWatcher.Watch(options)
		if err != nil {
			switch err {
			case io.EOF:
				// watch closed normally
			case io.ErrUnexpectedEOF:
				glog.V(1).Infof("%s: Watch for %v closed with unexpected EOF: %v", r.name, r.expectedType, err)
			default:
				utilruntime.HandleError(fmt.Errorf("%s: Failed to watch %v: %v", r.name, r.expectedType, err))
			}
			// If this is "connection refused" error, it means that most likely apiserver is not responsive.
			// It doesn't make sense to re-list all objects because most likely we will be able to restart
			// watch where we ended.
			// If that's the case wait and resend watch request.
			if urlError, ok := err.(*url.Error); ok {
				if opError, ok := urlError.Err.(*net.OpError); ok {
					if errno, ok := opError.Err.(syscall.Errno); ok && errno == syscall.ECONNREFUSED {
						time.Sleep(time.Second)
						continue
					}
				}
			}
			return nil
		}

		if err := r.watchHandler(w, &resourceVersion, resyncerrc, stopCh); err != nil {
			if err != errorStopRequested {
				glog.Warningf("%s: watch of %v ended with: %v", r.name, r.expectedType, err)
			}
			return nil
		}
	}
}