summaryrefslogtreecommitdiff
path: root/vendor/k8s.io/client-go/tools/cache/shared_informer.go
blob: f6ce07f7af36124b253b8b3ee4694fe6cbef6b2e (plain)
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
/*
Copyright 2015 The Kubernetes Authors.

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/

package cache

import (
	"fmt"
	"sync"
	"time"

	"k8s.io/apimachinery/pkg/runtime"
	"k8s.io/apimachinery/pkg/util/clock"
	utilruntime "k8s.io/apimachinery/pkg/util/runtime"
	"k8s.io/apimachinery/pkg/util/wait"
	"k8s.io/client-go/util/buffer"
	"k8s.io/client-go/util/retry"

	"github.com/golang/glog"
)

// SharedInformer has a shared data cache and is capable of distributing notifications for changes
// to the cache to multiple listeners who registered via AddEventHandler. If you use this, there is
// one behavior change compared to a standard Informer.  When you receive a notification, the cache
// will be AT LEAST as fresh as the notification, but it MAY be more fresh.  You should NOT depend
// on the contents of the cache exactly matching the notification you've received in handler
// functions.  If there was a create, followed by a delete, the cache may NOT have your item.  This
// has advantages over the broadcaster since it allows us to share a common cache across many
// controllers. Extending the broadcaster would have required us keep duplicate caches for each
// watch.
type SharedInformer interface {
	// AddEventHandler adds an event handler to the shared informer using the shared informer's resync
	// period.  Events to a single handler are delivered sequentially, but there is no coordination
	// between different handlers.
	AddEventHandler(handler ResourceEventHandler)
	// AddEventHandlerWithResyncPeriod adds an event handler to the shared informer using the
	// specified resync period.  Events to a single handler are delivered sequentially, but there is
	// no coordination between different handlers.
	AddEventHandlerWithResyncPeriod(handler ResourceEventHandler, resyncPeriod time.Duration)
	// GetStore returns the Store.
	GetStore() Store
	// GetController gives back a synthetic interface that "votes" to start the informer
	GetController() Controller
	// Run starts the shared informer, which will be stopped when stopCh is closed.
	Run(stopCh <-chan struct{})
	// HasSynced returns true if the shared informer's store has synced.
	HasSynced() bool
	// LastSyncResourceVersion is the resource version observed when last synced with the underlying
	// store. The value returned is not synchronized with access to the underlying store and is not
	// thread-safe.
	LastSyncResourceVersion() string
}

type SharedIndexInformer interface {
	SharedInformer
	// AddIndexers add indexers to the informer before it starts.
	AddIndexers(indexers Indexers) error
	GetIndexer() Indexer
}

// NewSharedInformer creates a new instance for the listwatcher.
func NewSharedInformer(lw ListerWatcher, objType runtime.Object, resyncPeriod time.Duration) SharedInformer {
	return NewSharedIndexInformer(lw, objType, resyncPeriod, Indexers{})
}

// NewSharedIndexInformer creates a new instance for the listwatcher.
func NewSharedIndexInformer(lw ListerWatcher, objType runtime.Object, defaultEventHandlerResyncPeriod time.Duration, indexers Indexers) SharedIndexInformer {
	realClock := &clock.RealClock{}
	sharedIndexInformer := &sharedIndexInformer{
		processor:                       &sharedProcessor{clock: realClock},
		indexer:                         NewIndexer(DeletionHandlingMetaNamespaceKeyFunc, indexers),
		listerWatcher:                   lw,
		objectType:                      objType,
		resyncCheckPeriod:               defaultEventHandlerResyncPeriod,
		defaultEventHandlerResyncPeriod: defaultEventHandlerResyncPeriod,
		cacheMutationDetector:           NewCacheMutationDetector(fmt.Sprintf("%T", objType)),
		clock: realClock,
	}
	return sharedIndexInformer
}

// InformerSynced is a function that can be used to determine if an informer has synced.  This is useful for determining if caches have synced.
type InformerSynced func() bool

const (
	// syncedPollPeriod controls how often you look at the status of your sync funcs
	syncedPollPeriod = 100 * time.Millisecond

	// initialBufferSize is the initial number of event notifications that can be buffered.
	initialBufferSize = 1024
)

// WaitForCacheSync waits for caches to populate.  It returns true if it was successful, false
// if the controller should shutdown
func WaitForCacheSync(stopCh <-chan struct{}, cacheSyncs ...InformerSynced) bool {
	err := wait.PollUntil(syncedPollPeriod,
		func() (bool, error) {
			for _, syncFunc := range cacheSyncs {
				if !syncFunc() {
					return false, nil
				}
			}
			return true, nil
		},
		stopCh)
	if err != nil {
		glog.V(2).Infof("stop requested")
		return false
	}

	glog.V(4).Infof("caches populated")
	return true
}

type sharedIndexInformer struct {
	indexer    Indexer
	controller Controller

	processor             *sharedProcessor
	cacheMutationDetector CacheMutationDetector

	// This block is tracked to handle late initialization of the controller
	listerWatcher ListerWatcher
	objectType    runtime.Object

	// resyncCheckPeriod is how often we want the reflector's resync timer to fire so it can call
	// shouldResync to check if any of our listeners need a resync.
	resyncCheckPeriod time.Duration
	// defaultEventHandlerResyncPeriod is the default resync period for any handlers added via
	// AddEventHandler (i.e. they don't specify one and just want to use the shared informer's default
	// value).
	defaultEventHandlerResyncPeriod time.Duration
	// clock allows for testability
	clock clock.Clock

	started, stopped bool
	startedLock      sync.Mutex

	// blockDeltas gives a way to stop all event distribution so that a late event handler
	// can safely join the shared informer.
	blockDeltas sync.Mutex
}

// dummyController hides the fact that a SharedInformer is different from a dedicated one
// where a caller can `Run`.  The run method is disconnected in this case, because higher
// level logic will decide when to start the SharedInformer and related controller.
// Because returning information back is always asynchronous, the legacy callers shouldn't
// notice any change in behavior.
type dummyController struct {
	informer *sharedIndexInformer
}

func (v *dummyController) Run(stopCh <-chan struct{}) {
}

func (v *dummyController) HasSynced() bool {
	return v.informer.HasSynced()
}

func (c *dummyController) LastSyncResourceVersion() string {
	return ""
}

type updateNotification struct {
	oldObj interface{}
	newObj interface{}
}

type addNotification struct {
	newObj interface{}
}

type deleteNotification struct {
	oldObj interface{}
}

func (s *sharedIndexInformer) Run(stopCh <-chan struct{}) {
	defer utilruntime.HandleCrash()

	fifo := NewDeltaFIFO(MetaNamespaceKeyFunc, nil, s.indexer)

	cfg := &Config{
		Queue:            fifo,
		ListerWatcher:    s.listerWatcher,
		ObjectType:       s.objectType,
		FullResyncPeriod: s.resyncCheckPeriod,
		RetryOnError:     false,
		ShouldResync:     s.processor.shouldResync,

		Process: s.HandleDeltas,
	}

	func() {
		s.startedLock.Lock()
		defer s.startedLock.Unlock()

		s.controller = New(cfg)
		s.controller.(*controller).clock = s.clock
		s.started = true
	}()

	// Separate stop channel because Processor should be stopped strictly after controller
	processorStopCh := make(chan struct{})
	var wg wait.Group
	defer wg.Wait()              // Wait for Processor to stop
	defer close(processorStopCh) // Tell Processor to stop
	wg.StartWithChannel(processorStopCh, s.cacheMutationDetector.Run)
	wg.StartWithChannel(processorStopCh, s.processor.run)

	defer func() {
		s.startedLock.Lock()
		defer s.startedLock.Unlock()
		s.stopped = true // Don't want any new listeners
	}()
	s.controller.Run(stopCh)
}

func (s *sharedIndexInformer) HasSynced() bool {
	s.startedLock.Lock()
	defer s.startedLock.Unlock()

	if s.controller == nil {
		return false
	}
	return s.controller.HasSynced()
}

func (s *sharedIndexInformer) LastSyncResourceVersion() string {
	s.startedLock.Lock()
	defer s.startedLock.Unlock()

	if s.controller == nil {
		return ""
	}
	return s.controller.LastSyncResourceVersion()
}

func (s *sharedIndexInformer) GetStore() Store {
	return s.indexer
}

func (s *sharedIndexInformer) GetIndexer() Indexer {
	return s.indexer
}

func (s *sharedIndexInformer) AddIndexers(indexers Indexers) error {
	s.startedLock.Lock()
	defer s.startedLock.Unlock()

	if s.started {
		return fmt.Errorf("informer has already started")
	}

	return s.indexer.AddIndexers(indexers)
}

func (s *sharedIndexInformer) GetController() Controller {
	return &dummyController{informer: s}
}

func (s *sharedIndexInformer) AddEventHandler(handler ResourceEventHandler) {
	s.AddEventHandlerWithResyncPeriod(handler, s.defaultEventHandlerResyncPeriod)
}

func determineResyncPeriod(desired, check time.Duration) time.Duration {
	if desired == 0 {
		return desired
	}
	if check == 0 {
		glog.Warningf("The specified resyncPeriod %v is invalid because this shared informer doesn't support resyncing", desired)
		return 0
	}
	if desired < check {
		glog.Warningf("The specified resyncPeriod %v is being increased to the minimum resyncCheckPeriod %v", desired, check)
		return check
	}
	return desired
}

const minimumResyncPeriod = 1 * time.Second

func (s *sharedIndexInformer) AddEventHandlerWithResyncPeriod(handler ResourceEventHandler, resyncPeriod time.Duration) {
	s.startedLock.Lock()
	defer s.startedLock.Unlock()

	if s.stopped {
		glog.V(2).Infof("Handler %v was not added to shared informer because it has stopped already", handler)
		return
	}

	if resyncPeriod > 0 {
		if resyncPeriod < minimumResyncPeriod {
			glog.Warningf("resyncPeriod %d is too small. Changing it to the minimum allowed value of %d", resyncPeriod, minimumResyncPeriod)
			resyncPeriod = minimumResyncPeriod
		}

		if resyncPeriod < s.resyncCheckPeriod {
			if s.started {
				glog.Warningf("resyncPeriod %d is smaller than resyncCheckPeriod %d and the informer has already started. Changing it to %d", resyncPeriod, s.resyncCheckPeriod, s.resyncCheckPeriod)
				resyncPeriod = s.resyncCheckPeriod
			} else {
				// if the event handler's resyncPeriod is smaller than the current resyncCheckPeriod, update
				// resyncCheckPeriod to match resyncPeriod and adjust the resync periods of all the listeners
				// accordingly
				s.resyncCheckPeriod = resyncPeriod
				s.processor.resyncCheckPeriodChanged(resyncPeriod)
			}
		}
	}

	listener := newProcessListener(handler, resyncPeriod, determineResyncPeriod(resyncPeriod, s.resyncCheckPeriod), s.clock.Now(), initialBufferSize)

	if !s.started {
		s.processor.addListener(listener)
		return
	}

	// in order to safely join, we have to
	// 1. stop sending add/update/delete notifications
	// 2. do a list against the store
	// 3. send synthetic "Add" events to the new handler
	// 4. unblock
	s.blockDeltas.Lock()
	defer s.blockDeltas.Unlock()

	s.processor.addAndStartListener(listener)
	for _, item := range s.indexer.List() {
		listener.add(addNotification{newObj: item})
	}
}

func (s *sharedIndexInformer) HandleDeltas(obj interface{}) error {
	s.blockDeltas.Lock()
	defer s.blockDeltas.Unlock()

	// from oldest to newest
	for _, d := range obj.(Deltas) {
		switch d.Type {
		case Sync, Added, Updated:
			isSync := d.Type == Sync
			s.cacheMutationDetector.AddObject(d.Object)
			if old, exists, err := s.indexer.Get(d.Object); err == nil && exists {
				if err := s.indexer.Update(d.Object); err != nil {
					return err
				}
				s.processor.distribute(updateNotification{oldObj: old, newObj: d.Object}, isSync)
			} else {
				if err := s.indexer.Add(d.Object); err != nil {
					return err
				}
				s.processor.distribute(addNotification{newObj: d.Object}, isSync)
			}
		case Deleted:
			if err := s.indexer.Delete(d.Object); err != nil {
				return err
			}
			s.processor.distribute(deleteNotification{oldObj: d.Object}, false)
		}
	}
	return nil
}

type sharedProcessor struct {
	listenersLock    sync.RWMutex
	listeners        []*processorListener
	syncingListeners []*processorListener
	clock            clock.Clock
	wg               wait.Group
}

func (p *sharedProcessor) addAndStartListener(listener *processorListener) {
	p.listenersLock.Lock()
	defer p.listenersLock.Unlock()

	p.addListenerLocked(listener)
	p.wg.Start(listener.run)
	p.wg.Start(listener.pop)
}

func (p *sharedProcessor) addListener(listener *processorListener) {
	p.listenersLock.Lock()
	defer p.listenersLock.Unlock()

	p.addListenerLocked(listener)
}

func (p *sharedProcessor) addListenerLocked(listener *processorListener) {
	p.listeners = append(p.listeners, listener)
	p.syncingListeners = append(p.syncingListeners, listener)
}

func (p *sharedProcessor) distribute(obj interface{}, sync bool) {
	p.listenersLock.RLock()
	defer p.listenersLock.RUnlock()

	if sync {
		for _, listener := range p.syncingListeners {
			listener.add(obj)
		}
	} else {
		for _, listener := range p.listeners {
			listener.add(obj)
		}
	}
}

func (p *sharedProcessor) run(stopCh <-chan struct{}) {
	func() {
		p.listenersLock.RLock()
		defer p.listenersLock.RUnlock()
		for _, listener := range p.listeners {
			p.wg.Start(listener.run)
			p.wg.Start(listener.pop)
		}
	}()
	<-stopCh
	p.listenersLock.RLock()
	defer p.listenersLock.RUnlock()
	for _, listener := range p.listeners {
		close(listener.addCh) // Tell .pop() to stop. .pop() will tell .run() to stop
	}
	p.wg.Wait() // Wait for all .pop() and .run() to stop
}

// shouldResync queries every listener to determine if any of them need a resync, based on each
// listener's resyncPeriod.
func (p *sharedProcessor) shouldResync() bool {
	p.listenersLock.Lock()
	defer p.listenersLock.Unlock()

	p.syncingListeners = []*processorListener{}

	resyncNeeded := false
	now := p.clock.Now()
	for _, listener := range p.listeners {
		// need to loop through all the listeners to see if they need to resync so we can prepare any
		// listeners that are going to be resyncing.
		if listener.shouldResync(now) {
			resyncNeeded = true
			p.syncingListeners = append(p.syncingListeners, listener)
			listener.determineNextResync(now)
		}
	}
	return resyncNeeded
}

func (p *sharedProcessor) resyncCheckPeriodChanged(resyncCheckPeriod time.Duration) {
	p.listenersLock.RLock()
	defer p.listenersLock.RUnlock()

	for _, listener := range p.listeners {
		resyncPeriod := determineResyncPeriod(listener.requestedResyncPeriod, resyncCheckPeriod)
		listener.setResyncPeriod(resyncPeriod)
	}
}

type processorListener struct {
	nextCh chan interface{}
	addCh  chan interface{}

	handler ResourceEventHandler

	// pendingNotifications is an unbounded ring buffer that holds all notifications not yet distributed.
	// There is one per listener, but a failing/stalled listener will have infinite pendingNotifications
	// added until we OOM.
	// TODO: This is no worse than before, since reflectors were backed by unbounded DeltaFIFOs, but
	// we should try to do something better.
	pendingNotifications buffer.RingGrowing

	// requestedResyncPeriod is how frequently the listener wants a full resync from the shared informer
	requestedResyncPeriod time.Duration
	// resyncPeriod is how frequently the listener wants a full resync from the shared informer. This
	// value may differ from requestedResyncPeriod if the shared informer adjusts it to align with the
	// informer's overall resync check period.
	resyncPeriod time.Duration
	// nextResync is the earliest time the listener should get a full resync
	nextResync time.Time
	// resyncLock guards access to resyncPeriod and nextResync
	resyncLock sync.Mutex
}

func newProcessListener(handler ResourceEventHandler, requestedResyncPeriod, resyncPeriod time.Duration, now time.Time, bufferSize int) *processorListener {
	ret := &processorListener{
		nextCh:                make(chan interface{}),
		addCh:                 make(chan interface{}),
		handler:               handler,
		pendingNotifications:  *buffer.NewRingGrowing(bufferSize),
		requestedResyncPeriod: requestedResyncPeriod,
		resyncPeriod:          resyncPeriod,
	}

	ret.determineNextResync(now)

	return ret
}

func (p *processorListener) add(notification interface{}) {
	p.addCh <- notification
}

func (p *processorListener) pop() {
	defer utilruntime.HandleCrash()
	defer close(p.nextCh) // Tell .run() to stop

	var nextCh chan<- interface{}
	var notification interface{}
	for {
		select {
		case nextCh <- notification:
			// Notification dispatched
			var ok bool
			notification, ok = p.pendingNotifications.ReadOne()
			if !ok { // Nothing to pop
				nextCh = nil // Disable this select case
			}
		case notificationToAdd, ok := <-p.addCh:
			if !ok {
				return
			}
			if notification == nil { // No notification to pop (and pendingNotifications is empty)
				// Optimize the case - skip adding to pendingNotifications
				notification = notificationToAdd
				nextCh = p.nextCh
			} else { // There is already a notification waiting to be dispatched
				p.pendingNotifications.WriteOne(notificationToAdd)
			}
		}
	}
}

func (p *processorListener) run() {
	// this call blocks until the channel is closed.  When a panic happens during the notification
	// we will catch it, **the offending item will be skipped!**, and after a short delay (one second)
	// the next notification will be attempted.  This is usually better than the alternative of never
	// delivering again.
	stopCh := make(chan struct{})
	wait.Until(func() {
		// this gives us a few quick retries before a long pause and then a few more quick retries
		err := wait.ExponentialBackoff(retry.DefaultRetry, func() (bool, error) {
			for next := range p.nextCh {
				switch notification := next.(type) {
				case updateNotification:
					p.handler.OnUpdate(notification.oldObj, notification.newObj)
				case addNotification:
					p.handler.OnAdd(notification.newObj)
				case deleteNotification:
					p.handler.OnDelete(notification.oldObj)
				default:
					utilruntime.HandleError(fmt.Errorf("unrecognized notification: %#v", next))
				}
			}
			// the only way to get here is if the p.nextCh is empty and closed
			return true, nil
		})

		// the only way to get here is if the p.nextCh is empty and closed
		if err == nil {
			close(stopCh)
		}
	}, 1*time.Minute, stopCh)
}

// shouldResync deterimines if the listener needs a resync. If the listener's resyncPeriod is 0,
// this always returns false.
func (p *processorListener) shouldResync(now time.Time) bool {
	p.resyncLock.Lock()
	defer p.resyncLock.Unlock()

	if p.resyncPeriod == 0 {
		return false
	}

	return now.After(p.nextResync) || now.Equal(p.nextResync)
}

func (p *processorListener) determineNextResync(now time.Time) {
	p.resyncLock.Lock()
	defer p.resyncLock.Unlock()

	p.nextResync = now.Add(p.resyncPeriod)
}

func (p *processorListener) setResyncPeriod(resyncPeriod time.Duration) {
	p.resyncLock.Lock()
	defer p.resyncLock.Unlock()

	p.resyncPeriod = resyncPeriod
}