forked from kubernetes/kubernetes
-
Notifications
You must be signed in to change notification settings - Fork 0
/
daemon_controller.go
1455 lines (1300 loc) · 53.4 KB
/
daemon_controller.go
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
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
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 daemon
import (
"fmt"
"reflect"
"sort"
"sync"
"time"
"github.com/golang/glog"
apps "k8s.io/api/apps/v1"
"k8s.io/api/core/v1"
"k8s.io/apimachinery/pkg/api/errors"
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
"k8s.io/apimachinery/pkg/labels"
utilerrors "k8s.io/apimachinery/pkg/util/errors"
utilruntime "k8s.io/apimachinery/pkg/util/runtime"
"k8s.io/apimachinery/pkg/util/sets"
"k8s.io/apimachinery/pkg/util/wait"
utilfeature "k8s.io/apiserver/pkg/util/feature"
appsinformers "k8s.io/client-go/informers/apps/v1"
coreinformers "k8s.io/client-go/informers/core/v1"
clientset "k8s.io/client-go/kubernetes"
"k8s.io/client-go/kubernetes/scheme"
unversionedapps "k8s.io/client-go/kubernetes/typed/apps/v1"
v1core "k8s.io/client-go/kubernetes/typed/core/v1"
appslisters "k8s.io/client-go/listers/apps/v1"
corelisters "k8s.io/client-go/listers/core/v1"
"k8s.io/client-go/tools/cache"
"k8s.io/client-go/tools/record"
"k8s.io/client-go/util/integer"
"k8s.io/client-go/util/workqueue"
podutil "k8s.io/kubernetes/pkg/api/v1/pod"
v1helper "k8s.io/kubernetes/pkg/apis/core/v1/helper"
"k8s.io/kubernetes/pkg/controller"
"k8s.io/kubernetes/pkg/controller/daemon/util"
"k8s.io/kubernetes/pkg/features"
kubelettypes "k8s.io/kubernetes/pkg/kubelet/types"
"k8s.io/kubernetes/pkg/scheduler/algorithm"
"k8s.io/kubernetes/pkg/scheduler/algorithm/predicates"
"k8s.io/kubernetes/pkg/scheduler/schedulercache"
"k8s.io/kubernetes/pkg/util/metrics"
)
const (
// BurstReplicas is a rate limiter for booting pods on a lot of pods.
// The value of 250 is chosen b/c values that are too high can cause registry DoS issues.
BurstReplicas = 250
// StatusUpdateRetries limits the number of retries if sending a status update to API server fails.
StatusUpdateRetries = 1
)
// Reasons for DaemonSet events
const (
// SelectingAllReason is added to an event when a DaemonSet selects all Pods.
SelectingAllReason = "SelectingAll"
// FailedPlacementReason is added to an event when a DaemonSet can't schedule a Pod to a specified node.
FailedPlacementReason = "FailedPlacement"
// FailedDaemonPodReason is added to an event when the status of a Pod of a DaemonSet is 'Failed'.
FailedDaemonPodReason = "FailedDaemonPod"
)
// controllerKind contains the schema.GroupVersionKind for this controller type.
var controllerKind = apps.SchemeGroupVersion.WithKind("DaemonSet")
// DaemonSetsController is responsible for synchronizing DaemonSet objects stored
// in the system with actual running pods.
type DaemonSetsController struct {
kubeClient clientset.Interface
eventRecorder record.EventRecorder
podControl controller.PodControlInterface
crControl controller.ControllerRevisionControlInterface
// An dsc is temporarily suspended after creating/deleting these many replicas.
// It resumes normal action after observing the watch events for them.
burstReplicas int
// To allow injection of syncDaemonSet for testing.
syncHandler func(dsKey string) error
// used for unit testing
enqueueDaemonSet func(ds *apps.DaemonSet)
enqueueDaemonSetRateLimited func(ds *apps.DaemonSet)
// A TTLCache of pod creates/deletes each ds expects to see
expectations controller.ControllerExpectationsInterface
// dsLister can list/get daemonsets from the shared informer's store
dsLister appslisters.DaemonSetLister
// dsStoreSynced returns true if the daemonset store has been synced at least once.
// Added as a member to the struct to allow injection for testing.
dsStoreSynced cache.InformerSynced
// historyLister get list/get history from the shared informers's store
historyLister appslisters.ControllerRevisionLister
// historyStoreSynced returns true if the history store has been synced at least once.
// Added as a member to the struct to allow injection for testing.
historyStoreSynced cache.InformerSynced
// podLister get list/get pods from the shared informers's store
podLister corelisters.PodLister
// podStoreSynced returns true if the pod store has been synced at least once.
// Added as a member to the struct to allow injection for testing.
podStoreSynced cache.InformerSynced
// nodeLister can list/get nodes from the shared informer's store
nodeLister corelisters.NodeLister
// nodeStoreSynced returns true if the node store has been synced at least once.
// Added as a member to the struct to allow injection for testing.
nodeStoreSynced cache.InformerSynced
// DaemonSet keys that need to be synced.
queue workqueue.RateLimitingInterface
// The DaemonSet that has suspended pods on nodes; the key is node name, the value
// is DaemonSet set that want to run pods but can't schedule in latest syncup cycle.
suspendedDaemonPodsMutex sync.Mutex
suspendedDaemonPods map[string]sets.String
}
// NewDaemonSetsController creates a new DaemonSetsController
func NewDaemonSetsController(daemonSetInformer appsinformers.DaemonSetInformer, historyInformer appsinformers.ControllerRevisionInformer, podInformer coreinformers.PodInformer, nodeInformer coreinformers.NodeInformer, kubeClient clientset.Interface) (*DaemonSetsController, error) {
eventBroadcaster := record.NewBroadcaster()
eventBroadcaster.StartLogging(glog.Infof)
// TODO: remove the wrapper when every clients have moved to use the clientset.
eventBroadcaster.StartRecordingToSink(&v1core.EventSinkImpl{Interface: v1core.New(kubeClient.CoreV1().RESTClient()).Events("")})
if kubeClient != nil && kubeClient.CoreV1().RESTClient().GetRateLimiter() != nil {
if err := metrics.RegisterMetricAndTrackRateLimiterUsage("daemon_controller", kubeClient.CoreV1().RESTClient().GetRateLimiter()); err != nil {
return nil, err
}
}
dsc := &DaemonSetsController{
kubeClient: kubeClient,
eventRecorder: eventBroadcaster.NewRecorder(scheme.Scheme, v1.EventSource{Component: "daemonset-controller"}),
podControl: controller.RealPodControl{
KubeClient: kubeClient,
Recorder: eventBroadcaster.NewRecorder(scheme.Scheme, v1.EventSource{Component: "daemonset-controller"}),
},
crControl: controller.RealControllerRevisionControl{
KubeClient: kubeClient,
},
burstReplicas: BurstReplicas,
expectations: controller.NewControllerExpectations(),
queue: workqueue.NewNamedRateLimitingQueue(workqueue.DefaultControllerRateLimiter(), "daemonset"),
suspendedDaemonPods: map[string]sets.String{},
}
daemonSetInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
AddFunc: func(obj interface{}) {
ds := obj.(*apps.DaemonSet)
glog.V(4).Infof("Adding daemon set %s", ds.Name)
dsc.enqueueDaemonSet(ds)
},
UpdateFunc: func(old, cur interface{}) {
oldDS := old.(*apps.DaemonSet)
curDS := cur.(*apps.DaemonSet)
glog.V(4).Infof("Updating daemon set %s", oldDS.Name)
dsc.enqueueDaemonSet(curDS)
},
DeleteFunc: dsc.deleteDaemonset,
})
dsc.dsLister = daemonSetInformer.Lister()
dsc.dsStoreSynced = daemonSetInformer.Informer().HasSynced
historyInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
AddFunc: dsc.addHistory,
UpdateFunc: dsc.updateHistory,
DeleteFunc: dsc.deleteHistory,
})
dsc.historyLister = historyInformer.Lister()
dsc.historyStoreSynced = historyInformer.Informer().HasSynced
// Watch for creation/deletion of pods. The reason we watch is that we don't want a daemon set to create/delete
// more pods until all the effects (expectations) of a daemon set's create/delete have been observed.
podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
AddFunc: dsc.addPod,
UpdateFunc: dsc.updatePod,
DeleteFunc: dsc.deletePod,
})
dsc.podLister = podInformer.Lister()
dsc.podStoreSynced = podInformer.Informer().HasSynced
nodeInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
AddFunc: dsc.addNode,
UpdateFunc: dsc.updateNode,
},
)
dsc.nodeStoreSynced = nodeInformer.Informer().HasSynced
dsc.nodeLister = nodeInformer.Lister()
dsc.syncHandler = dsc.syncDaemonSet
dsc.enqueueDaemonSet = dsc.enqueue
dsc.enqueueDaemonSetRateLimited = dsc.enqueueRateLimited
return dsc, nil
}
func (dsc *DaemonSetsController) deleteDaemonset(obj interface{}) {
ds, ok := obj.(*apps.DaemonSet)
if !ok {
tombstone, ok := obj.(cache.DeletedFinalStateUnknown)
if !ok {
utilruntime.HandleError(fmt.Errorf("Couldn't get object from tombstone %#v", obj))
return
}
ds, ok = tombstone.Obj.(*apps.DaemonSet)
if !ok {
utilruntime.HandleError(fmt.Errorf("Tombstone contained object that is not a DaemonSet %#v", obj))
return
}
}
glog.V(4).Infof("Deleting daemon set %s", ds.Name)
dsc.enqueueDaemonSet(ds)
}
// Run begins watching and syncing daemon sets.
func (dsc *DaemonSetsController) Run(workers int, stopCh <-chan struct{}) {
defer utilruntime.HandleCrash()
defer dsc.queue.ShutDown()
glog.Infof("Starting daemon sets controller")
defer glog.Infof("Shutting down daemon sets controller")
if !controller.WaitForCacheSync("daemon sets", stopCh, dsc.podStoreSynced, dsc.nodeStoreSynced, dsc.historyStoreSynced, dsc.dsStoreSynced) {
return
}
for i := 0; i < workers; i++ {
go wait.Until(dsc.runWorker, time.Second, stopCh)
}
<-stopCh
}
func (dsc *DaemonSetsController) runWorker() {
for dsc.processNextWorkItem() {
}
}
// processNextWorkItem deals with one key off the queue. It returns false when it's time to quit.
func (dsc *DaemonSetsController) processNextWorkItem() bool {
dsKey, quit := dsc.queue.Get()
if quit {
return false
}
defer dsc.queue.Done(dsKey)
err := dsc.syncHandler(dsKey.(string))
if err == nil {
dsc.queue.Forget(dsKey)
return true
}
utilruntime.HandleError(fmt.Errorf("%v failed with : %v", dsKey, err))
dsc.queue.AddRateLimited(dsKey)
return true
}
func (dsc *DaemonSetsController) enqueue(ds *apps.DaemonSet) {
key, err := controller.KeyFunc(ds)
if err != nil {
utilruntime.HandleError(fmt.Errorf("Couldn't get key for object %#v: %v", ds, err))
return
}
// TODO: Handle overlapping controllers better. See comment in ReplicationManager.
dsc.queue.Add(key)
}
func (dsc *DaemonSetsController) enqueueRateLimited(ds *apps.DaemonSet) {
key, err := controller.KeyFunc(ds)
if err != nil {
utilruntime.HandleError(fmt.Errorf("Couldn't get key for object %#v: %v", ds, err))
return
}
dsc.queue.AddRateLimited(key)
}
func (dsc *DaemonSetsController) enqueueDaemonSetAfter(obj interface{}, after time.Duration) {
key, err := controller.KeyFunc(obj)
if err != nil {
utilruntime.HandleError(fmt.Errorf("Couldn't get key for object %+v: %v", obj, err))
return
}
// TODO: Handle overlapping controllers better. See comment in ReplicationManager.
dsc.queue.AddAfter(key, after)
}
// getDaemonSetsForPod returns a list of DaemonSets that potentially match the pod.
func (dsc *DaemonSetsController) getDaemonSetsForPod(pod *v1.Pod) []*apps.DaemonSet {
sets, err := dsc.dsLister.GetPodDaemonSets(pod)
if err != nil {
return nil
}
if len(sets) > 1 {
// ControllerRef will ensure we don't do anything crazy, but more than one
// item in this list nevertheless constitutes user error.
utilruntime.HandleError(fmt.Errorf("user error! more than one daemon is selecting pods with labels: %+v", pod.Labels))
}
return sets
}
// getDaemonSetsForHistory returns a list of DaemonSets that potentially
// match a ControllerRevision.
func (dsc *DaemonSetsController) getDaemonSetsForHistory(history *apps.ControllerRevision) []*apps.DaemonSet {
daemonSets, err := dsc.dsLister.GetHistoryDaemonSets(history)
if err != nil || len(daemonSets) == 0 {
return nil
}
if len(daemonSets) > 1 {
// ControllerRef will ensure we don't do anything crazy, but more than one
// item in this list nevertheless constitutes user error.
glog.V(4).Infof("User error! more than one DaemonSets is selecting ControllerRevision %s/%s with labels: %#v",
history.Namespace, history.Name, history.Labels)
}
return daemonSets
}
// addHistory enqueues the DaemonSet that manages a ControllerRevision when the ControllerRevision is created
// or when the controller manager is restarted.
func (dsc *DaemonSetsController) addHistory(obj interface{}) {
history := obj.(*apps.ControllerRevision)
if history.DeletionTimestamp != nil {
// On a restart of the controller manager, it's possible for an object to
// show up in a state that is already pending deletion.
dsc.deleteHistory(history)
return
}
// If it has a ControllerRef, that's all that matters.
if controllerRef := metav1.GetControllerOf(history); controllerRef != nil {
ds := dsc.resolveControllerRef(history.Namespace, controllerRef)
if ds == nil {
return
}
glog.V(4).Infof("ControllerRevision %s added.", history.Name)
return
}
// Otherwise, it's an orphan. Get a list of all matching DaemonSets and sync
// them to see if anyone wants to adopt it.
daemonSets := dsc.getDaemonSetsForHistory(history)
if len(daemonSets) == 0 {
return
}
glog.V(4).Infof("Orphan ControllerRevision %s added.", history.Name)
for _, ds := range daemonSets {
dsc.enqueueDaemonSet(ds)
}
}
// updateHistory figures out what DaemonSet(s) manage a ControllerRevision when the ControllerRevision
// is updated and wake them up. If anything of the ControllerRevision has changed, we need to awaken
// both the old and new DaemonSets.
func (dsc *DaemonSetsController) updateHistory(old, cur interface{}) {
curHistory := cur.(*apps.ControllerRevision)
oldHistory := old.(*apps.ControllerRevision)
if curHistory.ResourceVersion == oldHistory.ResourceVersion {
// Periodic resync will send update events for all known ControllerRevisions.
return
}
curControllerRef := metav1.GetControllerOf(curHistory)
oldControllerRef := metav1.GetControllerOf(oldHistory)
controllerRefChanged := !reflect.DeepEqual(curControllerRef, oldControllerRef)
if controllerRefChanged && oldControllerRef != nil {
// The ControllerRef was changed. Sync the old controller, if any.
if ds := dsc.resolveControllerRef(oldHistory.Namespace, oldControllerRef); ds != nil {
dsc.enqueueDaemonSet(ds)
}
}
// If it has a ControllerRef, that's all that matters.
if curControllerRef != nil {
ds := dsc.resolveControllerRef(curHistory.Namespace, curControllerRef)
if ds == nil {
return
}
glog.V(4).Infof("ControllerRevision %s updated.", curHistory.Name)
dsc.enqueueDaemonSet(ds)
return
}
// Otherwise, it's an orphan. If anything changed, sync matching controllers
// to see if anyone wants to adopt it now.
labelChanged := !reflect.DeepEqual(curHistory.Labels, oldHistory.Labels)
if labelChanged || controllerRefChanged {
daemonSets := dsc.getDaemonSetsForHistory(curHistory)
if len(daemonSets) == 0 {
return
}
glog.V(4).Infof("Orphan ControllerRevision %s updated.", curHistory.Name)
for _, ds := range daemonSets {
dsc.enqueueDaemonSet(ds)
}
}
}
// deleteHistory enqueues the DaemonSet that manages a ControllerRevision when
// the ControllerRevision is deleted. obj could be an *app.ControllerRevision, or
// a DeletionFinalStateUnknown marker item.
func (dsc *DaemonSetsController) deleteHistory(obj interface{}) {
history, ok := obj.(*apps.ControllerRevision)
// When a delete is dropped, the relist will notice a ControllerRevision in the store not
// in the list, leading to the insertion of a tombstone object which contains
// the deleted key/value. Note that this value might be stale. If the ControllerRevision
// changed labels the new DaemonSet will not be woken up till the periodic resync.
if !ok {
tombstone, ok := obj.(cache.DeletedFinalStateUnknown)
if !ok {
utilruntime.HandleError(fmt.Errorf("Couldn't get object from tombstone %#v", obj))
return
}
history, ok = tombstone.Obj.(*apps.ControllerRevision)
if !ok {
utilruntime.HandleError(fmt.Errorf("Tombstone contained object that is not a ControllerRevision %#v", obj))
return
}
}
controllerRef := metav1.GetControllerOf(history)
if controllerRef == nil {
// No controller should care about orphans being deleted.
return
}
ds := dsc.resolveControllerRef(history.Namespace, controllerRef)
if ds == nil {
return
}
glog.V(4).Infof("ControllerRevision %s deleted.", history.Name)
dsc.enqueueDaemonSet(ds)
}
func (dsc *DaemonSetsController) addPod(obj interface{}) {
pod := obj.(*v1.Pod)
if pod.DeletionTimestamp != nil {
// on a restart of the controller manager, it's possible a new pod shows up in a state that
// is already pending deletion. Prevent the pod from being a creation observation.
dsc.deletePod(pod)
return
}
// If it has a ControllerRef, that's all that matters.
if controllerRef := metav1.GetControllerOf(pod); controllerRef != nil {
ds := dsc.resolveControllerRef(pod.Namespace, controllerRef)
if ds == nil {
return
}
dsKey, err := controller.KeyFunc(ds)
if err != nil {
return
}
glog.V(4).Infof("Pod %s added.", pod.Name)
dsc.expectations.CreationObserved(dsKey)
dsc.enqueueDaemonSet(ds)
return
}
// Otherwise, it's an orphan. Get a list of all matching DaemonSets and sync
// them to see if anyone wants to adopt it.
// DO NOT observe creation because no controller should be waiting for an
// orphan.
dss := dsc.getDaemonSetsForPod(pod)
if len(dss) == 0 {
return
}
glog.V(4).Infof("Orphan Pod %s added.", pod.Name)
for _, ds := range dss {
dsc.enqueueDaemonSet(ds)
}
}
// When a pod is updated, figure out what sets manage it and wake them
// up. If the labels of the pod have changed we need to awaken both the old
// and new set. old and cur must be *v1.Pod types.
func (dsc *DaemonSetsController) updatePod(old, cur interface{}) {
curPod := cur.(*v1.Pod)
oldPod := old.(*v1.Pod)
if curPod.ResourceVersion == oldPod.ResourceVersion {
// Periodic resync will send update events for all known pods.
// Two different versions of the same pod will always have different RVs.
return
}
curControllerRef := metav1.GetControllerOf(curPod)
oldControllerRef := metav1.GetControllerOf(oldPod)
controllerRefChanged := !reflect.DeepEqual(curControllerRef, oldControllerRef)
if controllerRefChanged && oldControllerRef != nil {
// The ControllerRef was changed. Sync the old controller, if any.
if ds := dsc.resolveControllerRef(oldPod.Namespace, oldControllerRef); ds != nil {
dsc.enqueueDaemonSet(ds)
}
}
// If it has a ControllerRef, that's all that matters.
if curControllerRef != nil {
ds := dsc.resolveControllerRef(curPod.Namespace, curControllerRef)
if ds == nil {
return
}
glog.V(4).Infof("Pod %s updated.", curPod.Name)
dsc.enqueueDaemonSet(ds)
changedToReady := !podutil.IsPodReady(oldPod) && podutil.IsPodReady(curPod)
// See https://github.com/kubernetes/kubernetes/pull/38076 for more details
if changedToReady && ds.Spec.MinReadySeconds > 0 {
// Add a second to avoid milliseconds skew in AddAfter.
// See https://github.com/kubernetes/kubernetes/issues/39785#issuecomment-279959133 for more info.
dsc.enqueueDaemonSetAfter(ds, (time.Duration(ds.Spec.MinReadySeconds)*time.Second)+time.Second)
}
return
}
// Otherwise, it's an orphan. If anything changed, sync matching controllers
// to see if anyone wants to adopt it now.
dss := dsc.getDaemonSetsForPod(curPod)
if len(dss) == 0 {
return
}
glog.V(4).Infof("Orphan Pod %s updated.", curPod.Name)
labelChanged := !reflect.DeepEqual(curPod.Labels, oldPod.Labels)
if labelChanged || controllerRefChanged {
for _, ds := range dss {
dsc.enqueueDaemonSet(ds)
}
}
}
// listSuspendedDaemonPods lists the Daemon pods that 'want to run, but should not schedule'
// for the node.
func (dsc *DaemonSetsController) listSuspendedDaemonPods(node string) (dss []string) {
dsc.suspendedDaemonPodsMutex.Lock()
defer dsc.suspendedDaemonPodsMutex.Unlock()
if _, found := dsc.suspendedDaemonPods[node]; !found {
return nil
}
for k := range dsc.suspendedDaemonPods[node] {
dss = append(dss, k)
}
return
}
// requeueSuspendedDaemonPods enqueues all DaemonSets which has pods that 'want to run,
// but should not schedule' for the node; so DaemonSetController will sync up them again.
func (dsc *DaemonSetsController) requeueSuspendedDaemonPods(node string) {
dss := dsc.listSuspendedDaemonPods(node)
for _, dsKey := range dss {
if ns, name, err := cache.SplitMetaNamespaceKey(dsKey); err != nil {
glog.Errorf("Failed to get DaemonSet's namespace and name from %s: %v", dsKey, err)
continue
} else if ds, err := dsc.dsLister.DaemonSets(ns).Get(name); err != nil {
glog.Errorf("Failed to get DaemonSet %s/%s: %v", ns, name, err)
continue
} else {
dsc.enqueueDaemonSetRateLimited(ds)
}
}
}
// addSuspendedDaemonPods adds DaemonSet which has pods that 'want to run,
// but should not schedule' for the node to the suspended queue.
func (dsc *DaemonSetsController) addSuspendedDaemonPods(node, ds string) {
dsc.suspendedDaemonPodsMutex.Lock()
defer dsc.suspendedDaemonPodsMutex.Unlock()
if _, found := dsc.suspendedDaemonPods[node]; !found {
dsc.suspendedDaemonPods[node] = sets.NewString()
}
dsc.suspendedDaemonPods[node].Insert(ds)
}
// removeSuspendedDaemonPods removes DaemonSet which has pods that 'want to run,
// but should not schedule' for the node from suspended queue.
func (dsc *DaemonSetsController) removeSuspendedDaemonPods(node, ds string) {
dsc.suspendedDaemonPodsMutex.Lock()
defer dsc.suspendedDaemonPodsMutex.Unlock()
if _, found := dsc.suspendedDaemonPods[node]; !found {
return
}
dsc.suspendedDaemonPods[node].Delete(ds)
if len(dsc.suspendedDaemonPods[node]) == 0 {
delete(dsc.suspendedDaemonPods, node)
}
}
func (dsc *DaemonSetsController) deletePod(obj interface{}) {
pod, ok := obj.(*v1.Pod)
// When a delete is dropped, the relist will notice a pod in the store not
// in the list, leading to the insertion of a tombstone object which contains
// the deleted key/value. Note that this value might be stale. If the pod
// changed labels the new daemonset will not be woken up till the periodic
// resync.
if !ok {
tombstone, ok := obj.(cache.DeletedFinalStateUnknown)
if !ok {
utilruntime.HandleError(fmt.Errorf("couldn't get object from tombstone %#v", obj))
return
}
pod, ok = tombstone.Obj.(*v1.Pod)
if !ok {
utilruntime.HandleError(fmt.Errorf("tombstone contained object that is not a pod %#v", obj))
return
}
}
controllerRef := metav1.GetControllerOf(pod)
if controllerRef == nil {
// No controller should care about orphans being deleted.
if len(pod.Spec.NodeName) != 0 {
// If scheduled pods were deleted, requeue suspended daemon pods.
dsc.requeueSuspendedDaemonPods(pod.Spec.NodeName)
}
return
}
ds := dsc.resolveControllerRef(pod.Namespace, controllerRef)
if ds == nil {
if len(pod.Spec.NodeName) != 0 {
// If scheduled pods were deleted, requeue suspended daemon pods.
dsc.requeueSuspendedDaemonPods(pod.Spec.NodeName)
}
return
}
dsKey, err := controller.KeyFunc(ds)
if err != nil {
return
}
glog.V(4).Infof("Pod %s deleted.", pod.Name)
dsc.expectations.DeletionObserved(dsKey)
dsc.enqueueDaemonSet(ds)
}
func (dsc *DaemonSetsController) addNode(obj interface{}) {
// TODO: it'd be nice to pass a hint with these enqueues, so that each ds would only examine the added node (unless it has other work to do, too).
dsList, err := dsc.dsLister.List(labels.Everything())
if err != nil {
glog.V(4).Infof("Error enqueueing daemon sets: %v", err)
return
}
node := obj.(*v1.Node)
for _, ds := range dsList {
_, shouldSchedule, _, err := dsc.nodeShouldRunDaemonPod(node, ds)
if err != nil {
continue
}
if shouldSchedule {
dsc.enqueueDaemonSet(ds)
}
}
}
// nodeInSameCondition returns true if all effective types ("Status" is true) equals;
// otherwise, returns false.
func nodeInSameCondition(old []v1.NodeCondition, cur []v1.NodeCondition) bool {
if len(old) == 0 && len(cur) == 0 {
return true
}
c1map := map[v1.NodeConditionType]v1.ConditionStatus{}
for _, c := range old {
if c.Status == v1.ConditionTrue {
c1map[c.Type] = c.Status
}
}
for _, c := range cur {
if c.Status != v1.ConditionTrue {
continue
}
if _, found := c1map[c.Type]; !found {
return false
}
delete(c1map, c.Type)
}
return len(c1map) == 0
}
func (dsc *DaemonSetsController) updateNode(old, cur interface{}) {
oldNode := old.(*v1.Node)
curNode := cur.(*v1.Node)
if reflect.DeepEqual(oldNode.Labels, curNode.Labels) &&
reflect.DeepEqual(oldNode.Spec.Taints, curNode.Spec.Taints) &&
nodeInSameCondition(oldNode.Status.Conditions, curNode.Status.Conditions) {
// If node labels, taints and condition didn't change, we can ignore this update.
return
}
dsList, err := dsc.dsLister.List(labels.Everything())
if err != nil {
glog.V(4).Infof("Error listing daemon sets: %v", err)
return
}
// TODO: it'd be nice to pass a hint with these enqueues, so that each ds would only examine the added node (unless it has other work to do, too).
for _, ds := range dsList {
_, oldShouldSchedule, oldShouldContinueRunning, err := dsc.nodeShouldRunDaemonPod(oldNode, ds)
if err != nil {
continue
}
_, currentShouldSchedule, currentShouldContinueRunning, err := dsc.nodeShouldRunDaemonPod(curNode, ds)
if err != nil {
continue
}
if (oldShouldSchedule != currentShouldSchedule) || (oldShouldContinueRunning != currentShouldContinueRunning) {
dsc.enqueueDaemonSet(ds)
}
}
}
// getDaemonPods returns daemon pods owned by the given ds.
// This also reconciles ControllerRef by adopting/orphaning.
// Note that returned Pods are pointers to objects in the cache.
// If you want to modify one, you need to deep-copy it first.
func (dsc *DaemonSetsController) getDaemonPods(ds *apps.DaemonSet) ([]*v1.Pod, error) {
selector, err := metav1.LabelSelectorAsSelector(ds.Spec.Selector)
if err != nil {
return nil, err
}
// List all pods to include those that don't match the selector anymore but
// have a ControllerRef pointing to this controller.
pods, err := dsc.podLister.Pods(ds.Namespace).List(labels.Everything())
if err != nil {
return nil, err
}
// If any adoptions are attempted, we should first recheck for deletion with
// an uncached quorum read sometime after listing Pods (see #42639).
dsNotDeleted := controller.RecheckDeletionTimestamp(func() (metav1.Object, error) {
fresh, err := dsc.kubeClient.AppsV1().DaemonSets(ds.Namespace).Get(ds.Name, metav1.GetOptions{})
if err != nil {
return nil, err
}
if fresh.UID != ds.UID {
return nil, fmt.Errorf("original DaemonSet %v/%v is gone: got uid %v, wanted %v", ds.Namespace, ds.Name, fresh.UID, ds.UID)
}
return fresh, nil
})
// Use ControllerRefManager to adopt/orphan as needed.
cm := controller.NewPodControllerRefManager(dsc.podControl, ds, selector, controllerKind, dsNotDeleted)
return cm.ClaimPods(pods)
}
// getNodesToDaemonPods returns a map from nodes to daemon pods (corresponding to ds) running on the nodes.
// This also reconciles ControllerRef by adopting/orphaning.
// Note that returned Pods are pointers to objects in the cache.
// If you want to modify one, you need to deep-copy it first.
func (dsc *DaemonSetsController) getNodesToDaemonPods(ds *apps.DaemonSet) (map[string][]*v1.Pod, error) {
claimedPods, err := dsc.getDaemonPods(ds)
if err != nil {
return nil, err
}
// Group Pods by Node name.
nodeToDaemonPods := make(map[string][]*v1.Pod)
for _, pod := range claimedPods {
nodeName := pod.Spec.NodeName
nodeToDaemonPods[nodeName] = append(nodeToDaemonPods[nodeName], pod)
}
return nodeToDaemonPods, nil
}
// resolveControllerRef returns the controller referenced by a ControllerRef,
// or nil if the ControllerRef could not be resolved to a matching controller
// of the correct Kind.
func (dsc *DaemonSetsController) resolveControllerRef(namespace string, controllerRef *metav1.OwnerReference) *apps.DaemonSet {
// We can't look up by UID, so look up by Name and then verify UID.
// Don't even try to look up by Name if it's the wrong Kind.
if controllerRef.Kind != controllerKind.Kind {
return nil
}
ds, err := dsc.dsLister.DaemonSets(namespace).Get(controllerRef.Name)
if err != nil {
return nil
}
if ds.UID != controllerRef.UID {
// The controller we found with this Name is not the same one that the
// ControllerRef points to.
return nil
}
return ds
}
// manage manages the scheduling and running of Pods of ds on nodes.
// After figuring out which nodes should run a Pod of ds but not yet running one and
// which nodes should not run a Pod of ds but currently running one, it calls function
// syncNodes with a list of pods to remove and a list of nodes to run a Pod of ds.
func (dsc *DaemonSetsController) manage(ds *apps.DaemonSet, hash string) error {
// Find out which nodes are running the daemon pods controlled by ds.
nodeToDaemonPods, err := dsc.getNodesToDaemonPods(ds)
if err != nil {
return fmt.Errorf("couldn't get node to daemon pod mapping for daemon set %q: %v", ds.Name, err)
}
// For each node, if the node is running the daemon pod but isn't supposed to, kill the daemon
// pod. If the node is supposed to run the daemon pod, but isn't, create the daemon pod on the node.
nodeList, err := dsc.nodeLister.List(labels.Everything())
if err != nil {
return fmt.Errorf("couldn't get list of nodes when syncing daemon set %#v: %v", ds, err)
}
var nodesNeedingDaemonPods, podsToDelete []string
var failedPodsObserved int
for _, node := range nodeList {
wantToRun, shouldSchedule, shouldContinueRunning, err := dsc.nodeShouldRunDaemonPod(node, ds)
if err != nil {
continue
}
daemonPods, exists := nodeToDaemonPods[node.Name]
dsKey, _ := cache.MetaNamespaceKeyFunc(ds)
dsc.removeSuspendedDaemonPods(node.Name, dsKey)
switch {
case wantToRun && !shouldSchedule:
// If daemon pod is supposed to run, but can not be scheduled, add to suspended list.
dsc.addSuspendedDaemonPods(node.Name, dsKey)
case shouldSchedule && !exists:
// If daemon pod is supposed to be running on node, but isn't, create daemon pod.
nodesNeedingDaemonPods = append(nodesNeedingDaemonPods, node.Name)
case shouldContinueRunning:
// If a daemon pod failed, delete it
// If there's non-daemon pods left on this node, we will create it in the next sync loop
var daemonPodsRunning []*v1.Pod
for _, pod := range daemonPods {
if pod.DeletionTimestamp != nil {
continue
}
if pod.Status.Phase == v1.PodFailed {
msg := fmt.Sprintf("Found failed daemon pod %s/%s on node %s, will try to kill it", pod.Namespace, pod.Name, node.Name)
glog.V(2).Infof(msg)
// Emit an event so that it's discoverable to users.
dsc.eventRecorder.Eventf(ds, v1.EventTypeWarning, FailedDaemonPodReason, msg)
podsToDelete = append(podsToDelete, pod.Name)
failedPodsObserved++
} else {
daemonPodsRunning = append(daemonPodsRunning, pod)
}
}
// If daemon pod is supposed to be running on node, but more than 1 daemon pod is running, delete the excess daemon pods.
// Sort the daemon pods by creation time, so the oldest is preserved.
if len(daemonPodsRunning) > 1 {
sort.Sort(podByCreationTimestamp(daemonPodsRunning))
for i := 1; i < len(daemonPodsRunning); i++ {
podsToDelete = append(podsToDelete, daemonPodsRunning[i].Name)
}
}
case !shouldContinueRunning && exists:
// If daemon pod isn't supposed to run on node, but it is, delete all daemon pods on node.
for _, pod := range daemonPods {
podsToDelete = append(podsToDelete, pod.Name)
}
}
}
// Label new pods using the hash label value of the current history when creating them
if err = dsc.syncNodes(ds, podsToDelete, nodesNeedingDaemonPods, hash); err != nil {
return err
}
// Throw an error when the daemon pods fail, to use ratelimiter to prevent kill-recreate hot loop
if failedPodsObserved > 0 {
return fmt.Errorf("deleted %d failed pods of DaemonSet %s/%s", failedPodsObserved, ds.Namespace, ds.Name)
}
return nil
}
// syncNodes deletes given pods and creates new daemon set pods on the given nodes
// returns slice with erros if any
func (dsc *DaemonSetsController) syncNodes(ds *apps.DaemonSet, podsToDelete, nodesNeedingDaemonPods []string, hash string) error {
// We need to set expectations before creating/deleting pods to avoid race conditions.
dsKey, err := controller.KeyFunc(ds)
if err != nil {
return fmt.Errorf("couldn't get key for object %#v: %v", ds, err)
}
createDiff := len(nodesNeedingDaemonPods)
deleteDiff := len(podsToDelete)
if createDiff > dsc.burstReplicas {
createDiff = dsc.burstReplicas
}
if deleteDiff > dsc.burstReplicas {
deleteDiff = dsc.burstReplicas
}
dsc.expectations.SetExpectations(dsKey, createDiff, deleteDiff)
// error channel to communicate back failures. make the buffer big enough to avoid any blocking
errCh := make(chan error, createDiff+deleteDiff)
glog.V(4).Infof("Nodes needing daemon pods for daemon set %s: %+v, creating %d", ds.Name, nodesNeedingDaemonPods, createDiff)
createWait := sync.WaitGroup{}
// If the returned error is not nil we have a parse error.
// The controller handles this via the hash.
generation, err := util.GetTemplateGeneration(ds)
if err != nil {
generation = nil
}
template := util.CreatePodTemplate(ds.Spec.Template, generation, hash)
// Batch the pod creates. Batch sizes start at SlowStartInitialBatchSize
// and double with each successful iteration in a kind of "slow start".
// This handles attempts to start large numbers of pods that would
// likely all fail with the same error. For example a project with a
// low quota that attempts to create a large number of pods will be
// prevented from spamming the API service with the pod create requests
// after one of its pods fails. Conveniently, this also prevents the
// event spam that those failures would generate.
batchSize := integer.IntMin(createDiff, controller.SlowStartInitialBatchSize)
for pos := 0; createDiff > pos; batchSize, pos = integer.IntMin(2*batchSize, createDiff-(pos+batchSize)), pos+batchSize {
errorCount := len(errCh)
createWait.Add(batchSize)
for i := pos; i < pos+batchSize; i++ {
go func(ix int) {
defer createWait.Done()
var err error
podTemplate := &template
if false /*disabled for 1.10*/ && utilfeature.DefaultFeatureGate.Enabled(features.ScheduleDaemonSetPods) {
podTemplate = template.DeepCopy()
podTemplate.Spec.Affinity = util.ReplaceDaemonSetPodHostnameNodeAffinity(
podTemplate.Spec.Affinity, nodesNeedingDaemonPods[ix])
podTemplate.Spec.Tolerations = util.AppendNoScheduleTolerationIfNotExist(podTemplate.Spec.Tolerations)
err = dsc.podControl.CreatePodsWithControllerRef(ds.Namespace, podTemplate,
ds, metav1.NewControllerRef(ds, controllerKind))
} else {
err = dsc.podControl.CreatePodsOnNode(nodesNeedingDaemonPods[ix], ds.Namespace, podTemplate,
ds, metav1.NewControllerRef(ds, controllerKind))
}
if err != nil && errors.IsTimeout(err) {
// Pod is created but its initialization has timed out.
// If the initialization is successful eventually, the
// controller will observe the creation via the informer.
// If the initialization fails, or if the pod keeps
// uninitialized for a long time, the informer will not
// receive any update, and the controller will create a new
// pod when the expectation expires.
return
}
if err != nil {
glog.V(2).Infof("Failed creation, decrementing expectations for set %q/%q", ds.Namespace, ds.Name)
dsc.expectations.CreationObserved(dsKey)
errCh <- err
utilruntime.HandleError(err)
}
}(i)
}
createWait.Wait()
// any skipped pods that we never attempted to start shouldn't be expected.
skippedPods := createDiff - batchSize
if errorCount < len(errCh) && skippedPods > 0 {
glog.V(2).Infof("Slow-start failure. Skipping creation of %d pods, decrementing expectations for set %q/%q", skippedPods, ds.Namespace, ds.Name)
for i := 0; i < skippedPods; i++ {
dsc.expectations.CreationObserved(dsKey)
}
// The skipped pods will be retried later. The next controller resync will
// retry the slow start process.
break
}
}
glog.V(4).Infof("Pods to delete for daemon set %s: %+v, deleting %d", ds.Name, podsToDelete, deleteDiff)
deleteWait := sync.WaitGroup{}
deleteWait.Add(deleteDiff)
for i := 0; i < deleteDiff; i++ {
go func(ix int) {
defer deleteWait.Done()
if err := dsc.podControl.DeletePod(ds.Namespace, podsToDelete[ix], ds); err != nil {
glog.V(2).Infof("Failed deletion, decrementing expectations for set %q/%q", ds.Namespace, ds.Name)
dsc.expectations.DeletionObserved(dsKey)
errCh <- err
utilruntime.HandleError(err)
}
}(i)
}
deleteWait.Wait()