forked from kubernetes/kubernetes
-
Notifications
You must be signed in to change notification settings - Fork 1
/
stateful_set.go
322 lines (288 loc) · 10.9 KB
/
stateful_set.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
/*
Copyright 2016 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 statefulset
import (
"fmt"
"reflect"
"sort"
"time"
"k8s.io/apimachinery/pkg/api/errors"
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
utilruntime "k8s.io/apimachinery/pkg/util/runtime"
"k8s.io/apimachinery/pkg/util/wait"
v1core "k8s.io/client-go/kubernetes/typed/core/v1"
clientv1 "k8s.io/client-go/pkg/api/v1"
"k8s.io/client-go/tools/cache"
"k8s.io/client-go/tools/record"
"k8s.io/client-go/util/workqueue"
"k8s.io/kubernetes/pkg/api"
"k8s.io/kubernetes/pkg/api/v1"
apps "k8s.io/kubernetes/pkg/apis/apps/v1beta1"
"k8s.io/kubernetes/pkg/client/clientset_generated/clientset"
appsinformers "k8s.io/kubernetes/pkg/client/informers/informers_generated/externalversions/apps/v1beta1"
coreinformers "k8s.io/kubernetes/pkg/client/informers/informers_generated/externalversions/core/v1"
appslisters "k8s.io/kubernetes/pkg/client/listers/apps/v1beta1"
corelisters "k8s.io/kubernetes/pkg/client/listers/core/v1"
"k8s.io/kubernetes/pkg/controller"
"github.com/golang/glog"
)
const (
// period to relist statefulsets and verify pets
statefulSetResyncPeriod = 30 * time.Second
)
// StatefulSetController controls statefulsets.
type StatefulSetController struct {
// client interface
kubeClient clientset.Interface
// control returns an interface capable of syncing a stateful set.
// Abstracted out for testing.
control StatefulSetControlInterface
// podLister is able to list/get pods from a shared informer's store
podLister corelisters.PodLister
// podListerSynced returns true if the pod shared informer has synced at least once
podListerSynced cache.InformerSynced
// setLister is able to list/get stateful sets from a shared informer's store
setLister appslisters.StatefulSetLister
// setListerSynced returns true if the stateful set shared informer has synced at least once
setListerSynced cache.InformerSynced
// pvcListerSynced returns true if the pvc shared informer has synced at least once
pvcListerSynced cache.InformerSynced
// StatefulSets that need to be synced.
queue workqueue.RateLimitingInterface
}
// NewStatefulSetController creates a new statefulset controller.
func NewStatefulSetController(
podInformer coreinformers.PodInformer,
setInformer appsinformers.StatefulSetInformer,
pvcInformer coreinformers.PersistentVolumeClaimInformer,
kubeClient clientset.Interface,
) *StatefulSetController {
eventBroadcaster := record.NewBroadcaster()
eventBroadcaster.StartLogging(glog.Infof)
eventBroadcaster.StartRecordingToSink(&v1core.EventSinkImpl{Interface: v1core.New(kubeClient.Core().RESTClient()).Events("")})
recorder := eventBroadcaster.NewRecorder(api.Scheme, clientv1.EventSource{Component: "statefulset"})
ssc := &StatefulSetController{
kubeClient: kubeClient,
control: NewDefaultStatefulSetControl(
NewRealStatefulPodControl(
kubeClient,
setInformer.Lister(),
podInformer.Lister(),
pvcInformer.Lister(),
recorder,
),
),
pvcListerSynced: pvcInformer.Informer().HasSynced,
queue: workqueue.NewNamedRateLimitingQueue(workqueue.DefaultControllerRateLimiter(), "statefulset"),
}
podInformer.Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
// lookup the statefulset and enqueue
AddFunc: ssc.addPod,
// lookup current and old statefulset if labels changed
UpdateFunc: ssc.updatePod,
// lookup statefulset accounting for deletion tombstones
DeleteFunc: ssc.deletePod,
})
ssc.podLister = podInformer.Lister()
ssc.podListerSynced = podInformer.Informer().HasSynced
setInformer.Informer().AddEventHandlerWithResyncPeriod(
cache.ResourceEventHandlerFuncs{
AddFunc: ssc.enqueueStatefulSet,
UpdateFunc: func(old, cur interface{}) {
oldPS := old.(*apps.StatefulSet)
curPS := cur.(*apps.StatefulSet)
if oldPS.Status.Replicas != curPS.Status.Replicas {
glog.V(4).Infof("Observed updated replica count for StatefulSet: %v, %d->%d", curPS.Name, oldPS.Status.Replicas, curPS.Status.Replicas)
}
ssc.enqueueStatefulSet(cur)
},
DeleteFunc: ssc.enqueueStatefulSet,
},
statefulSetResyncPeriod,
)
ssc.setLister = setInformer.Lister()
ssc.setListerSynced = setInformer.Informer().HasSynced
// TODO: Watch volumes
return ssc
}
// Run runs the statefulset controller.
func (ssc *StatefulSetController) Run(workers int, stopCh <-chan struct{}) {
defer utilruntime.HandleCrash()
defer ssc.queue.ShutDown()
glog.Infof("Starting statefulset controller")
if !cache.WaitForCacheSync(stopCh, ssc.podListerSynced, ssc.setListerSynced, ssc.pvcListerSynced) {
utilruntime.HandleError(fmt.Errorf("timed out waiting for caches to sync"))
return
}
for i := 0; i < workers; i++ {
go wait.Until(ssc.worker, time.Second, stopCh)
}
<-stopCh
glog.Infof("Shutting down statefulset controller")
}
// addPod adds the statefulset for the pod to the sync queue
func (ssc *StatefulSetController) addPod(obj interface{}) {
pod := obj.(*v1.Pod)
glog.V(4).Infof("Pod %s created, labels: %+v", pod.Name, pod.Labels)
set := ssc.getStatefulSetForPod(pod)
if set == nil {
return
}
ssc.enqueueStatefulSet(set)
}
// updatePod adds the statefulset for the current and old pods to the sync queue.
// If the labels of the pod didn't change, this method enqueues a single statefulset.
func (ssc *StatefulSetController) 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
}
set := ssc.getStatefulSetForPod(curPod)
if set == nil {
return
}
ssc.enqueueStatefulSet(set)
// TODO will we need this going forward with controller ref impl?
if !reflect.DeepEqual(curPod.Labels, oldPod.Labels) {
if oldSet := ssc.getStatefulSetForPod(oldPod); oldSet != nil {
ssc.enqueueStatefulSet(oldSet)
}
}
}
// deletePod enqueues the statefulset for the pod accounting for deletion tombstones.
func (ssc *StatefulSetController) 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 StatefulSet 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
}
}
glog.V(4).Infof("Pod %s/%s deleted through %v.", pod.Namespace, pod.Name, utilruntime.GetCaller())
if set := ssc.getStatefulSetForPod(pod); set != nil {
ssc.enqueueStatefulSet(set)
}
}
// getPodsForStatefulSets returns the pods that match the selectors of the given statefulset.
func (ssc *StatefulSetController) getPodsForStatefulSet(set *apps.StatefulSet) ([]*v1.Pod, error) {
sel, err := metav1.LabelSelectorAsSelector(set.Spec.Selector)
if err != nil {
return []*v1.Pod{}, err
}
return ssc.podLister.Pods(set.Namespace).List(sel)
}
// getStatefulSetForPod returns the StatefulSet managing the given pod.
func (ssc *StatefulSetController) getStatefulSetForPod(pod *v1.Pod) *apps.StatefulSet {
sets, err := ssc.setLister.GetPodStatefulSets(pod)
if err != nil {
glog.V(4).Infof("No StatefulSets found for pod %v, StatefulSet controller will avoid syncing", pod.Name)
return nil
}
// More than one set is selecting the same Pod
if len(sets) > 1 {
utilruntime.HandleError(
fmt.Errorf(
"user error: more than one StatefulSet is selecting pods with labels: %+v",
pod.Labels))
// The timestamp sort should not be necessary because we will enforce the CreatedBy requirement by
// name
sort.Sort(overlappingStatefulSets(sets))
// return the first created set for which pod is a member
for i := range sets {
if isMemberOf(sets[i], pod) {
return sets[i]
}
}
glog.V(4).Infof("No StatefulSets found for pod %v, StatefulSet controller will avoid syncing", pod.Name)
return nil
}
return sets[0]
}
// enqueueStatefulSet enqueues the given statefulset in the work queue.
func (ssc *StatefulSetController) enqueueStatefulSet(obj interface{}) {
key, err := controller.KeyFunc(obj)
if err != nil {
utilruntime.HandleError(fmt.Errorf("Cound't get key for object %+v: %v", obj, err))
return
}
ssc.queue.Add(key)
}
// processNextWorkItem dequeues items, processes them, and marks them done. It enforces that the syncHandler is never
// invoked concurrently with the same key.
func (ssc *StatefulSetController) processNextWorkItem() bool {
key, quit := ssc.queue.Get()
if quit {
return false
}
defer ssc.queue.Done(key)
if err := ssc.sync(key.(string)); err != nil {
utilruntime.HandleError(fmt.Errorf("Error syncing StatefulSet %v, requeuing: %v", key.(string), err))
ssc.queue.AddRateLimited(key)
} else {
ssc.queue.Forget(key)
}
return true
}
// worker runs a worker goroutine that invokes processNextWorkItem until the the controller's queue is closed
func (ssc *StatefulSetController) worker() {
for ssc.processNextWorkItem() {
}
}
// sync syncs the given statefulset.
func (ssc *StatefulSetController) sync(key string) error {
startTime := time.Now()
defer func() {
glog.V(4).Infof("Finished syncing statefulset %q (%v)", key, time.Now().Sub(startTime))
}()
namespace, name, err := cache.SplitMetaNamespaceKey(key)
if err != nil {
return err
}
set, err := ssc.setLister.StatefulSets(namespace).Get(name)
if errors.IsNotFound(err) {
glog.Infof("StatefulSet has been deleted %v", key)
return nil
}
if err != nil {
utilruntime.HandleError(fmt.Errorf("Unable to retrieve StatefulSet %v from store: %v", key, err))
return err
}
pods, err := ssc.getPodsForStatefulSet(set)
if err != nil {
return err
}
return ssc.syncStatefulSet(set, pods)
}
// syncStatefulSet syncs a tuple of (statefulset, []*v1.Pod).
func (ssc *StatefulSetController) syncStatefulSet(set *apps.StatefulSet, pods []*v1.Pod) error {
glog.V(2).Infof("Syncing StatefulSet %v/%v with %d pods", set.Namespace, set.Name, len(pods))
if err := ssc.control.UpdateStatefulSet(set, pods); err != nil {
glog.V(2).Infof("Error syncing StatefulSet %s/%s with %d pods : %s", set.Namespace, set.Name, err)
return err
}
glog.V(2).Infof("Succesfully synced StatefulSet %s/%s successful", set.Namespace, set.Name)
return nil
}