forked from adamlaska/moby
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdaemon.go
More file actions
1490 lines (1291 loc) · 47.5 KB
/
daemon.go
File metadata and controls
1490 lines (1291 loc) · 47.5 KB
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
// Package daemon exposes the functions that occur on the host server
// that the Docker daemon is running.
//
// In implementing the various functions of the daemon, there is often
// a method-specific struct for configuring the runtime behavior.
package daemon // import "github.com/docker/docker/daemon"
import (
"context"
"fmt"
"net"
"net/url"
"os"
"path"
"path/filepath"
"runtime"
"sync"
"time"
"github.com/containerd/containerd"
"github.com/containerd/containerd/defaults"
"github.com/containerd/containerd/pkg/dialer"
"github.com/containerd/containerd/pkg/userns"
"github.com/containerd/containerd/remotes/docker"
"github.com/docker/docker/api/types"
containertypes "github.com/docker/docker/api/types/container"
"github.com/docker/docker/api/types/swarm"
"github.com/docker/docker/builder"
"github.com/docker/docker/container"
"github.com/docker/docker/daemon/config"
"github.com/docker/docker/daemon/events"
"github.com/docker/docker/daemon/exec"
_ "github.com/docker/docker/daemon/graphdriver/register" // register graph drivers
"github.com/docker/docker/daemon/images"
"github.com/docker/docker/daemon/logger"
"github.com/docker/docker/daemon/network"
"github.com/docker/docker/daemon/stats"
dmetadata "github.com/docker/docker/distribution/metadata"
"github.com/docker/docker/dockerversion"
"github.com/docker/docker/errdefs"
"github.com/docker/docker/image"
"github.com/docker/docker/layer"
libcontainerdtypes "github.com/docker/docker/libcontainerd/types"
"github.com/docker/docker/libnetwork"
"github.com/docker/docker/libnetwork/cluster"
nwconfig "github.com/docker/docker/libnetwork/config"
"github.com/docker/docker/pkg/fileutils"
"github.com/docker/docker/pkg/idtools"
"github.com/docker/docker/pkg/plugingetter"
"github.com/docker/docker/pkg/sysinfo"
"github.com/docker/docker/pkg/system"
"github.com/docker/docker/pkg/truncindex"
"github.com/docker/docker/plugin"
pluginexec "github.com/docker/docker/plugin/executor/containerd"
refstore "github.com/docker/docker/reference"
"github.com/docker/docker/registry"
"github.com/docker/docker/runconfig"
volumesservice "github.com/docker/docker/volume/service"
"github.com/moby/buildkit/util/resolver"
resolverconfig "github.com/moby/buildkit/util/resolver/config"
"github.com/moby/locker"
"github.com/pkg/errors"
"github.com/sirupsen/logrus"
"go.etcd.io/bbolt"
"golang.org/x/sync/semaphore"
"golang.org/x/sync/singleflight"
"google.golang.org/grpc"
"google.golang.org/grpc/backoff"
"google.golang.org/grpc/credentials/insecure"
)
// ContainersNamespace is the name of the namespace used for users containers
const (
ContainersNamespace = "moby"
)
var (
errSystemNotSupported = errors.New("the Docker daemon is not supported on this platform")
)
// Daemon holds information about the Docker daemon.
type Daemon struct {
id string
repository string
containers container.Store
containersReplica container.ViewDB
execCommands *exec.Store
imageService *images.ImageService
idIndex *truncindex.TruncIndex
configStore *config.Config
statsCollector *stats.Collector
defaultLogConfig containertypes.LogConfig
registryService registry.Service
EventsService *events.Events
netController libnetwork.NetworkController
volumes *volumesservice.VolumesService
root string
sysInfoOnce sync.Once
sysInfo *sysinfo.SysInfo
shutdown bool
idMapping idtools.IdentityMapping
graphDriver string // TODO: move graphDriver field to an InfoService
PluginStore *plugin.Store // TODO: remove
pluginManager *plugin.Manager
linkIndex *linkIndex
containerdCli *containerd.Client
containerd libcontainerdtypes.Client
defaultIsolation containertypes.Isolation // Default isolation mode on Windows
clusterProvider cluster.Provider
cluster Cluster
genericResources []swarm.GenericResource
metricsPluginListener net.Listener
machineMemory uint64
seccompProfile []byte
seccompProfilePath string
usage singleflight.Group
pruneRunning int32
hosts map[string]bool // hosts stores the addresses the daemon is listening on
startupDone chan struct{}
attachmentStore network.AttachmentStore
attachableNetworkLock *locker.Locker
// This is used for Windows which doesn't currently support running on containerd
// It stores metadata for the content store (used for manifest caching)
// This needs to be closed on daemon exit
mdDB *bbolt.DB
}
// StoreHosts stores the addresses the daemon is listening on
func (daemon *Daemon) StoreHosts(hosts []string) {
if daemon.hosts == nil {
daemon.hosts = make(map[string]bool)
}
for _, h := range hosts {
daemon.hosts[h] = true
}
}
// HasExperimental returns whether the experimental features of the daemon are enabled or not
func (daemon *Daemon) HasExperimental() bool {
return daemon.configStore != nil && daemon.configStore.Experimental
}
// Features returns the features map from configStore
func (daemon *Daemon) Features() *map[string]bool {
return &daemon.configStore.Features
}
// RegistryHosts returns registry configuration in containerd resolvers format
func (daemon *Daemon) RegistryHosts() docker.RegistryHosts {
var (
registryKey = "docker.io"
mirrors = make([]string, len(daemon.configStore.Mirrors))
m = map[string]resolverconfig.RegistryConfig{}
)
// must trim "https://" or "http://" prefix
for i, v := range daemon.configStore.Mirrors {
if uri, err := url.Parse(v); err == nil {
v = uri.Host
}
mirrors[i] = v
}
// set mirrors for default registry
m[registryKey] = resolverconfig.RegistryConfig{Mirrors: mirrors}
for _, v := range daemon.configStore.InsecureRegistries {
u, err := url.Parse(v)
c := resolverconfig.RegistryConfig{}
if err == nil {
v = u.Host
t := true
if u.Scheme == "http" {
c.PlainHTTP = &t
} else {
c.Insecure = &t
}
}
m[v] = c
}
for k, v := range m {
v.TLSConfigDir = []string{registry.HostCertsDir(k)}
m[k] = v
}
certsDir := registry.CertsDir()
if fis, err := os.ReadDir(certsDir); err == nil {
for _, fi := range fis {
if _, ok := m[fi.Name()]; !ok {
m[fi.Name()] = resolverconfig.RegistryConfig{
TLSConfigDir: []string{filepath.Join(certsDir, fi.Name())},
}
}
}
}
return resolver.NewRegistryConfig(m)
}
func (daemon *Daemon) restore() error {
var mapLock sync.Mutex
containers := make(map[string]*container.Container)
logrus.Info("Loading containers: start.")
dir, err := os.ReadDir(daemon.repository)
if err != nil {
return err
}
// parallelLimit is the maximum number of parallel startup jobs that we
// allow (this is the limited used for all startup semaphores). The multipler
// (128) was chosen after some fairly significant benchmarking -- don't change
// it unless you've tested it significantly (this value is adjusted if
// RLIMIT_NOFILE is small to avoid EMFILE).
parallelLimit := adjustParallelLimit(len(dir), 128*runtime.NumCPU())
// Re-used for all parallel startup jobs.
var group sync.WaitGroup
sem := semaphore.NewWeighted(int64(parallelLimit))
for _, v := range dir {
group.Add(1)
go func(id string) {
defer group.Done()
_ = sem.Acquire(context.Background(), 1)
defer sem.Release(1)
log := logrus.WithField("container", id)
c, err := daemon.load(id)
if err != nil {
log.WithError(err).Error("failed to load container")
return
}
if !system.IsOSSupported(c.OS) {
log.Errorf("failed to load container: %s (%q)", system.ErrNotSupportedOperatingSystem, c.OS)
return
}
// Ignore the container if it does not support the current driver being used by the graph
if (c.Driver == "" && daemon.graphDriver == "aufs") || c.Driver == daemon.graphDriver {
rwlayer, err := daemon.imageService.GetLayerByID(c.ID)
if err != nil {
log.WithError(err).Error("failed to load container mount")
return
}
c.RWLayer = rwlayer
log.WithFields(logrus.Fields{
"running": c.IsRunning(),
"paused": c.IsPaused(),
}).Debug("loaded container")
mapLock.Lock()
containers[c.ID] = c
mapLock.Unlock()
} else {
log.Debugf("cannot load container because it was created with another storage driver")
}
}(v.Name())
}
group.Wait()
removeContainers := make(map[string]*container.Container)
restartContainers := make(map[*container.Container]chan struct{})
activeSandboxes := make(map[string]interface{})
for _, c := range containers {
group.Add(1)
go func(c *container.Container) {
defer group.Done()
_ = sem.Acquire(context.Background(), 1)
defer sem.Release(1)
log := logrus.WithField("container", c.ID)
if err := daemon.registerName(c); err != nil {
log.WithError(err).Errorf("failed to register container name: %s", c.Name)
mapLock.Lock()
delete(containers, c.ID)
mapLock.Unlock()
return
}
if err := daemon.Register(c); err != nil {
log.WithError(err).Error("failed to register container")
mapLock.Lock()
delete(containers, c.ID)
mapLock.Unlock()
return
}
}(c)
}
group.Wait()
for _, c := range containers {
group.Add(1)
go func(c *container.Container) {
defer group.Done()
_ = sem.Acquire(context.Background(), 1)
defer sem.Release(1)
log := logrus.WithField("container", c.ID)
daemon.backportMountSpec(c)
if err := daemon.checkpointAndSave(c); err != nil {
log.WithError(err).Error("error saving backported mountspec to disk")
}
daemon.setStateCounter(c)
logger := func(c *container.Container) *logrus.Entry {
return log.WithFields(logrus.Fields{
"running": c.IsRunning(),
"paused": c.IsPaused(),
"restarting": c.IsRestarting(),
})
}
logger(c).Debug("restoring container")
var (
err error
alive bool
ec uint32
exitedAt time.Time
process libcontainerdtypes.Process
)
alive, _, process, err = daemon.containerd.Restore(context.Background(), c.ID, c.InitializeStdio)
if err != nil && !errdefs.IsNotFound(err) {
logger(c).WithError(err).Error("failed to restore container with containerd")
return
}
logger(c).Debugf("alive: %v", alive)
if !alive {
// If process is not nil, cleanup dead container from containerd.
// If process is nil then the above `containerd.Restore` returned an errdefs.NotFoundError,
// and docker's view of the container state will be updated accorrdingly via SetStopped further down.
if process != nil {
logger(c).Debug("cleaning up dead container process")
ec, exitedAt, err = process.Delete(context.Background())
if err != nil && !errdefs.IsNotFound(err) {
logger(c).WithError(err).Error("failed to delete container from containerd")
return
}
}
} else if !daemon.configStore.LiveRestoreEnabled {
logger(c).Debug("shutting down container considered alive by containerd")
if err := daemon.shutdownContainer(c); err != nil && !errdefs.IsNotFound(err) {
log.WithError(err).Error("error shutting down container")
return
}
c.ResetRestartManager(false)
}
if c.IsRunning() || c.IsPaused() {
logger(c).Debug("syncing container on disk state with real state")
c.RestartManager().Cancel() // manually start containers because some need to wait for swarm networking
switch {
case c.IsPaused() && alive:
s, err := daemon.containerd.Status(context.Background(), c.ID)
if err != nil {
logger(c).WithError(err).Error("failed to get container status")
} else {
logger(c).WithField("state", s).Info("restored container paused")
switch s {
case containerd.Paused, containerd.Pausing:
// nothing to do
case containerd.Stopped:
alive = false
case containerd.Unknown:
log.Error("unknown status for paused container during restore")
default:
// running
c.Lock()
c.Paused = false
daemon.setStateCounter(c)
daemon.updateHealthMonitor(c)
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
log.WithError(err).Error("failed to update paused container state")
}
c.Unlock()
}
}
case !c.IsPaused() && alive:
logger(c).Debug("restoring healthcheck")
c.Lock()
daemon.updateHealthMonitor(c)
c.Unlock()
}
if !alive {
logger(c).Debug("setting stopped state")
c.Lock()
c.SetStopped(&container.ExitStatus{ExitCode: int(ec), ExitedAt: exitedAt})
daemon.Cleanup(c)
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
log.WithError(err).Error("failed to update stopped container state")
}
c.Unlock()
logger(c).Debug("set stopped state")
}
// we call Mount and then Unmount to get BaseFs of the container
if err := daemon.Mount(c); err != nil {
// The mount is unlikely to fail. However, in case mount fails
// the container should be allowed to restore here. Some functionalities
// (like docker exec -u user) might be missing but container is able to be
// stopped/restarted/removed.
// See #29365 for related information.
// The error is only logged here.
logger(c).WithError(err).Warn("failed to mount container to get BaseFs path")
} else {
if err := daemon.Unmount(c); err != nil {
logger(c).WithError(err).Warn("failed to umount container to get BaseFs path")
}
}
c.ResetRestartManager(false)
if !c.HostConfig.NetworkMode.IsContainer() && c.IsRunning() {
options, err := daemon.buildSandboxOptions(c)
if err != nil {
logger(c).WithError(err).Warn("failed to build sandbox option to restore container")
}
mapLock.Lock()
activeSandboxes[c.NetworkSettings.SandboxID] = options
mapLock.Unlock()
}
}
// get list of containers we need to restart
// Do not autostart containers which
// has endpoints in a swarm scope
// network yet since the cluster is
// not initialized yet. We will start
// it after the cluster is
// initialized.
if daemon.configStore.AutoRestart && c.ShouldRestart() && !c.NetworkSettings.HasSwarmEndpoint && c.HasBeenStartedBefore {
mapLock.Lock()
restartContainers[c] = make(chan struct{})
mapLock.Unlock()
} else if c.HostConfig != nil && c.HostConfig.AutoRemove {
mapLock.Lock()
removeContainers[c.ID] = c
mapLock.Unlock()
}
c.Lock()
if c.RemovalInProgress {
// We probably crashed in the middle of a removal, reset
// the flag.
//
// We DO NOT remove the container here as we do not
// know if the user had requested for either the
// associated volumes, network links or both to also
// be removed. So we put the container in the "dead"
// state and leave further processing up to them.
c.RemovalInProgress = false
c.Dead = true
if err := c.CheckpointTo(daemon.containersReplica); err != nil {
log.WithError(err).Error("failed to update RemovalInProgress container state")
} else {
log.Debugf("reset RemovalInProgress state for container")
}
}
c.Unlock()
logger(c).Debug("done restoring container")
}(c)
}
group.Wait()
daemon.netController, err = daemon.initNetworkController(daemon.configStore, activeSandboxes)
if err != nil {
return fmt.Errorf("Error initializing network controller: %v", err)
}
// Now that all the containers are registered, register the links
for _, c := range containers {
group.Add(1)
go func(c *container.Container) {
_ = sem.Acquire(context.Background(), 1)
if err := daemon.registerLinks(c, c.HostConfig); err != nil {
logrus.WithField("container", c.ID).WithError(err).Error("failed to register link for container")
}
sem.Release(1)
group.Done()
}(c)
}
group.Wait()
for c, notifier := range restartContainers {
group.Add(1)
go func(c *container.Container, chNotify chan struct{}) {
_ = sem.Acquire(context.Background(), 1)
log := logrus.WithField("container", c.ID)
log.Debug("starting container")
// ignore errors here as this is a best effort to wait for children to be
// running before we try to start the container
children := daemon.children(c)
timeout := time.NewTimer(5 * time.Second)
defer timeout.Stop()
for _, child := range children {
if notifier, exists := restartContainers[child]; exists {
select {
case <-notifier:
case <-timeout.C:
}
}
}
if err := daemon.containerStart(c, "", "", true); err != nil {
log.WithError(err).Error("failed to start container")
}
close(chNotify)
sem.Release(1)
group.Done()
}(c, notifier)
}
group.Wait()
for id := range removeContainers {
group.Add(1)
go func(cid string) {
_ = sem.Acquire(context.Background(), 1)
if err := daemon.ContainerRm(cid, &types.ContainerRmConfig{ForceRemove: true, RemoveVolume: true}); err != nil {
logrus.WithField("container", cid).WithError(err).Error("failed to remove container")
}
sem.Release(1)
group.Done()
}(id)
}
group.Wait()
// any containers that were started above would already have had this done,
// however we need to now prepare the mountpoints for the rest of the containers as well.
// This shouldn't cause any issue running on the containers that already had this run.
// This must be run after any containers with a restart policy so that containerized plugins
// can have a chance to be running before we try to initialize them.
for _, c := range containers {
// if the container has restart policy, do not
// prepare the mountpoints since it has been done on restarting.
// This is to speed up the daemon start when a restart container
// has a volume and the volume driver is not available.
if _, ok := restartContainers[c]; ok {
continue
} else if _, ok := removeContainers[c.ID]; ok {
// container is automatically removed, skip it.
continue
}
group.Add(1)
go func(c *container.Container) {
_ = sem.Acquire(context.Background(), 1)
if err := daemon.prepareMountPoints(c); err != nil {
logrus.WithField("container", c.ID).WithError(err).Error("failed to prepare mountpoints for container")
}
sem.Release(1)
group.Done()
}(c)
}
group.Wait()
logrus.Info("Loading containers: done.")
return nil
}
// RestartSwarmContainers restarts any autostart container which has a
// swarm endpoint.
func (daemon *Daemon) RestartSwarmContainers() {
ctx := context.Background()
// parallelLimit is the maximum number of parallel startup jobs that we
// allow (this is the limited used for all startup semaphores). The multipler
// (128) was chosen after some fairly significant benchmarking -- don't change
// it unless you've tested it significantly (this value is adjusted if
// RLIMIT_NOFILE is small to avoid EMFILE).
parallelLimit := adjustParallelLimit(len(daemon.List()), 128*runtime.NumCPU())
var group sync.WaitGroup
sem := semaphore.NewWeighted(int64(parallelLimit))
for _, c := range daemon.List() {
if !c.IsRunning() && !c.IsPaused() {
// Autostart all the containers which has a
// swarm endpoint now that the cluster is
// initialized.
if daemon.configStore.AutoRestart && c.ShouldRestart() && c.NetworkSettings.HasSwarmEndpoint && c.HasBeenStartedBefore {
group.Add(1)
go func(c *container.Container) {
if err := sem.Acquire(ctx, 1); err != nil {
// ctx is done.
group.Done()
return
}
if err := daemon.containerStart(c, "", "", true); err != nil {
logrus.WithField("container", c.ID).WithError(err).Error("failed to start swarm container")
}
sem.Release(1)
group.Done()
}(c)
}
}
}
group.Wait()
}
func (daemon *Daemon) children(c *container.Container) map[string]*container.Container {
return daemon.linkIndex.children(c)
}
// parents returns the names of the parent containers of the container
// with the given name.
func (daemon *Daemon) parents(c *container.Container) map[string]*container.Container {
return daemon.linkIndex.parents(c)
}
func (daemon *Daemon) registerLink(parent, child *container.Container, alias string) error {
fullName := path.Join(parent.Name, alias)
if err := daemon.containersReplica.ReserveName(fullName, child.ID); err != nil {
if err == container.ErrNameReserved {
logrus.Warnf("error registering link for %s, to %s, as alias %s, ignoring: %v", parent.ID, child.ID, alias, err)
return nil
}
return err
}
daemon.linkIndex.link(parent, child, fullName)
return nil
}
// DaemonJoinsCluster informs the daemon has joined the cluster and provides
// the handler to query the cluster component
func (daemon *Daemon) DaemonJoinsCluster(clusterProvider cluster.Provider) {
daemon.setClusterProvider(clusterProvider)
}
// DaemonLeavesCluster informs the daemon has left the cluster
func (daemon *Daemon) DaemonLeavesCluster() {
// Daemon is in charge of removing the attachable networks with
// connected containers when the node leaves the swarm
daemon.clearAttachableNetworks()
// We no longer need the cluster provider, stop it now so that
// the network agent will stop listening to cluster events.
daemon.setClusterProvider(nil)
// Wait for the networking cluster agent to stop
daemon.netController.AgentStopWait()
// Daemon is in charge of removing the ingress network when the
// node leaves the swarm. Wait for job to be done or timeout.
// This is called also on graceful daemon shutdown. We need to
// wait, because the ingress release has to happen before the
// network controller is stopped.
if done, err := daemon.ReleaseIngress(); err == nil {
timeout := time.NewTimer(5 * time.Second)
defer timeout.Stop()
select {
case <-done:
case <-timeout.C:
logrus.Warn("timeout while waiting for ingress network removal")
}
} else {
logrus.Warnf("failed to initiate ingress network removal: %v", err)
}
daemon.attachmentStore.ClearAttachments()
}
// setClusterProvider sets a component for querying the current cluster state.
func (daemon *Daemon) setClusterProvider(clusterProvider cluster.Provider) {
daemon.clusterProvider = clusterProvider
daemon.netController.SetClusterProvider(clusterProvider)
daemon.attachableNetworkLock = locker.New()
}
// IsSwarmCompatible verifies if the current daemon
// configuration is compatible with the swarm mode
func (daemon *Daemon) IsSwarmCompatible() error {
if daemon.configStore == nil {
return nil
}
return daemon.configStore.IsSwarmCompatible()
}
// NewDaemon sets up everything for the daemon to be able to service
// requests from the webserver.
func NewDaemon(ctx context.Context, config *config.Config, pluginStore *plugin.Store) (daemon *Daemon, err error) {
setDefaultMtu(config)
registryService, err := registry.NewService(config.ServiceOptions)
if err != nil {
return nil, err
}
// Ensure that we have a correct root key limit for launching containers.
if err := modifyRootKeyLimit(); err != nil {
logrus.Warnf("unable to modify root key limit, number of containers could be limited by this quota: %v", err)
}
// Ensure we have compatible and valid configuration options
if err := verifyDaemonSettings(config); err != nil {
return nil, err
}
// Do we have a disabled network?
config.DisableBridge = isBridgeNetworkDisabled(config)
// Setup the resolv.conf
setupResolvConf(config)
// Verify the platform is supported as a daemon
if !platformSupported {
return nil, errSystemNotSupported
}
// Validate platform-specific requirements
if err := checkSystem(); err != nil {
return nil, err
}
idMapping, err := setupRemappedRoot(config)
if err != nil {
return nil, err
}
rootIDs := idMapping.RootPair()
if err := setupDaemonProcess(config); err != nil {
return nil, err
}
// set up the tmpDir to use a canonical path
tmp, err := prepareTempDir(config.Root)
if err != nil {
return nil, fmt.Errorf("Unable to get the TempDir under %s: %s", config.Root, err)
}
realTmp, err := fileutils.ReadSymlinkedDirectory(tmp)
if err != nil {
return nil, fmt.Errorf("Unable to get the full path to the TempDir (%s): %s", tmp, err)
}
if isWindows {
if _, err := os.Stat(realTmp); err != nil && os.IsNotExist(err) {
if err := system.MkdirAll(realTmp, 0700); err != nil {
return nil, fmt.Errorf("Unable to create the TempDir (%s): %s", realTmp, err)
}
}
os.Setenv("TEMP", realTmp)
os.Setenv("TMP", realTmp)
} else {
os.Setenv("TMPDIR", realTmp)
}
d := &Daemon{
configStore: config,
PluginStore: pluginStore,
startupDone: make(chan struct{}),
}
// Ensure the daemon is properly shutdown if there is a failure during
// initialization
defer func() {
if err != nil {
if err := d.Shutdown(); err != nil {
logrus.Error(err)
}
}
}()
if err := d.setGenericResources(config); err != nil {
return nil, err
}
// set up SIGUSR1 handler on Unix-like systems, or a Win32 global event
// on Windows to dump Go routine stacks
stackDumpDir := config.Root
if execRoot := config.GetExecRoot(); execRoot != "" {
stackDumpDir = execRoot
}
d.setupDumpStackTrap(stackDumpDir)
if err := d.setupSeccompProfile(); err != nil {
return nil, err
}
// Set the default isolation mode (only applicable on Windows)
if err := d.setDefaultIsolation(); err != nil {
return nil, fmt.Errorf("error setting default isolation mode: %v", err)
}
if err := configureMaxThreads(config); err != nil {
logrus.Warnf("Failed to configure golang's threads limit: %v", err)
}
// ensureDefaultAppArmorProfile does nothing if apparmor is disabled
if err := ensureDefaultAppArmorProfile(); err != nil {
logrus.Errorf(err.Error())
}
daemonRepo := filepath.Join(config.Root, "containers")
if err := idtools.MkdirAllAndChown(daemonRepo, 0710, idtools.Identity{
UID: idtools.CurrentIdentity().UID,
GID: rootIDs.GID,
}); err != nil {
return nil, err
}
// Create the directory where we'll store the runtime scripts (i.e. in
// order to support runtimeArgs)
daemonRuntimes := filepath.Join(config.Root, "runtimes")
if err := system.MkdirAll(daemonRuntimes, 0700); err != nil {
return nil, err
}
if err := d.loadRuntimes(); err != nil {
return nil, err
}
if isWindows {
if err := system.MkdirAll(filepath.Join(config.Root, "credentialspecs"), 0); err != nil {
return nil, err
}
}
if isWindows {
// On Windows we don't support the environment variable, or a user supplied graphdriver
d.graphDriver = "windowsfilter"
} else {
// Unix platforms however run a single graphdriver for all containers, and it can
// be set through an environment variable, a daemon start parameter, or chosen through
// initialization of the layerstore through driver priority order for example.
if drv := os.Getenv("DOCKER_DRIVER"); drv != "" {
d.graphDriver = drv
logrus.Infof("Setting the storage driver from the $DOCKER_DRIVER environment variable (%s)", drv)
} else {
d.graphDriver = config.GraphDriver // May still be empty. Layerstore init determines instead.
}
}
d.registryService = registryService
logger.RegisterPluginGetter(d.PluginStore)
metricsSockPath, err := d.listenMetricsSock()
if err != nil {
return nil, err
}
registerMetricsPluginCallback(d.PluginStore, metricsSockPath)
backoffConfig := backoff.DefaultConfig
backoffConfig.MaxDelay = 3 * time.Second
connParams := grpc.ConnectParams{
Backoff: backoffConfig,
}
gopts := []grpc.DialOption{
// WithBlock makes sure that the following containerd request
// is reliable.
//
// NOTE: In one edge case with high load pressure, kernel kills
// dockerd, containerd and containerd-shims caused by OOM.
// When both dockerd and containerd restart, but containerd
// will take time to recover all the existing containers. Before
// containerd serving, dockerd will failed with gRPC error.
// That bad thing is that restore action will still ignore the
// any non-NotFound errors and returns running state for
// already stopped container. It is unexpected behavior. And
// we need to restart dockerd to make sure that anything is OK.
//
// It is painful. Add WithBlock can prevent the edge case. And
// n common case, the containerd will be serving in shortly.
// It is not harm to add WithBlock for containerd connection.
grpc.WithBlock(),
grpc.WithTransportCredentials(insecure.NewCredentials()),
grpc.WithConnectParams(connParams),
grpc.WithContextDialer(dialer.ContextDialer),
// TODO(stevvooe): We may need to allow configuration of this on the client.
grpc.WithDefaultCallOptions(grpc.MaxCallRecvMsgSize(defaults.DefaultMaxRecvMsgSize)),
grpc.WithDefaultCallOptions(grpc.MaxCallSendMsgSize(defaults.DefaultMaxSendMsgSize)),
}
if config.ContainerdAddr != "" {
d.containerdCli, err = containerd.New(config.ContainerdAddr, containerd.WithDefaultNamespace(config.ContainerdNamespace), containerd.WithDialOpts(gopts), containerd.WithTimeout(60*time.Second))
if err != nil {
return nil, errors.Wrapf(err, "failed to dial %q", config.ContainerdAddr)
}
}
createPluginExec := func(m *plugin.Manager) (plugin.Executor, error) {
var pluginCli *containerd.Client
if config.ContainerdAddr != "" {
pluginCli, err = containerd.New(config.ContainerdAddr, containerd.WithDefaultNamespace(config.ContainerdPluginNamespace), containerd.WithDialOpts(gopts), containerd.WithTimeout(60*time.Second))
if err != nil {
return nil, errors.Wrapf(err, "failed to dial %q", config.ContainerdAddr)
}
}
var rt types.Runtime
if runtime.GOOS != "windows" {
rtPtr, err := d.getRuntime(config.GetDefaultRuntimeName())
if err != nil {
return nil, err
}
rt = *rtPtr
}
return pluginexec.New(ctx, getPluginExecRoot(config.Root), pluginCli, config.ContainerdPluginNamespace, m, rt)
}
// Plugin system initialization should happen before restore. Do not change order.
d.pluginManager, err = plugin.NewManager(plugin.ManagerConfig{
Root: filepath.Join(config.Root, "plugins"),
ExecRoot: getPluginExecRoot(config.Root),
Store: d.PluginStore,
CreateExecutor: createPluginExec,
RegistryService: registryService,
LiveRestoreEnabled: config.LiveRestoreEnabled,
LogPluginEvent: d.LogPluginEvent, // todo: make private
AuthzMiddleware: config.AuthzMiddleware,
})
if err != nil {
return nil, errors.Wrap(err, "couldn't create plugin manager")
}
if err := d.setupDefaultLogConfig(); err != nil {
return nil, err
}
layerStore, err := layer.NewStoreFromOptions(layer.StoreOptions{
Root: config.Root,
MetadataStorePathTemplate: filepath.Join(config.Root, "image", "%s", "layerdb"),
GraphDriver: d.graphDriver,
GraphDriverOptions: config.GraphOptions,
IDMapping: idMapping,
PluginGetter: d.PluginStore,
ExperimentalEnabled: config.Experimental,
})
if err != nil {
return nil, err
}
// As layerstore initialization may set the driver
d.graphDriver = layerStore.DriverName()
// Configure and validate the kernels security support. Note this is a Linux/FreeBSD
// operation only, so it is safe to pass *just* the runtime OS graphdriver.
if err := configureKernelSecuritySupport(config, d.graphDriver); err != nil {
return nil, err
}
imageRoot := filepath.Join(config.Root, "image", d.graphDriver)
ifs, err := image.NewFSStoreBackend(filepath.Join(imageRoot, "imagedb"))
if err != nil {
return nil, err
}
imageStore, err := image.NewImageStore(ifs, layerStore)
if err != nil {
return nil, err
}
d.volumes, err = volumesservice.NewVolumeService(config.Root, d.PluginStore, rootIDs, d)
if err != nil {
return nil, err
}
trustKey, err := loadOrCreateTrustKey(config.TrustKeyPath)
if err != nil {
return nil, err
}
trustDir := filepath.Join(config.Root, "trust")
if err := system.MkdirAll(trustDir, 0700); err != nil {
return nil, err
}
// We have a single tag/reference store for the daemon globally. However, it's
// stored under the graphdriver. On host platforms which only support a single
// container OS, but multiple selectable graphdrivers, this means depending on which
// graphdriver is chosen, the global reference store is under there. For
// platforms which support multiple container operating systems, this is slightly
// more problematic as where does the global ref store get located? Fortunately,
// for Windows, which is currently the only daemon supporting multiple container
// operating systems, the list of graphdrivers available isn't user configurable.