/
rpc.go
1252 lines (1098 loc) · 38.1 KB
/
rpc.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
package consul
import (
"context"
"crypto/tls"
"encoding/binary"
"errors"
"fmt"
"io"
"math"
"net"
"strings"
"sync/atomic"
"time"
"github.com/armon/go-metrics"
"github.com/armon/go-metrics/prometheus"
"github.com/hashicorp/go-connlimit"
"github.com/hashicorp/go-hclog"
"github.com/hashicorp/go-memdb"
"github.com/hashicorp/go-raftchunking"
"github.com/hashicorp/memberlist"
"github.com/hashicorp/raft"
"github.com/hashicorp/yamux"
"google.golang.org/grpc"
msgpackrpc "github.com/hashicorp/consul-net-rpc/net-rpc-msgpackrpc"
"github.com/hashicorp/consul/acl"
"github.com/hashicorp/consul/agent/consul/rate"
"github.com/hashicorp/consul/agent/consul/state"
"github.com/hashicorp/consul/agent/consul/wanfed"
"github.com/hashicorp/consul/agent/metadata"
"github.com/hashicorp/consul/agent/pool"
"github.com/hashicorp/consul/agent/rpc/middleware"
"github.com/hashicorp/consul/agent/structs"
"github.com/hashicorp/consul/lib"
"github.com/hashicorp/consul/logging"
)
var RPCCounters = []prometheus.CounterDefinition{
{
Name: []string{"rpc", "accept_conn"},
Help: "Increments when a server accepts an RPC connection.",
},
{
Name: []string{"rpc", "raft_handoff"},
Help: "Increments when a server accepts a Raft-related RPC connection.",
},
{
Name: []string{"rpc", "request_error"},
Help: "Increments when a server returns an error from an RPC request.",
},
{
Name: []string{"rpc", "request"},
Help: "Increments when a server receives a Consul-related RPC request.",
},
{
Name: []string{"rpc", "cross-dc"},
Help: "Increments when a server sends a (potentially blocking) cross datacenter RPC query.",
},
{
Name: []string{"rpc", "query"},
Help: "Increments when a server receives a read request, indicating the rate of new read queries.",
},
}
var RPCGauges = []prometheus.GaugeDefinition{
{
Name: []string{"rpc", "queries_blocking"},
Help: "Shows the current number of in-flight blocking queries the server is handling.",
},
}
var RPCSummaries = []prometheus.SummaryDefinition{
{
Name: []string{"rpc", "consistentRead"},
Help: "Measures the time spent confirming that a consistent read can be performed.",
},
}
const (
// Warn if the Raft command is larger than this.
// If it's over 1MB something is probably being abusive.
raftWarnSize = 1024 * 1024
// enqueueLimit caps how long we will wait to enqueue
// a new Raft command. Something is probably wrong if this
// value is ever reached. However, it prevents us from blocking
// the requesting goroutine forever.
enqueueLimit = 30 * time.Second
)
var ErrChunkingResubmit = errors.New("please resubmit call for rechunking")
// partitionUnsetter is used to describe requests values that can unset their
// EnterpriseMeta.Partition value.
type partitionUnsetter interface {
// UnsetPartition is used to strip a Partition value from the request before
// it is forwarded to a remote datacenter. By unsetting the value, the server
// that handles the request can decide which partition should be used (or do nothing).
// This ensures that servers that are Partition-enabled (pre-1.11, or non-Enterprise)
// don't inadvertently cause servers that are not Partition-enabled (<= 1.10 or non-Enterprise)
// to filter their responses by Partition. In other words, this ensures upgraded servers
// remain compatible with non-upgraded servers.
UnsetPartition()
}
func (s *Server) rpcLogger() hclog.Logger {
return s.loggers.Named(logging.RPC)
}
// listen is used to listen for incoming RPC connections
func (s *Server) listen(listener net.Listener) {
for {
// Accept a connection
conn, err := listener.Accept()
if err != nil {
if s.shutdown {
return
}
s.rpcLogger().Error("failed to accept RPC conn", "error", err)
continue
}
free, err := s.rpcConnLimiter.Accept(conn)
if err != nil {
s.rpcLogger().Error("rejecting RPC conn from because rpc_max_conns_per_client exceeded", "conn", logConn(conn))
conn.Close()
continue
}
// Wrap conn so it will be auto-freed from conn limiter when it closes.
conn = connlimit.Wrap(conn, free)
go s.handleConn(conn, false)
metrics.IncrCounter([]string{"rpc", "accept_conn"}, 1)
}
}
// logConn is a wrapper around memberlist's LogConn so that we format references
// to "from" addresses in a consistent way. This is just a shorter name.
func logConn(conn net.Conn) string {
return memberlist.LogConn(conn)
}
// handleConn is used to determine if this is a Raft or
// Consul type RPC connection and invoke the correct handler
func (s *Server) handleConn(conn net.Conn, isTLS bool) {
// Limit how long the client can hold the connection open before they send the
// magic byte (and authenticate when mTLS is enabled). If `isTLS == true` then
// this also enforces a timeout on how long it takes for the handshake to
// complete since tls.Conn.Read implicitly calls Handshake().
if s.config.RPCHandshakeTimeout > 0 {
conn.SetReadDeadline(time.Now().Add(s.config.RPCHandshakeTimeout))
}
if !isTLS && s.tlsConfigurator.MutualTLSCapable() {
// See if actually this is native TLS multiplexed onto the old
// "type-byte" system.
peekedConn, nativeTLS, err := pool.PeekForTLS(conn)
if err != nil {
if err != io.EOF {
s.rpcLogger().Error(
"failed to read first byte",
"conn", logConn(conn),
"error", err,
)
}
conn.Close()
return
}
if nativeTLS {
s.handleNativeTLS(peekedConn)
return
}
conn = peekedConn
}
// Read a single byte
buf := make([]byte, 1)
if _, err := conn.Read(buf); err != nil {
if err != io.EOF {
s.rpcLogger().Error("failed to read byte",
"conn", logConn(conn),
"error", err,
)
}
conn.Close()
return
}
typ := pool.RPCType(buf[0])
// Reset the deadline as we aren't sure what is expected next - it depends on
// the protocol.
if s.config.RPCHandshakeTimeout > 0 {
conn.SetReadDeadline(time.Time{})
}
// Enforce TLS if VerifyIncoming is set
if s.tlsConfigurator.VerifyIncomingRPC() && !isTLS && typ != pool.RPCTLS && typ != pool.RPCTLSInsecure {
s.rpcLogger().Warn("Non-TLS connection attempted with VerifyIncoming set", "conn", logConn(conn))
conn.Close()
return
}
// Switch on the byte
switch typ {
case pool.RPCConsul:
s.handleConsulConn(conn)
case pool.RPCRaft:
s.handleRaftRPC(conn)
case pool.RPCTLS:
// Don't allow malicious client to create TLS-in-TLS for ever.
if isTLS {
s.rpcLogger().Error("TLS connection attempting to establish inner TLS connection", "conn", logConn(conn))
conn.Close()
return
}
conn = tls.Server(conn, s.tlsConfigurator.IncomingRPCConfig())
s.handleConn(conn, true)
case pool.RPCMultiplexV2:
s.handleMultiplexV2(conn)
case pool.RPCSnapshot:
s.handleSnapshotConn(conn)
case pool.RPCTLSInsecure:
// Don't allow malicious client to create TLS-in-TLS for ever.
if isTLS {
s.rpcLogger().Error("TLS connection attempting to establish inner TLS connection", "conn", logConn(conn))
conn.Close()
return
}
conn = tls.Server(conn, s.tlsConfigurator.IncomingInsecureRPCConfig())
s.handleInsecureConn(conn)
case pool.RPCGRPC:
s.grpcHandler.Handle(conn)
default:
if !s.handleEnterpriseRPCConn(typ, conn, isTLS) {
s.rpcLogger().Error("unrecognized RPC byte",
"byte", typ,
"conn", logConn(conn),
)
conn.Close()
}
}
}
func (s *Server) handleNativeTLS(conn net.Conn) {
s.rpcLogger().Trace(
"detected actual TLS over RPC port",
"conn", logConn(conn),
)
tlscfg := s.tlsConfigurator.IncomingALPNRPCConfig(pool.RPCNextProtos)
tlsConn := tls.Server(conn, tlscfg)
// Force the handshake to conclude.
if err := tlsConn.Handshake(); err != nil {
s.rpcLogger().Error(
"TLS handshake failed",
"conn", logConn(conn),
"error", err,
)
conn.Close()
return
}
// Reset the deadline as we aren't sure what is expected next - it depends on
// the protocol.
if s.config.RPCHandshakeTimeout > 0 {
conn.SetReadDeadline(time.Time{})
}
var (
cs = tlsConn.ConnectionState()
sni = cs.ServerName
nextProto = cs.NegotiatedProtocol
transport = s.memberlistTransportWAN
)
s.rpcLogger().Trace(
"accepted nativeTLS RPC",
"sni", sni,
"protocol", nextProto,
"conn", logConn(conn),
)
switch nextProto {
case pool.ALPN_RPCConsul:
s.handleConsulConn(tlsConn)
case pool.ALPN_RPCRaft:
s.handleRaftRPC(tlsConn)
case pool.ALPN_RPCMultiplexV2:
s.handleMultiplexV2(tlsConn)
case pool.ALPN_RPCSnapshot:
s.handleSnapshotConn(tlsConn)
case pool.ALPN_RPCGRPC:
s.grpcHandler.Handle(tlsConn)
case pool.ALPN_WANGossipPacket:
if err := s.handleALPN_WANGossipPacketStream(tlsConn); err != nil && err != io.EOF {
s.rpcLogger().Error(
"failed to ingest RPC",
"sni", sni,
"protocol", nextProto,
"conn", logConn(conn),
"error", err,
)
}
case pool.ALPN_WANGossipStream:
// No need to defer the conn.Close() here, the Ingest methods do that.
if err := transport.IngestStream(tlsConn); err != nil {
s.rpcLogger().Error(
"failed to ingest RPC",
"sni", sni,
"protocol", nextProto,
"conn", logConn(conn),
"error", err,
)
}
default:
if !s.handleEnterpriseNativeTLSConn(nextProto, conn) {
s.rpcLogger().Error(
"discarding RPC for unknown negotiated protocol",
"failed to ingest RPC",
"protocol", nextProto,
"conn", logConn(conn),
)
conn.Close()
}
}
}
// handleMultiplexV2 is used to multiplex a single incoming connection
// using the Yamux multiplexer
func (s *Server) handleMultiplexV2(conn net.Conn) {
defer conn.Close()
conf := yamux.DefaultConfig()
// override the default because LogOutput conflicts with Logger
conf.LogOutput = nil
// TODO: should this be created once and cached?
conf.Logger = s.logger.StandardLogger(&hclog.StandardLoggerOptions{InferLevels: true})
server, _ := yamux.Server(conn, conf)
for {
sub, err := server.Accept()
if err != nil {
if err != io.EOF {
s.rpcLogger().Error("multiplex conn accept failed",
"conn", logConn(conn),
"error", err,
)
}
return
}
// In the beginning only RPC was supposed to be multiplexed
// with yamux. In order to add the ability to multiplex network
// area connections, this workaround was added.
// This code peeks the first byte and checks if it is
// RPCGossip, in which case this is handled by enterprise code.
// Otherwise this connection is handled like before by the RPC
// handler.
// This wouldn't work if a normal RPC could start with
// RPCGossip(6). In messagepack a 6 encodes a positive fixint:
// https://github.com/msgpack/msgpack/blob/master/spec.md.
// None of the RPCs we are doing starts with that, usually it is
// a string for datacenter.
peeked, first, err := pool.PeekFirstByte(sub)
if err != nil {
s.rpcLogger().Error("Problem peeking connection", "conn", logConn(sub), "err", err)
sub.Close()
return
}
sub = peeked
switch first {
case byte(pool.RPCGossip):
buf := make([]byte, 1)
sub.Read(buf)
go func() {
if !s.handleEnterpriseRPCConn(pool.RPCGossip, sub, false) {
s.rpcLogger().Error("unrecognized RPC byte",
"byte", pool.RPCGossip,
"conn", logConn(conn),
)
sub.Close()
}
}()
default:
go s.handleConsulConn(sub)
}
}
}
// handleConsulConn is used to service a single Consul RPC connection
func (s *Server) handleConsulConn(conn net.Conn) {
defer conn.Close()
rpcCodec := msgpackrpc.NewCodecFromHandle(true, true, conn, structs.MsgpackHandle)
for {
select {
case <-s.shutdownCh:
return
default:
}
if err := s.rpcServer.ServeRequest(rpcCodec); err != nil {
//EOF or closed are not considered as errors.
if err == io.EOF || strings.Contains(err.Error(), "closed") {
return
}
metrics.IncrCounter([]string{"rpc", "request_error"}, 1)
// When a rate-limiting error is returned, it's already logged, so skip logging.
if errors.Is(err, rate.ErrRetryLater) || errors.Is(err, rate.ErrRetryElsewhere) {
return
}
s.rpcLogger().Error("RPC error",
"conn", logConn(conn),
"error", err,
)
return
}
metrics.IncrCounter([]string{"rpc", "request"}, 1)
}
}
// handleInsecureConsulConn is used to service a single Consul INSECURERPC connection
func (s *Server) handleInsecureConn(conn net.Conn) {
defer conn.Close()
rpcCodec := msgpackrpc.NewCodecFromHandle(true, true, conn, structs.MsgpackHandle)
for {
select {
case <-s.shutdownCh:
return
default:
}
if err := s.insecureRPCServer.ServeRequest(rpcCodec); err != nil {
if err != io.EOF && !strings.Contains(err.Error(), "closed") {
s.rpcLogger().Error("INSECURERPC error",
"conn", logConn(conn),
"error", err,
)
metrics.IncrCounter([]string{"rpc", "request_error"}, 1)
}
return
}
metrics.IncrCounter([]string{"rpc", "request"}, 1)
}
}
// handleSnapshotConn is used to dispatch snapshot saves and restores, which
// stream so don't use the normal RPC mechanism.
func (s *Server) handleSnapshotConn(conn net.Conn) {
go func() {
defer conn.Close()
if err := s.handleSnapshotRequest(conn); err != nil {
s.rpcLogger().Error("Snapshot RPC error",
"conn", logConn(conn),
"error", err,
)
}
}()
}
func (s *Server) handleRaftRPC(conn net.Conn) {
if tlsConn, ok := conn.(*tls.Conn); ok {
err := s.tlsConfigurator.AuthorizeServerConn(s.config.Datacenter, tlsConn)
if err != nil {
s.rpcLogger().Warn(err.Error(), "from", conn.RemoteAddr(), "operation", "raft RPC")
conn.Close()
return
}
}
metrics.IncrCounter([]string{"rpc", "raft_handoff"}, 1)
s.raftLayer.Handoff(conn)
}
func (s *Server) handleALPN_WANGossipPacketStream(conn net.Conn) error {
defer conn.Close()
transport := s.memberlistTransportWAN
for {
select {
case <-s.shutdownCh:
return nil
default:
}
// Note: if we need to change this format to have additional header
// information we can just negotiate a different ALPN protocol instead
// of needing any sort of version field here.
prefixLen, err := readUint32(conn, wanfed.GossipPacketMaxIdleTime)
if err != nil {
return err
}
// Avoid a memory exhaustion DOS vector here by capping how large this
// packet can be to something reasonable.
if prefixLen > wanfed.GossipPacketMaxByteSize {
return fmt.Errorf("gossip packet size %d exceeds threshold of %d", prefixLen, wanfed.GossipPacketMaxByteSize)
}
lc := &limitedConn{
Conn: conn,
lr: io.LimitReader(conn, int64(prefixLen)),
}
if err := transport.IngestPacket(lc, conn.RemoteAddr(), time.Now(), false); err != nil {
return err
}
}
}
func readUint32(conn net.Conn, timeout time.Duration) (uint32, error) {
// Since requests are framed we can easily just set a deadline on
// reading that frame and then disable it for the rest of the body.
if err := conn.SetReadDeadline(time.Now().Add(timeout)); err != nil {
return 0, err
}
var v uint32
if err := binary.Read(conn, binary.BigEndian, &v); err != nil {
return 0, err
}
if err := conn.SetReadDeadline(time.Time{}); err != nil {
return 0, err
}
return v, nil
}
type limitedConn struct {
net.Conn
lr io.Reader
}
func (c *limitedConn) Read(b []byte) (n int, err error) {
return c.lr.Read(b)
}
func getWaitTime(rpcHoldTimeout time.Duration, retryCount int) time.Duration {
const backoffMultiplier = 2.0
rpcHoldTimeoutInMilli := int(rpcHoldTimeout.Milliseconds())
initialBackoffInMilli := rpcHoldTimeoutInMilli / structs.JitterFraction
if initialBackoffInMilli < 1 {
initialBackoffInMilli = 1
}
waitTimeInMilli := initialBackoffInMilli * int(math.Pow(backoffMultiplier, float64(retryCount-1)))
return time.Duration(waitTimeInMilli) * time.Millisecond
}
// canRetry returns true if the request and error indicate that a retry is safe.
func canRetry(info structs.RPCInfo, err error, start time.Time, config *Config, retryableMessages []error) bool {
if info != nil {
timedOut, timeoutError := info.HasTimedOut(start, config.RPCHoldTimeout, config.MaxQueryTime, config.DefaultQueryTime)
if timeoutError != nil {
return false
}
if timedOut {
return false
}
}
if info == nil && time.Since(start) > config.RPCHoldTimeout {
// When not RPCInfo, timeout is only RPCHoldTimeout
return false
}
// No leader errors are always safe to retry since no state could have
// been changed.
if structs.IsErrNoLeader(err) {
return true
}
for _, m := range retryableMessages {
if err != nil && strings.Contains(err.Error(), m.Error()) {
return true
}
}
// Reads are safe to retry for stream errors, such as if a server was
// being shut down.
return info != nil && info.IsRead() && lib.IsErrEOF(err)
}
// ForwardRPC is used to potentially forward an RPC request to a remote DC or
// to the local leader depending upon the request.
//
// Returns a bool of if forwarding was performed, as well as any error. If
// false is returned (with no error) it is assumed that the current server
// should handle the request.
func (s *Server) ForwardRPC(method string, info structs.RPCInfo, reply interface{}) (bool, error) {
forwardToDC := func(dc string) error {
return s.forwardDC(method, dc, info, reply)
}
forwardToLeader := func(leader *metadata.Server) error {
return s.connPool.RPC(s.config.Datacenter, leader.ShortName, leader.Addr,
method, info, reply)
}
return s.forwardRPC(info, forwardToDC, forwardToLeader)
}
// ForwardGRPC is used to potentially forward an RPC request to a remote DC or
// to the local leader depending upon the request.
//
// Returns a bool of if forwarding was performed, as well as any error. If
// false is returned (with no error) it is assumed that the current server
// should handle the request.
func (s *Server) ForwardGRPC(connPool GRPCClientConner, info structs.RPCInfo, f func(*grpc.ClientConn) error) (handled bool, err error) {
forwardToDC := func(dc string) error {
conn, err := connPool.ClientConn(dc)
if err != nil {
return err
}
return f(conn)
}
forwardToLeader := func(leader *metadata.Server) error {
conn, err := connPool.ClientConnLeader()
if err != nil {
return err
}
return f(conn)
}
return s.forwardRPC(info, forwardToDC, forwardToLeader)
}
// forwardRPC is used to potentially forward an RPC request to a remote DC or
// to the local leader depending upon the request.
//
// If info.RequestDatacenter() does not match the local datacenter, then the
// request will be forwarded to the DC using forwardToDC.
//
// Stale read requests will be handled locally if the current node has an
// initialized raft database, otherwise requests will be forwarded to the local
// leader using forwardToLeader.
//
// Returns a bool of if forwarding was performed, as well as any error. If
// false is returned (with no error) it is assumed that the current server
// should handle the request.
func (s *Server) forwardRPC(
info structs.RPCInfo,
forwardToDC func(dc string) error,
forwardToLeader func(leader *metadata.Server) error,
) (handled bool, err error) {
// Forward the request to the requested datacenter.
if handled, err := s.forwardRequestToOtherDatacenter(info, forwardToDC); handled || err != nil {
return handled, err
}
// See if we should let this server handle the read request without
// shipping the request to the leader.
if s.canServeReadRequest(info) {
return false, nil
}
return s.forwardRequestToLeader(info, forwardToLeader)
}
// forwardRequestToOtherDatacenter is an implementation detail of forwardRPC.
// See the comment for forwardRPC for more details.
func (s *Server) forwardRequestToOtherDatacenter(info structs.RPCInfo, forwardToDC func(dc string) error) (handled bool, err error) {
// Handle DC forwarding
dc := info.RequestDatacenter()
if dc == "" {
dc = s.config.Datacenter
}
if dc != s.config.Datacenter {
// Local tokens only work within the current datacenter. Check to see
// if we are attempting to forward one to a remote datacenter and strip
// it, falling back on the anonymous token on the other end.
if token := info.TokenSecret(); token != "" {
done, ident, err := s.ResolveIdentityFromToken(token)
if done {
if err != nil && !acl.IsErrNotFound(err) {
return false, err
}
if ident != nil && ident.IsLocal() {
// Strip it from the request.
info.SetTokenSecret("")
defer info.SetTokenSecret(token)
}
}
}
// In order to interoperate with servers that can interpret Partition, but
// may not handle it correctly (eg. 1.10 servers), we need to unset the value.
// Unsetting the Partition ensures that the server that handles the request
// uses its Partition, or an empty value (aka doing nothing).
// For requests that are not Partition-aware, this is a no-op.
if v, ok := info.(partitionUnsetter); ok {
v.UnsetPartition()
}
return true, forwardToDC(dc)
}
return false, nil
}
// canServeReadRequest determines if the request is a stale read request and
// the current node can safely process that request.
func (s *Server) canServeReadRequest(info structs.RPCInfo) bool {
// Check if we can allow a stale read, ensure our local DB is initialized
return info.IsRead() && info.AllowStaleRead() && !s.raft.LastContact().IsZero()
}
// forwardRequestToLeader is an implementation detail of forwardRPC.
// See the comment for forwardRPC for more details.
func (s *Server) forwardRequestToLeader(info structs.RPCInfo, forwardToLeader func(leader *metadata.Server) error) (handled bool, err error) {
firstCheck := time.Now()
retryCount := 0
previousJitter := time.Duration(0)
CHECK_LEADER:
retryCount++
// Fail fast if we are in the process of leaving
select {
case <-s.leaveCh:
return true, structs.ErrNoLeader
default:
}
// Find the leader
isLeader, leader, rpcErr := s.getLeader()
// Handle the case we are the leader
if isLeader {
return false, nil
}
// Handle the case of a known leader
if leader != nil {
rpcErr = forwardToLeader(leader)
if rpcErr == nil {
return true, nil
}
}
retryableMessages := []error{
// If we are chunking and it doesn't seem to have completed, try again.
ErrChunkingResubmit,
rate.ErrRetryLater,
}
if retry := canRetry(info, rpcErr, firstCheck, s.config, retryableMessages); retry {
// Gate the request until there is a leader
jitter := lib.RandomStaggerWithRange(previousJitter, getWaitTime(s.config.RPCHoldTimeout, retryCount))
previousJitter = jitter
select {
case <-time.After(jitter):
goto CHECK_LEADER
case <-s.leaveCh:
case <-s.shutdownCh:
}
}
// No leader found and hold time exceeded
return true, rpcErr
}
// getLeader returns if the current node is the leader, and if not then it
// returns the leader which is potentially nil if the cluster has not yet
// elected a leader. In the case of not having a leader elected yet
// then a NoClusterLeader error gets returned. In the case of Raft having
// a leader but out internal tracking failing to find the leader we
// return a LeaderNotTracked error. Therefore if the err is nil AND
// the bool is false then the Server will be non-nil
func (s *Server) getLeader() (bool, *metadata.Server, error) {
// Check if we are the leader
if s.IsLeader() {
return true, nil, nil
}
// Get the leader
leader := s.raft.Leader()
if leader == "" {
return false, nil, structs.ErrNoLeader
}
// Lookup the server
server := s.serverLookup.Server(leader)
// if server is nil this indicates that while we have a Raft leader
// something has caused that node to be considered unhealthy which
// cascades into its removal from the serverLookup struct. In this case
// we should not report no cluster leader but instead report a different
// error so as not to confuse our users as to the what the root cause of
// an issue might be.
if server == nil {
s.logger.Warn("Raft has a leader but other tracking of the node would indicate that the node is unhealthy or does not exist. The network may be misconfigured.", "leader", leader)
return false, nil, structs.ErrLeaderNotTracked
}
return false, server, nil
}
// forwardDC is used to forward an RPC call to a remote DC, or fail if no servers
func (s *Server) forwardDC(method, dc string, args interface{}, reply interface{}) error {
manager, server, ok := s.router.FindRoute(dc)
if !ok {
if s.router.HasDatacenter(dc) {
s.rpcLogger().Warn("RPC request to DC is currently failing as no server can be reached", "datacenter", dc)
return structs.ErrDCNotAvailable
}
s.rpcLogger().Warn("RPC request for DC is currently failing as no path was found",
"datacenter", dc,
"method", method,
)
return structs.ErrNoDCPath
}
metrics.IncrCounterWithLabels([]string{"rpc", "cross-dc"}, 1,
[]metrics.Label{{Name: "datacenter", Value: dc}})
if err := s.connPool.RPC(dc, server.ShortName, server.Addr, method, args, reply); err != nil {
manager.NotifyFailedServer(server)
s.rpcLogger().Error("RPC failed to server in DC",
"server", server.Addr,
"datacenter", dc,
"method", method,
"error", err,
)
return err
}
return nil
}
// keyringRPCs is used to forward an RPC request to a server in each dc. This
// will only error for RPC-related errors. Otherwise, application-level errors
// can be sent in the response objects.
func (s *Server) keyringRPCs(method string, args interface{}, dcs []string) (*structs.KeyringResponses, error) {
errorCh := make(chan error, len(dcs))
respCh := make(chan *structs.KeyringResponses, len(dcs))
for _, dc := range dcs {
go func(dc string) {
rr := &structs.KeyringResponses{}
if err := s.forwardDC(method, dc, args, &rr); err != nil {
errorCh <- err
return
}
respCh <- rr
}(dc)
}
responses := &structs.KeyringResponses{}
for i := 0; i < len(dcs); i++ {
select {
case err := <-errorCh:
return nil, err
case rr := <-respCh:
responses.Add(rr)
}
}
return responses, nil
}
type raftEncoder func(structs.MessageType, interface{}) ([]byte, error)
// leaderRaftApply is used by the leader to persist data to Raft for internal cluster management activities.
// This method MUST not be called from RPC endpoints, since it would result in duplicated RPC metrics.
func (s *Server) leaderRaftApply(method string, t structs.MessageType, msg interface{}) (interface{}, error) {
start := time.Now()
resp, err := s.raftApplyMsgpack(t, msg)
s.rpcRecorder.Record(method, middleware.RPCTypeInternal, start, &msg, err != nil)
return resp, err
}
// raftApplyMsgpack encodes the msg using msgpack and calls raft.Apply. See
// raftApplyWithEncoder.
// Deprecated: use raftApplyMsgpack
func (s *Server) raftApply(t structs.MessageType, msg interface{}) (interface{}, error) {
return s.raftApplyMsgpack(t, msg)
}
// raftApplyMsgpack encodes the msg using msgpack and calls raft.Apply. See
// raftApplyWithEncoder.
func (s *Server) raftApplyMsgpack(t structs.MessageType, msg interface{}) (interface{}, error) {
return s.raftApplyWithEncoder(t, msg, structs.Encode)
}
// raftApplyProtobuf encodes the msg using protobuf and calls raft.Apply. See
// raftApplyWithEncoder.
func (s *Server) raftApplyProtobuf(t structs.MessageType, msg interface{}) (interface{}, error) {
return s.raftApplyWithEncoder(t, msg, structs.EncodeProtoInterface)
}
// raftApplyWithEncoder encodes a message, and then calls raft.Apply with the
// encoded message. Returns the FSM response along with any errors. If the
// FSM.Apply response is an error it will be returned as the error return
// value with a nil response.
func (s *Server) raftApplyWithEncoder(
t structs.MessageType,
msg interface{},
encoder raftEncoder,
) (response interface{}, err error) {
if encoder == nil {
return nil, fmt.Errorf("Failed to encode request: nil encoder")
}
buf, err := encoder(t, msg)
if err != nil {
return nil, fmt.Errorf("Failed to encode request: %v", err)
}
// Warn if the command is very large
if n := len(buf); n > raftWarnSize {
s.rpcLogger().Warn("Attempting to apply large raft entry", "size_in_bytes", n)
}
var chunked bool
var future raft.ApplyFuture
switch {
case len(buf) <= raft.SuggestedMaxDataSize || t != structs.KVSRequestType:
future = s.raft.Apply(buf, enqueueLimit)
default:
chunked = true
future = raftchunking.ChunkingApply(buf, nil, enqueueLimit, s.raft.ApplyLog)
}
if err := future.Error(); err != nil {
return nil, err
}
resp := future.Response()
if chunked {
// In this case we didn't apply all chunks successfully, possibly due
// to a term change; resubmit
if resp == nil {
return nil, ErrChunkingResubmit
}
// We expect that this conversion should always work
chunkedSuccess, ok := resp.(raftchunking.ChunkingSuccess)
if !ok {
return nil, errors.New("unknown type of response back from chunking FSM")
}
resp = chunkedSuccess.Response
}
if err, ok := resp.(error); ok {
return nil, err
}
return resp, nil
}
// queryFn is used to perform a query operation. See Server.blockingQuery for
// the requirements of this function.
type queryFn func(memdb.WatchSet, *state.Store) error
// blockingQueryOptions are options used by Server.blockingQuery to modify the
// behaviour of the query operation, or to populate response metadata.
type blockingQueryOptions interface {
GetToken() string
GetMinQueryIndex() uint64
GetMaxQueryTime() (time.Duration, error)
GetRequireConsistent() bool
}
// blockingQueryResponseMeta is an interface used to populate the response struct
// with metadata about the query and the state of the server.
type blockingQueryResponseMeta interface {
SetLastContact(time.Duration)
SetKnownLeader(bool)
GetIndex() uint64
SetIndex(uint64)
SetResultsFilteredByACLs(bool)
}
// blockingQuery performs a blocking query if opts.GetMinQueryIndex is
// greater than 0, otherwise performs a non-blocking query. Blocking queries will
// block until responseMeta.Index is greater than opts.GetMinQueryIndex,
// or opts.GetMaxQueryTime is reached. Non-blocking queries return immediately
// after performing the query.
//