-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmigration.c
1896 lines (1614 loc) · 57.1 KB
/
migration.c
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
/*
* QEMU live migration
*
* Copyright IBM, Corp. 2008
*
* Authors:
* Anthony Liguori <[email protected]>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qemu/cutils.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "migration/migration.h"
#include "migration/qemu-file.h"
#include "sysemu/sysemu.h"
#include "block/block.h"
#include "qapi/qmp/qerror.h"
#include "qapi/util.h"
#include "qemu/sockets.h"
#include "qemu/rcu.h"
#include "migration/block.h"
#include "migration/postcopy-ram.h"
#include "qemu/thread.h"
#include "qmp-commands.h"
#include "trace.h"
#include "qapi-event.h"
#include "qom/cpu.h"
#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "io/channel-buffer.h"
#include "io/channel-tls.h"
#define MAX_THROTTLE (32 << 20) /* Migration transfer speed throttling */
/* Amount of time to allocate to each "chunk" of bandwidth-throttled
* data. */
#define BUFFER_DELAY 100
#define XFER_LIMIT_RATIO (1000 / BUFFER_DELAY)
/* Default compression thread count */
#define DEFAULT_MIGRATE_COMPRESS_THREAD_COUNT 8
/* Default decompression thread count, usually decompression is at
* least 4 times as fast as compression.*/
#define DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT 2
/*0: means nocompress, 1: best speed, ... 9: best compress ratio */
#define DEFAULT_MIGRATE_COMPRESS_LEVEL 1
/* Define default autoconverge cpu throttle migration parameters */
#define DEFAULT_MIGRATE_CPU_THROTTLE_INITIAL 20
#define DEFAULT_MIGRATE_CPU_THROTTLE_INCREMENT 10
/* Migration XBZRLE default cache size */
#define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024)
static NotifierList migration_state_notifiers =
NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);
static bool deferred_incoming;
/*
* Current state of incoming postcopy; note this is not part of
* MigrationIncomingState since it's state is used during cleanup
* at the end as MIS is being freed.
*/
static PostcopyState incoming_postcopy_state;
/* When we add fault tolerance, we could have several
migrations at once. For now we don't need to add
dynamic creation of migration */
/* For outgoing */
MigrationState *migrate_get_current(void)
{
static bool once;
static MigrationState current_migration = {
.state = MIGRATION_STATUS_NONE,
.bandwidth_limit = MAX_THROTTLE,
.xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
.mbps = -1,
.parameters = {
.compress_level = DEFAULT_MIGRATE_COMPRESS_LEVEL,
.compress_threads = DEFAULT_MIGRATE_COMPRESS_THREAD_COUNT,
.decompress_threads = DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT,
.cpu_throttle_initial = DEFAULT_MIGRATE_CPU_THROTTLE_INITIAL,
.cpu_throttle_increment = DEFAULT_MIGRATE_CPU_THROTTLE_INCREMENT,
},
};
if (!once) {
qemu_mutex_init(¤t_migration.src_page_req_mutex);
once = true;
}
return ¤t_migration;
}
/* For incoming */
static MigrationIncomingState *mis_current;
MigrationIncomingState *migration_incoming_get_current(void)
{
return mis_current;
}
MigrationIncomingState *migration_incoming_state_new(QEMUFile* f)
{
mis_current = g_new0(MigrationIncomingState, 1);
mis_current->from_src_file = f;
mis_current->state = MIGRATION_STATUS_NONE;
QLIST_INIT(&mis_current->loadvm_handlers);
qemu_mutex_init(&mis_current->rp_mutex);
qemu_event_init(&mis_current->main_thread_load_event, false);
return mis_current;
}
void migration_incoming_state_destroy(void)
{
qemu_event_destroy(&mis_current->main_thread_load_event);
loadvm_free_handlers(mis_current);
g_free(mis_current);
mis_current = NULL;
}
typedef struct {
bool optional;
uint32_t size;
uint8_t runstate[100];
RunState state;
bool received;
} GlobalState;
static GlobalState global_state;
int global_state_store(void)
{
if (!runstate_store((char *)global_state.runstate,
sizeof(global_state.runstate))) {
error_report("runstate name too big: %s", global_state.runstate);
trace_migrate_state_too_big();
return -EINVAL;
}
return 0;
}
void global_state_store_running(void)
{
const char *state = RunState_lookup[RUN_STATE_RUNNING];
strncpy((char *)global_state.runstate,
state, sizeof(global_state.runstate));
}
static bool global_state_received(void)
{
return global_state.received;
}
static RunState global_state_get_runstate(void)
{
return global_state.state;
}
void global_state_set_optional(void)
{
global_state.optional = true;
}
static bool global_state_needed(void *opaque)
{
GlobalState *s = opaque;
char *runstate = (char *)s->runstate;
/* If it is not optional, it is mandatory */
if (s->optional == false) {
return true;
}
/* If state is running or paused, it is not needed */
if (strcmp(runstate, "running") == 0 ||
strcmp(runstate, "paused") == 0) {
return false;
}
/* for any other state it is needed */
return true;
}
static int global_state_post_load(void *opaque, int version_id)
{
GlobalState *s = opaque;
Error *local_err = NULL;
int r;
char *runstate = (char *)s->runstate;
s->received = true;
trace_migrate_global_state_post_load(runstate);
r = qapi_enum_parse(RunState_lookup, runstate, RUN_STATE__MAX,
-1, &local_err);
if (r == -1) {
if (local_err) {
error_report_err(local_err);
}
return -EINVAL;
}
s->state = r;
return 0;
}
static void global_state_pre_save(void *opaque)
{
GlobalState *s = opaque;
trace_migrate_global_state_pre_save((char *)s->runstate);
s->size = strlen((char *)s->runstate) + 1;
}
static const VMStateDescription vmstate_globalstate = {
.name = "globalstate",
.version_id = 1,
.minimum_version_id = 1,
.post_load = global_state_post_load,
.pre_save = global_state_pre_save,
.needed = global_state_needed,
.fields = (VMStateField[]) {
VMSTATE_UINT32(size, GlobalState),
VMSTATE_BUFFER(runstate, GlobalState),
VMSTATE_END_OF_LIST()
},
};
void register_global_state(void)
{
/* We would use it independently that we receive it */
strcpy((char *)&global_state.runstate, "");
global_state.received = false;
vmstate_register(NULL, 0, &vmstate_globalstate, &global_state);
}
static void migrate_generate_event(int new_state)
{
if (migrate_use_events()) {
qapi_event_send_migration(new_state, &error_abort);
}
}
/*
* Called on -incoming with a defer: uri.
* The migration can be started later after any parameters have been
* changed.
*/
static void deferred_incoming_migration(Error **errp)
{
if (deferred_incoming) {
error_setg(errp, "Incoming migration already deferred");
}
deferred_incoming = true;
}
/* Request a range of pages from the source VM at the given
* start address.
* rbname: Name of the RAMBlock to request the page in, if NULL it's the same
* as the last request (a name must have been given previously)
* Start: Address offset within the RB
* Len: Length in bytes required - must be a multiple of pagesize
*/
void migrate_send_rp_req_pages(MigrationIncomingState *mis, const char *rbname,
ram_addr_t start, size_t len)
{
uint8_t bufc[12 + 1 + 255]; /* start (8), len (4), rbname up to 256 */
size_t msglen = 12; /* start + len */
*(uint64_t *)bufc = cpu_to_be64((uint64_t)start);
*(uint32_t *)(bufc + 8) = cpu_to_be32((uint32_t)len);
if (rbname) {
int rbname_len = strlen(rbname);
assert(rbname_len < 256);
bufc[msglen++] = rbname_len;
memcpy(bufc + msglen, rbname, rbname_len);
msglen += rbname_len;
migrate_send_rp_message(mis, MIG_RP_MSG_REQ_PAGES_ID, msglen, bufc);
} else {
migrate_send_rp_message(mis, MIG_RP_MSG_REQ_PAGES, msglen, bufc);
}
}
void qemu_start_incoming_migration(const char *uri, Error **errp)
{
const char *p;
qapi_event_send_migration(MIGRATION_STATUS_SETUP, &error_abort);
if (!strcmp(uri, "defer")) {
deferred_incoming_migration(errp);
} else if (strstart(uri, "tcp:", &p)) {
tcp_start_incoming_migration(p, errp);
#ifdef CONFIG_RDMA
} else if (strstart(uri, "rdma:", &p)) {
rdma_start_incoming_migration(p, errp);
#endif
} else if (strstart(uri, "exec:", &p)) {
exec_start_incoming_migration(p, errp);
} else if (strstart(uri, "unix:", &p)) {
unix_start_incoming_migration(p, errp);
} else if (strstart(uri, "fd:", &p)) {
fd_start_incoming_migration(p, errp);
} else {
error_setg(errp, "unknown migration protocol: %s", uri);
}
}
static void process_incoming_migration_bh(void *opaque)
{
Error *local_err = NULL;
MigrationIncomingState *mis = opaque;
/* Make sure all file formats flush their mutable metadata */
bdrv_invalidate_cache_all(&local_err);
if (local_err) {
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_FAILED);
error_report_err(local_err);
migrate_decompress_threads_join();
exit(EXIT_FAILURE);
}
/*
* This must happen after all error conditions are dealt with and
* we're sure the VM is going to be running on this host.
*/
qemu_announce_self();
/* If global state section was not received or we are in running
state, we need to obey autostart. Any other state is set with
runstate_set. */
if (!global_state_received() ||
global_state_get_runstate() == RUN_STATE_RUNNING) {
if (autostart) {
vm_start();
} else {
runstate_set(RUN_STATE_PAUSED);
}
} else {
runstate_set(global_state_get_runstate());
}
migrate_decompress_threads_join();
/*
* This must happen after any state changes since as soon as an external
* observer sees this event they might start to prod at the VM assuming
* it's ready to use.
*/
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_COMPLETED);
qemu_bh_delete(mis->bh);
migration_incoming_state_destroy();
}
static void process_incoming_migration_co(void *opaque)
{
QEMUFile *f = opaque;
MigrationIncomingState *mis;
PostcopyState ps;
int ret;
mis = migration_incoming_state_new(f);
postcopy_state_set(POSTCOPY_INCOMING_NONE);
migrate_set_state(&mis->state, MIGRATION_STATUS_NONE,
MIGRATION_STATUS_ACTIVE);
ret = qemu_loadvm_state(f);
ps = postcopy_state_get();
trace_process_incoming_migration_co_end(ret, ps);
if (ps != POSTCOPY_INCOMING_NONE) {
if (ps == POSTCOPY_INCOMING_ADVISE) {
/*
* Where a migration had postcopy enabled (and thus went to advise)
* but managed to complete within the precopy period, we can use
* the normal exit.
*/
postcopy_ram_incoming_cleanup(mis);
} else if (ret >= 0) {
/*
* Postcopy was started, cleanup should happen at the end of the
* postcopy thread.
*/
trace_process_incoming_migration_co_postcopy_end_main();
return;
}
/* Else if something went wrong then just fall out of the normal exit */
}
qemu_fclose(f);
free_xbzrle_decoded_buf();
if (ret < 0) {
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_FAILED);
error_report("load of migration failed: %s", strerror(-ret));
migrate_decompress_threads_join();
exit(EXIT_FAILURE);
}
mis->bh = qemu_bh_new(process_incoming_migration_bh, mis);
qemu_bh_schedule(mis->bh);
}
void migration_fd_process_incoming(QEMUFile *f)
{
Coroutine *co = qemu_coroutine_create(process_incoming_migration_co, f);
migrate_decompress_threads_create();
qemu_file_set_blocking(f, false);
qemu_coroutine_enter(co);
}
void migration_channel_process_incoming(MigrationState *s,
QIOChannel *ioc)
{
trace_migration_set_incoming_channel(
ioc, object_get_typename(OBJECT(ioc)));
if (s->parameters.tls_creds &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
Error *local_err = NULL;
migration_tls_channel_process_incoming(s, ioc, &local_err);
if (local_err) {
error_report_err(local_err);
}
} else {
QEMUFile *f = qemu_fopen_channel_input(ioc);
migration_fd_process_incoming(f);
}
}
void migration_channel_connect(MigrationState *s,
QIOChannel *ioc,
const char *hostname)
{
trace_migration_set_outgoing_channel(
ioc, object_get_typename(OBJECT(ioc)), hostname);
if (s->parameters.tls_creds &&
!object_dynamic_cast(OBJECT(ioc),
TYPE_QIO_CHANNEL_TLS)) {
Error *local_err = NULL;
migration_tls_channel_connect(s, ioc, hostname, &local_err);
if (local_err) {
migrate_fd_error(s, local_err);
error_free(local_err);
}
} else {
QEMUFile *f = qemu_fopen_channel_output(ioc);
s->to_dst_file = f;
migrate_fd_connect(s);
}
}
/*
* Send a message on the return channel back to the source
* of the migration.
*/
void migrate_send_rp_message(MigrationIncomingState *mis,
enum mig_rp_message_type message_type,
uint16_t len, void *data)
{
trace_migrate_send_rp_message((int)message_type, len);
qemu_mutex_lock(&mis->rp_mutex);
qemu_put_be16(mis->to_src_file, (unsigned int)message_type);
qemu_put_be16(mis->to_src_file, len);
qemu_put_buffer(mis->to_src_file, data, len);
qemu_fflush(mis->to_src_file);
qemu_mutex_unlock(&mis->rp_mutex);
}
/*
* Send a 'SHUT' message on the return channel with the given value
* to indicate that we've finished with the RP. Non-0 value indicates
* error.
*/
void migrate_send_rp_shut(MigrationIncomingState *mis,
uint32_t value)
{
uint32_t buf;
buf = cpu_to_be32(value);
migrate_send_rp_message(mis, MIG_RP_MSG_SHUT, sizeof(buf), &buf);
}
/*
* Send a 'PONG' message on the return channel with the given value
* (normally in response to a 'PING')
*/
void migrate_send_rp_pong(MigrationIncomingState *mis,
uint32_t value)
{
uint32_t buf;
buf = cpu_to_be32(value);
migrate_send_rp_message(mis, MIG_RP_MSG_PONG, sizeof(buf), &buf);
}
/* amount of nanoseconds we are willing to wait for migration to be down.
* the choice of nanoseconds is because it is the maximum resolution that
* get_clock() can achieve. It is an internal measure. All user-visible
* units must be in seconds */
static uint64_t max_downtime = 300000000;
uint64_t migrate_max_downtime(void)
{
return max_downtime;
}
MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp)
{
MigrationCapabilityStatusList *head = NULL;
MigrationCapabilityStatusList *caps;
MigrationState *s = migrate_get_current();
int i;
caps = NULL; /* silence compiler warning */
for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
if (head == NULL) {
head = g_malloc0(sizeof(*caps));
caps = head;
} else {
caps->next = g_malloc0(sizeof(*caps));
caps = caps->next;
}
caps->value =
g_malloc(sizeof(*caps->value));
caps->value->capability = i;
caps->value->state = s->enabled_capabilities[i];
}
return head;
}
MigrationParameters *qmp_query_migrate_parameters(Error **errp)
{
MigrationParameters *params;
MigrationState *s = migrate_get_current();
params = g_malloc0(sizeof(*params));
params->compress_level = s->parameters.compress_level;
params->compress_threads = s->parameters.compress_threads;
params->decompress_threads = s->parameters.decompress_threads;
params->cpu_throttle_initial = s->parameters.cpu_throttle_initial;
params->cpu_throttle_increment = s->parameters.cpu_throttle_increment;
params->tls_creds = g_strdup(s->parameters.tls_creds);
params->tls_hostname = g_strdup(s->parameters.tls_hostname);
return params;
}
/*
* Return true if we're already in the middle of a migration
* (i.e. any of the active or setup states)
*/
static bool migration_is_setup_or_active(int state)
{
switch (state) {
case MIGRATION_STATUS_ACTIVE:
case MIGRATION_STATUS_POSTCOPY_ACTIVE:
case MIGRATION_STATUS_SETUP:
return true;
default:
return false;
}
}
static void get_xbzrle_cache_stats(MigrationInfo *info)
{
if (migrate_use_xbzrle()) {
info->has_xbzrle_cache = true;
info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache));
info->xbzrle_cache->cache_size = migrate_xbzrle_cache_size();
info->xbzrle_cache->bytes = xbzrle_mig_bytes_transferred();
info->xbzrle_cache->pages = xbzrle_mig_pages_transferred();
info->xbzrle_cache->cache_miss = xbzrle_mig_pages_cache_miss();
info->xbzrle_cache->cache_miss_rate = xbzrle_mig_cache_miss_rate();
info->xbzrle_cache->overflow = xbzrle_mig_pages_overflow();
}
}
static void populate_ram_info(MigrationInfo *info, MigrationState *s)
{
info->has_ram = true;
info->ram = g_malloc0(sizeof(*info->ram));
info->ram->transferred = ram_bytes_transferred();
info->ram->total = ram_bytes_total();
info->ram->duplicate = dup_mig_pages_transferred();
info->ram->skipped = skipped_mig_pages_transferred();
info->ram->normal = norm_mig_pages_transferred();
info->ram->normal_bytes = norm_mig_bytes_transferred();
info->ram->mbps = s->mbps;
info->ram->dirty_sync_count = s->dirty_sync_count;
info->ram->postcopy_requests = s->postcopy_requests;
if (s->state != MIGRATION_STATUS_COMPLETED) {
info->ram->remaining = ram_bytes_remaining();
info->ram->dirty_pages_rate = s->dirty_pages_rate;
}
}
MigrationInfo *qmp_query_migrate(Error **errp)
{
MigrationInfo *info = g_malloc0(sizeof(*info));
MigrationState *s = migrate_get_current();
switch (s->state) {
case MIGRATION_STATUS_NONE:
/* no migration has happened ever */
break;
case MIGRATION_STATUS_SETUP:
info->has_status = true;
info->has_total_time = false;
break;
case MIGRATION_STATUS_ACTIVE:
case MIGRATION_STATUS_CANCELLING:
info->has_status = true;
info->has_total_time = true;
info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME)
- s->total_time;
info->has_expected_downtime = true;
info->expected_downtime = s->expected_downtime;
info->has_setup_time = true;
info->setup_time = s->setup_time;
populate_ram_info(info, s);
if (blk_mig_active()) {
info->has_disk = true;
info->disk = g_malloc0(sizeof(*info->disk));
info->disk->transferred = blk_mig_bytes_transferred();
info->disk->remaining = blk_mig_bytes_remaining();
info->disk->total = blk_mig_bytes_total();
}
if (cpu_throttle_active()) {
info->has_cpu_throttle_percentage = true;
info->cpu_throttle_percentage = cpu_throttle_get_percentage();
}
get_xbzrle_cache_stats(info);
break;
case MIGRATION_STATUS_POSTCOPY_ACTIVE:
/* Mostly the same as active; TODO add some postcopy stats */
info->has_status = true;
info->has_total_time = true;
info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME)
- s->total_time;
info->has_expected_downtime = true;
info->expected_downtime = s->expected_downtime;
info->has_setup_time = true;
info->setup_time = s->setup_time;
populate_ram_info(info, s);
if (blk_mig_active()) {
info->has_disk = true;
info->disk = g_malloc0(sizeof(*info->disk));
info->disk->transferred = blk_mig_bytes_transferred();
info->disk->remaining = blk_mig_bytes_remaining();
info->disk->total = blk_mig_bytes_total();
}
get_xbzrle_cache_stats(info);
break;
case MIGRATION_STATUS_COMPLETED:
get_xbzrle_cache_stats(info);
info->has_status = true;
info->has_total_time = true;
info->total_time = s->total_time;
info->has_downtime = true;
info->downtime = s->downtime;
info->has_setup_time = true;
info->setup_time = s->setup_time;
populate_ram_info(info, s);
break;
case MIGRATION_STATUS_FAILED:
info->has_status = true;
if (s->error) {
info->has_error_desc = true;
info->error_desc = g_strdup(error_get_pretty(s->error));
}
break;
case MIGRATION_STATUS_CANCELLED:
info->has_status = true;
break;
}
info->status = s->state;
return info;
}
void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
Error **errp)
{
MigrationState *s = migrate_get_current();
MigrationCapabilityStatusList *cap;
bool old_postcopy_cap = migrate_postcopy_ram();
if (migration_is_setup_or_active(s->state)) {
error_setg(errp, QERR_MIGRATION_ACTIVE);
return;
}
for (cap = params; cap; cap = cap->next) {
s->enabled_capabilities[cap->value->capability] = cap->value->state;
}
if (migrate_postcopy_ram()) {
if (migrate_use_compression()) {
/* The decompression threads asynchronously write into RAM
* rather than use the atomic copies needed to avoid
* userfaulting. It should be possible to fix the decompression
* threads for compatibility in future.
*/
error_report("Postcopy is not currently compatible with "
"compression");
s->enabled_capabilities[MIGRATION_CAPABILITY_POSTCOPY_RAM] =
false;
}
/* This check is reasonably expensive, so only when it's being
* set the first time, also it's only the destination that needs
* special support.
*/
if (!old_postcopy_cap && runstate_check(RUN_STATE_INMIGRATE) &&
!postcopy_ram_supported_by_host()) {
/* postcopy_ram_supported_by_host will have emitted a more
* detailed message
*/
error_report("Postcopy is not supported");
s->enabled_capabilities[MIGRATION_CAPABILITY_POSTCOPY_RAM] =
false;
}
}
}
void qmp_migrate_set_parameters(bool has_compress_level,
int64_t compress_level,
bool has_compress_threads,
int64_t compress_threads,
bool has_decompress_threads,
int64_t decompress_threads,
bool has_cpu_throttle_initial,
int64_t cpu_throttle_initial,
bool has_cpu_throttle_increment,
int64_t cpu_throttle_increment,
bool has_tls_creds,
const char *tls_creds,
bool has_tls_hostname,
const char *tls_hostname,
Error **errp)
{
MigrationState *s = migrate_get_current();
if (has_compress_level && (compress_level < 0 || compress_level > 9)) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "compress_level",
"is invalid, it should be in the range of 0 to 9");
return;
}
if (has_compress_threads &&
(compress_threads < 1 || compress_threads > 255)) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
"compress_threads",
"is invalid, it should be in the range of 1 to 255");
return;
}
if (has_decompress_threads &&
(decompress_threads < 1 || decompress_threads > 255)) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
"decompress_threads",
"is invalid, it should be in the range of 1 to 255");
return;
}
if (has_cpu_throttle_initial &&
(cpu_throttle_initial < 1 || cpu_throttle_initial > 99)) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
"cpu_throttle_initial",
"an integer in the range of 1 to 99");
}
if (has_cpu_throttle_increment &&
(cpu_throttle_increment < 1 || cpu_throttle_increment > 99)) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
"cpu_throttle_increment",
"an integer in the range of 1 to 99");
}
if (has_compress_level) {
s->parameters.compress_level = compress_level;
}
if (has_compress_threads) {
s->parameters.compress_threads = compress_threads;
}
if (has_decompress_threads) {
s->parameters.decompress_threads = decompress_threads;
}
if (has_cpu_throttle_initial) {
s->parameters.cpu_throttle_initial = cpu_throttle_initial;
}
if (has_cpu_throttle_increment) {
s->parameters.cpu_throttle_increment = cpu_throttle_increment;
}
if (has_tls_creds) {
g_free(s->parameters.tls_creds);
s->parameters.tls_creds = g_strdup(tls_creds);
}
if (has_tls_hostname) {
g_free(s->parameters.tls_hostname);
s->parameters.tls_hostname = g_strdup(tls_hostname);
}
}
void qmp_migrate_start_postcopy(Error **errp)
{
MigrationState *s = migrate_get_current();
if (!migrate_postcopy_ram()) {
error_setg(errp, "Enable postcopy with migrate_set_capability before"
" the start of migration");
return;
}
if (s->state == MIGRATION_STATUS_NONE) {
error_setg(errp, "Postcopy must be started after migration has been"
" started");
return;
}
/*
* we don't error if migration has finished since that would be racy
* with issuing this command.
*/
atomic_set(&s->start_postcopy, true);
}
/* shared migration helpers */
void migrate_set_state(int *state, int old_state, int new_state)
{
if (atomic_cmpxchg(state, old_state, new_state) == old_state) {
trace_migrate_set_state(new_state);
migrate_generate_event(new_state);
}
}
static void migrate_fd_cleanup(void *opaque)
{
MigrationState *s = opaque;
qemu_bh_delete(s->cleanup_bh);
s->cleanup_bh = NULL;
flush_page_queue(s);
if (s->to_dst_file) {
trace_migrate_fd_cleanup();
qemu_mutex_unlock_iothread();
if (s->migration_thread_running) {
qemu_thread_join(&s->thread);
s->migration_thread_running = false;
}
qemu_mutex_lock_iothread();
migrate_compress_threads_join();
qemu_fclose(s->to_dst_file);
s->to_dst_file = NULL;
}
assert((s->state != MIGRATION_STATUS_ACTIVE) &&
(s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE));
if (s->state == MIGRATION_STATUS_CANCELLING) {
migrate_set_state(&s->state, MIGRATION_STATUS_CANCELLING,
MIGRATION_STATUS_CANCELLED);
}
notifier_list_notify(&migration_state_notifiers, s);
}
void migrate_fd_error(MigrationState *s, const Error *error)
{
trace_migrate_fd_error(error ? error_get_pretty(error) : "");
assert(s->to_dst_file == NULL);
migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
MIGRATION_STATUS_FAILED);
if (!s->error) {
s->error = error_copy(error);
}
notifier_list_notify(&migration_state_notifiers, s);
}
static void migrate_fd_cancel(MigrationState *s)
{
int old_state ;
QEMUFile *f = migrate_get_current()->to_dst_file;
trace_migrate_fd_cancel();
if (s->rp_state.from_dst_file) {
/* shutdown the rp socket, so causing the rp thread to shutdown */
qemu_file_shutdown(s->rp_state.from_dst_file);
}
do {
old_state = s->state;
if (!migration_is_setup_or_active(old_state)) {
break;
}
migrate_set_state(&s->state, old_state, MIGRATION_STATUS_CANCELLING);
} while (s->state != MIGRATION_STATUS_CANCELLING);
/*
* If we're unlucky the migration code might be stuck somewhere in a
* send/write while the network has failed and is waiting to timeout;
* if we've got shutdown(2) available then we can force it to quit.
* The outgoing qemu file gets closed in migrate_fd_cleanup that is
* called in a bh, so there is no race against this cancel.
*/
if (s->state == MIGRATION_STATUS_CANCELLING && f) {
qemu_file_shutdown(f);
}
}
void add_migration_state_change_notifier(Notifier *notify)
{
notifier_list_add(&migration_state_notifiers, notify);
}
void remove_migration_state_change_notifier(Notifier *notify)
{
notifier_remove(notify);
}
bool migration_in_setup(MigrationState *s)
{
return s->state == MIGRATION_STATUS_SETUP;
}
bool migration_has_finished(MigrationState *s)
{
return s->state == MIGRATION_STATUS_COMPLETED;
}
bool migration_has_failed(MigrationState *s)
{
return (s->state == MIGRATION_STATUS_CANCELLED ||
s->state == MIGRATION_STATUS_FAILED);
}
bool migration_in_postcopy(MigrationState *s)
{
return (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE);
}
bool migration_in_postcopy_after_devices(MigrationState *s)
{
return migration_in_postcopy(s) && s->postcopy_after_devices;
}
MigrationState *migrate_init(const MigrationParams *params)
{
MigrationState *s = migrate_get_current();
/*
* Reinitialise all migration state, except
* parameters/capabilities that the user set, and
* locks.
*/
s->bytes_xfer = 0;
s->xfer_limit = 0;
s->cleanup_bh = 0;
s->to_dst_file = NULL;
s->state = MIGRATION_STATUS_NONE;
s->params = *params;
s->rp_state.from_dst_file = NULL;
s->rp_state.error = false;
s->mbps = 0.0;