aboutsummaryrefslogtreecommitdiff
path: root/migration/colo.c
blob: 245a46d59dea5eefaf189fb93393587fb243a4d4 (plain)
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
/*
 * COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
 * (a.k.a. Fault Tolerance or Continuous Replication)
 *
 * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
 * Copyright (c) 2016 FUJITSU LIMITED
 * Copyright (c) 2016 Intel Corporation
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or
 * later.  See the COPYING file in the top-level directory.
 */

#include "qemu/osdep.h"
#include "sysemu/sysemu.h"
#include "qapi/error.h"
#include "qemu-file-channel.h"
#include "migration.h"
#include "qemu-file.h"
#include "savevm.h"
#include "migration/colo.h"
#include "block.h"
#include "io/channel-buffer.h"
#include "trace.h"
#include "qemu/error-report.h"
#include "migration/failover.h"
#include "replication.h"
#include "qmp-commands.h"

static bool vmstate_loading;

#define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)

bool migration_in_colo_state(void)
{
    MigrationState *s = migrate_get_current();

    return (s->state == MIGRATION_STATUS_COLO);
}

bool migration_incoming_in_colo_state(void)
{
    MigrationIncomingState *mis = migration_incoming_get_current();

    return mis && (mis->state == MIGRATION_STATUS_COLO);
}

static bool colo_runstate_is_stopped(void)
{
    return runstate_check(RUN_STATE_COLO) || !runstate_is_running();
}

static void secondary_vm_do_failover(void)
{
    int old_state;
    MigrationIncomingState *mis = migration_incoming_get_current();

    /* Can not do failover during the process of VM's loading VMstate, Or
     * it will break the secondary VM.
     */
    if (vmstate_loading) {
        old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
                        FAILOVER_STATUS_RELAUNCH);
        if (old_state != FAILOVER_STATUS_ACTIVE) {
            error_report("Unknown error while do failover for secondary VM,"
                         "old_state: %s", FailoverStatus_str(old_state));
        }
        return;
    }

    migrate_set_state(&mis->state, MIGRATION_STATUS_COLO,
                      MIGRATION_STATUS_COMPLETED);

    if (!autostart) {
        error_report("\"-S\" qemu option will be ignored in secondary side");
        /* recover runstate to normal migration finish state */
        autostart = true;
    }
    /*
     * Make sure COLO incoming thread not block in recv or send,
     * If mis->from_src_file and mis->to_src_file use the same fd,
     * The second shutdown() will return -1, we ignore this value,
     * It is harmless.
     */
    if (mis->from_src_file) {
        qemu_file_shutdown(mis->from_src_file);
    }
    if (mis->to_src_file) {
        qemu_file_shutdown(mis->to_src_file);
    }

    old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
                                   FAILOVER_STATUS_COMPLETED);
    if (old_state != FAILOVER_STATUS_ACTIVE) {
        error_report("Incorrect state (%s) while doing failover for "
                     "secondary VM", FailoverStatus_str(old_state));
        return;
    }
    /* Notify COLO incoming thread that failover work is finished */
    qemu_sem_post(&mis->colo_incoming_sem);
    /* For Secondary VM, jump to incoming co */
    if (mis->migration_incoming_co) {
        qemu_coroutine_enter(mis->migration_incoming_co);
    }
}

static void primary_vm_do_failover(void)
{
    MigrationState *s = migrate_get_current();
    int old_state;

    migrate_set_state(&s->state, MIGRATION_STATUS_COLO,
                      MIGRATION_STATUS_COMPLETED);

    /*
     * Wake up COLO thread which may blocked in recv() or send(),
     * The s->rp_state.from_dst_file and s->to_dst_file may use the
     * same fd, but we still shutdown the fd for twice, it is harmless.
     */
    if (s->to_dst_file) {
        qemu_file_shutdown(s->to_dst_file);
    }
    if (s->rp_state.from_dst_file) {
        qemu_file_shutdown(s->rp_state.from_dst_file);
    }

    old_state = failover_set_state(FAILOVER_STATUS_ACTIVE,
                                   FAILOVER_STATUS_COMPLETED);
    if (old_state != FAILOVER_STATUS_ACTIVE) {
        error_report("Incorrect state (%s) while doing failover for Primary VM",
                     FailoverStatus_str(old_state));
        return;
    }
    /* Notify COLO thread that failover work is finished */
    qemu_sem_post(&s->colo_exit_sem);
}

void colo_do_failover(MigrationState *s)
{
    /* Make sure VM stopped while failover happened. */
    if (!colo_runstate_is_stopped()) {
        vm_stop_force_state(RUN_STATE_COLO);
    }

    if (get_colo_mode() == COLO_MODE_PRIMARY) {
        primary_vm_do_failover();
    } else {
        secondary_vm_do_failover();
    }
}

void qmp_xen_set_replication(bool enable, bool primary,
                             bool has_failover, bool failover,
                             Error **errp)
{
#ifdef CONFIG_REPLICATION
    ReplicationMode mode = primary ?
                           REPLICATION_MODE_PRIMARY :
                           REPLICATION_MODE_SECONDARY;

    if (has_failover && enable) {
        error_setg(errp, "Parameter 'failover' is only for"
                   " stopping replication");
        return;
    }

    if (enable) {
        replication_start_all(mode, errp);
    } else {
        if (!has_failover) {
            failover = NULL;
        }
        replication_stop_all(failover, failover ? NULL : errp);
    }
#else
    abort();
#endif
}

ReplicationStatus *qmp_query_xen_replication_status(Error **errp)
{
#ifdef CONFIG_REPLICATION
    Error *err = NULL;
    ReplicationStatus *s = g_new0(ReplicationStatus, 1);

    replication_get_error_all(&err);
    if (err) {
        s->error = true;
        s->has_desc = true;
        s->desc = g_strdup(error_get_pretty(err));
    } else {
        s->error = false;
    }

    error_free(err);
    return s;
#else
    abort();
#endif
}

void qmp_xen_colo_do_checkpoint(Error **errp)
{
#ifdef CONFIG_REPLICATION
    replication_do_checkpoint_all(errp);
#else
    abort();
#endif
}

static void colo_send_message(QEMUFile *f, COLOMessage msg,
                              Error **errp)
{
    int ret;

    if (msg >= COLO_MESSAGE__MAX) {
        error_setg(errp, "%s: Invalid message", __func__);
        return;
    }
    qemu_put_be32(f, msg);
    qemu_fflush(f);

    ret = qemu_file_get_error(f);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Can't send COLO message");
    }
    trace_colo_send_message(COLOMessage_str(msg));
}

static void colo_send_message_value(QEMUFile *f, COLOMessage msg,
                                    uint64_t value, Error **errp)
{
    Error *local_err = NULL;
    int ret;

    colo_send_message(f, msg, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }
    qemu_put_be64(f, value);
    qemu_fflush(f);

    ret = qemu_file_get_error(f);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Failed to send value for message:%s",
                         COLOMessage_str(msg));
    }
}

static COLOMessage colo_receive_message(QEMUFile *f, Error **errp)
{
    COLOMessage msg;
    int ret;

    msg = qemu_get_be32(f);
    ret = qemu_file_get_error(f);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Can't receive COLO message");
        return msg;
    }
    if (msg >= COLO_MESSAGE__MAX) {
        error_setg(errp, "%s: Invalid message", __func__);
        return msg;
    }
    trace_colo_receive_message(COLOMessage_str(msg));
    return msg;
}

static void colo_receive_check_message(QEMUFile *f, COLOMessage expect_msg,
                                       Error **errp)
{
    COLOMessage msg;
    Error *local_err = NULL;

    msg = colo_receive_message(f, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }
    if (msg != expect_msg) {
        error_setg(errp, "Unexpected COLO message %d, expected %d",
                          msg, expect_msg);
    }
}

static uint64_t colo_receive_message_value(QEMUFile *f, uint32_t expect_msg,
                                           Error **errp)
{
    Error *local_err = NULL;
    uint64_t value;
    int ret;

    colo_receive_check_message(f, expect_msg, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return 0;
    }

    value = qemu_get_be64(f);
    ret = qemu_file_get_error(f);
    if (ret < 0) {
        error_setg_errno(errp, -ret, "Failed to get value for COLO message: %s",
                         COLOMessage_str(expect_msg));
    }
    return value;
}

static int colo_do_checkpoint_transaction(MigrationState *s,
                                          QIOChannelBuffer *bioc,
                                          QEMUFile *fb)
{
    Error *local_err = NULL;
    int ret = -1;

    colo_send_message(s->to_dst_file, COLO_MESSAGE_CHECKPOINT_REQUEST,
                      &local_err);
    if (local_err) {
        goto out;
    }

    colo_receive_check_message(s->rp_state.from_dst_file,
                    COLO_MESSAGE_CHECKPOINT_REPLY, &local_err);
    if (local_err) {
        goto out;
    }
    /* Reset channel-buffer directly */
    qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);
    bioc->usage = 0;

    qemu_mutex_lock_iothread();
    if (failover_get_state() != FAILOVER_STATUS_NONE) {
        qemu_mutex_unlock_iothread();
        goto out;
    }
    vm_stop_force_state(RUN_STATE_COLO);
    qemu_mutex_unlock_iothread();
    trace_colo_vm_state_change("run", "stop");
    /*
     * Failover request bh could be called after vm_stop_force_state(),
     * So we need check failover_request_is_active() again.
     */
    if (failover_get_state() != FAILOVER_STATUS_NONE) {
        goto out;
    }

    /* Disable block migration */
    migrate_set_block_enabled(false, &local_err);
    qemu_savevm_state_header(fb);
    qemu_savevm_state_setup(fb);
    qemu_mutex_lock_iothread();
    qemu_savevm_state_complete_precopy(fb, false, false);
    qemu_mutex_unlock_iothread();

    qemu_fflush(fb);

    colo_send_message(s->to_dst_file, COLO_MESSAGE_VMSTATE_SEND, &local_err);
    if (local_err) {
        goto out;
    }
    /*
     * We need the size of the VMstate data in Secondary side,
     * With which we can decide how much data should be read.
     */
    colo_send_message_value(s->to_dst_file, COLO_MESSAGE_VMSTATE_SIZE,
                            bioc->usage, &local_err);
    if (local_err) {
        goto out;
    }

    qemu_put_buffer(s->to_dst_file, bioc->data, bioc->usage);
    qemu_fflush(s->to_dst_file);
    ret = qemu_file_get_error(s->to_dst_file);
    if (ret < 0) {
        goto out;
    }

    colo_receive_check_message(s->rp_state.from_dst_file,
                       COLO_MESSAGE_VMSTATE_RECEIVED, &local_err);
    if (local_err) {
        goto out;
    }

    colo_receive_check_message(s->rp_state.from_dst_file,
                       COLO_MESSAGE_VMSTATE_LOADED, &local_err);
    if (local_err) {
        goto out;
    }

    ret = 0;

    qemu_mutex_lock_iothread();
    vm_start();
    qemu_mutex_unlock_iothread();
    trace_colo_vm_state_change("stop", "run");

out:
    if (local_err) {
        error_report_err(local_err);
    }
    return ret;
}

static void colo_process_checkpoint(MigrationState *s)
{
    QIOChannelBuffer *bioc;
    QEMUFile *fb = NULL;
    int64_t current_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
    Error *local_err = NULL;
    int ret;

    failover_init_state();

    s->rp_state.from_dst_file = qemu_file_get_return_path(s->to_dst_file);
    if (!s->rp_state.from_dst_file) {
        error_report("Open QEMUFile from_dst_file failed");
        goto out;
    }

    /*
     * Wait for Secondary finish loading VM states and enter COLO
     * restore.
     */
    colo_receive_check_message(s->rp_state.from_dst_file,
                       COLO_MESSAGE_CHECKPOINT_READY, &local_err);
    if (local_err) {
        goto out;
    }
    bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
    fb = qemu_fopen_channel_output(QIO_CHANNEL(bioc));
    object_unref(OBJECT(bioc));

    qemu_mutex_lock_iothread();
    vm_start();
    qemu_mutex_unlock_iothread();
    trace_colo_vm_state_change("stop", "run");

    timer_mod(s->colo_delay_timer,
            current_time + s->parameters.x_checkpoint_delay);

    while (s->state == MIGRATION_STATUS_COLO) {
        if (failover_get_state() != FAILOVER_STATUS_NONE) {
            error_report("failover request");
            goto out;
        }

        qemu_sem_wait(&s->colo_checkpoint_sem);

        ret = colo_do_checkpoint_transaction(s, bioc, fb);
        if (ret < 0) {
            goto out;
        }
    }

out:
    /* Throw the unreported error message after exited from loop */
    if (local_err) {
        error_report_err(local_err);
    }

    if (fb) {
        qemu_fclose(fb);
    }

    timer_del(s->colo_delay_timer);

    /* Hope this not to be too long to wait here */
    qemu_sem_wait(&s->colo_exit_sem);
    qemu_sem_destroy(&s->colo_exit_sem);
    /*
     * Must be called after failover BH is completed,
     * Or the failover BH may shutdown the wrong fd that
     * re-used by other threads after we release here.
     */
    if (s->rp_state.from_dst_file) {
        qemu_fclose(s->rp_state.from_dst_file);
    }
}

void colo_checkpoint_notify(void *opaque)
{
    MigrationState *s = opaque;
    int64_t next_notify_time;

    qemu_sem_post(&s->colo_checkpoint_sem);
    s->colo_checkpoint_time = qemu_clock_get_ms(QEMU_CLOCK_HOST);
    next_notify_time = s->colo_checkpoint_time +
                    s->parameters.x_checkpoint_delay;
    timer_mod(s->colo_delay_timer, next_notify_time);
}

void migrate_start_colo_process(MigrationState *s)
{
    qemu_mutex_unlock_iothread();
    qemu_sem_init(&s->colo_checkpoint_sem, 0);
    s->colo_delay_timer =  timer_new_ms(QEMU_CLOCK_HOST,
                                colo_checkpoint_notify, s);

    qemu_sem_init(&s->colo_exit_sem, 0);
    migrate_set_state(&s->state, MIGRATION_STATUS_ACTIVE,
                      MIGRATION_STATUS_COLO);
    colo_process_checkpoint(s);
    qemu_mutex_lock_iothread();
}

static void colo_wait_handle_message(QEMUFile *f, int *checkpoint_request,
                                     Error **errp)
{
    COLOMessage msg;
    Error *local_err = NULL;

    msg = colo_receive_message(f, &local_err);
    if (local_err) {
        error_propagate(errp, local_err);
        return;
    }

    switch (msg) {
    case COLO_MESSAGE_CHECKPOINT_REQUEST:
        *checkpoint_request = 1;
        break;
    default:
        *checkpoint_request = 0;
        error_setg(errp, "Got unknown COLO message: %d", msg);
        break;
    }
}

void *colo_process_incoming_thread(void *opaque)
{
    MigrationIncomingState *mis = opaque;
    QEMUFile *fb = NULL;
    QIOChannelBuffer *bioc = NULL; /* Cache incoming device state */
    uint64_t total_size;
    uint64_t value;
    Error *local_err = NULL;

    qemu_sem_init(&mis->colo_incoming_sem, 0);

    migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
                      MIGRATION_STATUS_COLO);

    failover_init_state();

    mis->to_src_file = qemu_file_get_return_path(mis->from_src_file);
    if (!mis->to_src_file) {
        error_report("COLO incoming thread: Open QEMUFile to_src_file failed");
        goto out;
    }
    /*
     * Note: the communication between Primary side and Secondary side
     * should be sequential, we set the fd to unblocked in migration incoming
     * coroutine, and here we are in the COLO incoming thread, so it is ok to
     * set the fd back to blocked.
     */
    qemu_file_set_blocking(mis->from_src_file, true);

    bioc = qio_channel_buffer_new(COLO_BUFFER_BASE_SIZE);
    fb = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
    object_unref(OBJECT(bioc));

    colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_READY,
                      &local_err);
    if (local_err) {
        goto out;
    }

    while (mis->state == MIGRATION_STATUS_COLO) {
        int request = 0;

        colo_wait_handle_message(mis->from_src_file, &request, &local_err);
        if (local_err) {
            goto out;
        }
        assert(request);
        if (failover_get_state() != FAILOVER_STATUS_NONE) {
            error_report("failover request");
            goto out;
        }

        /* FIXME: This is unnecessary for periodic checkpoint mode */
        colo_send_message(mis->to_src_file, COLO_MESSAGE_CHECKPOINT_REPLY,
                     &local_err);
        if (local_err) {
            goto out;
        }

        colo_receive_check_message(mis->from_src_file,
                           COLO_MESSAGE_VMSTATE_SEND, &local_err);
        if (local_err) {
            goto out;
        }

        value = colo_receive_message_value(mis->from_src_file,
                                 COLO_MESSAGE_VMSTATE_SIZE, &local_err);
        if (local_err) {
            goto out;
        }

        /*
         * Read VM device state data into channel buffer,
         * It's better to re-use the memory allocated.
         * Here we need to handle the channel buffer directly.
         */
        if (value > bioc->capacity) {
            bioc->capacity = value;
            bioc->data = g_realloc(bioc->data, bioc->capacity);
        }
        total_size = qemu_get_buffer(mis->from_src_file, bioc->data, value);
        if (total_size != value) {
            error_report("Got %" PRIu64 " VMState data, less than expected"
                        " %" PRIu64, total_size, value);
            goto out;
        }
        bioc->usage = total_size;
        qio_channel_io_seek(QIO_CHANNEL(bioc), 0, 0, NULL);

        colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_RECEIVED,
                     &local_err);
        if (local_err) {
            goto out;
        }

        qemu_mutex_lock_iothread();
        qemu_system_reset(SHUTDOWN_CAUSE_NONE);
        vmstate_loading = true;
        if (qemu_loadvm_state(fb) < 0) {
            error_report("COLO: loadvm failed");
            qemu_mutex_unlock_iothread();
            goto out;
        }

        vmstate_loading = false;
        qemu_mutex_unlock_iothread();

        if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
            failover_set_state(FAILOVER_STATUS_RELAUNCH,
                            FAILOVER_STATUS_NONE);
            failover_request_active(NULL);
            goto out;
        }

        colo_send_message(mis->to_src_file, COLO_MESSAGE_VMSTATE_LOADED,
                     &local_err);
        if (local_err) {
            goto out;
        }
    }

out:
    vmstate_loading = false;
    /* Throw the unreported error message after exited from loop */
    if (local_err) {
        error_report_err(local_err);
    }

    if (fb) {
        qemu_fclose(fb);
    }

    /* Hope this not to be too long to loop here */
    qemu_sem_wait(&mis->colo_incoming_sem);
    qemu_sem_destroy(&mis->colo_incoming_sem);
    /* Must be called after failover BH is completed */
    if (mis->to_src_file) {
        qemu_fclose(mis->to_src_file);
    }
    migration_incoming_exit_colo();

    return NULL;
}