aboutsummaryrefslogtreecommitdiff
path: root/migration.c
blob: a704d48669f2bf2d6bcfd941028cdef7f0390814 (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
/*
 * QEMU live migration
 *
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * 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-common.h"
#include "migration/migration.h"
#include "monitor/monitor.h"
#include "migration/qemu-file.h"
#include "sysemu/sysemu.h"
#include "block/block.h"
#include "qemu/sockets.h"
#include "migration/block.h"
#include "qemu/thread.h"
#include "qmp-commands.h"
#include "trace.h"

//#define DEBUG_MIGRATION

#ifdef DEBUG_MIGRATION
#define DPRINTF(fmt, ...) \
    do { printf("migration: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
    do { } while (0)
#endif

enum {
    MIG_STATE_ERROR,
    MIG_STATE_SETUP,
    MIG_STATE_CANCELLED,
    MIG_STATE_ACTIVE,
    MIG_STATE_COMPLETED,
};

#define MAX_THROTTLE  (32 << 20)      /* Migration 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)

/* Migration XBZRLE default cache size */
#define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024)

static NotifierList migration_state_notifiers =
    NOTIFIER_LIST_INITIALIZER(migration_state_notifiers);

/* When we add fault tolerance, we could have several
   migrations at once.  For now we don't need to add
   dynamic creation of migration */

MigrationState *migrate_get_current(void)
{
    static MigrationState current_migration = {
        .state = MIG_STATE_SETUP,
        .bandwidth_limit = MAX_THROTTLE,
        .xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE,
        .mbps = -1,
    };

    return &current_migration;
}

void qemu_start_incoming_migration(const char *uri, Error **errp)
{
    const char *p;

    if (strstart(uri, "tcp:", &p))
        tcp_start_incoming_migration(p, errp);
#if !defined(WIN32)
    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);
#endif
    else {
        error_setg(errp, "unknown migration protocol: %s", uri);
    }
}

static void process_incoming_migration_co(void *opaque)
{
    QEMUFile *f = opaque;
    int ret;

    ret = qemu_loadvm_state(f);
    qemu_fclose(f);
    if (ret < 0) {
        fprintf(stderr, "load of migration failed\n");
        exit(EXIT_FAILURE);
    }
    qemu_announce_self();
    DPRINTF("successfully loaded vm state\n");

    bdrv_clear_incoming_migration_all();
    /* Make sure all file formats flush their mutable metadata */
    bdrv_invalidate_cache_all();

    if (autostart) {
        vm_start();
    } else {
        runstate_set(RUN_STATE_PAUSED);
    }
}

void process_incoming_migration(QEMUFile *f)
{
    Coroutine *co = qemu_coroutine_create(process_incoming_migration_co);
    int fd = qemu_get_fd(f);

    assert(fd != -1);
    qemu_set_nonblock(fd);
    qemu_coroutine_enter(co, f);
}

/* 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 = 30000000;

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;

    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;
}

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->overflow = xbzrle_mig_pages_overflow();
    }
}

MigrationInfo *qmp_query_migrate(Error **errp)
{
    MigrationInfo *info = g_malloc0(sizeof(*info));
    MigrationState *s = migrate_get_current();

    switch (s->state) {
    case MIG_STATE_SETUP:
        /* no migration has happened ever */
        break;
    case MIG_STATE_ACTIVE:
        info->has_status = true;
        info->status = g_strdup("active");
        info->has_total_time = true;
        info->total_time = qemu_get_clock_ms(rt_clock)
            - s->total_time;
        info->has_expected_downtime = true;
        info->expected_downtime = s->expected_downtime;

        info->has_ram = true;
        info->ram = g_malloc0(sizeof(*info->ram));
        info->ram->transferred = ram_bytes_transferred();
        info->ram->remaining = ram_bytes_remaining();
        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->dirty_pages_rate = s->dirty_pages_rate;
        info->ram->mbps = s->mbps;

        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 MIG_STATE_COMPLETED:
        get_xbzrle_cache_stats(info);

        info->has_status = true;
        info->status = g_strdup("completed");
        info->total_time = s->total_time;
        info->has_downtime = true;
        info->downtime = s->downtime;

        info->has_ram = true;
        info->ram = g_malloc0(sizeof(*info->ram));
        info->ram->transferred = ram_bytes_transferred();
        info->ram->remaining = 0;
        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;
        break;
    case MIG_STATE_ERROR:
        info->has_status = true;
        info->status = g_strdup("failed");
        break;
    case MIG_STATE_CANCELLED:
        info->has_status = true;
        info->status = g_strdup("cancelled");
        break;
    }

    return info;
}

void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params,
                                  Error **errp)
{
    MigrationState *s = migrate_get_current();
    MigrationCapabilityStatusList *cap;

    if (s->state == MIG_STATE_ACTIVE) {
        error_set(errp, QERR_MIGRATION_ACTIVE);
        return;
    }

    for (cap = params; cap; cap = cap->next) {
        s->enabled_capabilities[cap->value->capability] = cap->value->state;
    }
}

/* shared migration helpers */

static void migrate_fd_cleanup(void *opaque)
{
    MigrationState *s = opaque;

    qemu_bh_delete(s->cleanup_bh);
    s->cleanup_bh = NULL;

    if (s->file) {
        DPRINTF("closing file\n");
        qemu_mutex_unlock_iothread();
        qemu_thread_join(&s->thread);
        qemu_mutex_lock_iothread();

        qemu_fclose(s->file);
        s->file = NULL;
    }

    assert(s->state != MIG_STATE_ACTIVE);

    if (s->state != MIG_STATE_COMPLETED) {
        qemu_savevm_state_cancel();
    }

    notifier_list_notify(&migration_state_notifiers, s);
}

static void migrate_finish_set_state(MigrationState *s, int new_state)
{
    if (__sync_val_compare_and_swap(&s->state, MIG_STATE_ACTIVE,
                                    new_state) == new_state) {
        trace_migrate_set_state(new_state);
    }
}

void migrate_fd_error(MigrationState *s)
{
    DPRINTF("setting error state\n");
    assert(s->file == NULL);
    s->state = MIG_STATE_ERROR;
    trace_migrate_set_state(MIG_STATE_ERROR);
    notifier_list_notify(&migration_state_notifiers, s);
}

static void migrate_fd_cancel(MigrationState *s)
{
    DPRINTF("cancelling migration\n");

    migrate_finish_set_state(s, MIG_STATE_CANCELLED);
}

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_is_active(MigrationState *s)
{
    return s->state == MIG_STATE_ACTIVE;
}

bool migration_has_finished(MigrationState *s)
{
    return s->state == MIG_STATE_COMPLETED;
}

bool migration_has_failed(MigrationState *s)
{
    return (s->state == MIG_STATE_CANCELLED ||
            s->state == MIG_STATE_ERROR);
}

static MigrationState *migrate_init(const MigrationParams *params)
{
    MigrationState *s = migrate_get_current();
    int64_t bandwidth_limit = s->bandwidth_limit;
    bool enabled_capabilities[MIGRATION_CAPABILITY_MAX];
    int64_t xbzrle_cache_size = s->xbzrle_cache_size;

    memcpy(enabled_capabilities, s->enabled_capabilities,
           sizeof(enabled_capabilities));

    memset(s, 0, sizeof(*s));
    s->params = *params;
    memcpy(s->enabled_capabilities, enabled_capabilities,
           sizeof(enabled_capabilities));
    s->xbzrle_cache_size = xbzrle_cache_size;

    s->bandwidth_limit = bandwidth_limit;
    s->state = MIG_STATE_SETUP;
    trace_migrate_set_state(MIG_STATE_SETUP);

    s->total_time = qemu_get_clock_ms(rt_clock);
    return s;
}

static GSList *migration_blockers;

void migrate_add_blocker(Error *reason)
{
    migration_blockers = g_slist_prepend(migration_blockers, reason);
}

void migrate_del_blocker(Error *reason)
{
    migration_blockers = g_slist_remove(migration_blockers, reason);
}

void qmp_migrate(const char *uri, bool has_blk, bool blk,
                 bool has_inc, bool inc, bool has_detach, bool detach,
                 Error **errp)
{
    Error *local_err = NULL;
    MigrationState *s = migrate_get_current();
    MigrationParams params;
    const char *p;

    params.blk = blk;
    params.shared = inc;

    if (s->state == MIG_STATE_ACTIVE) {
        error_set(errp, QERR_MIGRATION_ACTIVE);
        return;
    }

    if (qemu_savevm_state_blocked(errp)) {
        return;
    }

    if (migration_blockers) {
        *errp = error_copy(migration_blockers->data);
        return;
    }

    s = migrate_init(&params);

    if (strstart(uri, "tcp:", &p)) {
        tcp_start_outgoing_migration(s, p, &local_err);
#if !defined(WIN32)
    } else if (strstart(uri, "exec:", &p)) {
        exec_start_outgoing_migration(s, p, &local_err);
    } else if (strstart(uri, "unix:", &p)) {
        unix_start_outgoing_migration(s, p, &local_err);
    } else if (strstart(uri, "fd:", &p)) {
        fd_start_outgoing_migration(s, p, &local_err);
#endif
    } else {
        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "uri", "a valid migration protocol");
        return;
    }

    if (local_err) {
        migrate_fd_error(s);
        error_propagate(errp, local_err);
        return;
    }
}

void qmp_migrate_cancel(Error **errp)
{
    migrate_fd_cancel(migrate_get_current());
}

void qmp_migrate_set_cache_size(int64_t value, Error **errp)
{
    MigrationState *s = migrate_get_current();

    /* Check for truncation */
    if (value != (size_t)value) {
        error_set(errp, QERR_INVALID_PARAMETER_VALUE, "cache size",
                  "exceeding address space");
        return;
    }

    s->xbzrle_cache_size = xbzrle_cache_resize(value);
}

int64_t qmp_query_migrate_cache_size(Error **errp)
{
    return migrate_xbzrle_cache_size();
}

void qmp_migrate_set_speed(int64_t value, Error **errp)
{
    MigrationState *s;

    if (value < 0) {
        value = 0;
    }
    if (value > SIZE_MAX) {
        value = SIZE_MAX;
    }

    s = migrate_get_current();
    s->bandwidth_limit = value;
    if (s->file) {
        qemu_file_set_rate_limit(s->file, s->bandwidth_limit / XFER_LIMIT_RATIO);
    }
}

void qmp_migrate_set_downtime(double value, Error **errp)
{
    value *= 1e9;
    value = MAX(0, MIN(UINT64_MAX, value));
    max_downtime = (uint64_t)value;
}

bool migrate_rdma_pin_all(void)
{
    MigrationState *s;

    s = migrate_get_current();

    return s->enabled_capabilities[MIGRATION_CAPABILITY_X_RDMA_PIN_ALL];
}

int migrate_use_xbzrle(void)
{
    MigrationState *s;

    s = migrate_get_current();

    return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE];
}

int64_t migrate_xbzrle_cache_size(void)
{
    MigrationState *s;

    s = migrate_get_current();

    return s->xbzrle_cache_size;
}

/* migration thread support */

static void *migration_thread(void *opaque)
{
    MigrationState *s = opaque;
    int64_t initial_time = qemu_get_clock_ms(rt_clock);
    int64_t initial_bytes = 0;
    int64_t max_size = 0;
    int64_t start_time = initial_time;
    bool old_vm_running = false;

    DPRINTF("beginning savevm\n");
    qemu_savevm_state_begin(s->file, &s->params);

    while (s->state == MIG_STATE_ACTIVE) {
        int64_t current_time;
        uint64_t pending_size;

        if (!qemu_file_rate_limit(s->file)) {
            DPRINTF("iterate\n");
            pending_size = qemu_savevm_state_pending(s->file, max_size);
            DPRINTF("pending size %lu max %lu\n", pending_size, max_size);
            if (pending_size && pending_size >= max_size) {
                qemu_savevm_state_iterate(s->file);
            } else {
                DPRINTF("done iterating\n");
                qemu_mutex_lock_iothread();
                start_time = qemu_get_clock_ms(rt_clock);
                qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER);
                old_vm_running = runstate_is_running();
                vm_stop_force_state(RUN_STATE_FINISH_MIGRATE);
                qemu_file_set_rate_limit(s->file, INT_MAX);
                qemu_savevm_state_complete(s->file);
                qemu_mutex_unlock_iothread();
                if (!qemu_file_get_error(s->file)) {
                    migrate_finish_set_state(s, MIG_STATE_COMPLETED);
                    break;
                }
            }
        }

        if (qemu_file_get_error(s->file)) {
            migrate_finish_set_state(s, MIG_STATE_ERROR);
            break;
        }
        current_time = qemu_get_clock_ms(rt_clock);
        if (current_time >= initial_time + BUFFER_DELAY) {
            uint64_t transferred_bytes = qemu_ftell(s->file) - initial_bytes;
            uint64_t time_spent = current_time - initial_time;
            double bandwidth = transferred_bytes / time_spent;
            max_size = bandwidth * migrate_max_downtime() / 1000000;

            s->mbps = time_spent ? (((double) transferred_bytes * 8.0) /
                    ((double) time_spent / 1000.0)) / 1000.0 / 1000.0 : -1;

            DPRINTF("transferred %" PRIu64 " time_spent %" PRIu64
                    " bandwidth %g max_size %" PRId64 "\n",
                    transferred_bytes, time_spent, bandwidth, max_size);
            /* if we haven't sent anything, we don't want to recalculate
               10000 is a small enough number for our purposes */
            if (s->dirty_bytes_rate && transferred_bytes > 10000) {
                s->expected_downtime = s->dirty_bytes_rate / bandwidth;
            }

            qemu_file_reset_rate_limit(s->file);
            initial_time = current_time;
            initial_bytes = qemu_ftell(s->file);
        }
        if (qemu_file_rate_limit(s->file)) {
            /* usleep expects microseconds */
            g_usleep((initial_time + BUFFER_DELAY - current_time)*1000);
        }
    }

    qemu_mutex_lock_iothread();
    if (s->state == MIG_STATE_COMPLETED) {
        int64_t end_time = qemu_get_clock_ms(rt_clock);
        s->total_time = end_time - s->total_time;
        s->downtime = end_time - start_time;
        runstate_set(RUN_STATE_POSTMIGRATE);
    } else {
        if (old_vm_running) {
            vm_start();
        }
    }
    qemu_bh_schedule(s->cleanup_bh);
    qemu_mutex_unlock_iothread();

    return NULL;
}

void migrate_fd_connect(MigrationState *s)
{
    s->state = MIG_STATE_ACTIVE;
    trace_migrate_set_state(MIG_STATE_ACTIVE);

    /* This is a best 1st approximation. ns to ms */
    s->expected_downtime = max_downtime/1000000;
    s->cleanup_bh = qemu_bh_new(migrate_fd_cleanup, s);

    qemu_file_set_rate_limit(s->file,
                             s->bandwidth_limit / XFER_LIMIT_RATIO);

    qemu_thread_create(&s->thread, migration_thread, s,
                       QEMU_THREAD_JOINABLE);
    notifier_list_notify(&migration_state_notifiers, s);
}