aboutsummaryrefslogtreecommitdiffstats
path: root/block-migration.c
blob: 7d04d6db0a30a82f15bae8fdbb9579956d432b2d (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
/*
 * QEMU live block migration
 *
 * Copyright IBM, Corp. 2009
 *
 * Authors:
 *  Liran Schour   <lirans@il.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#include "qemu-common.h"
#include "block_int.h"
#include "hw/hw.h"
#include "qemu-queue.h"
#include "qemu-timer.h"
#include "monitor.h"
#include "block-migration.h"
#include "migration.h"
#include <assert.h>

#define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)

#define BLK_MIG_FLAG_DEVICE_BLOCK       0x01
#define BLK_MIG_FLAG_EOS                0x02
#define BLK_MIG_FLAG_PROGRESS           0x04

#define MAX_IS_ALLOCATED_SEARCH 65536

//#define DEBUG_BLK_MIGRATION

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

typedef struct BlkMigDevState {
    BlockDriverState *bs;
    int bulk_completed;
    int shared_base;
    int64_t cur_sector;
    int64_t cur_dirty;
    int64_t completed_sectors;
    int64_t total_sectors;
    int64_t dirty;
    QSIMPLEQ_ENTRY(BlkMigDevState) entry;
} BlkMigDevState;

typedef struct BlkMigBlock {
    uint8_t *buf;
    BlkMigDevState *bmds;
    int64_t sector;
    struct iovec iov;
    QEMUIOVector qiov;
    BlockDriverAIOCB *aiocb;
    int ret;
    int64_t time;
    QSIMPLEQ_ENTRY(BlkMigBlock) entry;
} BlkMigBlock;

typedef struct BlkMigState {
    int blk_enable;
    int shared_base;
    QSIMPLEQ_HEAD(bmds_list, BlkMigDevState) bmds_list;
    QSIMPLEQ_HEAD(blk_list, BlkMigBlock) blk_list;
    int submitted;
    int read_done;
    int transferred;
    int64_t total_sector_sum;
    int prev_progress;
    int bulk_completed;
    long double total_time;
    int reads;
} BlkMigState;

static BlkMigState block_mig_state;

static void blk_send(QEMUFile *f, BlkMigBlock * blk)
{
    int len;

    /* sector number and flags */
    qemu_put_be64(f, (blk->sector << BDRV_SECTOR_BITS)
                     | BLK_MIG_FLAG_DEVICE_BLOCK);

    /* device name */
    len = strlen(blk->bmds->bs->device_name);
    qemu_put_byte(f, len);
    qemu_put_buffer(f, (uint8_t *)blk->bmds->bs->device_name, len);

    qemu_put_buffer(f, blk->buf, BLOCK_SIZE);
}

int blk_mig_active(void)
{
    return !QSIMPLEQ_EMPTY(&block_mig_state.bmds_list);
}

uint64_t blk_mig_bytes_transferred(void)
{
    BlkMigDevState *bmds;
    uint64_t sum = 0;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        sum += bmds->completed_sectors;
    }
    return sum << BDRV_SECTOR_BITS;
}

uint64_t blk_mig_bytes_remaining(void)
{
    return blk_mig_bytes_total() - blk_mig_bytes_transferred();
}

uint64_t blk_mig_bytes_total(void)
{
    BlkMigDevState *bmds;
    uint64_t sum = 0;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        sum += bmds->total_sectors;
    }
    return sum << BDRV_SECTOR_BITS;
}

static inline void add_avg_read_time(int64_t time)
{
    block_mig_state.reads++;
    block_mig_state.total_time += time;
}

static inline long double compute_read_bwidth(void)
{
    assert(block_mig_state.total_time != 0);
    return  (block_mig_state.reads * BLOCK_SIZE)/ block_mig_state.total_time;
}

static void blk_mig_read_cb(void *opaque, int ret)
{
    BlkMigBlock *blk = opaque;

    blk->ret = ret;

    blk->time = qemu_get_clock_ns(rt_clock) - blk->time;

    add_avg_read_time(blk->time);

    QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);

    block_mig_state.submitted--;
    block_mig_state.read_done++;
    assert(block_mig_state.submitted >= 0);
}

static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
                                BlkMigDevState *bmds)
{
    int64_t total_sectors = bmds->total_sectors;
    int64_t cur_sector = bmds->cur_sector;
    BlockDriverState *bs = bmds->bs;
    BlkMigBlock *blk;
    int nr_sectors;

    if (bmds->shared_base) {
        while (cur_sector < total_sectors &&
               !bdrv_is_allocated(bs, cur_sector, MAX_IS_ALLOCATED_SEARCH,
                                  &nr_sectors)) {
            cur_sector += nr_sectors;
        }
    }

    if (cur_sector >= total_sectors) {
        bmds->cur_sector = bmds->completed_sectors = total_sectors;
        return 1;
    }

    bmds->completed_sectors = cur_sector;

    cur_sector &= ~((int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK - 1);

    /* we are going to transfer a full block even if it is not allocated */
    nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;

    if (total_sectors - cur_sector < BDRV_SECTORS_PER_DIRTY_CHUNK) {
        nr_sectors = total_sectors - cur_sector;
    }

    blk = qemu_malloc(sizeof(BlkMigBlock));
    blk->buf = qemu_malloc(BLOCK_SIZE);
    blk->bmds = bmds;
    blk->sector = cur_sector;

    blk->iov.iov_base = blk->buf;
    blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
    qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);

    blk->time = qemu_get_clock_ns(rt_clock);

    blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
                                nr_sectors, blk_mig_read_cb, blk);
    if (!blk->aiocb) {
        goto error;
    }
    block_mig_state.submitted++;

    bdrv_reset_dirty(bs, cur_sector, nr_sectors);
    bmds->cur_sector = cur_sector + nr_sectors;

    return (bmds->cur_sector >= total_sectors);

error:
    monitor_printf(mon, "Error reading sector %" PRId64 "\n", cur_sector);
    qemu_file_set_error(f);
    qemu_free(blk->buf);
    qemu_free(blk);
    return 0;
}

static void set_dirty_tracking(int enable)
{
    BlkMigDevState *bmds;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        bdrv_set_dirty_tracking(bmds->bs, enable);
    }
}

static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
{
    Monitor *mon = opaque;
    BlkMigDevState *bmds;
    int64_t sectors;

    if (bs->type == BDRV_TYPE_HD) {
        sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
        if (sectors == 0) {
            return;
        }

        bmds = qemu_mallocz(sizeof(BlkMigDevState));
        bmds->bs = bs;
        bmds->bulk_completed = 0;
        bmds->total_sectors = sectors;
        bmds->completed_sectors = 0;
        bmds->shared_base = block_mig_state.shared_base;

        block_mig_state.total_sector_sum += sectors;

        if (bmds->shared_base) {
            monitor_printf(mon, "Start migration for %s with shared base "
                                "image\n",
                           bs->device_name);
        } else {
            monitor_printf(mon, "Start full migration for %s\n",
                           bs->device_name);
        }

        QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry);
    }
}

static void init_blk_migration(Monitor *mon, QEMUFile *f)
{
    block_mig_state.submitted = 0;
    block_mig_state.read_done = 0;
    block_mig_state.transferred = 0;
    block_mig_state.total_sector_sum = 0;
    block_mig_state.prev_progress = -1;
    block_mig_state.bulk_completed = 0;
    block_mig_state.total_time = 0;
    block_mig_state.reads = 0;

    bdrv_iterate(init_blk_migration_it, mon);
}

static int blk_mig_save_bulked_block(Monitor *mon, QEMUFile *f)
{
    int64_t completed_sector_sum = 0;
    BlkMigDevState *bmds;
    int progress;
    int ret = 0;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        if (bmds->bulk_completed == 0) {
            if (mig_save_device_bulk(mon, f, bmds) == 1) {
                /* completed bulk section for this device */
                bmds->bulk_completed = 1;
            }
            completed_sector_sum += bmds->completed_sectors;
            ret = 1;
            break;
        } else {
            completed_sector_sum += bmds->completed_sectors;
        }
    }

    progress = completed_sector_sum * 100 / block_mig_state.total_sector_sum;
    if (progress != block_mig_state.prev_progress) {
        block_mig_state.prev_progress = progress;
        qemu_put_be64(f, (progress << BDRV_SECTOR_BITS)
                         | BLK_MIG_FLAG_PROGRESS);
        monitor_printf(mon, "Completed %d %%\r", progress);
        monitor_flush(mon);
    }

    return ret;
}

static void blk_mig_reset_dirty_cursor(void)
{
    BlkMigDevState *bmds;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        bmds->cur_dirty = 0;
    }
}

static int mig_save_device_dirty(Monitor *mon, QEMUFile *f,
                                 BlkMigDevState *bmds, int is_async)
{
    BlkMigBlock *blk;
    int64_t total_sectors = bmds->total_sectors;
    int64_t sector;
    int nr_sectors;

    for (sector = bmds->cur_dirty; sector < bmds->total_sectors;) {
        if (bdrv_get_dirty(bmds->bs, sector)) {

            if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) {
                nr_sectors = total_sectors - sector;
            } else {
                nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
            }
            blk = qemu_malloc(sizeof(BlkMigBlock));
            blk->buf = qemu_malloc(BLOCK_SIZE);
            blk->bmds = bmds;
            blk->sector = sector;

            if (is_async) {
                blk->iov.iov_base = blk->buf;
                blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE;
                qemu_iovec_init_external(&blk->qiov, &blk->iov, 1);

		blk->time = qemu_get_clock_ns(rt_clock);

                blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov,
                                            nr_sectors, blk_mig_read_cb, blk);
                if (!blk->aiocb) {
                    goto error;
                }
                block_mig_state.submitted++;
            } else {
                if (bdrv_read(bmds->bs, sector, blk->buf,
                              nr_sectors) < 0) {
                    goto error;
                }
                blk_send(f, blk);

                qemu_free(blk->buf);
                qemu_free(blk);
            }

            bdrv_reset_dirty(bmds->bs, sector, nr_sectors);
            break;
        }
        sector += BDRV_SECTORS_PER_DIRTY_CHUNK;
        bmds->cur_dirty = sector;
    }

    return (bmds->cur_dirty >= bmds->total_sectors);

error:
    monitor_printf(mon, "Error reading sector %" PRId64 "\n", sector);
    qemu_file_set_error(f);
    qemu_free(blk->buf);
    qemu_free(blk);
    return 0;
}

static int blk_mig_save_dirty_block(Monitor *mon, QEMUFile *f, int is_async)
{
    BlkMigDevState *bmds;
    int ret = 0;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        if (mig_save_device_dirty(mon, f, bmds, is_async) == 0) {
            ret = 1;
            break;
        }
    }

    return ret;
}

static void flush_blks(QEMUFile* f)
{
    BlkMigBlock *blk;

    DPRINTF("%s Enter submitted %d read_done %d transferred %d\n",
            __FUNCTION__, block_mig_state.submitted, block_mig_state.read_done,
            block_mig_state.transferred);

    while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
        if (qemu_file_rate_limit(f)) {
            break;
        }
        if (blk->ret < 0) {
            qemu_file_set_error(f);
            break;
        }
        blk_send(f, blk);

        QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
        qemu_free(blk->buf);
        qemu_free(blk);

        block_mig_state.read_done--;
        block_mig_state.transferred++;
        assert(block_mig_state.read_done >= 0);
    }

    DPRINTF("%s Exit submitted %d read_done %d transferred %d\n", __FUNCTION__,
            block_mig_state.submitted, block_mig_state.read_done,
            block_mig_state.transferred);
}

static int64_t get_remaining_dirty(void)
{
    BlkMigDevState *bmds;
    int64_t dirty = 0;

    QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
        dirty += bdrv_get_dirty_count(bmds->bs);
    }

    return dirty * BLOCK_SIZE;
}

static int is_stage2_completed(void)
{
    int64_t remaining_dirty;
    long double bwidth;

    if (block_mig_state.bulk_completed == 1) {

        remaining_dirty = get_remaining_dirty();
	if (remaining_dirty == 0) {
	    return 1;
	}

	bwidth = compute_read_bwidth();

	if ((remaining_dirty / bwidth) <=
            migrate_max_downtime()) {
            /* finish stage2 because we think that we can finish remaing work
               below max_downtime */

            return 1;
        }
    }

    return 0;
}

static void blk_mig_cleanup(Monitor *mon)
{
    BlkMigDevState *bmds;
    BlkMigBlock *blk;

    while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
        QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
        qemu_free(bmds);
    }

    while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
        QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
        qemu_free(blk->buf);
        qemu_free(blk);
    }

    set_dirty_tracking(0);

    monitor_printf(mon, "\n");
}

static int block_save_live(Monitor *mon, QEMUFile *f, int stage, void *opaque)
{
    DPRINTF("Enter save live stage %d submitted %d transferred %d\n",
            stage, block_mig_state.submitted, block_mig_state.transferred);

    if (stage < 0) {
        blk_mig_cleanup(mon);
        return 0;
    }

    if (block_mig_state.blk_enable != 1) {
        /* no need to migrate storage */
        qemu_put_be64(f, BLK_MIG_FLAG_EOS);
        return 1;
    }

    if (stage == 1) {
        init_blk_migration(mon, f);

        /* start track dirty blocks */
        set_dirty_tracking(1);
    }

    flush_blks(f);

    if (qemu_file_has_error(f)) {
        blk_mig_cleanup(mon);
        return 0;
    }

    blk_mig_reset_dirty_cursor();

    if (stage == 2) {
        /* control the rate of transfer */
        while ((block_mig_state.submitted +
                block_mig_state.read_done) * BLOCK_SIZE <
               qemu_file_get_rate_limit(f)) {
            if (block_mig_state.bulk_completed == 0) {
                /* first finish the bulk phase */
                if (blk_mig_save_bulked_block(mon, f) == 0) {
                    /* finished saving bulk on all devices */
                    block_mig_state.bulk_completed = 1;
                }
            } else {
                if (blk_mig_save_dirty_block(mon, f, 1) == 0) {
                    /* no more dirty blocks */
                    break;
                }
            }
        }

        flush_blks(f);

        if (qemu_file_has_error(f)) {
            blk_mig_cleanup(mon);
            return 0;
        }
    }

    if (stage == 3) {
        /* we know for sure that save bulk is completed and
           all async read completed */
        assert(block_mig_state.submitted == 0);

        while (blk_mig_save_dirty_block(mon, f, 0) != 0);
        blk_mig_cleanup(mon);

        /* report completion */
        qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);

        if (qemu_file_has_error(f)) {
            return 0;
        }

        monitor_printf(mon, "Block migration completed\n");
    }

    qemu_put_be64(f, BLK_MIG_FLAG_EOS);

    return ((stage == 2) && is_stage2_completed());
}

static int block_load(QEMUFile *f, void *opaque, int version_id)
{
    static int banner_printed;
    int len, flags;
    char device_name[256];
    int64_t addr;
    BlockDriverState *bs;
    uint8_t *buf;

    do {
        addr = qemu_get_be64(f);

        flags = addr & ~BDRV_SECTOR_MASK;
        addr >>= BDRV_SECTOR_BITS;

        if (flags & BLK_MIG_FLAG_DEVICE_BLOCK) {
            /* get device name */
            len = qemu_get_byte(f);
            qemu_get_buffer(f, (uint8_t *)device_name, len);
            device_name[len] = '\0';

            bs = bdrv_find(device_name);
            if (!bs) {
                fprintf(stderr, "Error unknown block device %s\n",
                        device_name);
                return -EINVAL;
            }

            buf = qemu_malloc(BLOCK_SIZE);

            qemu_get_buffer(f, buf, BLOCK_SIZE);
            bdrv_write(bs, addr, buf, BDRV_SECTORS_PER_DIRTY_CHUNK);

            qemu_free(buf);
        } else if (flags & BLK_MIG_FLAG_PROGRESS) {
            if (!banner_printed) {
                printf("Receiving block device images\n");
                banner_printed = 1;
            }
            printf("Completed %d %%%c", (int)addr,
                   (addr == 100) ? '\n' : '\r');
            fflush(stdout);
        } else if (!(flags & BLK_MIG_FLAG_EOS)) {
            fprintf(stderr, "Unknown flags\n");
            return -EINVAL;
        }
        if (qemu_file_has_error(f)) {
            return -EIO;
        }
    } while (!(flags & BLK_MIG_FLAG_EOS));

    return 0;
}

static void block_set_params(int blk_enable, int shared_base, void *opaque)
{
    block_mig_state.blk_enable = blk_enable;
    block_mig_state.shared_base = shared_base;

    /* shared base means that blk_enable = 1 */
    block_mig_state.blk_enable |= shared_base;
}

void blk_mig_init(void)
{
    QSIMPLEQ_INIT(&block_mig_state.bmds_list);
    QSIMPLEQ_INIT(&block_mig_state.blk_list);

    register_savevm_live("block", 0, 1, block_set_params, block_save_live,
                         NULL, block_load, &block_mig_state);
}