#include "block_int.h"
#include "hw/hw.h"
#include "qemu-queue.h"
+#include "monitor.h"
#include "block-migration.h"
#include <assert.h>
#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 MAX_BLOCKS_READ 10000
int bulk_completed;
int shared_base;
int64_t cur_sector;
+ int64_t completed_sectors;
int64_t total_sectors;
int64_t dirty;
QSIMPLEQ_ENTRY(BlkMigDevState) entry;
int submitted;
int read_done;
int transferred;
- int64_t print_completion;
+ int64_t total_sector_sum;
+ int prev_progress;
} 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 void blk_mig_read_cb(void *opaque, int ret)
{
BlkMigBlock *blk = opaque;
assert(block_mig_state.submitted >= 0);
}
-static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds, int is_async)
+static int mig_save_device_bulk(Monitor *mon, QEMUFile *f,
+ BlkMigDevState *bmds, int is_async)
{
int64_t total_sectors = bmds->total_sectors;
int64_t cur_sector = bmds->cur_sector;
BlockDriverState *bs = bmds->bs;
- int len, nr_sectors;
BlkMigBlock *blk;
- uint8_t *tmp_buf;
+ int nr_sectors;
if (bmds->shared_base) {
while (cur_sector < total_sectors &&
}
if (cur_sector >= total_sectors) {
- bmds->cur_sector = total_sectors;
+ bmds->cur_sector = bmds->completed_sectors = total_sectors;
return 1;
}
- if (cur_sector >= block_mig_state.print_completion) {
- printf("Completed %" PRId64 " %%\r", cur_sector * 100 / total_sectors);
- fflush(stdout);
- block_mig_state.print_completion +=
- (BDRV_SECTORS_PER_DIRTY_CHUNK * 10000);
- }
+ bmds->completed_sectors = cur_sector;
cur_sector &= ~((int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK - 1);
nr_sectors = total_sectors - cur_sector;
}
- if (is_async) {
- blk = qemu_malloc(sizeof(BlkMigBlock));
- blk->buf = qemu_malloc(BLOCK_SIZE);
-
- bmds->cur_sector = cur_sector + nr_sectors;
- blk->sector = cur_sector;
- blk->bmds = bmds;
+ blk = qemu_malloc(sizeof(BlkMigBlock));
+ blk->buf = qemu_malloc(BLOCK_SIZE);
+ blk->bmds = bmds;
+ blk->sector = cur_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->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
nr_sectors, blk_mig_read_cb, blk);
-
if (!blk->aiocb) {
- printf("Error reading sector %" PRId64 "\n", cur_sector);
- qemu_free(blk->buf);
- qemu_free(blk);
- return 0;
+ goto error;
}
-
- bdrv_reset_dirty(bs, cur_sector, nr_sectors);
block_mig_state.submitted++;
-
} else {
- tmp_buf = qemu_malloc(BLOCK_SIZE);
-
- if (bdrv_read(bs, cur_sector, tmp_buf, nr_sectors) < 0) {
- printf("Error reading sector %" PRId64 "\n", cur_sector);
+ if (bdrv_read(bs, cur_sector, blk->buf, nr_sectors) < 0) {
+ goto error;
}
+ blk_send(f, blk);
- bdrv_reset_dirty(bs, cur_sector, nr_sectors);
-
- /* sector number and flags */
- qemu_put_be64(f, (cur_sector << BDRV_SECTOR_BITS)
- | BLK_MIG_FLAG_DEVICE_BLOCK);
-
- /* device name */
- len = strlen(bs->device_name);
- qemu_put_byte(f, len);
- qemu_put_buffer(f, (uint8_t *)bs->device_name, len);
-
- qemu_put_buffer(f, tmp_buf, BLOCK_SIZE);
-
- bmds->cur_sector = cur_sector + BDRV_SECTORS_PER_DIRTY_CHUNK;
-
- qemu_free(tmp_buf);
+ qemu_free(blk->buf);
+ qemu_free(blk);
}
- return (bmds->cur_sector >= total_sectors);
-}
-
-static void send_blk(QEMUFile *f, BlkMigBlock * blk)
-{
- int len;
-
- /* sector number and flags */
- qemu_put_be64(f, (blk->sector << BDRV_SECTOR_BITS)
- | BLK_MIG_FLAG_DEVICE_BLOCK);
+ bdrv_reset_dirty(bs, cur_sector, nr_sectors);
+ bmds->cur_sector = cur_sector + nr_sectors;
- /* 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);
+ return (bmds->cur_sector >= total_sectors);
- qemu_put_buffer(f, blk->buf, BLOCK_SIZE);
+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)
}
}
-static void init_blk_migration(QEMUFile *f)
+static void init_blk_migration(Monitor *mon, QEMUFile *f)
{
BlkMigDevState *bmds;
BlockDriverState *bs;
+ int64_t sectors;
block_mig_state.submitted = 0;
block_mig_state.read_done = 0;
block_mig_state.transferred = 0;
- block_mig_state.print_completion = 0;
+ block_mig_state.total_sector_sum = 0;
+ block_mig_state.prev_progress = -1;
for (bs = bdrv_first; bs != NULL; bs = bs->next) {
if (bs->type == BDRV_TYPE_HD) {
+ sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
+ if (sectors == 0) {
+ continue;
+ }
+
bmds = qemu_mallocz(sizeof(BlkMigDevState));
bmds->bs = bs;
bmds->bulk_completed = 0;
- bmds->total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
+ 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) {
- printf("Start migration for %s with shared base image\n",
- bs->device_name);
+ monitor_printf(mon, "Start migration for %s with shared base "
+ "image\n",
+ bs->device_name);
} else {
- printf("Start full migration for %s\n", bs->device_name);
+ monitor_printf(mon, "Start full migration for %s\n",
+ bs->device_name);
}
QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry);
}
}
-static int blk_mig_save_bulked_block(QEMUFile *f, int is_async)
+static int blk_mig_save_bulked_block(Monitor *mon, QEMUFile *f, int is_async)
{
+ 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(f, bmds, is_async) == 1) {
+ if (mig_save_device_bulk(mon, f, bmds, is_async) == 1) {
/* completed bulk section for this device */
bmds->bulk_completed = 1;
}
- return 1;
+ completed_sector_sum += bmds->completed_sectors;
+ ret = 1;
+ break;
+ } else {
+ completed_sector_sum += bmds->completed_sectors;
}
}
- /* we reached here means bulk is completed */
- return 0;
+ 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;
}
#define MAX_NUM_BLOCKS 4
-static void blk_mig_save_dirty_blocks(QEMUFile *f)
+static void blk_mig_save_dirty_blocks(Monitor *mon, QEMUFile *f)
{
BlkMigDevState *bmds;
- uint8_t *buf;
+ BlkMigBlock blk;
int64_t sector;
- int len;
- buf = qemu_malloc(BLOCK_SIZE);
+ blk.buf = qemu_malloc(BLOCK_SIZE);
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
for (sector = 0; sector < bmds->cur_sector;) {
if (bdrv_get_dirty(bmds->bs, sector)) {
- if (bdrv_read(bmds->bs, sector, buf,
+ if (bdrv_read(bmds->bs, sector, blk.buf,
BDRV_SECTORS_PER_DIRTY_CHUNK) < 0) {
- /* FIXME: add error handling */
+ monitor_printf(mon, "Error reading sector %" PRId64 "\n",
+ sector);
+ qemu_file_set_error(f);
+ qemu_free(blk.buf);
+ return;
}
-
- /* sector number and flags */
- qemu_put_be64(f, (sector << BDRV_SECTOR_BITS)
- | BLK_MIG_FLAG_DEVICE_BLOCK);
-
- /* device name */
- len = strlen(bmds->bs->device_name);
- qemu_put_byte(f, len);
- qemu_put_buffer(f, (uint8_t *)bmds->bs->device_name, len);
-
- qemu_put_buffer(f, buf, BLOCK_SIZE);
+ blk.bmds = bmds;
+ blk.sector = sector;
+ blk_send(f, &blk);
bdrv_reset_dirty(bmds->bs, sector,
BDRV_SECTORS_PER_DIRTY_CHUNK);
}
}
- qemu_free(buf);
+ qemu_free(blk.buf);
}
static void flush_blks(QEMUFile* f)
if (qemu_file_rate_limit(f)) {
break;
}
- send_blk(f, blk);
+ 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);
return 1;
}
-static int block_save_live(QEMUFile *f, int stage, void *opaque)
+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);
}
if (stage == 1) {
- init_blk_migration(f);
+ 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;
+ }
+
/* control the rate of transfer */
while ((block_mig_state.submitted +
block_mig_state.read_done) * BLOCK_SIZE <
qemu_file_get_rate_limit(f)) {
- if (blk_mig_save_bulked_block(f, 1) == 0) {
+ if (blk_mig_save_bulked_block(mon, f, 1) == 0) {
/* no more bulk blocks for now */
break;
}
flush_blks(f);
+ if (qemu_file_has_error(f)) {
+ blk_mig_cleanup(mon);
+ return 0;
+ }
+
if (stage == 3) {
- while (blk_mig_save_bulked_block(f, 0) != 0) {
+ while (blk_mig_save_bulked_block(mon, f, 0) != 0) {
/* empty */
}
- blk_mig_save_dirty_blocks(f);
+ blk_mig_save_dirty_blocks(mon, f);
+ blk_mig_cleanup(mon);
+
+ /* report completion */
+ qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
- /* stop track dirty blocks */
- set_dirty_tracking(0);
+ if (qemu_file_has_error(f)) {
+ return 0;
+ }
- printf("\nBlock migration completed\n");
+ monitor_printf(mon, "Block migration completed\n");
}
qemu_put_be64(f, BLK_MIG_FLAG_EOS);
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;
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);
- if (bs != NULL) {
- bdrv_write(bs, addr, buf, BDRV_SECTORS_PER_DIRTY_CHUNK);
- } else {
- printf("Error unknown block device %s\n", device_name);
- /* FIXME: add error handling */
- }
+ 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)) {
- printf("Unknown flags\n");
- /* FIXME: add error handling */
+ fprintf(stderr, "Unknown flags\n");
+ return -EINVAL;
+ }
+ if (qemu_file_has_error(f)) {
+ return -EIO;
}
} while (!(flags & BLK_MIG_FLAG_EOS));
projects / qemu.git / blobdiff