Signed-off-by: Pierre Riteau <pierre.rit...@irisa.fr> --- block-migration.c | 366 ++++++++++++++++++++++++++--------------------------- block-migration.h | 2 +- savevm.c | 41 +++--- 3 files changed, 200 insertions(+), 209 deletions(-)
diff --git a/block-migration.c b/block-migration.c index 09771ed..0cb162a 100644 --- a/block-migration.c +++ b/block-migration.c @@ -21,23 +21,23 @@ #define SECTOR_SIZE (1 << SECTOR_BITS) #define SECTOR_MASK ~(SECTOR_SIZE - 1); -#define BLOCK_SIZE (block_mig_state->sectors_per_block << SECTOR_BITS) +#define BLOCK_SIZE (block_mig_state->sectors_per_block << SECTOR_BITS) #define BLK_MIG_FLAG_DEVICE_BLOCK 0x01 #define BLK_MIG_FLAG_EOS 0x02 #define MAX_IS_ALLOCATED_SEARCH 65536 -#define MAX_BLOCKS_READ 10000 -#define BLOCKS_READ_CHANGE 100 -#define INITIAL_BLOCKS_READ 100 +#define MAX_BLOCKS_READ 10000 +#define BLOCKS_READ_CHANGE 100 +#define INITIAL_BLOCKS_READ 100 //#define DEBUG_BLK_MIGRATION #ifdef DEBUG_BLK_MIGRATION -#define dprintf(fmt, ...) \ +#define dprintf(fmt, ...) \ do { printf("blk_migration: " fmt, ## __VA_ARGS__); } while (0) #else -#define dprintf(fmt, ...) \ +#define dprintf(fmt, ...) \ do { } while (0) #endif @@ -68,87 +68,87 @@ typedef struct BlkMigState { int64_t print_completion; } BlkMigState; -static BlkMigState *block_mig_state = NULL; +static BlkMigState *block_mig_state = NULL; static void blk_mig_read_cb(void *opaque, int ret) { BlkMigBlock *blk = opaque; - + blk->ret = ret; - + /* insert at the end */ - if(block_mig_state->last_blk == NULL) { + if (block_mig_state->last_blk == NULL) { block_mig_state->first_blk = blk; block_mig_state->last_blk = blk; } else { block_mig_state->last_blk->next = blk; block_mig_state->last_blk = blk; } - + block_mig_state->submitted--; block_mig_state->read_done++; assert(block_mig_state->submitted >= 0); - + return; } static int mig_read_device_bulk(QEMUFile *f, BlkMigDevState *bms) -{ +{ int nr_sectors; int64_t total_sectors, cur_sector = 0; BlockDriverState *bs = bms->bs; BlkMigBlock *blk; - + blk = qemu_malloc(sizeof(BlkMigBlock)); blk->buf = qemu_malloc(BLOCK_SIZE); - + cur_sector = bms->cur_sector; total_sectors = bdrv_getlength(bs) >> SECTOR_BITS; - - if(bms->shared_base) { - while(cur_sector < bms->total_sectors && - !bdrv_is_allocated(bms->bs, cur_sector, + + if (bms->shared_base) { + while (cur_sector < bms->total_sectors && + !bdrv_is_allocated(bms->bs, cur_sector, MAX_IS_ALLOCATED_SEARCH, &nr_sectors)) { cur_sector += nr_sectors; } } - - if(cur_sector >= total_sectors) { + + if (cur_sector >= total_sectors) { bms->cur_sector = total_sectors; qemu_free(blk->buf); qemu_free(blk); return 1; } - - if(cur_sector >= block_mig_state->print_completion) { + + if (cur_sector >= block_mig_state->print_completion) { printf("Completed %" PRId64 " %%\r", cur_sector * 100 / total_sectors); fflush(stdout); - block_mig_state->print_completion += + block_mig_state->print_completion += (block_mig_state->sectors_per_block * 10000); } - - /* we going to transfder BLOCK_SIZE any way even if it is not allocated */ + + /* we going to transfer BLOCK_SIZE any way even if it is not allocated */ nr_sectors = block_mig_state->sectors_per_block; - cur_sector &= ~((int64_t)block_mig_state->sectors_per_block -1); - - if(total_sectors - cur_sector < block_mig_state->sectors_per_block) { + cur_sector &= ~((int64_t)block_mig_state->sectors_per_block - 1); + + if (total_sectors - cur_sector < block_mig_state->sectors_per_block) { nr_sectors = (total_sectors - cur_sector); } - + bms->cur_sector = cur_sector + nr_sectors; blk->sector = cur_sector; blk->bmds = bms; blk->next = NULL; - + blk->iov.iov_base = blk->buf; blk->iov.iov_len = nr_sectors * 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) { + + if (!blk->aiocb) { printf("Error reading sector %" PRId64 "\n", cur_sector); qemu_free(blk->buf); qemu_free(blk); @@ -157,90 +157,86 @@ static int mig_read_device_bulk(QEMUFile *f, BlkMigDevState *bms) bdrv_reset_dirty(bms->bs, cur_sector, nr_sectors); block_mig_state->submitted++; - + return (bms->cur_sector >= total_sectors); } static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds) -{ +{ int len, nr_sectors; int64_t total_sectors = bmds->total_sectors, cur_sector = 0; uint8_t *tmp_buf = NULL; BlockDriverState *bs = bmds->bs; tmp_buf = qemu_malloc(BLOCK_SIZE); - + cur_sector = bmds->cur_sector; - - if(bmds->shared_base) { - while(cur_sector < bmds->total_sectors && - !bdrv_is_allocated(bmds->bs, cur_sector, + + if (bmds->shared_base) { + while (cur_sector < bmds->total_sectors && + !bdrv_is_allocated(bmds->bs, cur_sector, MAX_IS_ALLOCATED_SEARCH, &nr_sectors)) { cur_sector += nr_sectors; } } - - if(cur_sector >= total_sectors) { + + if (cur_sector >= total_sectors) { bmds->cur_sector = total_sectors; qemu_free(tmp_buf); return 1; } - - if(cur_sector >= block_mig_state->print_completion) { + + if (cur_sector >= block_mig_state->print_completion) { printf("Completed %" PRId64 " %%\r", cur_sector * 100 / total_sectors); fflush(stdout); - block_mig_state->print_completion += + block_mig_state->print_completion += (block_mig_state->sectors_per_block * 10000); } - - cur_sector &= ~((int64_t)block_mig_state->sectors_per_block -1); - - /* we going to transfer - BLOCK_SIZE - any way even if it is not allocated */ + + cur_sector &= ~((int64_t)block_mig_state->sectors_per_block - 1); + + /* we going to transfer BLOCK_SIZE any way even if it is not allocated */ nr_sectors = block_mig_state->sectors_per_block; - - if(total_sectors - cur_sector < block_mig_state->sectors_per_block) { + + if (total_sectors - cur_sector < block_mig_state->sectors_per_block) { nr_sectors = (total_sectors - cur_sector); } - - if(bdrv_read(bs, cur_sector, tmp_buf, nr_sectors) < 0) { + + if (bdrv_read(bs, cur_sector, tmp_buf, nr_sectors) < 0) { printf("Error reading sector %" PRId64 "\n", cur_sector); } bdrv_reset_dirty(bs, cur_sector, nr_sectors); - + /* Device name */ - qemu_put_be64(f,(cur_sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK); - + qemu_put_be64(f, (cur_sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK); + 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); - + + qemu_put_buffer(f, tmp_buf, BLOCK_SIZE); + bmds->cur_sector = cur_sector + block_mig_state->sectors_per_block; - + qemu_free(tmp_buf); - + return (bmds->cur_sector >= total_sectors); } static void send_blk(QEMUFile *f, BlkMigBlock * blk) { int len; - - /* Device name */ - qemu_put_be64(f,(blk->sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK); - + + /* Device name */ + qemu_put_be64(f, (blk->sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK); + 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); - + + qemu_put_buffer(f, blk->buf, BLOCK_SIZE); + return; } @@ -251,10 +247,10 @@ static void blk_mig_save_dev_info(QEMUFile *f, BlkMigDevState *bmds) static void set_dirty_tracking(int enable) { BlkMigDevState *bmds; - for(bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) { - bdrv_set_dirty_tracking(bmds->bs,enable); + for (bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) { + bdrv_set_dirty_tracking(bmds->bs, enable); } - + return; } @@ -262,35 +258,35 @@ static void init_blk_migration(QEMUFile *f) { BlkMigDevState **pbmds, *bmds; BlockDriverState *bs; - + for (bs = bdrv_first; bs != NULL; bs = bs->next) { - if(bs->type == BDRV_TYPE_HD) { + if (bs->type == BDRV_TYPE_HD) { bmds = qemu_mallocz(sizeof(BlkMigDevState)); bmds->bs = bs; bmds->bulk_completed = 0; bmds->total_sectors = bdrv_getlength(bs) >> SECTOR_BITS; bmds->shared_base = block_mig_state->shared_base; - - if(bmds->shared_base) { - printf("Start migration for %s with shared base image\n", + + if (bmds->shared_base) { + printf("Start migration for %s with shared base image\n", bs->device_name); } else { printf("Start full migration for %s\n", bs->device_name); } - + /* insert at the end */ pbmds = &block_mig_state->bmds_first; - while (*pbmds != NULL) + while (*pbmds != NULL) { pbmds = &(*pbmds)->next; + } *pbmds = bmds; - + blk_mig_save_dev_info(f, bmds); - } - } - + } + block_mig_state->sectors_per_block = bdrv_get_sectors_per_chunk(); - + return; } @@ -299,14 +295,14 @@ static int blk_mig_save_bulked_block(QEMUFile *f, int is_async) BlkMigDevState *bmds; for (bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) { - if(bmds->bulk_completed == 0) { - if(is_async) { - if(mig_read_device_bulk(f, bmds) == 1) { + if (bmds->bulk_completed == 0) { + if (is_async) { + if (mig_read_device_bulk(f, bmds) == 1) { /* completed bulk section for this device */ bmds->bulk_completed = 1; } } else { - if(mig_save_device_bulk(f,bmds) == 1) { + if (mig_save_device_bulk(f, bmds) == 1) { /* completed bulk section for this device */ bmds->bulk_completed = 1; } @@ -314,12 +310,11 @@ static int blk_mig_save_bulked_block(QEMUFile *f, int is_async) return 1; } } - + /* we reached here means bulk is completed */ block_mig_state->bulk_completed = 1; - + return 0; - } #define MAX_NUM_BLOCKS 4 @@ -330,70 +325,70 @@ static void blk_mig_save_dirty_blocks(QEMUFile *f) uint8_t buf[BLOCK_SIZE]; int64_t sector; int len; - - for(bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) { - for(sector = 0; sector < bmds->cur_sector;) { - - if(bdrv_get_dirty(bmds->bs,sector)) { - - if(bdrv_read(bmds->bs, sector, buf, + + for (bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) { + for (sector = 0; sector < bmds->cur_sector;) { + + if (bdrv_get_dirty(bmds->bs, sector)) { + + if (bdrv_read(bmds->bs, sector, buf, block_mig_state->sectors_per_block) < 0) { } - + /* device name */ - qemu_put_be64(f,(sector << SECTOR_BITS) + qemu_put_be64(f, (sector << SECTOR_BITS) | BLK_MIG_FLAG_DEVICE_BLOCK); - + 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_mig_state->sectors_per_block * + + qemu_put_buffer(f, buf, + (block_mig_state->sectors_per_block * SECTOR_SIZE)); - - bdrv_reset_dirty(bmds->bs, sector, + + bdrv_reset_dirty(bmds->bs, sector, block_mig_state->sectors_per_block); - + sector += block_mig_state->sectors_per_block; } else { /* sector is clean */ sector += block_mig_state->sectors_per_block; - } + } } } - + return; } static void flush_blks(QEMUFile* f) { BlkMigBlock *blk, *tmp; - - dprintf("%s Enter submitted %d read_done %d transfered\n", __FUNCTION__, + + dprintf("%s Enter submitted %d read_done %d transfered\n", __FUNCTION__, submitted, read_done, transfered); - - for(blk = block_mig_state->first_blk; + + for (blk = block_mig_state->first_blk; blk != NULL && !qemu_file_rate_limit(f); blk = tmp) { send_blk(f, blk); - + tmp = blk->next; qemu_free(blk->buf); qemu_free(blk); - + block_mig_state->read_done--; block_mig_state->transferred++; assert(block_mig_state->read_done >= 0); } block_mig_state->first_blk = blk; - - if(block_mig_state->first_blk == NULL) { + + if (block_mig_state->first_blk == NULL) { block_mig_state->last_blk = NULL; } - dprintf("%s Exit submitted %d read_done %d transferred%d\n", __FUNCTION__, - block_mig_state->submitted, block_mig_state->read_done, + 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); return; @@ -402,71 +397,72 @@ static void flush_blks(QEMUFile* f) static int is_stage2_completed(void) { BlkMigDevState *bmds; - - if(block_mig_state->submitted > 0) { + + if (block_mig_state->submitted > 0) { return 0; } - + for (bmds = block_mig_state->bmds_first; bmds != NULL; bmds = bmds->next) { - if(bmds->bulk_completed == 0) { + if (bmds->bulk_completed == 0) { return 0; } } - + return 1; } static int block_save_live(QEMUFile *f, int stage, void *opaque) { int ret = 1; - - dprintf("Enter save live stage %d submitted %d transferred %d\n", stage, + + dprintf("Enter save live stage %d submitted %d transferred %d\n", stage, submitted, transferred); - - if(block_mig_state->blk_enable != 1) { + + if (block_mig_state->blk_enable != 1) { /* no need to migrate storage */ - - qemu_put_be64(f,BLK_MIG_FLAG_EOS); + + qemu_put_be64(f, BLK_MIG_FLAG_EOS); return 1; } - - if(stage == 1) { + + if (stage == 1) { init_blk_migration(f); - + /* start track dirty blocks */ set_dirty_tracking(1); - } flush_blks(f); - + /* control the rate of transfer */ - while ((block_mig_state->submitted + block_mig_state->read_done) * - (BLOCK_SIZE) < + while ((block_mig_state->submitted + block_mig_state->read_done) * + (BLOCK_SIZE) < (qemu_file_get_rate_limit(f))) { - + ret = blk_mig_save_bulked_block(f, 1); - - if (ret == 0) /* no more bulk blocks for now*/ + + if (ret == 0) { + /* no more bulk blocks for now */ break; + } } - + flush_blks(f); - - if(stage == 3) { - - while(blk_mig_save_bulked_block(f, 0) != 0); - + + if (stage == 3) { + + while (blk_mig_save_bulked_block(f, 0) != 0); + blk_mig_save_dirty_blocks(f); - + /* stop track dirty blocks */ - set_dirty_tracking(0);; - - printf("\nBlock migration completed\n"); + set_dirty_tracking(0); + + printf("\nBlock migration completed\n"); } - - qemu_put_be64(f,BLK_MIG_FLAG_EOS); - + + qemu_put_be64(f, BLK_MIG_FLAG_EOS); + return ((stage == 2) && is_stage2_completed()); } @@ -477,43 +473,40 @@ static int block_load(QEMUFile *f, void *opaque, int version_id) int64_t addr; BlockDriverState *bs; uint8_t *buf; - + block_mig_state->sectors_per_block = bdrv_get_sectors_per_chunk(); buf = qemu_malloc(BLOCK_SIZE); - + do { - addr = qemu_get_be64(f); - + flags = addr & ~SECTOR_MASK; addr &= SECTOR_MASK; - - if(flags & BLK_MIG_FLAG_DEVICE_BLOCK) { - + + 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); - - qemu_get_buffer(f, buf, - BLOCK_SIZE); - if(bs != NULL) { - - bdrv_write(bs, (addr >> SECTOR_BITS), + + qemu_get_buffer(f, buf, BLOCK_SIZE); + if (bs != NULL) { + bdrv_write(bs, (addr >> SECTOR_BITS), buf, block_mig_state->sectors_per_block); } else { printf("Error unknown block device %s\n", device_name); } - } else if(flags & BLK_MIG_FLAG_EOS) { - + } else if (flags & BLK_MIG_FLAG_EOS) { + } else { printf("Unknown flags\n"); } - } while(!(flags & BLK_MIG_FLAG_EOS)); - + } while (!(flags & BLK_MIG_FLAG_EOS)); + qemu_free(buf); return 0; @@ -525,33 +518,30 @@ 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; - + return; } void blk_mig_info(void) { BlockDriverState *bs; - + for (bs = bdrv_first; bs != NULL; bs = bs->next) { printf("Device %s\n", bs->device_name); - if(bs->type == BDRV_TYPE_HD) { - printf("device %s format %s\n", + if (bs->type == BDRV_TYPE_HD) { + printf("device %s format %s\n", bs->device_name, bs->drv->format_name); } } } void blk_mig_init(void) -{ - +{ block_mig_state = qemu_mallocz(sizeof(BlkMigState)); - - register_savevm_live("block", 0, 1, block_set_params, block_save_live, - NULL, block_load, block_mig_state); - + register_savevm_live("block", 0, 1, block_set_params, block_save_live, + NULL, block_load, block_mig_state); } diff --git a/block-migration.h b/block-migration.h index c33d3cb..9961abd 100644 --- a/block-migration.h +++ b/block-migration.h @@ -23,7 +23,7 @@ typedef struct BlkMigDevState { int64_t total_sectors; int64_t dirty; } BlkMigDevState; - + void blk_mig_init(void); void blk_mig_info(void); #endif /* BLOCK_MIGRATION_H */ diff --git a/savevm.c b/savevm.c index 4668843..e875e16 100644 --- a/savevm.c +++ b/savevm.c @@ -264,11 +264,11 @@ QEMUFile *qemu_popen(FILE *stdio_file, const char *mode) s->stdio_file = stdio_file; - if(mode[0] == 'r') { - s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_pclose, + if (mode[0] == 'r') { + s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_pclose, NULL, NULL, NULL); } else { - s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_pclose, + s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_pclose, NULL, NULL, NULL); } return s->file; @@ -279,7 +279,7 @@ QEMUFile *qemu_popen_cmd(const char *command, const char *mode) FILE *popen_file; popen_file = popen(command, mode); - if(popen_file == NULL) { + if (popen_file == NULL) { return NULL; } @@ -313,11 +313,11 @@ QEMUFile *qemu_fdopen(int fd, const char *mode) if (!s->stdio_file) goto fail; - if(mode[0] == 'r') { - s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_fclose, + if (mode[0] == 'r') { + s->file = qemu_fopen_ops(s, NULL, stdio_get_buffer, stdio_fclose, NULL, NULL, NULL); } else { - s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_fclose, + s->file = qemu_fopen_ops(s, stdio_put_buffer, NULL, stdio_fclose, NULL, NULL, NULL); } return s->file; @@ -332,7 +332,7 @@ QEMUFile *qemu_fopen_socket(int fd) QEMUFileSocket *s = qemu_mallocz(sizeof(QEMUFileSocket)); s->fd = fd; - s->file = qemu_fopen_ops(s, NULL, socket_get_buffer, socket_close, + s->file = qemu_fopen_ops(s, NULL, socket_get_buffer, socket_close, NULL, NULL, NULL); return s->file; } @@ -369,12 +369,12 @@ QEMUFile *qemu_fopen(const char *filename, const char *mode) s->stdio_file = fopen(filename, mode); if (!s->stdio_file) goto fail; - - if(mode[0] == 'w') { - s->file = qemu_fopen_ops(s, file_put_buffer, NULL, stdio_fclose, + + if (mode[0] == 'w') { + s->file = qemu_fopen_ops(s, file_put_buffer, NULL, stdio_fclose, NULL, NULL, NULL); } else { - s->file = qemu_fopen_ops(s, NULL, file_get_buffer, stdio_fclose, + s->file = qemu_fopen_ops(s, NULL, file_get_buffer, stdio_fclose, NULL, NULL, NULL); } return s->file; @@ -403,7 +403,7 @@ static int bdrv_fclose(void *opaque) static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable) { if (is_writable) - return qemu_fopen_ops(bs, block_put_buffer, NULL, bdrv_fclose, + return qemu_fopen_ops(bs, block_put_buffer, NULL, bdrv_fclose, NULL, NULL, NULL); return qemu_fopen_ops(bs, NULL, block_get_buffer, bdrv_fclose, NULL, NULL, NULL); } @@ -605,8 +605,9 @@ int qemu_file_rate_limit(QEMUFile *f) size_t qemu_file_get_rate_limit(QEMUFile *f) { - if (f->get_rate_limit) + if (f->get_rate_limit) { return f->get_rate_limit(f->opaque); + } return 0; } @@ -1125,7 +1126,7 @@ int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, if (ret) return ret; } - while(field->name) { + while (field->name) { if ((field->field_exists && field->field_exists(opaque, version_id)) || (!field->field_exists && @@ -1176,7 +1177,7 @@ void vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd, if (vmsd->pre_save) { vmsd->pre_save(opaque); } - while(field->name) { + while (field->name) { if (!field->field_exists || field->field_exists(opaque, vmsd->version_id)) { void *base_addr = opaque + field->offset; @@ -1241,12 +1242,12 @@ int qemu_savevm_state_begin(QEMUFile *f, int blk_enable, int shared) SaveStateEntry *se; QTAILQ_FOREACH(se, &savevm_handlers, entry) { - if(se->set_params == NULL) { + if (se->set_params == NULL) { continue; - } - se->set_params(blk_enable, shared, se->opaque); + } + se->set_params(blk_enable, shared, se->opaque); } - + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); qemu_put_be32(f, QEMU_VM_FILE_VERSION); -- 1.6.5