diff options
Diffstat (limited to 'block/block-copy.c')
| -rw-r--r-- | block/block-copy.c | 136 |
1 files changed, 108 insertions, 28 deletions
diff --git a/block/block-copy.c b/block/block-copy.c index 0becad52da..ce116318b5 100644 --- a/block/block-copy.c +++ b/block/block-copy.c @@ -21,12 +21,14 @@ #include "qemu/units.h" #include "qemu/coroutine.h" #include "block/aio_task.h" +#include "qemu/error-report.h" #define BLOCK_COPY_MAX_COPY_RANGE (16 * MiB) #define BLOCK_COPY_MAX_BUFFER (1 * MiB) #define BLOCK_COPY_MAX_MEM (128 * MiB) #define BLOCK_COPY_MAX_WORKERS 64 #define BLOCK_COPY_SLICE_TIME 100000000ULL /* ns */ +#define BLOCK_COPY_CLUSTER_SIZE_DEFAULT (1 << 16) typedef enum { COPY_READ_WRITE_CLUSTER, @@ -290,9 +292,11 @@ static void coroutine_fn block_copy_task_end(BlockCopyTask *task, int ret) bdrv_set_dirty_bitmap(task->s->copy_bitmap, task->offset, task->bytes); } QLIST_REMOVE(task, list); - progress_set_remaining(task->s->progress, - bdrv_get_dirty_count(task->s->copy_bitmap) + - task->s->in_flight_bytes); + if (task->s->progress) { + progress_set_remaining(task->s->progress, + bdrv_get_dirty_count(task->s->copy_bitmap) + + task->s->in_flight_bytes); + } qemu_co_queue_restart_all(&task->wait_queue); } @@ -315,12 +319,82 @@ static uint32_t block_copy_max_transfer(BdrvChild *source, BdrvChild *target) target->bs->bl.max_transfer)); } +void block_copy_set_copy_opts(BlockCopyState *s, bool use_copy_range, + bool compress) +{ + /* Keep BDRV_REQ_SERIALISING set (or not set) in block_copy_state_new() */ + s->write_flags = (s->write_flags & BDRV_REQ_SERIALISING) | + (compress ? BDRV_REQ_WRITE_COMPRESSED : 0); + + if (s->max_transfer < s->cluster_size) { + /* + * copy_range does not respect max_transfer. We don't want to bother + * with requests smaller than block-copy cluster size, so fallback to + * buffered copying (read and write respect max_transfer on their + * behalf). + */ + s->method = COPY_READ_WRITE_CLUSTER; + } else if (compress) { + /* Compression supports only cluster-size writes and no copy-range. */ + s->method = COPY_READ_WRITE_CLUSTER; + } else { + /* + * If copy range enabled, start with COPY_RANGE_SMALL, until first + * successful copy_range (look at block_copy_do_copy). + */ + s->method = use_copy_range ? COPY_RANGE_SMALL : COPY_READ_WRITE; + } +} + +static int64_t block_copy_calculate_cluster_size(BlockDriverState *target, + Error **errp) +{ + int ret; + BlockDriverInfo bdi; + bool target_does_cow = bdrv_backing_chain_next(target); + + /* + * If there is no backing file on the target, we cannot rely on COW if our + * backup cluster size is smaller than the target cluster size. Even for + * targets with a backing file, try to avoid COW if possible. + */ + ret = bdrv_get_info(target, &bdi); + if (ret == -ENOTSUP && !target_does_cow) { + /* Cluster size is not defined */ + warn_report("The target block device doesn't provide " + "information about the block size and it doesn't have a " + "backing file. The default block size of %u bytes is " + "used. If the actual block size of the target exceeds " + "this default, the backup may be unusable", + BLOCK_COPY_CLUSTER_SIZE_DEFAULT); + return BLOCK_COPY_CLUSTER_SIZE_DEFAULT; + } else if (ret < 0 && !target_does_cow) { + error_setg_errno(errp, -ret, + "Couldn't determine the cluster size of the target image, " + "which has no backing file"); + error_append_hint(errp, + "Aborting, since this may create an unusable destination image\n"); + return ret; + } else if (ret < 0 && target_does_cow) { + /* Not fatal; just trudge on ahead. */ + return BLOCK_COPY_CLUSTER_SIZE_DEFAULT; + } + + return MAX(BLOCK_COPY_CLUSTER_SIZE_DEFAULT, bdi.cluster_size); +} + BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, - int64_t cluster_size, bool use_copy_range, - BdrvRequestFlags write_flags, Error **errp) + Error **errp) { BlockCopyState *s; + int64_t cluster_size; BdrvDirtyBitmap *copy_bitmap; + bool is_fleecing; + + cluster_size = block_copy_calculate_cluster_size(target->bs, errp); + if (cluster_size < 0) { + return NULL; + } copy_bitmap = bdrv_create_dirty_bitmap(source->bs, cluster_size, NULL, errp); @@ -329,6 +403,22 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, } bdrv_disable_dirty_bitmap(copy_bitmap); + /* + * If source is in backing chain of target assume that target is going to be + * used for "image fleecing", i.e. it should represent a kind of snapshot of + * source at backup-start point in time. And target is going to be read by + * somebody (for example, used as NBD export) during backup job. + * + * In this case, we need to add BDRV_REQ_SERIALISING write flag to avoid + * intersection of backup writes and third party reads from target, + * otherwise reading from target we may occasionally read already updated by + * guest data. + * + * For more information see commit f8d59dfb40bb and test + * tests/qemu-iotests/222 + */ + is_fleecing = bdrv_chain_contains(target->bs, source->bs); + s = g_new(BlockCopyState, 1); *s = (BlockCopyState) { .source = source, @@ -336,31 +426,14 @@ BlockCopyState *block_copy_state_new(BdrvChild *source, BdrvChild *target, .copy_bitmap = copy_bitmap, .cluster_size = cluster_size, .len = bdrv_dirty_bitmap_size(copy_bitmap), - .write_flags = write_flags, + .write_flags = (is_fleecing ? BDRV_REQ_SERIALISING : 0), .mem = shres_create(BLOCK_COPY_MAX_MEM), .max_transfer = QEMU_ALIGN_DOWN( block_copy_max_transfer(source, target), cluster_size), }; - if (s->max_transfer < cluster_size) { - /* - * copy_range does not respect max_transfer. We don't want to bother - * with requests smaller than block-copy cluster size, so fallback to - * buffered copying (read and write respect max_transfer on their - * behalf). - */ - s->method = COPY_READ_WRITE_CLUSTER; - } else if (write_flags & BDRV_REQ_WRITE_COMPRESSED) { - /* Compression supports only cluster-size writes and no copy-range. */ - s->method = COPY_READ_WRITE_CLUSTER; - } else { - /* - * If copy range enabled, start with COPY_RANGE_SMALL, until first - * successful copy_range (look at block_copy_do_copy). - */ - s->method = use_copy_range ? COPY_RANGE_SMALL : COPY_READ_WRITE; - } + block_copy_set_copy_opts(s, false, false); ratelimit_init(&s->rate_limit); qemu_co_mutex_init(&s->lock); @@ -522,7 +595,7 @@ static coroutine_fn int block_copy_task_entry(AioTask *task) t->call_state->ret = ret; t->call_state->error_is_read = error_is_read; } - } else { + } else if (s->progress) { progress_work_done(s->progress, t->bytes); } } @@ -628,9 +701,11 @@ int64_t block_copy_reset_unallocated(BlockCopyState *s, if (!ret) { qemu_co_mutex_lock(&s->lock); bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes); - progress_set_remaining(s->progress, - bdrv_get_dirty_count(s->copy_bitmap) + - s->in_flight_bytes); + if (s->progress) { + progress_set_remaining(s->progress, + bdrv_get_dirty_count(s->copy_bitmap) + + s->in_flight_bytes); + } qemu_co_mutex_unlock(&s->lock); } @@ -933,6 +1008,11 @@ BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s) return s->copy_bitmap; } +int64_t block_copy_cluster_size(BlockCopyState *s) +{ + return s->cluster_size; +} + void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip) { qatomic_set(&s->skip_unallocated, skip); |