#include "block/block-copy.h"
#include "qapi/error.h"
#include "qapi/qmp/qerror.h"
-#include "qemu/ratelimit.h"
#include "qemu/cutils.h"
#include "sysemu/block-backend.h"
#include "qemu/bitmap.h"
#include "qemu/error-report.h"
-#include "block/backup-top.h"
-
-#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
+#include "block/copy-before-write.h"
typedef struct BackupBlockJob {
BlockJob common;
- BlockDriverState *backup_top;
+ BlockDriverState *cbw;
BlockDriverState *source_bs;
+ BlockDriverState *target_bs;
BdrvDirtyBitmap *sync_bitmap;
BlockdevOnError on_source_error;
BlockdevOnError on_target_error;
uint64_t len;
- uint64_t bytes_read;
int64_t cluster_size;
+ BackupPerf perf;
BlockCopyState *bcs;
+
+ bool wait;
+ BlockCopyCallState *bg_bcs_call;
} BackupBlockJob;
static const BlockJobDriver backup_job_driver;
-static void backup_progress_bytes_callback(int64_t bytes, void *opaque)
-{
- BackupBlockJob *s = opaque;
-
- s->bytes_read += bytes;
- job_progress_update(&s->common.job, bytes);
-}
-
-static void backup_progress_reset_callback(void *opaque)
-{
- BackupBlockJob *s = opaque;
- uint64_t estimate = bdrv_get_dirty_count(s->bcs->copy_bitmap);
-
- job_progress_set_remaining(&s->common.job, estimate);
-}
-
-static int coroutine_fn backup_do_cow(BackupBlockJob *job,
- int64_t offset, uint64_t bytes,
- bool *error_is_read)
-{
- int ret = 0;
- int64_t start, end; /* bytes */
-
- start = QEMU_ALIGN_DOWN(offset, job->cluster_size);
- end = QEMU_ALIGN_UP(bytes + offset, job->cluster_size);
-
- trace_backup_do_cow_enter(job, start, offset, bytes);
-
- ret = block_copy(job->bcs, start, end - start, error_is_read);
-
- trace_backup_do_cow_return(job, offset, bytes, ret);
-
- return ret;
-}
-
static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
{
BdrvDirtyBitmap *bm;
if (ret < 0 && job->bitmap_mode == BITMAP_SYNC_MODE_ALWAYS) {
/* If we failed and synced, merge in the bits we didn't copy: */
- bdrv_dirty_bitmap_merge_internal(bm, job->bcs->copy_bitmap,
+ bdrv_dirty_bitmap_merge_internal(bm, block_copy_dirty_bitmap(job->bcs),
NULL, true);
}
}
static void backup_clean(Job *job)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
- AioContext *aio_context = bdrv_get_aio_context(s->backup_top);
-
- aio_context_acquire(aio_context);
- bdrv_backup_top_drop(s->backup_top);
- aio_context_release(aio_context);
+ block_job_remove_all_bdrv(&s->common);
+ bdrv_cbw_drop(s->cbw);
}
void backup_do_checkpoint(BlockJob *job, Error **errp)
return;
}
- bdrv_set_dirty_bitmap(backup_job->bcs->copy_bitmap, 0, backup_job->len);
+ bdrv_set_dirty_bitmap(block_copy_dirty_bitmap(backup_job->bcs), 0,
+ backup_job->len);
}
static BlockErrorAction backup_error_action(BackupBlockJob *job,
}
}
-static bool coroutine_fn yield_and_check(BackupBlockJob *job)
+static void coroutine_fn backup_block_copy_callback(void *opaque)
{
- uint64_t delay_ns;
-
- if (job_is_cancelled(&job->common.job)) {
- return true;
- }
-
- /*
- * We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
- * return. Without a yield, the VM would not reboot.
- */
- delay_ns = block_job_ratelimit_get_delay(&job->common, job->bytes_read);
- job->bytes_read = 0;
- job_sleep_ns(&job->common.job, delay_ns);
+ BackupBlockJob *s = opaque;
- if (job_is_cancelled(&job->common.job)) {
- return true;
+ if (s->wait) {
+ s->wait = false;
+ aio_co_wake(s->common.job.co);
+ } else {
+ job_enter(&s->common.job);
}
-
- return false;
}
static int coroutine_fn backup_loop(BackupBlockJob *job)
{
- bool error_is_read;
- int64_t offset;
- BdrvDirtyBitmapIter *bdbi;
+ BlockCopyCallState *s = NULL;
int ret = 0;
+ bool error_is_read;
+ BlockErrorAction act;
+
+ while (true) { /* retry loop */
+ job->bg_bcs_call = s = block_copy_async(job->bcs, 0,
+ QEMU_ALIGN_UP(job->len, job->cluster_size),
+ job->perf.max_workers, job->perf.max_chunk,
+ backup_block_copy_callback, job);
+
+ while (!block_copy_call_finished(s) &&
+ !job_is_cancelled(&job->common.job))
+ {
+ job_yield(&job->common.job);
+ }
- bdbi = bdrv_dirty_iter_new(job->bcs->copy_bitmap);
- while ((offset = bdrv_dirty_iter_next(bdbi)) != -1) {
- do {
- if (yield_and_check(job)) {
- goto out;
- }
- ret = backup_do_cow(job, offset, job->cluster_size, &error_is_read);
- if (ret < 0 && backup_error_action(job, error_is_read, -ret) ==
- BLOCK_ERROR_ACTION_REPORT)
- {
- goto out;
- }
- } while (ret < 0);
+ if (!block_copy_call_finished(s)) {
+ assert(job_is_cancelled(&job->common.job));
+ /*
+ * Note that we can't use job_yield() here, as it doesn't work for
+ * cancelled job.
+ */
+ block_copy_call_cancel(s);
+ job->wait = true;
+ qemu_coroutine_yield();
+ assert(block_copy_call_finished(s));
+ ret = 0;
+ goto out;
+ }
+
+ if (job_is_cancelled(&job->common.job) ||
+ block_copy_call_succeeded(s))
+ {
+ ret = 0;
+ goto out;
+ }
+
+ if (block_copy_call_cancelled(s)) {
+ /*
+ * Job is not cancelled but only block-copy call. This is possible
+ * after job pause. Now the pause is finished, start new block-copy
+ * iteration.
+ */
+ block_copy_call_free(s);
+ continue;
+ }
+
+ /* The only remaining case is failed block-copy call. */
+ assert(block_copy_call_failed(s));
+
+ ret = block_copy_call_status(s, &error_is_read);
+ act = backup_error_action(job, error_is_read, -ret);
+ switch (act) {
+ case BLOCK_ERROR_ACTION_REPORT:
+ goto out;
+ case BLOCK_ERROR_ACTION_STOP:
+ /*
+ * Go to pause prior to starting new block-copy call on the next
+ * iteration.
+ */
+ job_pause_point(&job->common.job);
+ break;
+ case BLOCK_ERROR_ACTION_IGNORE:
+ /* Proceed to new block-copy call to retry. */
+ break;
+ default:
+ abort();
+ }
+
+ block_copy_call_free(s);
}
- out:
- bdrv_dirty_iter_free(bdbi);
+out:
+ block_copy_call_free(s);
+ job->bg_bcs_call = NULL;
return ret;
}
-static void backup_init_copy_bitmap(BackupBlockJob *job)
+static void backup_init_bcs_bitmap(BackupBlockJob *job)
{
- bool ret;
uint64_t estimate;
+ BdrvDirtyBitmap *bcs_bitmap = block_copy_dirty_bitmap(job->bcs);
if (job->sync_mode == MIRROR_SYNC_MODE_BITMAP) {
- ret = bdrv_dirty_bitmap_merge_internal(job->bcs->copy_bitmap,
- job->sync_bitmap,
- NULL, true);
- assert(ret);
- } else {
- if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
- /*
- * We can't hog the coroutine to initialize this thoroughly.
- * Set a flag and resume work when we are able to yield safely.
- */
- job->bcs->skip_unallocated = true;
- }
- bdrv_set_dirty_bitmap(job->bcs->copy_bitmap, 0, job->len);
+ bdrv_clear_dirty_bitmap(bcs_bitmap, NULL);
+ bdrv_dirty_bitmap_merge_internal(bcs_bitmap, job->sync_bitmap, NULL,
+ true);
+ } else if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
+ /*
+ * We can't hog the coroutine to initialize this thoroughly.
+ * Set a flag and resume work when we are able to yield safely.
+ */
+ block_copy_set_skip_unallocated(job->bcs, true);
}
- estimate = bdrv_get_dirty_count(job->bcs->copy_bitmap);
+ estimate = bdrv_get_dirty_count(bcs_bitmap);
job_progress_set_remaining(&job->common.job, estimate);
}
static int coroutine_fn backup_run(Job *job, Error **errp)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
- int ret = 0;
+ int ret;
- backup_init_copy_bitmap(s);
+ backup_init_bcs_bitmap(s);
if (s->sync_mode == MIRROR_SYNC_MODE_TOP) {
int64_t offset = 0;
int64_t count;
for (offset = 0; offset < s->len; ) {
- if (yield_and_check(s)) {
- ret = -ECANCELED;
- goto out;
+ if (job_is_cancelled(job)) {
+ return -ECANCELED;
+ }
+
+ job_pause_point(job);
+
+ if (job_is_cancelled(job)) {
+ return -ECANCELED;
}
ret = block_copy_reset_unallocated(s->bcs, offset, &count);
if (ret < 0) {
- goto out;
+ return ret;
}
offset += count;
}
- s->bcs->skip_unallocated = false;
+ block_copy_set_skip_unallocated(s->bcs, false);
}
if (s->sync_mode == MIRROR_SYNC_MODE_NONE) {
/*
- * All bits are set in copy_bitmap to allow any cluster to be copied.
+ * All bits are set in bcs bitmap to allow any cluster to be copied.
* This does not actually require them to be copied.
*/
while (!job_is_cancelled(job)) {
job_yield(job);
}
} else {
- ret = backup_loop(s);
+ return backup_loop(s);
}
- out:
- return ret;
+ return 0;
+}
+
+static void coroutine_fn backup_pause(Job *job)
+{
+ BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+
+ if (s->bg_bcs_call && !block_copy_call_finished(s->bg_bcs_call)) {
+ block_copy_call_cancel(s->bg_bcs_call);
+ s->wait = true;
+ qemu_coroutine_yield();
+ }
+}
+
+static void coroutine_fn backup_set_speed(BlockJob *job, int64_t speed)
+{
+ BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+ /*
+ * block_job_set_speed() is called first from block_job_create(), when we
+ * don't yet have s->bcs.
+ */
+ if (s->bcs) {
+ block_copy_set_speed(s->bcs, speed);
+ if (s->bg_bcs_call) {
+ block_copy_kick(s->bg_bcs_call);
+ }
+ }
+}
+
+static bool backup_cancel(Job *job, bool force)
+{
+ BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+
+ bdrv_cancel_in_flight(s->target_bs);
+ return true;
}
static const BlockJobDriver backup_job_driver = {
.commit = backup_commit,
.abort = backup_abort,
.clean = backup_clean,
- }
+ .pause = backup_pause,
+ .cancel = backup_cancel,
+ },
+ .set_speed = backup_set_speed,
};
-static int64_t backup_calculate_cluster_size(BlockDriverState *target,
- Error **errp)
-{
- int ret;
- BlockDriverInfo bdi;
-
- /*
- * 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->backing) {
- /* 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",
- BACKUP_CLUSTER_SIZE_DEFAULT);
- return BACKUP_CLUSTER_SIZE_DEFAULT;
- } else if (ret < 0 && !target->backing) {
- 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->backing) {
- /* Not fatal; just trudge on ahead. */
- return BACKUP_CLUSTER_SIZE_DEFAULT;
- }
-
- return MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
-}
-
BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
BlockDriverState *target, int64_t speed,
MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
BitmapSyncMode bitmap_mode,
bool compress,
const char *filter_node_name,
+ BackupPerf *perf,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
int creation_flags,
BlockCompletionFunc *cb, void *opaque,
JobTxn *txn, Error **errp)
{
- int64_t len;
+ int64_t len, target_len;
BackupBlockJob *job = NULL;
int64_t cluster_size;
- BdrvRequestFlags write_flags;
- BlockDriverState *backup_top = NULL;
+ BlockDriverState *cbw = NULL;
BlockCopyState *bcs = NULL;
assert(bs);
assert(target);
+ GLOBAL_STATE_CODE();
/* QMP interface protects us from these cases */
assert(sync_mode != MIRROR_SYNC_MODE_INCREMENTAL);
return NULL;
}
- if (compress && !block_driver_can_compress(target->drv)) {
+ if (compress && !bdrv_supports_compressed_writes(target)) {
error_setg(errp, "Compression is not supported for this drive %s",
bdrv_get_device_name(target));
return NULL;
return NULL;
}
+ if (perf->max_workers < 1 || perf->max_workers > INT_MAX) {
+ error_setg(errp, "max-workers must be between 1 and %d", INT_MAX);
+ return NULL;
+ }
+
+ if (perf->max_chunk < 0) {
+ error_setg(errp, "max-chunk must be zero (which means no limit) or "
+ "positive");
+ return NULL;
+ }
+
if (sync_bitmap) {
/* If we need to write to this bitmap, check that we can: */
if (bitmap_mode != BITMAP_SYNC_MODE_NEVER &&
len = bdrv_getlength(bs);
if (len < 0) {
- error_setg_errno(errp, -len, "unable to get length for '%s'",
- bdrv_get_device_name(bs));
+ error_setg_errno(errp, -len, "Unable to get length for '%s'",
+ bdrv_get_device_or_node_name(bs));
goto error;
}
- cluster_size = backup_calculate_cluster_size(target, errp);
- if (cluster_size < 0) {
+ target_len = bdrv_getlength(target);
+ if (target_len < 0) {
+ error_setg_errno(errp, -target_len, "Unable to get length for '%s'",
+ bdrv_get_device_or_node_name(bs));
goto error;
}
- /*
- * 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
- */
- write_flags = (bdrv_chain_contains(target, bs) ? BDRV_REQ_SERIALISING : 0) |
- (compress ? BDRV_REQ_WRITE_COMPRESSED : 0),
+ if (target_len != len) {
+ error_setg(errp, "Source and target image have different sizes");
+ goto error;
+ }
+
+ cbw = bdrv_cbw_append(bs, target, filter_node_name, &bcs, errp);
+ if (!cbw) {
+ goto error;
+ }
+
+ cluster_size = block_copy_cluster_size(bcs);
- backup_top = bdrv_backup_top_append(bs, target, filter_node_name,
- cluster_size, write_flags, &bcs, errp);
- if (!backup_top) {
+ if (perf->max_chunk && perf->max_chunk < cluster_size) {
+ error_setg(errp, "Required max-chunk (%" PRIi64 ") is less than backup "
+ "cluster size (%" PRIi64 ")", perf->max_chunk, cluster_size);
goto error;
}
/* job->len is fixed, so we can't allow resize */
- job = block_job_create(job_id, &backup_job_driver, txn, backup_top,
+ job = block_job_create(job_id, &backup_job_driver, txn, cbw,
0, BLK_PERM_ALL,
speed, creation_flags, cb, opaque, errp);
if (!job) {
goto error;
}
- job->backup_top = backup_top;
+ job->cbw = cbw;
job->source_bs = bs;
+ job->target_bs = target;
job->on_source_error = on_source_error;
job->on_target_error = on_target_error;
job->sync_mode = sync_mode;
job->bcs = bcs;
job->cluster_size = cluster_size;
job->len = len;
+ job->perf = *perf;
- block_copy_set_callbacks(bcs, backup_progress_bytes_callback,
- backup_progress_reset_callback, job);
+ block_copy_set_copy_opts(bcs, perf->use_copy_range, compress);
+ block_copy_set_progress_meter(bcs, &job->common.job.progress);
+ block_copy_set_speed(bcs, speed);
- /* Required permissions are already taken by backup-top target */
+ /* Required permissions are taken by copy-before-write filter target */
block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
&error_abort);
if (sync_bitmap) {
bdrv_reclaim_dirty_bitmap(sync_bitmap, NULL);
}
- if (backup_top) {
- bdrv_backup_top_drop(backup_top);
+ if (cbw) {
+ bdrv_cbw_drop(cbw);
}
return NULL;
projects / qemu.git / blobdiff