qcow2: skip writing zero buffers to empty COW areas

If COW areas of the newly allocated clusters are zeroes on the backing
image, efficient bdrv_write_zeroes(flags=BDRV_REQ_NO_FALLBACK) can be
used on the whole cluster instead of writing explicit zero buffers later
in perform_cow().

iotest 060:
write to the discarded cluster does not trigger COW anymore.
Use a backing image instead.

Signed-off-by: Anton Nefedov <anton.nefedov@virtuozzo.com>
Message-id: 20190516142749.81019-2-anton.nefedov@virtuozzo.com
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Alberto Garcia <berto@igalia.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
This commit is contained in:
Anton Nefedov 2019-05-16 17:27:49 +03:00 committed by Max Reitz
parent 330c729571
commit c8bb23cbdb
7 changed files with 106 additions and 4 deletions

View File

@ -831,7 +831,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
assert(start->offset + start->nb_bytes <= end->offset); assert(start->offset + start->nb_bytes <= end->offset);
assert(!m->data_qiov || m->data_qiov->size == data_bytes); assert(!m->data_qiov || m->data_qiov->size == data_bytes);
if (start->nb_bytes == 0 && end->nb_bytes == 0) { if ((start->nb_bytes == 0 && end->nb_bytes == 0) || m->skip_cow) {
return 0; return 0;
} }

View File

@ -2103,6 +2103,11 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
continue; continue;
} }
/* If COW regions are handled already, skip this too */
if (m->skip_cow) {
continue;
}
/* The data (middle) region must be immediately after the /* The data (middle) region must be immediately after the
* start region */ * start region */
if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) { if (l2meta_cow_start(m) + m->cow_start.nb_bytes != offset) {
@ -2128,6 +2133,80 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
return false; return false;
} }
static bool is_unallocated(BlockDriverState *bs, int64_t offset, int64_t bytes)
{
int64_t nr;
return !bytes ||
(!bdrv_is_allocated_above(bs, NULL, offset, bytes, &nr) && nr == bytes);
}
static bool is_zero_cow(BlockDriverState *bs, QCowL2Meta *m)
{
/*
* This check is designed for optimization shortcut so it must be
* efficient.
* Instead of is_zero(), use is_unallocated() as it is faster (but not
* as accurate and can result in false negatives).
*/
return is_unallocated(bs, m->offset + m->cow_start.offset,
m->cow_start.nb_bytes) &&
is_unallocated(bs, m->offset + m->cow_end.offset,
m->cow_end.nb_bytes);
}
static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta)
{
BDRVQcow2State *s = bs->opaque;
QCowL2Meta *m;
if (!(s->data_file->bs->supported_zero_flags & BDRV_REQ_NO_FALLBACK)) {
return 0;
}
if (bs->encrypted) {
return 0;
}
for (m = l2meta; m != NULL; m = m->next) {
int ret;
if (!m->cow_start.nb_bytes && !m->cow_end.nb_bytes) {
continue;
}
if (!is_zero_cow(bs, m)) {
continue;
}
/*
* instead of writing zero COW buffers,
* efficiently zero out the whole clusters
*/
ret = qcow2_pre_write_overlap_check(bs, 0, m->alloc_offset,
m->nb_clusters * s->cluster_size,
true);
if (ret < 0) {
return ret;
}
BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_SPACE);
ret = bdrv_co_pwrite_zeroes(s->data_file, m->alloc_offset,
m->nb_clusters * s->cluster_size,
BDRV_REQ_NO_FALLBACK);
if (ret < 0) {
if (ret != -ENOTSUP && ret != -EAGAIN) {
return ret;
}
continue;
}
trace_qcow2_skip_cow(qemu_coroutine_self(), m->offset, m->nb_clusters);
m->skip_cow = true;
}
return 0;
}
static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, uint64_t bytes, QEMUIOVector *qiov,
int flags) int flags)
@ -2207,6 +2286,12 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes); qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes);
} }
/* Try to efficiently initialize the physical space with zeroes */
ret = handle_alloc_space(bs, l2meta);
if (ret < 0) {
goto out_unlocked;
}
/* If we need to do COW, check if it's possible to merge the /* If we need to do COW, check if it's possible to merge the
* writing of the guest data together with that of the COW regions. * writing of the guest data together with that of the COW regions.
* If it's not possible (or not necessary) then write the * If it's not possible (or not necessary) then write the

View File

@ -405,6 +405,12 @@ typedef struct QCowL2Meta
*/ */
Qcow2COWRegion cow_end; Qcow2COWRegion cow_end;
/*
* Indicates that COW regions are already handled and do not require
* any more processing.
*/
bool skip_cow;
/** /**
* The I/O vector with the data from the actual guest write request. * The I/O vector with the data from the actual guest write request.
* If non-NULL, this is meant to be merged together with the data * If non-NULL, this is meant to be merged together with the data

View File

@ -68,6 +68,7 @@ qcow2_writev_done_part(void *co, int cur_bytes) "co %p cur_bytes %d"
qcow2_writev_data(void *co, uint64_t offset) "co %p offset 0x%" PRIx64 qcow2_writev_data(void *co, uint64_t offset) "co %p offset 0x%" PRIx64
qcow2_pwrite_zeroes_start_req(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d" qcow2_pwrite_zeroes_start_req(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d"
qcow2_pwrite_zeroes(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d" qcow2_pwrite_zeroes(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d"
qcow2_skip_cow(void *co, uint64_t offset, int nb_clusters) "co %p offset 0x%" PRIx64 " nb_clusters %d"
# qcow2-cluster.c # qcow2-cluster.c
qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d" qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"

View File

@ -3215,6 +3215,8 @@
# #
# @cor_write: a write due to copy-on-read (since 2.11) # @cor_write: a write due to copy-on-read (since 2.11)
# #
# @cluster_alloc_space: an allocation of file space for a cluster (since 4.1)
#
# Since: 2.9 # Since: 2.9
## ##
{ 'enum': 'BlkdebugEvent', 'prefix': 'BLKDBG', { 'enum': 'BlkdebugEvent', 'prefix': 'BLKDBG',
@ -3233,7 +3235,7 @@
'pwritev_rmw_tail', 'pwritev_rmw_after_tail', 'pwritev', 'pwritev_rmw_tail', 'pwritev_rmw_after_tail', 'pwritev',
'pwritev_zero', 'pwritev_done', 'empty_image_prepare', 'pwritev_zero', 'pwritev_done', 'empty_image_prepare',
'l1_shrink_write_table', 'l1_shrink_free_l2_clusters', 'l1_shrink_write_table', 'l1_shrink_free_l2_clusters',
'cor_write'] } 'cor_write', 'cluster_alloc_space'] }
## ##
# @BlkdebugInjectErrorOptions: # @BlkdebugInjectErrorOptions:

View File

@ -150,10 +150,15 @@ $QEMU_IO -c "$OPEN_RO" -c "read -P 1 0 512" | _filter_qemu_io
echo echo
echo "=== Testing overlap while COW is in flight ===" echo "=== Testing overlap while COW is in flight ==="
echo echo
BACKING_IMG=$TEST_IMG.base
TEST_IMG=$BACKING_IMG _make_test_img 1G
$QEMU_IO -c 'write 0k 64k' "$BACKING_IMG" | _filter_qemu_io
# compat=0.10 is required in order to make the following discard actually # compat=0.10 is required in order to make the following discard actually
# unallocate the sector rather than make it a zero sector - we want COW, after # unallocate the sector rather than make it a zero sector - we want COW, after
# all. # all.
IMGOPTS='compat=0.10' _make_test_img 1G IMGOPTS='compat=0.10' _make_test_img -b "$BACKING_IMG" 1G
# Write two clusters, the second one enforces creation of an L2 table after # Write two clusters, the second one enforces creation of an L2 table after
# the first data cluster. # the first data cluster.
$QEMU_IO -c 'write 0k 64k' -c 'write 512M 64k' "$TEST_IMG" | _filter_qemu_io $QEMU_IO -c 'write 0k 64k' -c 'write 512M 64k' "$TEST_IMG" | _filter_qemu_io

View File

@ -97,7 +97,10 @@ read 512/512 bytes at offset 0
=== Testing overlap while COW is in flight === === Testing overlap while COW is in flight ===
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=1073741824
wrote 65536/65536 bytes at offset 0
64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 backing_file=TEST_DIR/t.IMGFMT.base
wrote 65536/65536 bytes at offset 0 wrote 65536/65536 bytes at offset 0
64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
wrote 65536/65536 bytes at offset 536870912 wrote 65536/65536 bytes at offset 536870912