From: Max Reitz <mreitz@redhat.com>
To: qemu-block@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>,
Peter Maydell <peter.maydell@linaro.org>,
qemu-devel@nongnu.org, Max Reitz <mreitz@redhat.com>
Subject: [Qemu-devel] [PULL 19/21] qcow2: skip writing zero buffers to empty COW areas
Date: Tue, 28 May 2019 21:28:45 +0200 [thread overview]
Message-ID: <20190528192847.2730-20-mreitz@redhat.com> (raw)
In-Reply-To: <20190528192847.2730-1-mreitz@redhat.com>
From: Anton Nefedov <anton.nefedov@virtuozzo.com>
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>
---
qapi/block-core.json | 4 +-
block/qcow2.h | 6 +++
block/qcow2-cluster.c | 2 +-
block/qcow2.c | 85 ++++++++++++++++++++++++++++++++++++++
block/trace-events | 1 +
tests/qemu-iotests/060 | 7 +++-
tests/qemu-iotests/060.out | 5 ++-
7 files changed, 106 insertions(+), 4 deletions(-)
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 7ccbfff9d0..3e4042be7f 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -3215,6 +3215,8 @@
#
# @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
##
{ 'enum': 'BlkdebugEvent', 'prefix': 'BLKDBG',
@@ -3233,7 +3235,7 @@
'pwritev_rmw_tail', 'pwritev_rmw_after_tail', 'pwritev',
'pwritev_zero', 'pwritev_done', 'empty_image_prepare',
'l1_shrink_write_table', 'l1_shrink_free_l2_clusters',
- 'cor_write'] }
+ 'cor_write', 'cluster_alloc_space'] }
##
# @BlkdebugInjectErrorOptions:
diff --git a/block/qcow2.h b/block/qcow2.h
index e873ae5d12..567375e56c 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -405,6 +405,12 @@ typedef struct QCowL2Meta
*/
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.
* If non-NULL, this is meant to be merged together with the data
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index 4a929900cf..cf892f37a8 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -831,7 +831,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
assert(start->offset + start->nb_bytes <= end->offset);
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;
}
diff --git a/block/qcow2.c b/block/qcow2.c
index dea765b2f4..f2cb131048 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -2103,6 +2103,11 @@ static bool merge_cow(uint64_t offset, unsigned bytes,
continue;
}
+ /* If COW regions are handled already, skip this too */
+ if (m->skip_cow) {
+ continue;
+ }
+
/* The data (middle) region must be immediately after the
* start region */
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;
}
+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,
uint64_t bytes, QEMUIOVector *qiov,
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);
}
+ /* 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
* writing of the guest data together with that of the COW regions.
* If it's not possible (or not necessary) then write the
diff --git a/block/trace-events b/block/trace-events
index 79ccd8d824..1e0653ce6d 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -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_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_skip_cow(void *co, uint64_t offset, int nb_clusters) "co %p offset 0x%" PRIx64 " nb_clusters %d"
# qcow2-cluster.c
qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"
diff --git a/tests/qemu-iotests/060 b/tests/qemu-iotests/060
index 89e911400c..b91d8321bb 100755
--- a/tests/qemu-iotests/060
+++ b/tests/qemu-iotests/060
@@ -150,10 +150,15 @@ $QEMU_IO -c "$OPEN_RO" -c "read -P 1 0 512" | _filter_qemu_io
echo
echo "=== Testing overlap while COW is in flight ==="
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
# unallocate the sector rather than make it a zero sector - we want COW, after
# 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
# the first data cluster.
$QEMU_IO -c 'write 0k 64k' -c 'write 512M 64k' "$TEST_IMG" | _filter_qemu_io
diff --git a/tests/qemu-iotests/060.out b/tests/qemu-iotests/060.out
index e42bf8c5a9..0f6b0658a1 100644
--- a/tests/qemu-iotests/060.out
+++ b/tests/qemu-iotests/060.out
@@ -97,7 +97,10 @@ read 512/512 bytes at offset 0
=== 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
64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
wrote 65536/65536 bytes at offset 536870912
--
2.21.0
next prev parent reply other threads:[~2019-05-28 19:45 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-28 19:28 [Qemu-devel] [PULL 00/21] Block patches Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 01/21] qcow2.h: add missing include Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 02/21] qcow2: add separate file for threaded data processing functions Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 03/21] qcow2-threads: use thread_pool_submit_co Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 04/21] qcow2-threads: qcow2_co_do_compress: protect queuing by mutex Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 05/21] qcow2-threads: split out generic path Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 06/21] qcow2: qcow2_co_preadv: improve locking Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 07/21] qcow2: bdrv_co_pwritev: move encryption code out of the lock Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 08/21] qcow2: do encryption in threads Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 09/21] block/backup: simplify backup_incremental_init_copy_bitmap Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 10/21] block/backup: move to copy_bitmap with granularity Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 11/21] block/backup: refactor and tolerate unallocated cluster skipping Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 12/21] block/backup: unify different modes code path Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 13/21] block/backup: refactor: split out backup_calculate_cluster_size Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 14/21] block: Use bdrv_unref_child() for all children in bdrv_close() Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 15/21] block: Make bdrv_root_attach_child() unref child_bs on failure Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 16/21] qemu-img: rebase: Reuse parent BlockDriverState Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 17/21] qemu-img: rebase: Reduce reads on in-chain rebase Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 18/21] qemu-img: rebase: Reuse in-chain BlockDriverState Max Reitz
2019-05-28 19:28 ` Max Reitz [this message]
2019-05-28 19:28 ` [Qemu-devel] [PULL 20/21] qcow2-bitmap: initialize bitmap directory alignment Max Reitz
2019-05-28 19:28 ` [Qemu-devel] [PULL 21/21] blockdev: loosen restrictions on drive-backup source node Max Reitz
2019-05-30 11:09 ` [Qemu-devel] [PULL 00/21] Block patches Peter Maydell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190528192847.2730-20-mreitz@redhat.com \
--to=mreitz@redhat.com \
--cc=kwolf@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).