qcow2: Merge the writing of the COW regions with the guest data

If the guest tries to write data that results on the allocation of a
new cluster, instead of writing the guest data first and then the data
from the COW regions, write everything together using one single I/O
operation.

This can improve the write performance by 25% or more, depending on
several factors such as the media type, the cluster size and the I/O
request size.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

1 files changed, 30 insertions, 10 deletions

diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index 3ac26d6bf7..01f210187c 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -776,6 +776,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
     assert(start->nb_bytes <= UINT_MAX - end->nb_bytes);
     assert(start->nb_bytes + end->nb_bytes <= UINT_MAX - data_bytes);
     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) {
         return 0;
@@ -807,7 +808,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
     /* The part of the buffer where the end region is located */
     end_buffer = start_buffer + buffer_size - end->nb_bytes;
 
-    qemu_iovec_init(&qiov, 1);
+    qemu_iovec_init(&qiov, 2 + (m->data_qiov ? m->data_qiov->niov : 0));
 
     qemu_co_mutex_unlock(&s->lock);
     /* First we read the existing data from both COW regions. We
@@ -842,17 +843,36 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m)
         }
     }
 
-    /* And now we can write everything */
-    qemu_iovec_reset(&qiov);
-    qemu_iovec_add(&qiov, start_buffer, start->nb_bytes);
-    ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov);
-    if (ret < 0) {
-        goto fail;
+    /* And now we can write everything. If we have the guest data we
+     * can write everything in one single operation */
+    if (m->data_qiov) {
+        qemu_iovec_reset(&qiov);
+        if (start->nb_bytes) {
+            qemu_iovec_add(&qiov, start_buffer, start->nb_bytes);
+        }
+        qemu_iovec_concat(&qiov, m->data_qiov, 0, data_bytes);
+        if (end->nb_bytes) {
+            qemu_iovec_add(&qiov, end_buffer, end->nb_bytes);
+        }
+        /* NOTE: we have a write_aio blkdebug event here followed by
+         * a cow_write one in do_perform_cow_write(), but there's only
+         * one single I/O operation */
+        BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+        ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov);
+    } else {
+        /* If there's no guest data then write both COW regions separately */
+        qemu_iovec_reset(&qiov);
+        qemu_iovec_add(&qiov, start_buffer, start->nb_bytes);
+        ret = do_perform_cow_write(bs, m->alloc_offset, start->offset, &qiov);
+        if (ret < 0) {
+            goto fail;
+        }
+
+        qemu_iovec_reset(&qiov);
+        qemu_iovec_add(&qiov, end_buffer, end->nb_bytes);
+        ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, &qiov);
     }
 
-    qemu_iovec_reset(&qiov);
-    qemu_iovec_add(&qiov, end_buffer, end->nb_bytes);
-    ret = do_perform_cow_write(bs, m->alloc_offset, end->offset, &qiov);
 fail:
     qemu_co_mutex_lock(&s->lock);