Pull request

* Copy offloading for qemu-img convert (iSCSI, raw, and qcow2)
 
    If the underlying storage supports copy offloading, qemu-img convert will
    use it instead of performing reads and writes.  This avoids data transfers
    and thus frees up storage bandwidth for other purposes.  SCSI EXTENDED COPY
    and Linux copy_file_range(2) are used to implement this optimization.
 
  * Drop spurious "WARNING: I\/O thread spun for 1000 iterations" warning
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJbFSBoAAoJEJykq7OBq3PISpEIAIcMao4/rzinAWXzS+ncK9LO
 6FtRVpgutpHaWX2ayySaz5n2CdR3cNMrpCI7sjY2Kw0lrdkqxPgl5n0SWD+VCl4W
 7+JLz/uF0iUV8X+99e7WGAjZbm9LSlxgn5AQKfrrwyPf0ZfzoYQ5nBMcQ6xjEeQP
 48j2WqJqN9/u8RBD07o11yn0+CE5g56/f12xVjR5ASVodzsAmcZ2OQRMQbM01isU
 1mBekJQkDxJkt5l13Rql8+t+vWz8/9BEW2c/eIDKvoayMqYJpdfKv4DqLloIuHnc
 3RkquA0zUuKtl7xEnEkH/We7fi4QPGW/vyBN7ychS/zKzZFQrXmwqrAuFSw3dKU=
 =vZp+
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

Pull request

 * Copy offloading for qemu-img convert (iSCSI, raw, and qcow2)

   If the underlying storage supports copy offloading, qemu-img convert will
   use it instead of performing reads and writes.  This avoids data transfers
   and thus frees up storage bandwidth for other purposes.  SCSI EXTENDED COPY
   and Linux copy_file_range(2) are used to implement this optimization.

 * Drop spurious "WARNING: I\/O thread spun for 1000 iterations" warning

# gpg: Signature made Mon 04 Jun 2018 12:20:08 BST
# gpg:                using RSA key 9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  main-loop: drop spin_counter
  qemu-img: Convert with copy offloading
  block-backend: Add blk_co_copy_range
  iscsi: Implement copy offloading
  iscsi: Create and use iscsi_co_wait_for_task
  iscsi: Query and save device designator when opening
  file-posix: Implement bdrv_co_copy_range
  qcow2: Implement copy offloading
  raw: Implement copy offloading
  raw: Check byte range uniformly
  block: Introduce API for copy offloading

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2018-06-04 18:34:04 +01:00
commit 0d514fa234
15 changed files with 908 additions and 125 deletions

View file

@ -1761,6 +1761,39 @@ static int coroutine_fn qcow2_co_block_status(BlockDriverState *bs,
return status;
}
static coroutine_fn int qcow2_handle_l2meta(BlockDriverState *bs,
QCowL2Meta **pl2meta,
bool link_l2)
{
int ret = 0;
QCowL2Meta *l2meta = *pl2meta;
while (l2meta != NULL) {
QCowL2Meta *next;
if (!ret && link_l2) {
ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
if (ret) {
goto out;
}
}
/* Take the request off the list of running requests */
if (l2meta->nb_clusters != 0) {
QLIST_REMOVE(l2meta, next_in_flight);
}
qemu_co_queue_restart_all(&l2meta->dependent_requests);
next = l2meta->next;
g_free(l2meta);
l2meta = next;
}
out:
*pl2meta = l2meta;
return ret;
}
static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov,
int flags)
@ -2047,24 +2080,9 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
}
}
while (l2meta != NULL) {
QCowL2Meta *next;
ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
if (ret < 0) {
goto fail;
}
/* Take the request off the list of running requests */
if (l2meta->nb_clusters != 0) {
QLIST_REMOVE(l2meta, next_in_flight);
}
qemu_co_queue_restart_all(&l2meta->dependent_requests);
next = l2meta->next;
g_free(l2meta);
l2meta = next;
ret = qcow2_handle_l2meta(bs, &l2meta, true);
if (ret) {
goto fail;
}
bytes -= cur_bytes;
@ -2075,18 +2093,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
ret = 0;
fail:
while (l2meta != NULL) {
QCowL2Meta *next;
if (l2meta->nb_clusters != 0) {
QLIST_REMOVE(l2meta, next_in_flight);
}
qemu_co_queue_restart_all(&l2meta->dependent_requests);
next = l2meta->next;
g_free(l2meta);
l2meta = next;
}
qcow2_handle_l2meta(bs, &l2meta, false);
qemu_co_mutex_unlock(&s->lock);
@ -3273,6 +3280,166 @@ static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs,
return ret;
}
static int coroutine_fn
qcow2_co_copy_range_from(BlockDriverState *bs,
BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
uint64_t bytes, BdrvRequestFlags flags)
{
BDRVQcow2State *s = bs->opaque;
int ret;
unsigned int cur_bytes; /* number of bytes in current iteration */
BdrvChild *child = NULL;
BdrvRequestFlags cur_flags;
assert(!bs->encrypted);
qemu_co_mutex_lock(&s->lock);
while (bytes != 0) {
uint64_t copy_offset = 0;
/* prepare next request */
cur_bytes = MIN(bytes, INT_MAX);
cur_flags = flags;
ret = qcow2_get_cluster_offset(bs, src_offset, &cur_bytes, &copy_offset);
if (ret < 0) {
goto out;
}
switch (ret) {
case QCOW2_CLUSTER_UNALLOCATED:
if (bs->backing && bs->backing->bs) {
int64_t backing_length = bdrv_getlength(bs->backing->bs);
if (src_offset >= backing_length) {
cur_flags |= BDRV_REQ_ZERO_WRITE;
} else {
child = bs->backing;
cur_bytes = MIN(cur_bytes, backing_length - src_offset);
copy_offset = src_offset;
}
} else {
cur_flags |= BDRV_REQ_ZERO_WRITE;
}
break;
case QCOW2_CLUSTER_ZERO_PLAIN:
case QCOW2_CLUSTER_ZERO_ALLOC:
cur_flags |= BDRV_REQ_ZERO_WRITE;
break;
case QCOW2_CLUSTER_COMPRESSED:
ret = -ENOTSUP;
goto out;
break;
case QCOW2_CLUSTER_NORMAL:
child = bs->file;
copy_offset += offset_into_cluster(s, src_offset);
if ((copy_offset & 511) != 0) {
ret = -EIO;
goto out;
}
break;
default:
abort();
}
qemu_co_mutex_unlock(&s->lock);
ret = bdrv_co_copy_range_from(child,
copy_offset,
dst, dst_offset,
cur_bytes, cur_flags);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
goto out;
}
bytes -= cur_bytes;
src_offset += cur_bytes;
dst_offset += cur_bytes;
}
ret = 0;
out:
qemu_co_mutex_unlock(&s->lock);
return ret;
}
static int coroutine_fn
qcow2_co_copy_range_to(BlockDriverState *bs,
BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
uint64_t bytes, BdrvRequestFlags flags)
{
BDRVQcow2State *s = bs->opaque;
int offset_in_cluster;
int ret;
unsigned int cur_bytes; /* number of sectors in current iteration */
uint64_t cluster_offset;
uint8_t *cluster_data = NULL;
QCowL2Meta *l2meta = NULL;
assert(!bs->encrypted);
s->cluster_cache_offset = -1; /* disable compressed cache */
qemu_co_mutex_lock(&s->lock);
while (bytes != 0) {
l2meta = NULL;
offset_in_cluster = offset_into_cluster(s, dst_offset);
cur_bytes = MIN(bytes, INT_MAX);
/* TODO:
* If src->bs == dst->bs, we could simply copy by incrementing
* the refcnt, without copying user data.
* Or if src->bs == dst->bs->backing->bs, we could copy by discarding. */
ret = qcow2_alloc_cluster_offset(bs, dst_offset, &cur_bytes,
&cluster_offset, &l2meta);
if (ret < 0) {
goto fail;
}
assert((cluster_offset & 511) == 0);
ret = qcow2_pre_write_overlap_check(bs, 0,
cluster_offset + offset_in_cluster, cur_bytes);
if (ret < 0) {
goto fail;
}
qemu_co_mutex_unlock(&s->lock);
ret = bdrv_co_copy_range_to(src, src_offset,
bs->file,
cluster_offset + offset_in_cluster,
cur_bytes, flags);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
goto fail;
}
ret = qcow2_handle_l2meta(bs, &l2meta, true);
if (ret) {
goto fail;
}
bytes -= cur_bytes;
dst_offset += cur_bytes;
}
ret = 0;
fail:
qcow2_handle_l2meta(bs, &l2meta, false);
qemu_co_mutex_unlock(&s->lock);
qemu_vfree(cluster_data);
trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
return ret;
}
static int qcow2_truncate(BlockDriverState *bs, int64_t offset,
PreallocMode prealloc, Error **errp)
{
@ -4521,6 +4688,8 @@ BlockDriver bdrv_qcow2 = {
.bdrv_co_pwrite_zeroes = qcow2_co_pwrite_zeroes,
.bdrv_co_pdiscard = qcow2_co_pdiscard,
.bdrv_co_copy_range_from = qcow2_co_copy_range_from,
.bdrv_co_copy_range_to = qcow2_co_copy_range_to,
.bdrv_truncate = qcow2_truncate,
.bdrv_co_pwritev_compressed = qcow2_co_pwritev_compressed,
.bdrv_make_empty = qcow2_make_empty,