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

@ -611,4 +611,36 @@ bool bdrv_can_store_new_dirty_bitmap(BlockDriverState *bs, const char *name,
*/
void bdrv_register_buf(BlockDriverState *bs, void *host, size_t size);
void bdrv_unregister_buf(BlockDriverState *bs, void *host);
/**
*
* bdrv_co_copy_range:
*
* Do offloaded copy between two children. If the operation is not implemented
* by the driver, or if the backend storage doesn't support it, a negative
* error code will be returned.
*
* Note: block layer doesn't emulate or fallback to a bounce buffer approach
* because usually the caller shouldn't attempt offloaded copy any more (e.g.
* calling copy_file_range(2)) after the first error, thus it should fall back
* to a read+write path in the caller level.
*
* @src: Source child to copy data from
* @src_offset: offset in @src image to read data
* @dst: Destination child to copy data to
* @dst_offset: offset in @dst image to write data
* @bytes: number of bytes to copy
* @flags: request flags. Must be one of:
* 0 - actually read data from src;
* BDRV_REQ_ZERO_WRITE - treat the @src range as zero data and do zero
* write on @dst as if bdrv_co_pwrite_zeroes is
* called. Used to simplify caller code, or
* during BlockDriver.bdrv_co_copy_range_from()
* recursion.
*
* Returns: 0 if succeeded; negative error code if failed.
**/
int coroutine_fn bdrv_co_copy_range(BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
uint64_t bytes, BdrvRequestFlags flags);
#endif

View file

@ -204,6 +204,37 @@ struct BlockDriver {
int coroutine_fn (*bdrv_co_pdiscard)(BlockDriverState *bs,
int64_t offset, int bytes);
/* Map [offset, offset + nbytes) range onto a child of @bs to copy from,
* and invoke bdrv_co_copy_range_from(child, ...), or invoke
* bdrv_co_copy_range_to() if @bs is the leaf child to copy data from.
*
* See the comment of bdrv_co_copy_range for the parameter and return value
* semantics.
*/
int coroutine_fn (*bdrv_co_copy_range_from)(BlockDriverState *bs,
BdrvChild *src,
uint64_t offset,
BdrvChild *dst,
uint64_t dst_offset,
uint64_t bytes,
BdrvRequestFlags flags);
/* Map [offset, offset + nbytes) range onto a child of bs to copy data to,
* and invoke bdrv_co_copy_range_to(child, src, ...), or perform the copy
* operation if @bs is the leaf and @src has the same BlockDriver. Return
* -ENOTSUP if @bs is the leaf but @src has a different BlockDriver.
*
* See the comment of bdrv_co_copy_range for the parameter and return value
* semantics.
*/
int coroutine_fn (*bdrv_co_copy_range_to)(BlockDriverState *bs,
BdrvChild *src,
uint64_t src_offset,
BdrvChild *dst,
uint64_t dst_offset,
uint64_t bytes,
BdrvRequestFlags flags);
/*
* Building block for bdrv_block_status[_above] and
* bdrv_is_allocated[_above]. The driver should answer only
@ -1102,4 +1133,11 @@ void bdrv_dec_in_flight(BlockDriverState *bs);
void blockdev_close_all_bdrv_states(void);
int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
uint64_t bytes, BdrvRequestFlags flags);
int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
uint64_t bytes, BdrvRequestFlags flags);
#endif /* BLOCK_INT_H */

View file

@ -25,9 +25,15 @@
#define QEMU_AIO_FLUSH 0x0008
#define QEMU_AIO_DISCARD 0x0010
#define QEMU_AIO_WRITE_ZEROES 0x0020
#define QEMU_AIO_COPY_RANGE 0x0040
#define QEMU_AIO_TYPE_MASK \
(QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
QEMU_AIO_DISCARD|QEMU_AIO_WRITE_ZEROES)
(QEMU_AIO_READ | \
QEMU_AIO_WRITE | \
QEMU_AIO_IOCTL | \
QEMU_AIO_FLUSH | \
QEMU_AIO_DISCARD | \
QEMU_AIO_WRITE_ZEROES | \
QEMU_AIO_COPY_RANGE)
/* AIO flags */
#define QEMU_AIO_MISALIGNED 0x1000

View file

@ -311,4 +311,8 @@
#define MMC_PROFILE_HDDVD_RW_DL 0x005A
#define MMC_PROFILE_INVALID 0xFFFF
#define XCOPY_DESC_OFFSET 16
#define IDENT_DESCR_TGT_DESCR_SIZE 32
#define XCOPY_BLK2BLK_SEG_DESC_SIZE 28
#endif

View file

@ -232,4 +232,8 @@ void blk_set_force_allow_inactivate(BlockBackend *blk);
void blk_register_buf(BlockBackend *blk, void *host, size_t size);
void blk_unregister_buf(BlockBackend *blk, void *host);
int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
BlockBackend *blk_out, int64_t off_out,
int bytes, BdrvRequestFlags flags);
#endif