Using 16KB bounce buffers creates a significant performance
penalty for I/O to encrypted volumes on storage with high
I/O latency (rotating rust & network drives), because it
triggers lots of fairly small I/O operations.
On tests with rotating rust, and cache=none|directsync,
write speed increased from 2MiB/s to 32MiB/s, on a par
with that achieved by the in-kernel luks driver.
Signed-off-by: Daniel P. Berrange <berra...@redhat.com>
---
block/crypto.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/block/crypto.c b/block/crypto.c
index 58ef6f2f52..207941db9a 100644
--- a/block/crypto.c
+++ b/block/crypto.c
@@ -379,7 +379,7 @@ static void block_crypto_close(BlockDriverState *bs)
}
-#define BLOCK_CRYPTO_MAX_SECTORS 32
+#define BLOCK_CRYPTO_MAX_SECTORS 2048
static coroutine_fn int
block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num,
@@ -396,9 +396,8 @@ block_crypto_co_readv(BlockDriverState *bs, int64_t
sector_num,
qemu_iovec_init(&hd_qiov, qiov->niov);
- /* Bounce buffer so we have a linear mem region for
- * entire sector. XXX optimize so we avoid bounce
- * buffer in case that qiov->niov == 1
+ /* Bounce buffer because we're not permitted to touch
+ * contents of qiov - it points to guest memory.
*/
cipher_data =
qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
@@ -464,9 +463,8 @@ block_crypto_co_writev(BlockDriverState *bs, int64_t
sector_num,
qemu_iovec_init(&hd_qiov, qiov->niov);
- /* Bounce buffer so we have a linear mem region for
- * entire sector. XXX optimize so we avoid bounce
- * buffer in case that qiov->niov == 1
+ /* Bounce buffer because we're not permitted to touch
+ * contents of qiov - it points to guest memory.
*/
cipher_data =
qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
--
2.13.3
