this patch introduces a new flag to indicate that we are going to sequentially
read from a file and do not plan to reread/reuse the data after it has been
read.
The current use of this flag is to open the source(s) of a qemu-img convert
process. If a protocol from block/raw-posix.c is used posix_fadvise is utilized
to advise to the kernel that we are going to read sequentially from the
file and a POSIX_FADV_DONTNEED advise is issued after each write to indicate
that there is no advantage keeping the blocks in the buffers. While the
first seems to offer a slight performance benefit the latter option avoids
that older data is swapped out to have the data unnecessarily buffered.
Signed-off-by: Peter Lieven <p...@kamp.de>
---
block/raw-posix.c | 14 ++++++++++++++
include/block/block.h | 1 +
qemu-img.c | 3 ++-
3 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/block/raw-posix.c b/block/raw-posix.c
index 161ea14..fa6d9d2 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -433,6 +433,13 @@ static int raw_open_common(BlockDriverState *bs, QDict
*options,
}
#endif
+#ifdef POSIX_FADV_SEQUENTIAL
+ if (bs->open_flags & BDRV_O_SEQUENTIAL &&
+ !(bs->open_flags & BDRV_O_NOCACHE)) {
+ posix_fadvise(s->fd, 0, 0, POSIX_FADV_SEQUENTIAL);
+ }
+#endif
+
ret = 0;
fail:
qemu_opts_del(opts);
@@ -902,6 +909,13 @@ static int aio_worker(void *arg)
ret = aiocb->aio_nbytes;
}
if (ret == aiocb->aio_nbytes) {
+#ifdef POSIX_FADV_DONTNEED
+ if (aiocb->bs->open_flags & BDRV_O_SEQUENTIAL &&
+ !(aiocb->bs->open_flags & BDRV_O_NOCACHE)) {
+ posix_fadvise(aiocb->aio_fildes, aiocb->aio_offset,
+ aiocb->aio_nbytes, POSIX_FADV_DONTNEED);
+ }
+#endif
ret = 0;
} else if (ret >= 0 && ret < aiocb->aio_nbytes) {
ret = -EINVAL;
diff --git a/include/block/block.h b/include/block/block.h
index 780f48b..502982f 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -105,6 +105,7 @@ typedef enum {
#define BDRV_O_PROTOCOL 0x8000 /* if no block driver is explicitly given:
select an appropriate protocol driver,
ignoring the format layer */
+#define BDRV_O_SEQUENTIAL 0x10000 /* open device for sequential read/write */
#define BDRV_O_CACHE_MASK (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
diff --git a/qemu-img.c b/qemu-img.c
index 78fc868..e7a5721 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -1298,7 +1298,8 @@ static int img_convert(int argc, char **argv)
total_sectors = 0;
for (bs_i = 0; bs_i < bs_n; bs_i++) {
- bs[bs_i] = bdrv_new_open(argv[optind + bs_i], fmt, BDRV_O_FLAGS, true,
+ bs[bs_i] = bdrv_new_open(argv[optind + bs_i], fmt,
+ BDRV_O_FLAGS | BDRV_O_SEQUENTIAL, true,
quiet);
if (!bs[bs_i]) {
error_report("Could not open '%s'", argv[optind + bs_i]);
--
1.7.9.5
