Statistics
| Branch: | Revision:

root / block @ 6f5f060b

Name Size
blkdebug.c 12.8 kB
bochs.c 6.6 kB
cloop.c 4.9 kB
cow.c 8.6 kB
curl.c 14.8 kB
dmg.c 8.3 kB
nbd.c 5.2 kB
parallels.c 4.4 kB
qcow.c 29.9 kB
qcow2-cluster.c 27.3 kB
qcow2-refcount.c 39.2 kB
qcow2-snapshot.c 12.4 kB
qcow2.c 41.1 kB
qcow2.h 6.9 kB
raw-posix-aio.h 1.3 kB
raw-posix.c 36.3 kB
raw-win32.c 11.2 kB
raw.c 3.7 kB
sheepdog.c 51.6 kB
vdi.c 29.2 kB
vmdk.c 25.4 kB
vpc.c 17.9 kB
vvfat.c 80.7 kB

Latest revisions

# Date Author Comment
6f5f060b 09/21/2010 04:39 pm Kevin Wolf

qcow2: Avoid bounce buffers for AIO write requests

qcow2 used to use bounce buffers for any AIO requests. This does not only imply
unnecessary copying, but also unbounded allocations which should be avoided.

This patch removes bounce buffers from the normal AIO write path. Encrypted...
9217e26f 09/21/2010 04:39 pm Kevin Wolf

vvfat: Fix double free for opening the image rw

Allocation and deallocation of bs->opaque is not in the control of a
block driver. Therefore it should not set bs->opaque to a data structure
used by another bs, or closing the image will lead to a double free....
a655211a 09/21/2010 04:39 pm Kevin Wolf

vvfat: Use cache=unsafe

The qcow file used for write support in vvfat is a temporary file,
so we can use cache=unsafe there. Without this, write support is just
too slow to be of any use.

Signed-off-by: Kevin Wolf <>
581b9e29 09/21/2010 04:39 pm Christoph Hellwig

raw-posix: handle > 512 byte alignment correctly

Replace the hardcoded handling of 512 byte alignment with bs->buffer_alignment
to handle larger sector size devices correctly.

Note that we can not rely on it to be initialize in bdrv_open, so deal
with the worst case there....
c2e2872b 09/21/2010 04:39 pm Laurent Vivier

nbd: correctly manage default port

block/nbd.c: use default port number when none is specified
qemu-nbd.c: use IANA-assigned port number: 10809

Signed-off-by: Laurent Vivier <>
Signed-off-by: Kevin Wolf <>
c01828fb 09/21/2010 04:39 pm Kevin Wolf

qcow2: Move sync out of write_refcount_block_entries

Signed-off-by: Kevin Wolf <>
1c4c2814 09/21/2010 04:39 pm Kevin Wolf

qcow2: Move sync out of update_refcount

Note that the flush is omitted intentionally in qcow2_free_clusters. If
anything, we can leak clusters here if we lose the writes.

Signed-off-by: Kevin Wolf <>
29216ed1 09/21/2010 04:39 pm Kevin Wolf

qcow2: Move sync out of qcow2_alloc_clusters

Signed-off-by: Kevin Wolf <>
9f8e668e 09/21/2010 04:39 pm Kevin Wolf

qcow2: Get rid of additional sync on COW

We always have a sync for the refcount update when a new cluster is
allocated. If we move this past the COW, we can save an additional sync.

Signed-off-by: Kevin Wolf <>
bd28f835 09/21/2010 04:39 pm Kevin Wolf

qcow2: Avoid bounce buffers for AIO read requests

qcow2 used to use bounce buffers for any AIO requests. This does not only imply
unnecessary copying, but also unbounded allocations which should be avoided.

This patch removes bounce buffers from the normal AIO read path, and constrains...

View revisions

Also available in: Atom