Re: [Qemu-devel] [PATCH v5] block:add-cow file format

[Marcelo Tosatti <mtosatti@redhat.com>]

On Tue, Nov 15, 2011 at 01:28:51PM +0800, Dong Xu Wang wrote:
> From: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
> 
> Provide a new file format: add-cow. The usage can be found in add-cow.txt of
> this patch.
> 
> Signed-off-by: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
> ---
>  Makefile.objs          |    1 +
>  block.c                |    2 +-
>  block.h                |    1 +
>  block/add-cow.c        |  417 ++++++++++++++++++++++++++++++++++++++++++++++++
>  block_int.h            |    1 +
>  docs/specs/add-cow.txt |   57 +++++++
>  6 files changed, 478 insertions(+), 1 deletions(-)
>  create mode 100644 block/add-cow.c
>  create mode 100644 docs/specs/add-cow.txt
> 
> diff --git a/Makefile.objs b/Makefile.objs
> index d7a6539..ad99243 100644
> --- a/Makefile.objs
> +++ b/Makefile.objs
> @@ -31,6 +31,7 @@ block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
>  
>  block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
>  block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
> +block-nested-y += add-cow.o
>  block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
>  block-nested-y += qed-check.o
>  block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
> diff --git a/block.c b/block.c
> index 86910b0..a2be27b 100644
> --- a/block.c
> +++ b/block.c
> @@ -106,7 +106,7 @@ int is_windows_drive(const char *filename)
>  #endif
>  
>  /* check if the path starts with "<protocol>:" */
> -static int path_has_protocol(const char *path)
> +int path_has_protocol(const char *path)
>  {
>  #ifdef _WIN32
>      if (is_windows_drive(path) ||
> diff --git a/block.h b/block.h
> index 051a25d..836284f 100644
> --- a/block.h
> +++ b/block.h
> @@ -276,6 +276,7 @@ char *bdrv_snapshot_dump(char *buf, int buf_size, QEMUSnapshotInfo *sn);
>  
>  char *get_human_readable_size(char *buf, int buf_size, int64_t size);
>  int path_is_absolute(const char *path);
> +int path_has_protocol(const char *path);
>  void path_combine(char *dest, int dest_size,
>                    const char *base_path,
>                    const char *filename);
> diff --git a/block/add-cow.c b/block/add-cow.c
> new file mode 100644
> index 0000000..54d30a9
> --- /dev/null
> +++ b/block/add-cow.c
> @@ -0,0 +1,417 @@
> +#include "qemu-common.h"
> +#include "block_int.h"
> +#include "module.h"
> +
> +#define ADD_COW_MAGIC       (((uint64_t)'A' << 56) | ((uint64_t)'D' << 48) | \
> +                            ((uint64_t)'D' << 40) | ((uint64_t)'_' << 32) | \
> +                            ((uint64_t)'C' << 24) | ((uint64_t)'O' << 16) | \
> +                            ((uint64_t)'W' << 8) | 0xFF)
> +#define ADD_COW_VERSION     1
> +#define ADD_COW_FILE_LEN    1024
> +
> +typedef struct AddCowHeader {
> +    uint64_t        magic;
> +    uint32_t        version;
> +    char            backing_file[ADD_COW_FILE_LEN];
> +    char            image_file[ADD_COW_FILE_LEN];
> +    uint64_t        size;
> +} QEMU_PACKED AddCowHeader;
> +
> +typedef struct BDRVAddCowState {
> +    char                image_file[ADD_COW_FILE_LEN];
> +    BlockDriverState    *image_hd;
> +    uint8_t             *bitmap;
> +    uint64_t            bitmap_size;
> +    CoMutex             lock;
> +} BDRVAddCowState;
> +
> +static int add_cow_probe(const uint8_t *buf, int buf_size, const char *filename)
> +{
> +    const AddCowHeader *header = (const void *)buf;
> +
> +    if (be64_to_cpu(header->magic) == ADD_COW_MAGIC &&
> +        be32_to_cpu(header->version) == ADD_COW_VERSION) {
> +        return 100;
> +    } else {
> +        return 0;
> +    }
> +}
> +
> +static int add_cow_open(BlockDriverState *bs, int flags)
> +{
> +    AddCowHeader    header;
> +    int64_t         size;
> +    char            image_filename[ADD_COW_FILE_LEN];
> +    int             image_flags;
> +    BlockDriver     *image_drv = NULL;
> +    int             ret;
> +    BDRVAddCowState *state = (BDRVAddCowState *)(bs->opaque);
> +
> +    ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
> +    if (ret != sizeof(header)) {
> +        goto fail;
> +    }
> +
> +    if (be64_to_cpu(header.magic) != ADD_COW_MAGIC ||
> +        be32_to_cpu(header.version) != ADD_COW_VERSION) {
> +        ret = -EINVAL;
> +        goto fail;
> +    }
> +
> +    size = be64_to_cpu(header.size);
> +    bs->total_sectors = size / BDRV_SECTOR_SIZE;
> +
> +    QEMU_BUILD_BUG_ON(sizeof(state->image_file) != sizeof(header.image_file));
> +    pstrcpy(bs->backing_file, sizeof(bs->backing_file),
> +            header.backing_file);
> +    pstrcpy(state->image_file, sizeof(state->image_file),
> +            header.image_file);
> +
> +    state->bitmap_size = ((bs->total_sectors + 7) >> 3);
> +    state->bitmap = g_malloc0(state->bitmap_size);
> +
> +    ret = bdrv_pread(bs->file, sizeof(header), state->bitmap,
> +            state->bitmap_size);
> +    if (ret != state->bitmap_size) {
> +        goto fail;
> +    }

Reading the entire bitmap in memory is not acceptable, it may be huge.
Better mmap it and use msync(MS_SYNC) when writing it back. This way the
host can free memory easily upon pressure.

> +   /* If there is a image_file, must be together with backing_file */
> +    if (state->image_file[0] != '\0') {
> +        state->image_hd = bdrv_new("");
> +
> +        if (path_has_protocol(state->image_file)) {
> +            pstrcpy(image_filename, sizeof(image_filename),
> +                    state->image_file);
> +        } else {
> +            path_combine(image_filename, sizeof(image_filename),
> +                         bs->filename, state->image_file);
> +        }
> +
> +        image_drv = bdrv_find_format("raw");
> +        image_flags =
> +             (flags & (~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING))) | BDRV_O_RDWR;

Why are you modifying flags here?