Re: [Qemu-block] [Qemu-devel] [PATCH] block/fleecing-filter: new filter driver for fleecing

[John Snow]

On 06/21/2018 11:48 AM, Vladimir Sementsov-Ogievskiy wrote:
> We need to synchronize backup job with reading from fleecing image
> like it was done in block/replication.c.
> 
> Otherwise, the following situation is theoretically possible:
> 
> 1. client start reading
> 2. client understand, that there is no corresponding cluster in
>    fleecing image
> 3. client is going to read from backing file (i.e. active image)
> 4. guest writes to active image
> 5. this write is stopped by backup(sync=none) and cluster is copied to
>    fleecing image
> 6. guest write continues...
> 7. and client reads _new_ (or partly new) date from active image
> 
> So, this fleecing-filter should be above fleecing image, the whole
> picture of fleecing looks like this:
> 
>     +-------+           +------------+
>     |       |           |            |
>     | guest |           | NBD client +<------+
>     |       |           |            |       |
>     ++-----++           +------------+       |only read
>      |     ^                                 |
>      | IO  |                                 |
>      v     |                           +-----+------+
>     ++-----+---------+                 |            |
>     |                |                 |  internal  |
>     |  active image  +----+            | NBD server |
>     |                |    |            |            |
>     +-+--------------+    |backup      +-+----------+
>       ^                   |sync=none     ^
>       |backing            |              |only read
>       |                   |              |
>     +-+--------------+    |       +------+----------+
>     |                |    |       |                 |
>     | fleecing image +<---+       | fleecing filter |
>     |                |            |                 |
>     +--------+-------+            +-----+-----------+
>              ^                          |
>              |                          |
>              +--------------------------+
>                        file
> 
> Signed-off-by: Vladimir Sementsov-Ogievskiy <address@hidden>
> ---
>  qapi/block-core.json    |  9 ++++---
>  block/fleecing-filter.c | 72 
> +++++++++++++++++++++++++++++++++++++++++++++++++
>  block/Makefile.objs     |  1 +
>  3 files changed, 79 insertions(+), 3 deletions(-)
>  create mode 100644 block/fleecing-filter.c
> 
> diff --git a/qapi/block-core.json b/qapi/block-core.json
> index dfaa050651..b21bc3b693 100644
> --- a/qapi/block-core.json
> +++ b/qapi/block-core.json
> @@ -2543,7 +2543,8 @@
>              'host_device', 'http', 'https', 'iscsi', 'luks', 'nbd', 'nfs',
>              'null-aio', 'null-co', 'nvme', 'parallels', 'qcow', 'qcow2', 
> 'qed',
>              'quorum', 'raw', 'rbd', 'replication', 'sheepdog', 'ssh',
> -            'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
> +            'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs',
> +            'fleecing-filter' ] }
>  
>  ##
>  # @BlockdevOptionsFile:
> @@ -3607,7 +3608,8 @@
>        'vmdk':       'BlockdevOptionsGenericCOWFormat',
>        'vpc':        'BlockdevOptionsGenericFormat',
>        'vvfat':      'BlockdevOptionsVVFAT',
> -      'vxhs':       'BlockdevOptionsVxHS'
> +      'vxhs':       'BlockdevOptionsVxHS',
> +      'fleecing-filter': 'BlockdevOptionsGenericFormat'
>    } }
>  
>  ##
> @@ -4135,7 +4137,8 @@
>        'vmdk':           'BlockdevCreateNotSupported',
>        'vpc':            'BlockdevCreateOptionsVpc',
>        'vvfat':          'BlockdevCreateNotSupported',
> -      'vxhs':           'BlockdevCreateNotSupported'
> +      'vxhs':           'BlockdevCreateNotSupported',
> +      'fleecing-filter': 'BlockdevCreateNotSupported'
>    } }
>  
>  ##
> diff --git a/block/fleecing-filter.c b/block/fleecing-filter.c
> new file mode 100644
> index 0000000000..60bac9c0b4
> --- /dev/null
> +++ b/block/fleecing-filter.c
> @@ -0,0 +1,72 @@
> +#include "qemu/osdep.h"
> +#include "qemu-common.h"
> +#include "block/blockjob.h"
> +#include "block/block_int.h"
> +#include "block/block_backup.h"
> +
> +static int64_t fleecing_getlength(BlockDriverState *bs)
> +{
> +    return bdrv_getlength(bs->file->bs);
> +}
> +
> +static coroutine_fn int fleecing_co_preadv(BlockDriverState *bs,
> +                                           uint64_t offset, uint64_t bytes,
> +                                           QEMUIOVector *qiov, int flags)
> +{
> +    int ret;
> +    BlockJob *job = bs->file->bs->backing->bs->job;
> +    CowRequest req;
> +
> +    backup_wait_for_overlapping_requests(job, offset, bytes);
> +    backup_cow_request_begin(&req, job, offset, bytes);
> +
> +    ret = bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
> +
> +    backup_cow_request_end(&req);
> +
> +    return ret;
> +}
> +
> +static coroutine_fn int fleecing_co_pwritev(BlockDriverState *bs,
> +                                            uint64_t offset, uint64_t bytes,
> +                                            QEMUIOVector *qiov, int flags)
> +{
> +    return -EINVAL;
> +}
> +
> +static bool fleecing_recurse_is_first_non_filter(BlockDriverState *bs,
> +                                                 BlockDriverState *candidate)
> +{
> +    return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
> +}
> +
> +static int fleecing_open(BlockDriverState *bs, QDict *options,
> +                         int flags, Error **errp)
> +{
> +    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false,
> +                               errp);
> +
> +    return bs->file ? 0 : -EINVAL;
> +}
> +
> +BlockDriver bdrv_fleecing_filter = {
> +    .format_name = "fleecing-filter",
> +    .protocol_name = "fleecing-filter",
> +    .instance_size = 0,
> +
> +    .bdrv_open = fleecing_open,
> +
> +    .bdrv_getlength = fleecing_getlength,
> +    .bdrv_co_preadv = fleecing_co_preadv,
> +    .bdrv_co_pwritev = fleecing_co_pwritev,
> +
> +    .is_filter = true,
> +    .bdrv_recurse_is_first_non_filter = fleecing_recurse_is_first_non_filter,
> +};
> +
> +static void bdrv_fleecing_init(void)
> +{
> +    bdrv_register(&bdrv_fleecing_filter);
> +}
> +
> +block_init(bdrv_fleecing_init);
> diff --git a/block/Makefile.objs b/block/Makefile.objs
> index 899bfb5e2c..aa0a6dd971 100644
> --- a/block/Makefile.objs
> +++ b/block/Makefile.objs
> @@ -27,6 +27,7 @@ block-obj-y += write-threshold.o
>  block-obj-y += backup.o
>  block-obj-$(CONFIG_REPLICATION) += replication.o
>  block-obj-y += throttle.o copy-on-read.o
> +block-obj-y += fleecing-filter.o
>  
>  block-obj-y += crypto.o
>  
> 

Dropping this one from review queue in favor of the fleecing discussion
on "[Qemu-devel] [PATCH v2 0/3] image fleecing"

--js