[sheepdog] [PATCH v2 03/11] sheep: introduce generational reference counting for object reclaim

[Kai Zhang]

MORITA Kazutaka <morita.kazutaka at gmail.com> writes:

> From: MORITA Kazutaka <morita.kazutaka at lab.ntt.co.jp>
>
> Generational reference counting is an algorithm to reclaim data
> efficiently without race conditions on distributed system.  This
> extends vdi objects structure to store generational reference counts,
> and increments the counts when creating snapshots.
>
> Signed-off-by: MORITA Kazutaka <morita.kazutaka at lab.ntt.co.jp>
> ---
>  include/sheepdog_proto.h |    9 +++++++--
>  sheep/vdi.c              |    8 +++++++-
>  2 files changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/include/sheepdog_proto.h b/include/sheepdog_proto.h
> index beef0a6..bb0f253 100644
> --- a/include/sheepdog_proto.h
> +++ b/include/sheepdog_proto.h
> @@ -101,8 +101,7 @@
>  #define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
>
>  #define SD_INODE_SIZE (sizeof(struct sd_inode))
> -#define SD_INODE_HEADER_SIZE (sizeof(struct sd_inode) - \
> -			      sizeof(uint32_t) * MAX_DATA_OBJS)
> +#define SD_INODE_HEADER_SIZE offsetof(struct sd_inode, data_vdi_id)
>  #define SD_ATTR_OBJ_SIZE (sizeof(struct sheepdog_vdi_attr))
>  #define CURRENT_VDI_ID 0
>
> @@ -193,6 +192,11 @@ struct sd_rsp {
>	};
>  };
>
> +struct generation_reference {
> +	int32_t generation;
> +	int32_t count;
> +};
> +
>  struct sd_inode {
>	char name[SD_MAX_VDI_LEN];
>	char tag[SD_MAX_VDI_TAG_LEN];
> @@ -209,6 +213,7 @@ struct sd_inode {
>	uint32_t parent_vdi_id;
>	uint32_t child_vdi_id[MAX_CHILDREN];
>	uint32_t data_vdi_id[MAX_DATA_OBJS];
> +	struct generation_reference data_ref[MAX_DATA_OBJS];
>  };
>

Does that mean it will incur an incompatable change?
Does we need to clean up all data before we upgrade to a new version?

>  struct sheepdog_vdi_attr {
> diff --git a/sheep/vdi.c b/sheep/vdi.c
> index 096244a..988145d 100644
> --- a/sheep/vdi.c
> +++ b/sheep/vdi.c
> @@ -291,6 +291,12 @@ static int create_vdi_obj(struct vdi_iocb *iocb, uint32_t new_vid,
>			ret = SD_RES_NO_BASE_VDI;
>			goto out;
>		}
> +
> +		for (i = 0; i < ARRAY_SIZE(base->data_ref); i++) {
> +			base->data_ref[i].count++;
> +			new->data_ref[i].generation =
> +				base->data_ref[i].generation + 1;
> +		}
>	}
>
>	if (iocb->create_snapshot && cur_vid != iocb->base_vid) {
> @@ -305,7 +311,7 @@ static int create_vdi_obj(struct vdi_iocb *iocb, uint32_t new_vid,
>
>	if (iocb->base_vid) {
>		ret = write_object(vid_to_vdi_oid(iocb->base_vid), (char *)base,
> -				   SD_INODE_HEADER_SIZE, 0, false);
> +				   SD_INODE_SIZE, 0, false);
>		if (ret != 0) {
>			sd_printf(SDOG_ERR, "failed");
>			ret = SD_RES_BASE_VDI_WRITE;
> --
> 1.7.9.5