sheepdog: support user-defined redundancy option

Sheepdog support two kinds of redundancy, full replication and erasure coding.

# create a fully replicated vdi with x copies
 -o redundancy=x (1 <= x <= SD_MAX_COPIES)

# create a erasure coded vdi with x data strips and y parity strips
 -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)

E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme

$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test

Cc: Kevin Wolf <kwolf@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Liu Yuan <namei.unix@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
This commit is contained in:
Liu Yuan 2013-11-07 22:56:38 +08:00 committed by Kevin Wolf
parent c31d482f29
commit b3af018f3b
2 changed files with 74 additions and 1 deletions

View File

@ -91,6 +91,14 @@
#define SD_NR_VDIS (1U << 24)
#define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22)
#define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
/*
* For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and
* (SD_EC_MAX_STRIP - 1) for parity strips
*
* SD_MAX_COPIES is sum of number of data strips and parity strips.
*/
#define SD_EC_MAX_STRIP 16
#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1)
#define SD_INODE_SIZE (sizeof(SheepdogInode))
#define CURRENT_VDI_ID 0
@ -1495,6 +1503,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
hdr.data_length = wlen;
hdr.vdi_size = s->inode.vdi_size;
hdr.copy_policy = s->inode.copy_policy;
hdr.copies = s->inode.nr_copies;
ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
@ -1562,6 +1571,60 @@ out:
return ret;
}
/*
* Sheepdog support two kinds of redundancy, full replication and erasure
* coding.
*
* # create a fully replicated vdi with x copies
* -o redundancy=x (1 <= x <= SD_MAX_COPIES)
*
* # create a erasure coded vdi with x data strips and y parity strips
* -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
*/
static int parse_redundancy(BDRVSheepdogState *s, const char *opt)
{
struct SheepdogInode *inode = &s->inode;
const char *n1, *n2;
long copy, parity;
char p[10];
pstrcpy(p, sizeof(p), opt);
n1 = strtok(p, ":");
n2 = strtok(NULL, ":");
if (!n1) {
return -EINVAL;
}
copy = strtol(n1, NULL, 10);
if (copy > SD_MAX_COPIES || copy < 1) {
return -EINVAL;
}
if (!n2) {
inode->copy_policy = 0;
inode->nr_copies = copy;
return 0;
}
if (copy != 2 && copy != 4 && copy != 8 && copy != 16) {
return -EINVAL;
}
parity = strtol(n2, NULL, 10);
if (parity >= SD_EC_MAX_STRIP || parity < 1) {
return -EINVAL;
}
/*
* 4 bits for parity and 4 bits for data.
* We have to compress upper data bits because it can't represent 16
*/
inode->copy_policy = ((copy / 2) << 4) + parity;
inode->nr_copies = copy + parity;
return 0;
}
static int sd_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
@ -1602,6 +1665,11 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
ret = -EINVAL;
goto out;
}
} else if (!strcmp(options->name, BLOCK_OPT_REDUNDANCY)) {
ret = parse_redundancy(s, options->value.s);
if (ret < 0) {
goto out;
}
}
options++;
}
@ -1644,7 +1712,6 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
bdrv_unref(bs);
}
/* TODO: allow users to specify copy number */
ret = do_sd_create(s, &vid, 0);
if (!prealloc || ret) {
goto out;
@ -2432,6 +2499,11 @@ static QEMUOptionParameter sd_create_options[] = {
.type = OPT_STRING,
.help = "Preallocation mode (allowed values: off, full)"
},
{
.name = BLOCK_OPT_REDUNDANCY,
.type = OPT_STRING,
.help = "Redundancy of the image"
},
{ NULL }
};

View File

@ -53,6 +53,7 @@
#define BLOCK_OPT_COMPAT_LEVEL "compat"
#define BLOCK_OPT_LAZY_REFCOUNTS "lazy_refcounts"
#define BLOCK_OPT_ADAPTER_TYPE "adapter_type"
#define BLOCK_OPT_REDUNDANCY "redundancy"
typedef struct BdrvTrackedRequest {
BlockDriverState *bs;