uint32_t data_length;
uint64_t oid;
uint64_t cow_oid;
- uint32_t copies;
- uint32_t rsvd;
+ uint8_t copies;
+ uint8_t copy_policy;
+ uint8_t reserved[6];
uint64_t offset;
} SheepdogObjReq;
uint32_t id;
uint32_t data_length;
uint32_t result;
- uint32_t copies;
+ uint8_t copies;
+ uint8_t copy_policy;
+ uint8_t reserved[2];
uint32_t pad[6];
} SheepdogObjRsp;
uint32_t data_length;
uint64_t vdi_size;
uint32_t vdi_id;
- uint32_t copies;
+ uint8_t copies;
+ uint8_t copy_policy;
+ uint8_t reserved[2];
uint32_t snapid;
uint32_t pad[3];
} SheepdogVdiReq;
return !!inode->snap_ctime;
}
-#undef dprintf
+#undef DPRINTF
#ifdef DEBUG_SDOG
-#define dprintf(fmt, args...) \
+#define DPRINTF(fmt, args...) \
do { \
fprintf(stdout, "%s %d: " fmt, __func__, __LINE__, ##args); \
} while (0)
#else
-#define dprintf(fmt, args...)
+#define DPRINTF(fmt, args...)
#endif
typedef struct SheepdogAIOCB SheepdogAIOCB;
int ret;
ret = qemu_co_send(sockfd, hdr, sizeof(*hdr));
- if (ret < sizeof(*hdr)) {
+ if (ret != sizeof(*hdr)) {
error_report("failed to send a req, %s", strerror(errno));
return ret;
}
ret = qemu_co_send(sockfd, data, *wlen);
- if (ret < *wlen) {
+ if (ret != *wlen) {
error_report("failed to send a req, %s", strerror(errno));
}
qemu_coroutine_enter(co, NULL);
}
-static int have_co_req(void *opaque)
-{
- /* this handler is set only when there is a pending request, so
- * always returns 1. */
- return 1;
-}
-
typedef struct SheepdogReqCo {
int sockfd;
SheepdogReq *hdr;
unsigned int *rlen = srco->rlen;
co = qemu_coroutine_self();
- qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, have_co_req, co);
+ qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, co);
ret = send_co_req(sockfd, hdr, data, wlen);
if (ret < 0) {
goto out;
}
- qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, have_co_req, co);
+ qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, co);
ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
- if (ret < sizeof(*hdr)) {
+ if (ret != sizeof(*hdr)) {
error_report("failed to get a rsp, %s", strerror(errno));
ret = -errno;
goto out;
if (*rlen) {
ret = qemu_co_recv(sockfd, data, *rlen);
- if (ret < *rlen) {
+ if (ret != *rlen) {
error_report("failed to get the data, %s", strerror(errno));
ret = -errno;
goto out;
out:
/* there is at most one request for this sockfd, so it is safe to
* set each handler to NULL. */
- qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL, NULL);
+ qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL);
srco->ret = ret;
srco->finished = true;
/* read a header */
ret = qemu_co_recv(fd, &rsp, sizeof(rsp));
- if (ret < 0) {
+ if (ret != sizeof(rsp)) {
error_report("failed to get the header, %s", strerror(errno));
goto out;
}
case AIOCB_READ_UDATA:
ret = qemu_co_recvv(fd, acb->qiov->iov, acb->qiov->niov,
aio_req->iov_offset, rsp.data_length);
- if (ret < 0) {
+ if (ret != rsp.data_length) {
error_report("failed to get the data, %s", strerror(errno));
goto out;
}
break;
case AIOCB_FLUSH_CACHE:
if (rsp.result == SD_RES_INVALID_PARMS) {
- dprintf("disable cache since the server doesn't support it\n");
+ DPRINTF("disable cache since the server doesn't support it\n");
s->cache_flags = SD_FLAG_CMD_DIRECT;
rsp.result = SD_RES_SUCCESS;
}
qemu_coroutine_enter(s->co_send, NULL);
}
-static int aio_flush_request(void *opaque)
-{
- BDRVSheepdogState *s = opaque;
-
- return !QLIST_EMPTY(&s->inflight_aio_head) ||
- !QLIST_EMPTY(&s->pending_aio_head);
-}
-
/*
* Return a socket discriptor to read/write objects.
*
return fd;
}
- qemu_aio_set_fd_handler(fd, co_read_response, NULL, aio_flush_request, s);
+ qemu_aio_set_fd_handler(fd, co_read_response, NULL, s);
return fd;
}
qemu_co_mutex_lock(&s->lock);
s->co_send = qemu_coroutine_self();
- qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request,
- aio_flush_request, s);
+ qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request, s);
socket_set_cork(s->fd, 1);
/* send a header */
ret = qemu_co_send(s->fd, &hdr, sizeof(hdr));
- if (ret < 0) {
+ if (ret != sizeof(hdr)) {
qemu_co_mutex_unlock(&s->lock);
error_report("failed to send a req, %s", strerror(errno));
return -errno;
if (wlen) {
ret = qemu_co_sendv(s->fd, iov, niov, aio_req->iov_offset, wlen);
- if (ret < 0) {
+ if (ret != wlen) {
qemu_co_mutex_unlock(&s->lock);
error_report("failed to send a data, %s", strerror(errno));
return -errno;
}
socket_set_cork(s->fd, 0);
- qemu_aio_set_fd_handler(s->fd, co_read_response, NULL,
- aio_flush_request, s);
+ qemu_aio_set_fd_handler(s->fd, co_read_response, NULL, s);
qemu_co_mutex_unlock(&s->lock);
return 0;
}
-static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
+static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies,
unsigned int datalen, uint64_t offset,
bool write, bool create, uint32_t cache_flags)
{
}
}
-static int read_object(int fd, char *buf, uint64_t oid, int copies,
+static int read_object(int fd, char *buf, uint64_t oid, uint8_t copies,
unsigned int datalen, uint64_t offset,
uint32_t cache_flags)
{
false, cache_flags);
}
-static int write_object(int fd, char *buf, uint64_t oid, int copies,
+static int write_object(int fd, char *buf, uint64_t oid, uint8_t copies,
unsigned int datalen, uint64_t offset, bool create,
uint32_t cache_flags)
{
return ret;
}
- aio_req->oid = vid_to_data_oid(s->inode.vdi_id,
- data_oid_to_idx(aio_req->oid));
+ if (is_data_obj(aio_req->oid)) {
+ aio_req->oid = vid_to_data_oid(s->inode.vdi_id,
+ data_oid_to_idx(aio_req->oid));
+ } else {
+ aio_req->oid = vid_to_vdi_oid(s->inode.vdi_id);
+ }
/* check whether this request becomes a CoW one */
- if (acb->aiocb_type == AIOCB_WRITE_UDATA) {
+ if (acb->aiocb_type == AIOCB_WRITE_UDATA && is_data_obj(aio_req->oid)) {
int idx = data_oid_to_idx(aio_req->oid);
AIOReq *areq;
* the same object */
QLIST_FOREACH(areq, &s->inflight_aio_head, aio_siblings) {
if (areq != aio_req && areq->oid == aio_req->oid) {
- dprintf("simultaneous CoW to %" PRIx64 "\n", aio_req->oid);
+ DPRINTF("simultaneous CoW to %" PRIx64 "\n", aio_req->oid);
QLIST_REMOVE(aio_req, aio_siblings);
QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req, aio_siblings);
return SD_RES_SUCCESS;
create = true;
}
out:
- return add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
- create, acb->aiocb_type);
+ if (is_data_obj(aio_req->oid)) {
+ return add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
+ create, acb->aiocb_type);
+ } else {
+ struct iovec iov;
+ iov.iov_base = &s->inode;
+ iov.iov_len = sizeof(s->inode);
+ return add_aio_request(s, aio_req, &iov, 1, false, AIOCB_WRITE_UDATA);
+ }
}
/* TODO Convert to fine grained options */
},
};
-static int sd_open(BlockDriverState *bs, QDict *options, int flags)
+static int sd_open(BlockDriverState *bs, QDict *options, int flags,
+ Error **errp)
{
int ret, fd;
uint32_t vid = 0;
s->discard_supported = true;
if (snapid || tag[0] != '\0') {
- dprintf("%" PRIx32 " snapshot inode was open.\n", vid);
+ DPRINTF("%" PRIx32 " snapshot inode was open.\n", vid);
s->is_snapshot = true;
}
g_free(buf);
return 0;
out:
- qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL);
+ qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
if (s->fd >= 0) {
closesocket(s->fd);
}
}
static int do_sd_create(BDRVSheepdogState *s, char *filename, int64_t vdi_size,
- uint32_t base_vid, uint32_t *vdi_id, int snapshot)
+ uint32_t base_vid, uint32_t *vdi_id, int snapshot,
+ uint8_t copy_policy)
{
SheepdogVdiReq hdr;
SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
hdr.data_length = wlen;
hdr.vdi_size = vdi_size;
+ hdr.copy_policy = copy_policy;
ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
uint32_t idx, max_idx;
int64_t vdi_size;
void *buf = g_malloc0(SD_DATA_OBJ_SIZE);
+ Error *local_err = NULL;
int ret;
- ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR);
+ ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR, &local_err);
if (ret < 0) {
+ qerror_report_err(local_err);
+ error_free(local_err);
goto out;
}
}
out:
if (bs) {
- bdrv_delete(bs);
+ bdrv_unref(bs);
}
g_free(buf);
return ret;
}
-static int sd_create(const char *filename, QEMUOptionParameter *options)
+static int sd_create(const char *filename, QEMUOptionParameter *options,
+ Error **errp)
{
int ret = 0;
uint32_t vid = 0, base_vid = 0;
char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
uint32_t snapid;
bool prealloc = false;
+ Error *local_err = NULL;
s = g_malloc0(sizeof(BDRVSheepdogState));
goto out;
}
- ret = bdrv_file_open(&bs, backing_file, NULL, 0);
+ ret = bdrv_file_open(&bs, backing_file, NULL, 0, &local_err);
if (ret < 0) {
+ qerror_report_err(local_err);
+ error_free(local_err);
goto out;
}
if (!is_snapshot(&s->inode)) {
error_report("cannot clone from a non snapshot vdi");
- bdrv_delete(bs);
+ bdrv_unref(bs);
ret = -EINVAL;
goto out;
}
base_vid = s->inode.vdi_id;
- bdrv_delete(bs);
+ bdrv_unref(bs);
}
- ret = do_sd_create(s, vdi, vdi_size, base_vid, &vid, 0);
+ /* TODO: allow users to specify copy number */
+ ret = do_sd_create(s, vdi, vdi_size, base_vid, &vid, 0, 0);
if (!prealloc || ret) {
goto out;
}
unsigned int wlen, rlen = 0;
int fd, ret;
- dprintf("%s\n", s->name);
+ DPRINTF("%s\n", s->name);
fd = connect_to_sdog(s);
if (fd < 0) {
error_report("%s, %s", sd_strerror(rsp->result), s->name);
}
- qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL);
+ qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
closesocket(s->fd);
g_free(s->host_spec);
}
char *buf;
bool deleted;
- dprintf("%" PRIx32 " is snapshot.\n", s->inode.vdi_id);
+ DPRINTF("%" PRIx32 " is snapshot.\n", s->inode.vdi_id);
buf = g_malloc(SD_INODE_SIZE);
*/
deleted = sd_delete(s);
ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &vid,
- !deleted);
+ !deleted, s->inode.copy_policy);
if (ret) {
goto out;
}
- dprintf("%" PRIx32 " is created.\n", vid);
+ DPRINTF("%" PRIx32 " is created.\n", vid);
fd = connect_to_sdog(s);
if (fd < 0) {
s->is_snapshot = false;
ret = 0;
- dprintf("%" PRIx32 " was newly created.\n", s->inode.vdi_id);
+ DPRINTF("%" PRIx32 " was newly created.\n", s->inode.vdi_id);
out:
g_free(buf);
}
if (create) {
- dprintf("update ino (%" PRIu32 ") %" PRIu64 " %" PRIu64 " %ld\n",
+ DPRINTF("update ino (%" PRIu32 ") %" PRIu64 " %" PRIu64 " %ld\n",
inode->vdi_id, oid,
vid_to_data_oid(inode->data_vdi_id[idx], idx), idx);
oid = vid_to_data_oid(inode->vdi_id, idx);
- dprintf("new oid %" PRIx64 "\n", oid);
+ DPRINTF("new oid %" PRIx64 "\n", oid);
}
aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, old_oid, done);
SheepdogInode *inode;
unsigned int datalen;
- dprintf("sn_info: name %s id_str %s s: name %s vm_state_size %" PRId64 " "
+ DPRINTF("sn_info: name %s id_str %s s: name %s vm_state_size %" PRId64 " "
"is_snapshot %d\n", sn_info->name, sn_info->id_str,
s->name, sn_info->vm_state_size, s->is_snapshot);
return -EINVAL;
}
- dprintf("%s %s\n", sn_info->name, sn_info->id_str);
+ DPRINTF("%s %s\n", sn_info->name, sn_info->id_str);
s->inode.vm_state_size = sn_info->vm_state_size;
s->inode.vm_clock_nsec = sn_info->vm_clock_nsec;
}
ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &new_vid,
- 1);
+ 1, s->inode.copy_policy);
if (ret < 0) {
error_report("failed to create inode for snapshot. %s",
strerror(errno));
}
memcpy(&s->inode, inode, datalen);
- dprintf("s->inode: name %s snap_id %x oid %x\n",
+ DPRINTF("s->inode: name %s snap_id %x oid %x\n",
s->inode.name, s->inode.snap_id, s->inode.vdi_id);
cleanup:
return ret;
}
-static int sd_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
+static int sd_snapshot_delete(BlockDriverState *bs,
+ const char *snapshot_id,
+ const char *name,
+ Error **errp)
{
/* FIXME: Delete specified snapshot id. */
return 0;
return acb->ret;
}
-static coroutine_fn int
-sd_co_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
- int *pnum)
+static coroutine_fn int64_t
+sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+ int *pnum)
{
BDRVSheepdogState *s = bs->opaque;
SheepdogInode *inode = &s->inode;
end = DIV_ROUND_UP((sector_num + nb_sectors) *
BDRV_SECTOR_SIZE, SD_DATA_OBJ_SIZE);
unsigned long idx;
- int ret = 1;
+ int64_t ret = BDRV_BLOCK_DATA;
for (idx = start; idx < end; idx++) {
if (inode->data_vdi_id[idx] == 0) {
.format_name = "sheepdog",
.protocol_name = "sheepdog",
.instance_size = sizeof(BDRVSheepdogState),
+ .bdrv_needs_filename = true,
.bdrv_file_open = sd_open,
.bdrv_close = sd_close,
.bdrv_create = sd_create,
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_getlength = sd_getlength,
.bdrv_truncate = sd_truncate,
.bdrv_co_writev = sd_co_writev,
.bdrv_co_flush_to_disk = sd_co_flush_to_disk,
.bdrv_co_discard = sd_co_discard,
- .bdrv_co_is_allocated = sd_co_is_allocated,
+ .bdrv_co_get_block_status = sd_co_get_block_status,
.bdrv_snapshot_create = sd_snapshot_create,
.bdrv_snapshot_goto = sd_snapshot_goto,
.format_name = "sheepdog",
.protocol_name = "sheepdog+tcp",
.instance_size = sizeof(BDRVSheepdogState),
+ .bdrv_needs_filename = true,
.bdrv_file_open = sd_open,
.bdrv_close = sd_close,
.bdrv_create = sd_create,
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_getlength = sd_getlength,
.bdrv_truncate = sd_truncate,
.bdrv_co_writev = sd_co_writev,
.bdrv_co_flush_to_disk = sd_co_flush_to_disk,
.bdrv_co_discard = sd_co_discard,
- .bdrv_co_is_allocated = sd_co_is_allocated,
+ .bdrv_co_get_block_status = sd_co_get_block_status,
.bdrv_snapshot_create = sd_snapshot_create,
.bdrv_snapshot_goto = sd_snapshot_goto,
.format_name = "sheepdog",
.protocol_name = "sheepdog+unix",
.instance_size = sizeof(BDRVSheepdogState),
+ .bdrv_needs_filename = true,
.bdrv_file_open = sd_open,
.bdrv_close = sd_close,
.bdrv_create = sd_create,
.bdrv_co_writev = sd_co_writev,
.bdrv_co_flush_to_disk = sd_co_flush_to_disk,
.bdrv_co_discard = sd_co_discard,
- .bdrv_co_is_allocated = sd_co_is_allocated,
+ .bdrv_co_get_block_status = sd_co_get_block_status,
.bdrv_snapshot_create = sd_snapshot_create,
.bdrv_snapshot_goto = sd_snapshot_goto,
projects / qemu.git / blobdiff