*/
#include "qemu-common.h"
-#include "qemu-error.h"
-#include "qemu_socket.h"
-#include "block_int.h"
-#include "bitops.h"
+#include "qemu/uri.h"
+#include "qemu/error-report.h"
+#include "qemu/sockets.h"
+#include "block/block_int.h"
+#include "qemu/bitops.h"
#define SD_PROTO_VER 0x01
#define SD_DEFAULT_ADDR "localhost"
-#define SD_DEFAULT_PORT "7000"
+#define SD_DEFAULT_PORT 7000
#define SD_OP_CREATE_AND_WRITE_OBJ 0x01
#define SD_OP_READ_OBJ 0x02
#define SD_OP_WRITE_OBJ 0x03
+/* 0x04 is used internally by Sheepdog */
+#define SD_OP_DISCARD_OBJ 0x05
#define SD_OP_NEW_VDI 0x11
#define SD_OP_LOCK_VDI 0x12
#define SD_OP_GET_VDI_INFO 0x14
#define SD_OP_READ_VDIS 0x15
#define SD_OP_FLUSH_VDI 0x16
+#define SD_OP_DEL_VDI 0x17
#define SD_FLAG_CMD_WRITE 0x01
#define SD_FLAG_CMD_COW 0x02
-#define SD_FLAG_CMD_CACHE 0x04
+#define SD_FLAG_CMD_CACHE 0x04 /* Writeback mode for cache */
+#define SD_FLAG_CMD_DIRECT 0x08 /* Don't use cache */
#define SD_RES_SUCCESS 0x00 /* Success */
#define SD_RES_UNKNOWN 0x01 /* Unknown error */
#define SD_RES_WAIT_FOR_FORMAT 0x16 /* Waiting for a format operation */
#define SD_RES_WAIT_FOR_JOIN 0x17 /* Waiting for other nodes joining */
#define SD_RES_JOIN_FAILED 0x18 /* Target node had failed to join sheepdog */
+#define SD_RES_HALT 0x19 /* Sheepdog is stopped serving IO request */
+#define SD_RES_READONLY 0x1A /* Object is read-only */
/*
* Object ID rules
#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)
-#define SECTOR_SIZE 512
#define SD_INODE_SIZE (sizeof(SheepdogInode))
#define CURRENT_VDI_ID 0
uint32_t id;
uint32_t data_length;
uint64_t vdi_size;
- uint32_t base_vdi_id;
+ uint32_t vdi_id;
uint32_t copies;
uint32_t snapid;
uint32_t pad[3];
enum AIOCBState {
AIOCB_WRITE_UDATA,
AIOCB_READ_UDATA,
+ AIOCB_FLUSH_CACHE,
+ AIOCB_DISCARD_OBJ,
};
struct SheepdogAIOCB {
char name[SD_MAX_VDI_LEN];
bool is_snapshot;
- bool cache_enabled;
+ uint32_t cache_flags;
+ bool discard_supported;
- char *addr;
- char *port;
+ char *host_spec;
+ bool is_unix;
int fd;
- int flush_fd;
CoMutex lock;
Coroutine *co_send;
{SD_RES_WAIT_FOR_FORMAT, "Sheepdog is waiting for a format operation"},
{SD_RES_WAIT_FOR_JOIN, "Sheepdog is waiting for other nodes joining"},
{SD_RES_JOIN_FAILED, "Target node had failed to join sheepdog"},
+ {SD_RES_HALT, "Sheepdog is stopped serving IO request"},
+ {SD_RES_READONLY, "Object is read-only"},
};
for (i = 0; i < ARRAY_SIZE(errors); ++i) {
acb->canceled = true;
}
-static AIOPool sd_aio_pool = {
+static const AIOCBInfo sd_aiocb_info = {
.aiocb_size = sizeof(SheepdogAIOCB),
.cancel = sd_aio_cancel,
};
static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
- int64_t sector_num, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+ int64_t sector_num, int nb_sectors)
{
SheepdogAIOCB *acb;
- acb = qemu_aio_get(&sd_aio_pool, bs, cb, opaque);
+ acb = qemu_aio_get(&sd_aiocb_info, bs, NULL, NULL);
acb->qiov = qiov;
return acb;
}
-static int connect_to_sdog(const char *addr, const char *port)
+static int connect_to_sdog(BDRVSheepdogState *s)
{
- char hbuf[NI_MAXHOST], sbuf[NI_MAXSERV];
- int fd, ret;
- struct addrinfo hints, *res, *res0;
-
- if (!addr) {
- addr = SD_DEFAULT_ADDR;
- port = SD_DEFAULT_PORT;
- }
-
- memset(&hints, 0, sizeof(hints));
- hints.ai_socktype = SOCK_STREAM;
-
- ret = getaddrinfo(addr, port, &hints, &res0);
- if (ret) {
- error_report("unable to get address info %s, %s",
- addr, strerror(errno));
- return -errno;
- }
-
- for (res = res0; res; res = res->ai_next) {
- ret = getnameinfo(res->ai_addr, res->ai_addrlen, hbuf, sizeof(hbuf),
- sbuf, sizeof(sbuf), NI_NUMERICHOST | NI_NUMERICSERV);
- if (ret) {
- continue;
- }
+ int fd;
+ Error *err = NULL;
- fd = socket(res->ai_family, res->ai_socktype, res->ai_protocol);
- if (fd < 0) {
- continue;
- }
+ if (s->is_unix) {
+ fd = unix_connect(s->host_spec, &err);
+ } else {
+ fd = inet_connect(s->host_spec, &err);
- reconnect:
- ret = connect(fd, res->ai_addr, res->ai_addrlen);
- if (ret < 0) {
- if (errno == EINTR) {
- goto reconnect;
+ if (err == NULL) {
+ int ret = socket_set_nodelay(fd);
+ if (ret < 0) {
+ error_report("%s", strerror(errno));
}
- close(fd);
- break;
}
+ }
- dprintf("connected to %s:%s\n", addr, port);
- goto success;
+ if (err != NULL) {
+ qerror_report_err(err);
+ error_free(err);
+ } else {
+ qemu_set_nonblock(fd);
}
- fd = -errno;
- error_report("failed connect to %s:%s", addr, port);
-success:
- freeaddrinfo(res0);
+
return fd;
}
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, NULL, co);
+ qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, have_co_req, co);
- socket_set_block(sockfd);
ret = send_co_req(sockfd, hdr, data, wlen);
if (ret < 0) {
goto out;
}
- qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, NULL, co);
+ qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, have_co_req, co);
ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
if (ret < sizeof(*hdr)) {
}
ret = 0;
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);
- socket_set_nonblock(sockfd);
srco->ret = ret;
srco->finished = true;
static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
struct iovec *iov, int niov, bool create,
enum AIOCBState aiocb_type);
+static int coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req);
static AIOReq *find_pending_req(BDRVSheepdogState *s, uint64_t oid)
int ret;
AIOReq *aio_req = NULL;
SheepdogAIOCB *acb;
- unsigned long idx;
+ uint64_t idx;
if (QLIST_EMPTY(&s->inflight_aio_head)) {
goto out;
* and max_dirty_data_idx are changed to include updated
* index between them.
*/
- s->inode.data_vdi_id[idx] = s->inode.vdi_id;
- s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
- s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
-
+ if (rsp.result == SD_RES_SUCCESS) {
+ s->inode.data_vdi_id[idx] = s->inode.vdi_id;
+ s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
+ s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
+ }
/*
* Some requests may be blocked because simultaneous
* create requests are not allowed, so we search the
* pending requests here.
*/
- send_pending_req(s, vid_to_data_oid(s->inode.vdi_id, idx));
+ send_pending_req(s, aio_req->oid);
}
break;
case AIOCB_READ_UDATA:
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");
+ s->cache_flags = SD_FLAG_CMD_DIRECT;
+ rsp.result = SD_RES_SUCCESS;
+ }
+ break;
+ case AIOCB_DISCARD_OBJ:
+ switch (rsp.result) {
+ case SD_RES_INVALID_PARMS:
+ error_report("sheep(%s) doesn't support discard command",
+ s->host_spec);
+ rsp.result = SD_RES_SUCCESS;
+ s->discard_supported = false;
+ break;
+ case SD_RES_SUCCESS:
+ idx = data_oid_to_idx(aio_req->oid);
+ s->inode.data_vdi_id[idx] = 0;
+ break;
+ default:
+ break;
+ }
}
- if (rsp.result != SD_RES_SUCCESS) {
+ switch (rsp.result) {
+ case SD_RES_SUCCESS:
+ break;
+ case SD_RES_READONLY:
+ ret = resend_aioreq(s, aio_req);
+ if (ret == SD_RES_SUCCESS) {
+ goto out;
+ }
+ /* fall through */
+ default:
acb->ret = -EIO;
error_report("%s", sd_strerror(rsp.result));
+ break;
}
free_aio_req(s, aio_req);
!QLIST_EMPTY(&s->pending_aio_head);
}
-static int set_nodelay(int fd)
-{
- int ret, opt;
-
- opt = 1;
- ret = setsockopt(fd, IPPROTO_TCP, TCP_NODELAY, (char *)&opt, sizeof(opt));
- return ret;
-}
-
/*
* Return a socket discriptor to read/write objects.
*
*/
static int get_sheep_fd(BDRVSheepdogState *s)
{
- int ret, fd;
+ int fd;
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
- error_report("%s", strerror(errno));
return fd;
}
- socket_set_nonblock(fd);
+ qemu_aio_set_fd_handler(fd, co_read_response, NULL, aio_flush_request, s);
+ return fd;
+}
- ret = set_nodelay(fd);
- if (ret) {
- error_report("%s", strerror(errno));
- closesocket(fd);
- return -errno;
+static int sd_parse_uri(BDRVSheepdogState *s, const char *filename,
+ char *vdi, uint32_t *snapid, char *tag)
+{
+ URI *uri;
+ QueryParams *qp = NULL;
+ int ret = 0;
+
+ uri = uri_parse(filename);
+ if (!uri) {
+ return -EINVAL;
}
- qemu_aio_set_fd_handler(fd, co_read_response, NULL, aio_flush_request, s);
- return fd;
+ /* transport */
+ if (!strcmp(uri->scheme, "sheepdog")) {
+ s->is_unix = false;
+ } else if (!strcmp(uri->scheme, "sheepdog+tcp")) {
+ s->is_unix = false;
+ } else if (!strcmp(uri->scheme, "sheepdog+unix")) {
+ s->is_unix = true;
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (uri->path == NULL || !strcmp(uri->path, "/")) {
+ ret = -EINVAL;
+ goto out;
+ }
+ pstrcpy(vdi, SD_MAX_VDI_LEN, uri->path + 1);
+
+ qp = query_params_parse(uri->query);
+ if (qp->n > 1 || (s->is_unix && !qp->n) || (!s->is_unix && qp->n)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (s->is_unix) {
+ /* sheepdog+unix:///vdiname?socket=path */
+ if (uri->server || uri->port || strcmp(qp->p[0].name, "socket")) {
+ ret = -EINVAL;
+ goto out;
+ }
+ s->host_spec = g_strdup(qp->p[0].value);
+ } else {
+ /* sheepdog[+tcp]://[host:port]/vdiname */
+ s->host_spec = g_strdup_printf("%s:%d", uri->server ?: SD_DEFAULT_ADDR,
+ uri->port ?: SD_DEFAULT_PORT);
+ }
+
+ /* snapshot tag */
+ if (uri->fragment) {
+ *snapid = strtoul(uri->fragment, NULL, 10);
+ if (*snapid == 0) {
+ pstrcpy(tag, SD_MAX_VDI_TAG_LEN, uri->fragment);
+ }
+ } else {
+ *snapid = CURRENT_VDI_ID; /* search current vdi */
+ }
+
+out:
+ if (qp) {
+ query_params_free(qp);
+ }
+ uri_free(uri);
+ return ret;
}
/*
- * Parse a filename
+ * Parse a filename (old syntax)
*
* filename must be one of the following formats:
* 1. [vdiname]
static int parse_vdiname(BDRVSheepdogState *s, const char *filename,
char *vdi, uint32_t *snapid, char *tag)
{
- char *p, *q;
- int nr_sep;
+ char *p, *q, *uri;
+ const char *host_spec, *vdi_spec;
+ int nr_sep, ret;
+ strstart(filename, "sheepdog:", (const char **)&filename);
p = q = g_strdup(filename);
/* count the number of separators */
}
p = q;
- /* use the first two tokens as hostname and port number. */
+ /* use the first two tokens as host_spec. */
if (nr_sep >= 2) {
- s->addr = p;
+ host_spec = p;
p = strchr(p, ':');
- *p++ = '\0';
-
- s->port = p;
+ p++;
p = strchr(p, ':');
*p++ = '\0';
} else {
- s->addr = NULL;
- s->port = 0;
+ host_spec = "";
}
- pstrcpy(vdi, SD_MAX_VDI_LEN, p);
+ vdi_spec = p;
- p = strchr(vdi, ':');
+ p = strchr(vdi_spec, ':');
if (p) {
- *p++ = '\0';
- *snapid = strtoul(p, NULL, 10);
- if (*snapid == 0) {
- pstrcpy(tag, SD_MAX_VDI_TAG_LEN, p);
- }
- } else {
- *snapid = CURRENT_VDI_ID; /* search current vdi */
+ *p++ = '#';
}
- if (s->addr == NULL) {
- g_free(q);
- }
+ uri = g_strdup_printf("sheepdog://%s/%s", host_spec, vdi_spec);
- return 0;
+ ret = sd_parse_uri(s, uri, vdi, snapid, tag);
+
+ g_free(q);
+ g_free(uri);
+
+ return ret;
}
-static int find_vdi_name(BDRVSheepdogState *s, char *filename, uint32_t snapid,
- char *tag, uint32_t *vid, int for_snapshot)
+static int find_vdi_name(BDRVSheepdogState *s, const char *filename,
+ uint32_t snapid, const char *tag, uint32_t *vid,
+ bool lock)
{
int ret, fd;
SheepdogVdiReq hdr;
unsigned int wlen, rlen = 0;
char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN];
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
return fd;
}
strncpy(buf + SD_MAX_VDI_LEN, tag, SD_MAX_VDI_TAG_LEN);
memset(&hdr, 0, sizeof(hdr));
- if (for_snapshot) {
- hdr.opcode = SD_OP_GET_VDI_INFO;
- } else {
+ if (lock) {
hdr.opcode = SD_OP_LOCK_VDI;
+ } else {
+ hdr.opcode = SD_OP_GET_VDI_INFO;
}
wlen = SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN;
hdr.proto_ver = SD_PROTO_VER;
{
int nr_copies = s->inode.nr_copies;
SheepdogObjReq hdr;
- unsigned int wlen;
+ unsigned int wlen = 0;
int ret;
uint64_t oid = aio_req->oid;
unsigned int datalen = aio_req->data_len;
memset(&hdr, 0, sizeof(hdr));
- if (aiocb_type == AIOCB_READ_UDATA) {
- wlen = 0;
+ switch (aiocb_type) {
+ case AIOCB_FLUSH_CACHE:
+ hdr.opcode = SD_OP_FLUSH_VDI;
+ break;
+ case AIOCB_READ_UDATA:
hdr.opcode = SD_OP_READ_OBJ;
hdr.flags = flags;
- } else if (create) {
- wlen = datalen;
- hdr.opcode = SD_OP_CREATE_AND_WRITE_OBJ;
- hdr.flags = SD_FLAG_CMD_WRITE | flags;
- } else {
+ break;
+ case AIOCB_WRITE_UDATA:
+ if (create) {
+ hdr.opcode = SD_OP_CREATE_AND_WRITE_OBJ;
+ } else {
+ hdr.opcode = SD_OP_WRITE_OBJ;
+ }
wlen = datalen;
- hdr.opcode = SD_OP_WRITE_OBJ;
hdr.flags = SD_FLAG_CMD_WRITE | flags;
+ break;
+ case AIOCB_DISCARD_OBJ:
+ hdr.opcode = SD_OP_DISCARD_OBJ;
+ break;
}
- if (s->cache_enabled) {
- hdr.flags |= SD_FLAG_CMD_CACHE;
+ if (s->cache_flags) {
+ hdr.flags |= s->cache_flags;
}
hdr.oid = oid;
static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
unsigned int datalen, uint64_t offset,
- bool write, bool create, bool cache)
+ bool write, bool create, uint32_t cache_flags)
{
SheepdogObjReq hdr;
SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr;
hdr.opcode = SD_OP_READ_OBJ;
}
- if (cache) {
- hdr.flags |= SD_FLAG_CMD_CACHE;
- }
+ hdr.flags |= cache_flags;
hdr.oid = oid;
hdr.data_length = datalen;
}
static int read_object(int fd, char *buf, uint64_t oid, int copies,
- unsigned int datalen, uint64_t offset, bool cache)
+ unsigned int datalen, uint64_t offset,
+ uint32_t cache_flags)
{
return read_write_object(fd, buf, oid, copies, datalen, offset, false,
- false, cache);
+ false, cache_flags);
}
static int write_object(int fd, char *buf, uint64_t oid, int copies,
unsigned int datalen, uint64_t offset, bool create,
- bool cache)
+ uint32_t cache_flags)
{
return read_write_object(fd, buf, oid, copies, datalen, offset, true,
- create, cache);
+ create, cache_flags);
+}
+
+/* update inode with the latest state */
+static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag)
+{
+ SheepdogInode *inode;
+ int ret = 0, fd;
+ uint32_t vid = 0;
+
+ fd = connect_to_sdog(s);
+ if (fd < 0) {
+ return -EIO;
+ }
+
+ inode = g_malloc(sizeof(s->inode));
+
+ ret = find_vdi_name(s, s->name, snapid, tag, &vid, false);
+ if (ret) {
+ goto out;
+ }
+
+ ret = read_object(fd, (char *)inode, vid_to_vdi_oid(vid),
+ s->inode.nr_copies, sizeof(*inode), 0, s->cache_flags);
+ if (ret < 0) {
+ goto out;
+ }
+
+ if (inode->vdi_id != s->inode.vdi_id) {
+ memcpy(&s->inode, inode, sizeof(s->inode));
+ }
+
+out:
+ g_free(inode);
+ closesocket(fd);
+
+ return ret;
+}
+
+static int coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
+{
+ SheepdogAIOCB *acb = aio_req->aiocb;
+ bool create = false;
+ int ret;
+
+ ret = reload_inode(s, 0, "");
+ if (ret < 0) {
+ return ret;
+ }
+
+ aio_req->oid = vid_to_data_oid(s->inode.vdi_id,
+ data_oid_to_idx(aio_req->oid));
+
+ /* check whether this request becomes a CoW one */
+ if (acb->aiocb_type == AIOCB_WRITE_UDATA) {
+ int idx = data_oid_to_idx(aio_req->oid);
+ AIOReq *areq;
+
+ if (s->inode.data_vdi_id[idx] == 0) {
+ create = true;
+ goto out;
+ }
+ if (is_data_obj_writable(&s->inode, idx)) {
+ goto out;
+ }
+
+ /* link to the pending list if there is another CoW request to
+ * 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);
+ QLIST_REMOVE(aio_req, aio_siblings);
+ QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req, aio_siblings);
+ return SD_RES_SUCCESS;
+ }
+ }
+
+ aio_req->base_oid = vid_to_data_oid(s->inode.data_vdi_id[idx], idx);
+ aio_req->flags |= SD_FLAG_CMD_COW;
+ create = true;
+ }
+out:
+ return add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
+ create, acb->aiocb_type);
}
-static int sd_open(BlockDriverState *bs, const char *filename, int flags)
+/* TODO Convert to fine grained options */
+static QemuOptsList runtime_opts = {
+ .name = "sheepdog",
+ .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+ .desc = {
+ {
+ .name = "filename",
+ .type = QEMU_OPT_STRING,
+ .help = "URL to the sheepdog image",
+ },
+ { /* end of list */ }
+ },
+};
+
+static int sd_open(BlockDriverState *bs, QDict *options, int flags)
{
int ret, fd;
uint32_t vid = 0;
char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
uint32_t snapid;
char *buf = NULL;
+ QemuOpts *opts;
+ Error *local_err = NULL;
+ const char *filename;
+
+ opts = qemu_opts_create_nofail(&runtime_opts);
+ qemu_opts_absorb_qdict(opts, options, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ ret = -EINVAL;
+ goto out;
+ }
- strstart(filename, "sheepdog:", (const char **)&filename);
+ filename = qemu_opt_get(opts, "filename");
QLIST_INIT(&s->inflight_aio_head);
QLIST_INIT(&s->pending_aio_head);
memset(vdi, 0, sizeof(vdi));
memset(tag, 0, sizeof(tag));
- if (parse_vdiname(s, filename, vdi, &snapid, tag) < 0) {
- ret = -EINVAL;
+
+ if (strstr(filename, "://")) {
+ ret = sd_parse_uri(s, filename, vdi, &snapid, tag);
+ } else {
+ ret = parse_vdiname(s, filename, vdi, &snapid, tag);
+ }
+ if (ret < 0) {
goto out;
}
s->fd = get_sheep_fd(s);
goto out;
}
- ret = find_vdi_name(s, vdi, snapid, tag, &vid, 0);
+ ret = find_vdi_name(s, vdi, snapid, tag, &vid, true);
if (ret) {
goto out;
}
- s->cache_enabled = true;
- s->flush_fd = connect_to_sdog(s->addr, s->port);
- if (s->flush_fd < 0) {
- error_report("failed to connect");
- ret = s->flush_fd;
- goto out;
+ /*
+ * QEMU block layer emulates writethrough cache as 'writeback + flush', so
+ * we always set SD_FLAG_CMD_CACHE (writeback cache) as default.
+ */
+ s->cache_flags = SD_FLAG_CMD_CACHE;
+ if (flags & BDRV_O_NOCACHE) {
+ s->cache_flags = SD_FLAG_CMD_DIRECT;
}
+ s->discard_supported = true;
if (snapid || tag[0] != '\0') {
dprintf("%" PRIx32 " snapshot inode was open.\n", vid);
s->is_snapshot = true;
}
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
- error_report("failed to connect");
ret = fd;
goto out;
}
buf = g_malloc(SD_INODE_SIZE);
ret = read_object(fd, buf, vid_to_vdi_oid(vid), 0, SD_INODE_SIZE, 0,
- s->cache_enabled);
+ s->cache_flags);
closesocket(fd);
s->min_dirty_data_idx = UINT32_MAX;
s->max_dirty_data_idx = 0;
- bs->total_sectors = s->inode.vdi_size / SECTOR_SIZE;
+ bs->total_sectors = s->inode.vdi_size / BDRV_SECTOR_SIZE;
pstrcpy(s->name, sizeof(s->name), vdi);
qemu_co_mutex_init(&s->lock);
+ qemu_opts_del(opts);
g_free(buf);
return 0;
out:
if (s->fd >= 0) {
closesocket(s->fd);
}
+ qemu_opts_del(opts);
g_free(buf);
return ret;
}
-static int do_sd_create(char *filename, int64_t vdi_size,
- uint32_t base_vid, uint32_t *vdi_id, int snapshot,
- const char *addr, const char *port)
+static int do_sd_create(BDRVSheepdogState *s, char *filename, int64_t vdi_size,
+ uint32_t base_vid, uint32_t *vdi_id, int snapshot)
{
SheepdogVdiReq hdr;
SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
unsigned int wlen, rlen = 0;
char buf[SD_MAX_VDI_LEN];
- fd = connect_to_sdog(addr, port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
return fd;
}
memset(&hdr, 0, sizeof(hdr));
hdr.opcode = SD_OP_NEW_VDI;
- hdr.base_vdi_id = base_vid;
+ hdr.vdi_id = base_vid;
wlen = SD_MAX_VDI_LEN;
void *buf = g_malloc0(SD_DATA_OBJ_SIZE);
int ret;
- ret = bdrv_file_open(&bs, filename, BDRV_O_RDWR);
+ ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR);
if (ret < 0) {
goto out;
}
char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
uint32_t snapid;
bool prealloc = false;
- const char *vdiname;
s = g_malloc0(sizeof(BDRVSheepdogState));
- strstart(filename, "sheepdog:", &vdiname);
-
memset(vdi, 0, sizeof(vdi));
memset(tag, 0, sizeof(tag));
- if (parse_vdiname(s, vdiname, vdi, &snapid, tag) < 0) {
- error_report("invalid filename");
- ret = -EINVAL;
+ if (strstr(filename, "://")) {
+ ret = sd_parse_uri(s, filename, vdi, &snapid, tag);
+ } else {
+ ret = parse_vdiname(s, filename, vdi, &snapid, tag);
+ }
+ if (ret < 0) {
goto out;
}
goto out;
}
- ret = bdrv_file_open(&bs, backing_file, 0);
+ ret = bdrv_file_open(&bs, backing_file, NULL, 0);
if (ret < 0) {
goto out;
}
bdrv_delete(bs);
}
- ret = do_sd_create(vdi, vdi_size, base_vid, &vid, 0, s->addr, s->port);
+ ret = do_sd_create(s, vdi, vdi_size, base_vid, &vid, 0);
if (!prealloc || ret) {
goto out;
}
dprintf("%s\n", s->name);
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
return;
}
memset(&hdr, 0, sizeof(hdr));
hdr.opcode = SD_OP_RELEASE_VDI;
+ hdr.vdi_id = s->inode.vdi_id;
wlen = strlen(s->name) + 1;
hdr.data_length = wlen;
hdr.flags = SD_FLAG_CMD_WRITE;
qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL);
closesocket(s->fd);
- if (s->cache_enabled) {
- closesocket(s->flush_fd);
- }
- g_free(s->addr);
+ g_free(s->host_spec);
}
static int64_t sd_getlength(BlockDriverState *bs)
return -EINVAL;
}
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
return fd;
}
datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
s->inode.vdi_size = offset;
ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
- s->inode.nr_copies, datalen, 0, false, s->cache_enabled);
+ s->inode.nr_copies, datalen, 0, false, s->cache_flags);
close(fd);
if (ret < 0) {
sd_finish_aiocb(acb);
}
+/* Delete current working VDI on the snapshot chain */
+static bool sd_delete(BDRVSheepdogState *s)
+{
+ unsigned int wlen = SD_MAX_VDI_LEN, rlen = 0;
+ SheepdogVdiReq hdr = {
+ .opcode = SD_OP_DEL_VDI,
+ .vdi_id = s->inode.vdi_id,
+ .data_length = wlen,
+ .flags = SD_FLAG_CMD_WRITE,
+ };
+ SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
+ int fd, ret;
+
+ fd = connect_to_sdog(s);
+ if (fd < 0) {
+ return false;
+ }
+
+ ret = do_req(fd, (SheepdogReq *)&hdr, s->name, &wlen, &rlen);
+ closesocket(fd);
+ if (ret) {
+ return false;
+ }
+ switch (rsp->result) {
+ case SD_RES_NO_VDI:
+ error_report("%s was already deleted", s->name);
+ /* fall through */
+ case SD_RES_SUCCESS:
+ break;
+ default:
+ error_report("%s, %s", sd_strerror(rsp->result), s->name);
+ return false;
+ }
+
+ return true;
+}
+
/*
* Create a writable VDI from a snapshot
*/
int ret, fd;
uint32_t vid;
char *buf;
+ bool deleted;
dprintf("%" PRIx32 " is snapshot.\n", s->inode.vdi_id);
buf = g_malloc(SD_INODE_SIZE);
- ret = do_sd_create(s->name, s->inode.vdi_size, s->inode.vdi_id, &vid, 1,
- s->addr, s->port);
+ /*
+ * Even If deletion fails, we will just create extra snapshot based on
+ * the workding VDI which was supposed to be deleted. So no need to
+ * false bail out.
+ */
+ deleted = sd_delete(s);
+ ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &vid,
+ !deleted);
if (ret) {
goto out;
}
dprintf("%" PRIx32 " is created.\n", vid);
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
- error_report("failed to connect");
ret = fd;
goto out;
}
ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies,
- SD_INODE_SIZE, 0, s->cache_enabled);
+ SD_INODE_SIZE, 0, s->cache_flags);
closesocket(fd);
{
SheepdogAIOCB *acb = p;
int ret = 0;
- unsigned long len, done = 0, total = acb->nb_sectors * SECTOR_SIZE;
- unsigned long idx = acb->sector_num * SECTOR_SIZE / SD_DATA_OBJ_SIZE;
+ unsigned long len, done = 0, total = acb->nb_sectors * BDRV_SECTOR_SIZE;
+ unsigned long idx = acb->sector_num * BDRV_SECTOR_SIZE / SD_DATA_OBJ_SIZE;
uint64_t oid;
- uint64_t offset = (acb->sector_num * SECTOR_SIZE) % SD_DATA_OBJ_SIZE;
+ uint64_t offset = (acb->sector_num * BDRV_SECTOR_SIZE) % SD_DATA_OBJ_SIZE;
BDRVSheepdogState *s = acb->common.bs->opaque;
SheepdogInode *inode = &s->inode;
AIOReq *aio_req;
flags = SD_FLAG_CMD_COW;
}
break;
+ case AIOCB_DISCARD_OBJ:
+ /*
+ * We discard the object only when the whole object is
+ * 1) allocated 2) trimmed. Otherwise, simply skip it.
+ */
+ if (len != SD_DATA_OBJ_SIZE || inode->data_vdi_id[idx] == 0) {
+ goto done;
+ }
+ break;
default:
break;
}
int ret;
if (bs->growable && sector_num + nb_sectors > bs->total_sectors) {
- ret = sd_truncate(bs, (sector_num + nb_sectors) * SECTOR_SIZE);
+ ret = sd_truncate(bs, (sector_num + nb_sectors) * BDRV_SECTOR_SIZE);
if (ret < 0) {
return ret;
}
bs->total_sectors = sector_num + nb_sectors;
}
- acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
+ acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
acb->aio_done_func = sd_write_done;
acb->aiocb_type = AIOCB_WRITE_UDATA;
SheepdogAIOCB *acb;
int ret;
- acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
+ acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
acb->aiocb_type = AIOCB_READ_UDATA;
acb->aio_done_func = sd_finish_aiocb;
static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
{
BDRVSheepdogState *s = bs->opaque;
- SheepdogObjReq hdr = { 0 };
- SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr;
- SheepdogInode *inode = &s->inode;
+ SheepdogAIOCB *acb;
+ AIOReq *aio_req;
int ret;
- unsigned int wlen = 0, rlen = 0;
- if (!s->cache_enabled) {
+ if (s->cache_flags != SD_FLAG_CMD_CACHE) {
return 0;
}
- hdr.opcode = SD_OP_FLUSH_VDI;
- hdr.oid = vid_to_vdi_oid(inode->vdi_id);
+ acb = sd_aio_setup(bs, NULL, 0, 0);
+ acb->aiocb_type = AIOCB_FLUSH_CACHE;
+ acb->aio_done_func = sd_finish_aiocb;
- ret = do_req(s->flush_fd, (SheepdogReq *)&hdr, NULL, &wlen, &rlen);
- if (ret) {
- error_report("failed to send a request to the sheep");
+ aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
+ 0, 0, 0, 0, 0);
+ QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
+ ret = add_aio_request(s, aio_req, NULL, 0, false, acb->aiocb_type);
+ if (ret < 0) {
+ error_report("add_aio_request is failed");
+ free_aio_req(s, aio_req);
+ qemu_aio_release(acb);
return ret;
}
- if (rsp->result == SD_RES_INVALID_PARMS) {
- dprintf("disable write cache since the server doesn't support it\n");
-
- s->cache_enabled = false;
- closesocket(s->flush_fd);
- return 0;
- }
-
- if (rsp->result != SD_RES_SUCCESS) {
- error_report("%s", sd_strerror(rsp->result));
- return -EIO;
- }
-
- return 0;
+ qemu_coroutine_yield();
+ return acb->ret;
}
static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
/* refresh inode. */
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
ret = fd;
goto cleanup;
}
ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
- s->inode.nr_copies, datalen, 0, false, s->cache_enabled);
+ s->inode.nr_copies, datalen, 0, false, s->cache_flags);
if (ret < 0) {
error_report("failed to write snapshot's inode.");
goto cleanup;
}
- ret = do_sd_create(s->name, s->inode.vdi_size, s->inode.vdi_id, &new_vid, 1,
- s->addr, s->port);
+ ret = do_sd_create(s, s->name, s->inode.vdi_size, s->inode.vdi_id, &new_vid,
+ 1);
if (ret < 0) {
error_report("failed to create inode for snapshot. %s",
strerror(errno));
inode = (SheepdogInode *)g_malloc(datalen);
ret = read_object(fd, (char *)inode, vid_to_vdi_oid(new_vid),
- s->inode.nr_copies, datalen, 0, s->cache_enabled);
+ s->inode.nr_copies, datalen, 0, s->cache_flags);
if (ret < 0) {
error_report("failed to read new inode info. %s", strerror(errno));
return ret;
}
+/*
+ * We implement rollback(loadvm) operation to the specified snapshot by
+ * 1) switch to the snapshot
+ * 2) rely on sd_create_branch to delete working VDI and
+ * 3) create a new working VDI based on the speicified snapshot
+ */
static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
{
BDRVSheepdogState *s = bs->opaque;
BDRVSheepdogState *old_s;
- char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
- char *buf = NULL;
- uint32_t vid;
+ char tag[SD_MAX_VDI_TAG_LEN];
uint32_t snapid = 0;
- int ret = 0, fd;
+ int ret = 0;
old_s = g_malloc(sizeof(BDRVSheepdogState));
memcpy(old_s, s, sizeof(BDRVSheepdogState));
- pstrcpy(vdi, sizeof(vdi), s->name);
-
snapid = strtoul(snapshot_id, NULL, 10);
if (snapid) {
tag[0] = 0;
pstrcpy(tag, sizeof(tag), s->name);
}
- ret = find_vdi_name(s, vdi, snapid, tag, &vid, 1);
- if (ret) {
- error_report("Failed to find_vdi_name");
- goto out;
- }
-
- fd = connect_to_sdog(s->addr, s->port);
- if (fd < 0) {
- error_report("failed to connect");
- ret = fd;
- goto out;
- }
-
- buf = g_malloc(SD_INODE_SIZE);
- ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies,
- SD_INODE_SIZE, 0, s->cache_enabled);
-
- closesocket(fd);
-
+ ret = reload_inode(s, snapid, tag);
if (ret) {
goto out;
}
- memcpy(&s->inode, buf, sizeof(s->inode));
-
if (!s->inode.vm_state_size) {
error_report("Invalid snapshot");
ret = -ENOENT;
s->is_snapshot = true;
- g_free(buf);
g_free(old_s);
return 0;
out:
/* recover bdrv_sd_state */
memcpy(s, old_s, sizeof(BDRVSheepdogState));
- g_free(buf);
g_free(old_s);
error_report("failed to open. recover old bdrv_sd_state.");
vdi_inuse = g_malloc(max);
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
ret = fd;
goto out;
hval = fnv_64a_buf(s->name, strlen(s->name), FNV1A_64_INIT);
start_nr = hval & (SD_NR_VDIS - 1);
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
- error_report("failed to connect");
ret = fd;
goto out;
}
/* we don't need to read entire object */
ret = read_object(fd, (char *)&inode, vid_to_vdi_oid(vid),
0, SD_INODE_SIZE - sizeof(inode.data_vdi_id), 0,
- s->cache_enabled);
+ s->cache_flags);
if (ret) {
continue;
uint32_t vdi_index;
uint64_t offset;
- fd = connect_to_sdog(s->addr, s->port);
+ fd = connect_to_sdog(s);
if (fd < 0) {
return fd;
}
if (load) {
ret = read_object(fd, (char *)data, vmstate_oid,
s->inode.nr_copies, data_len, offset,
- s->cache_enabled);
+ s->cache_flags);
} else {
ret = write_object(fd, (char *)data, vmstate_oid,
s->inode.nr_copies, data_len, offset, create,
- s->cache_enabled);
+ s->cache_flags);
}
if (ret < 0) {
return ret;
}
-static int sd_save_vmstate(BlockDriverState *bs, const uint8_t *data,
- int64_t pos, int size)
+static int sd_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t pos)
{
BDRVSheepdogState *s = bs->opaque;
+ void *buf;
+ int ret;
+
+ buf = qemu_blockalign(bs, qiov->size);
+ qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
+ ret = do_load_save_vmstate(s, (uint8_t *) buf, pos, qiov->size, 0);
+ qemu_vfree(buf);
- return do_load_save_vmstate(s, (uint8_t *)data, pos, size, 0);
+ return ret;
}
static int sd_load_vmstate(BlockDriverState *bs, uint8_t *data,
}
+static coroutine_fn int sd_co_discard(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors)
+{
+ SheepdogAIOCB *acb;
+ QEMUIOVector dummy;
+ BDRVSheepdogState *s = bs->opaque;
+ int ret;
+
+ if (!s->discard_supported) {
+ return 0;
+ }
+
+ acb = sd_aio_setup(bs, &dummy, sector_num, nb_sectors);
+ acb->aiocb_type = AIOCB_DISCARD_OBJ;
+ acb->aio_done_func = sd_finish_aiocb;
+
+ ret = sd_co_rw_vector(acb);
+ if (ret <= 0) {
+ qemu_aio_release(acb);
+ return ret;
+ }
+
+ qemu_coroutine_yield();
+
+ return acb->ret;
+}
+
+static coroutine_fn int
+sd_co_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+ int *pnum)
+{
+ BDRVSheepdogState *s = bs->opaque;
+ SheepdogInode *inode = &s->inode;
+ unsigned long start = sector_num * BDRV_SECTOR_SIZE / SD_DATA_OBJ_SIZE,
+ end = DIV_ROUND_UP((sector_num + nb_sectors) *
+ BDRV_SECTOR_SIZE, SD_DATA_OBJ_SIZE);
+ unsigned long idx;
+ int ret = 1;
+
+ for (idx = start; idx < end; idx++) {
+ if (inode->data_vdi_id[idx] == 0) {
+ break;
+ }
+ }
+ if (idx == start) {
+ /* Get the longest length of unallocated sectors */
+ ret = 0;
+ for (idx = start + 1; idx < end; idx++) {
+ if (inode->data_vdi_id[idx] != 0) {
+ break;
+ }
+ }
+ }
+
+ *pnum = (idx - start) * SD_DATA_OBJ_SIZE / BDRV_SECTOR_SIZE;
+ if (*pnum > nb_sectors) {
+ *pnum = nb_sectors;
+ }
+ return ret;
+}
+
static QEMUOptionParameter sd_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
{ NULL }
};
-BlockDriver bdrv_sheepdog = {
+static BlockDriver bdrv_sheepdog = {
.format_name = "sheepdog",
.protocol_name = "sheepdog",
.instance_size = sizeof(BDRVSheepdogState),
.bdrv_co_readv = sd_co_readv,
.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_snapshot_create = sd_snapshot_create,
+ .bdrv_snapshot_goto = sd_snapshot_goto,
+ .bdrv_snapshot_delete = sd_snapshot_delete,
+ .bdrv_snapshot_list = sd_snapshot_list,
+
+ .bdrv_save_vmstate = sd_save_vmstate,
+ .bdrv_load_vmstate = sd_load_vmstate,
+
+ .create_options = sd_create_options,
+};
+
+static BlockDriver bdrv_sheepdog_tcp = {
+ .format_name = "sheepdog",
+ .protocol_name = "sheepdog+tcp",
+ .instance_size = sizeof(BDRVSheepdogState),
+ .bdrv_file_open = sd_open,
+ .bdrv_close = sd_close,
+ .bdrv_create = sd_create,
+ .bdrv_getlength = sd_getlength,
+ .bdrv_truncate = sd_truncate,
+
+ .bdrv_co_readv = sd_co_readv,
+ .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_snapshot_create = sd_snapshot_create,
+ .bdrv_snapshot_goto = sd_snapshot_goto,
+ .bdrv_snapshot_delete = sd_snapshot_delete,
+ .bdrv_snapshot_list = sd_snapshot_list,
+
+ .bdrv_save_vmstate = sd_save_vmstate,
+ .bdrv_load_vmstate = sd_load_vmstate,
+
+ .create_options = sd_create_options,
+};
+
+static BlockDriver bdrv_sheepdog_unix = {
+ .format_name = "sheepdog",
+ .protocol_name = "sheepdog+unix",
+ .instance_size = sizeof(BDRVSheepdogState),
+ .bdrv_file_open = sd_open,
+ .bdrv_close = sd_close,
+ .bdrv_create = sd_create,
+ .bdrv_getlength = sd_getlength,
+ .bdrv_truncate = sd_truncate,
+
+ .bdrv_co_readv = sd_co_readv,
+ .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_snapshot_create = sd_snapshot_create,
.bdrv_snapshot_goto = sd_snapshot_goto,
static void bdrv_sheepdog_init(void)
{
bdrv_register(&bdrv_sheepdog);
+ bdrv_register(&bdrv_sheepdog_tcp);
+ bdrv_register(&bdrv_sheepdog_unix);
}
block_init(bdrv_sheepdog_init);
projects / qemu.git / blobdiff