op == CEPH_OSD_OP_WRITE);
}
-void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
struct ceph_file_layout *layout,
u64 snapid,
u64 off, u64 *plen, u64 *bno,
struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
u64 orig_len = *plen;
u64 objoff, objlen; /* extent in object */
+ int r;
reqhead->snapid = cpu_to_le64(snapid);
/* object extent? */
- ceph_calc_file_object_mapping(layout, off, plen, bno,
- &objoff, &objlen);
+ r = ceph_calc_file_object_mapping(layout, off, plen, bno,
+ &objoff, &objlen);
+ if (r < 0)
+ return r;
if (*plen < orig_len)
dout(" skipping last %llu, final file extent %llu~%llu\n",
orig_len - *plen, off, *plen);
dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
*bno, objoff, objlen, req->r_num_pages);
-
+ return 0;
}
EXPORT_SYMBOL(ceph_calc_raw_layout);
*
* fill osd op in request message.
*/
-static void calc_layout(struct ceph_osd_client *osdc,
- struct ceph_vino vino,
- struct ceph_file_layout *layout,
- u64 off, u64 *plen,
- struct ceph_osd_request *req,
- struct ceph_osd_req_op *op)
+static int calc_layout(struct ceph_osd_client *osdc,
+ struct ceph_vino vino,
+ struct ceph_file_layout *layout,
+ u64 off, u64 *plen,
+ struct ceph_osd_request *req,
+ struct ceph_osd_req_op *op)
{
u64 bno;
+ int r;
- ceph_calc_raw_layout(osdc, layout, vino.snap, off,
- plen, &bno, req, op);
+ r = ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+ plen, &bno, req, op);
+ if (r < 0)
+ return r;
snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno);
req->r_oid_len = strlen(req->r_oid);
+
+ return r;
}
/*
if (req->r_request)
ceph_msg_put(req->r_request);
if (req->r_con_filling_msg) {
- dout("release_request revoking pages %p from con %p\n",
+ dout("%s revoking pages %p from con %p\n", __func__,
req->r_pages, req->r_con_filling_msg);
- ceph_con_revoke_message(req->r_con_filling_msg,
- req->r_reply);
+ ceph_msg_revoke_incoming(req->r_reply);
req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
}
if (req->r_reply)
kref_init(&req->r_kref);
init_completion(&req->r_completion);
init_completion(&req->r_safe_completion);
+ rb_init_node(&req->r_node);
INIT_LIST_HEAD(&req->r_unsafe_item);
INIT_LIST_HEAD(&req->r_linger_item);
INIT_LIST_HEAD(&req->r_linger_osd);
INIT_LIST_HEAD(&req->r_req_lru_item);
+ INIT_LIST_HEAD(&req->r_osd_item);
+
req->r_flags = flags;
WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
}
ceph_pagelist_init(req->r_trail);
}
+
/* create request message; allow space for oid */
msg_size += MAX_OBJ_NAME_SIZE;
if (snapc)
return NULL;
}
- msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
memset(msg->front.iov_base, 0, msg->front.iov_len);
req->r_request = msg;
{
struct ceph_osd_req_op ops[3];
struct ceph_osd_request *req;
+ int r;
ops[0].op = opcode;
ops[0].extent.truncate_seq = truncate_seq;
use_mempool,
GFP_NOFS, NULL, NULL);
if (!req)
- return NULL;
+ return ERR_PTR(-ENOMEM);
/* calculate max write size */
- calc_layout(osdc, vino, layout, off, plen, req, ops);
+ r = calc_layout(osdc, vino, layout, off, plen, req, ops);
+ if (r < 0)
+ return ERR_PTR(r);
req->r_file_layout = *layout; /* keep a copy */
/* in case it differs from natural (file) alignment that
dout("__kick_osd_requests osd%d\n", osd->o_osd);
err = __reset_osd(osdc, osd);
- if (err == -EAGAIN)
+ if (err)
return;
list_for_each_entry(req, &osd->o_requests, r_osd_item) {
}
}
-static void kick_osd_requests(struct ceph_osd_client *osdc,
- struct ceph_osd *kickosd)
-{
- mutex_lock(&osdc->request_mutex);
- __kick_osd_requests(osdc, kickosd);
- mutex_unlock(&osdc->request_mutex);
-}
-
/*
* If the osd connection drops, we need to resubmit all requests.
*/
dout("osd_reset osd%d\n", osd->o_osd);
osdc = osd->o_osdc;
down_read(&osdc->map_sem);
- kick_osd_requests(osdc, osd);
+ mutex_lock(&osdc->request_mutex);
+ __kick_osd_requests(osdc, osd);
+ mutex_unlock(&osdc->request_mutex);
send_queued(osdc);
up_read(&osdc->map_sem);
}
/*
* Track open sessions with osds.
*/
-static struct ceph_osd *create_osd(struct ceph_osd_client *osdc)
+static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum)
{
struct ceph_osd *osd;
atomic_set(&osd->o_ref, 1);
osd->o_osdc = osdc;
+ osd->o_osd = onum;
+ RB_CLEAR_NODE(&osd->o_node);
INIT_LIST_HEAD(&osd->o_requests);
INIT_LIST_HEAD(&osd->o_linger_requests);
INIT_LIST_HEAD(&osd->o_osd_lru);
osd->o_incarnation = 1;
- ceph_con_init(osdc->client->msgr, &osd->o_con);
- osd->o_con.private = osd;
- osd->o_con.ops = &osd_con_ops;
- osd->o_con.peer_name.type = CEPH_ENTITY_TYPE_OSD;
+ ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr);
INIT_LIST_HEAD(&osd->o_keepalive_item);
return osd;
static void remove_all_osds(struct ceph_osd_client *osdc)
{
- dout("__remove_old_osds %p\n", osdc);
+ dout("%s %p\n", __func__, osdc);
mutex_lock(&osdc->request_mutex);
while (!RB_EMPTY_ROOT(&osdc->osds)) {
struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
if (list_empty(&osd->o_requests) &&
list_empty(&osd->o_linger_requests)) {
__remove_osd(osdc, osd);
+ ret = -ENODEV;
} else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd],
&osd->o_con.peer_addr,
sizeof(osd->o_con.peer_addr)) == 0 &&
ret = -EAGAIN;
} else {
ceph_con_close(&osd->o_con);
- ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]);
+ ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd,
+ &osdc->osdmap->osd_addr[osd->o_osd]);
osd->o_incarnation++;
}
return ret;
if (req->r_osd) {
/* make sure the original request isn't in flight. */
- ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+ ceph_msg_revoke(req->r_request);
list_del_init(&req->r_osd_item);
if (list_empty(&req->r_osd->o_requests) &&
req->r_osd = NULL;
}
+ list_del_init(&req->r_req_lru_item);
ceph_osdc_put_request(req);
- list_del_init(&req->r_req_lru_item);
if (osdc->num_requests == 0) {
dout(" no requests, canceling timeout\n");
__cancel_osd_timeout(osdc);
static void __cancel_request(struct ceph_osd_request *req)
{
if (req->r_sent && req->r_osd) {
- ceph_con_revoke(&req->r_osd->o_con, req->r_request);
+ ceph_msg_revoke(req->r_request);
req->r_sent = 0;
}
}
{
dout("__register_linger_request %p\n", req);
list_add_tail(&req->r_linger_item, &osdc->req_linger);
- list_add_tail(&req->r_linger_osd, &req->r_osd->o_linger_requests);
+ if (req->r_osd)
+ list_add_tail(&req->r_linger_osd,
+ &req->r_osd->o_linger_requests);
}
static void __unregister_linger_request(struct ceph_osd_client *osdc,
struct ceph_osd_request *req)
{
dout("__unregister_linger_request %p\n", req);
+ list_del_init(&req->r_linger_item);
if (req->r_osd) {
- list_del_init(&req->r_linger_item);
list_del_init(&req->r_linger_osd);
if (list_empty(&req->r_osd->o_requests) &&
req->r_osd = __lookup_osd(osdc, o);
if (!req->r_osd && o >= 0) {
err = -ENOMEM;
- req->r_osd = create_osd(osdc);
+ req->r_osd = create_osd(osdc, o);
if (!req->r_osd) {
list_move(&req->r_req_lru_item, &osdc->req_notarget);
goto out;
}
dout("map_request osd %p is osd%d\n", req->r_osd, o);
- req->r_osd->o_osd = o;
- req->r_osd->o_con.peer_name.num = cpu_to_le64(o);
__insert_osd(osdc, req->r_osd);
- ceph_con_open(&req->r_osd->o_con, &osdc->osdmap->osd_addr[o]);
+ ceph_con_open(&req->r_osd->o_con,
+ CEPH_ENTITY_TYPE_OSD, o,
+ &osdc->osdmap->osd_addr[o]);
}
if (req->r_osd) {
{
struct ceph_osd_client *osdc =
container_of(work, struct ceph_osd_client, timeout_work.work);
- struct ceph_osd_request *req, *last_req = NULL;
+ struct ceph_osd_request *req;
struct ceph_osd *osd;
- unsigned long timeout = osdc->client->options->osd_timeout * HZ;
unsigned long keepalive =
osdc->client->options->osd_keepalive_timeout * HZ;
- unsigned long last_stamp = 0;
struct list_head slow_osds;
dout("timeout\n");
down_read(&osdc->map_sem);
mutex_lock(&osdc->request_mutex);
- /*
- * reset osds that appear to be _really_ unresponsive. this
- * is a failsafe measure.. we really shouldn't be getting to
- * this point if the system is working properly. the monitors
- * should mark the osd as failed and we should find out about
- * it from an updated osd map.
- */
- while (timeout && !list_empty(&osdc->req_lru)) {
- req = list_entry(osdc->req_lru.next, struct ceph_osd_request,
- r_req_lru_item);
-
- /* hasn't been long enough since we sent it? */
- if (time_before(jiffies, req->r_stamp + timeout))
- break;
-
- /* hasn't been long enough since it was acked? */
- if (req->r_request->ack_stamp == 0 ||
- time_before(jiffies, req->r_request->ack_stamp + timeout))
- break;
-
- BUG_ON(req == last_req && req->r_stamp == last_stamp);
- last_req = req;
- last_stamp = req->r_stamp;
-
- osd = req->r_osd;
- BUG_ON(!osd);
- pr_warning(" tid %llu timed out on osd%d, will reset osd\n",
- req->r_tid, osd->o_osd);
- __kick_osd_requests(osdc, osd);
- }
-
/*
* ping osds that are a bit slow. this ensures that if there
* is a break in the TCP connection we will notice, and reopen
dout("kick_requests %s\n", force_resend ? " (force resend)" : "");
mutex_lock(&osdc->request_mutex);
- for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+ for (p = rb_first(&osdc->requests); p; ) {
req = rb_entry(p, struct ceph_osd_request, r_node);
+ p = rb_next(p);
err = __map_request(osdc, req, force_resend);
if (err < 0)
continue; /* error */
dout("%p tid %llu maps to no osd\n", req, req->r_tid);
needmap++; /* request a newer map */
} else if (err > 0) {
- dout("%p tid %llu requeued on osd%d\n", req, req->r_tid,
- req->r_osd ? req->r_osd->o_osd : -1);
- if (!req->r_linger)
+ if (!req->r_linger) {
+ dout("%p tid %llu requeued on osd%d\n", req,
+ req->r_tid,
+ req->r_osd ? req->r_osd->o_osd : -1);
req->r_flags |= CEPH_OSD_FLAG_RETRY;
+ }
+ }
+ if (req->r_linger && list_empty(&req->r_linger_item)) {
+ /*
+ * register as a linger so that we will
+ * re-submit below and get a new tid
+ */
+ dout("%p tid %llu restart on osd%d\n",
+ req, req->r_tid,
+ req->r_osd ? req->r_osd->o_osd : -1);
+ __register_linger_request(osdc, req);
+ __unregister_request(osdc, req);
}
}
epoch, maplen);
newmap = osdmap_apply_incremental(&p, next,
osdc->osdmap,
- osdc->client->msgr);
+ &osdc->client->msgr);
if (IS_ERR(newmap)) {
err = PTR_ERR(newmap);
goto bad;
if (!osdc->req_mempool)
goto out;
- err = ceph_msgpool_init(&osdc->msgpool_op, OSD_OP_FRONT_LEN, 10, true,
+ err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
+ OSD_OP_FRONT_LEN, 10, true,
"osd_op");
if (err < 0)
goto out_mempool;
- err = ceph_msgpool_init(&osdc->msgpool_op_reply,
+ err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
OSD_OPREPLY_FRONT_LEN, 10, true,
"osd_op_reply");
if (err < 0)
CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
NULL, 0, truncate_seq, truncate_size, NULL,
false, 1, page_align);
- if (!req)
- return -ENOMEM;
+ if (IS_ERR(req))
+ return PTR_ERR(req);
/* it may be a short read due to an object boundary */
req->r_pages = pages;
snapc, do_sync,
truncate_seq, truncate_size, mtime,
nofail, 1, page_align);
- if (!req)
- return -ENOMEM;
+ if (IS_ERR(req))
+ return PTR_ERR(req);
/* it may be a short write due to an object boundary */
req->r_pages = pages;
if (!req) {
*skip = 1;
m = NULL;
- pr_info("get_reply unknown tid %llu from osd%d\n", tid,
- osd->o_osd);
+ dout("get_reply unknown tid %llu from osd%d\n", tid,
+ osd->o_osd);
goto out;
}
if (req->r_con_filling_msg) {
- dout("get_reply revoking msg %p from old con %p\n",
+ dout("%s revoking msg %p from old con %p\n", __func__,
req->r_reply, req->r_con_filling_msg);
- ceph_con_revoke_message(req->r_con_filling_msg, req->r_reply);
+ ceph_msg_revoke_incoming(req->r_reply);
req->r_con_filling_msg->ops->put(req->r_con_filling_msg);
req->r_con_filling_msg = NULL;
}
int type = le16_to_cpu(hdr->type);
int front = le32_to_cpu(hdr->front_len);
+ *skip = 0;
switch (type) {
case CEPH_MSG_OSD_MAP:
case CEPH_MSG_WATCH_NOTIFY: