ceph: avoid reopening osd connections when address hasn't changed
We get a fault callback on _every_ tcp connection fault. Normally, we want to reopen the connection when that happens. If the address we have is bad, however, and connection attempts always result in a connection refused or similar error, explicitly closing and reopening the msgr connection just prevents the messenger's backoff logic from kicking in. The result can be a console full of [ 3974.417106] ceph: osd11 10.3.14.138:6800 connection failed [ 3974.423295] ceph: osd11 10.3.14.138:6800 connection failed [ 3974.429709] ceph: osd11 10.3.14.138:6800 connection failed Instead, if we get a fault, and have outstanding requests, but the osd address hasn't changed and the connection never successfully connected in the first place, do nothing to the osd connection. The messenger layer will back off and retry periodically, because we never connected and thus the lossy bit is not set. Instead, touch each request's r_stamp so that handle_timeout can tell the request is still alive and kicking. Signed-off-by: Sage Weil <sage@newdream.net>
This commit is contained in:
parent
3dd72fc0e6
commit
87b315a5b5
|
@ -365,6 +365,14 @@ void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
|
|||
queue_con(con);
|
||||
}
|
||||
|
||||
/*
|
||||
* return true if this connection ever successfully opened
|
||||
*/
|
||||
bool ceph_con_opened(struct ceph_connection *con)
|
||||
{
|
||||
return con->connect_seq > 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* generic get/put
|
||||
*/
|
||||
|
|
|
@ -223,6 +223,7 @@ extern void ceph_con_init(struct ceph_messenger *msgr,
|
|||
struct ceph_connection *con);
|
||||
extern void ceph_con_open(struct ceph_connection *con,
|
||||
struct ceph_entity_addr *addr);
|
||||
extern bool ceph_con_opened(struct ceph_connection *con);
|
||||
extern void ceph_con_close(struct ceph_connection *con);
|
||||
extern void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg);
|
||||
extern void ceph_con_revoke(struct ceph_connection *con, struct ceph_msg *msg);
|
||||
|
|
|
@ -413,11 +413,22 @@ static void remove_old_osds(struct ceph_osd_client *osdc, int remove_all)
|
|||
*/
|
||||
static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
|
||||
{
|
||||
struct ceph_osd_request *req;
|
||||
int ret = 0;
|
||||
|
||||
dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
|
||||
if (list_empty(&osd->o_requests)) {
|
||||
__remove_osd(osdc, osd);
|
||||
} else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd],
|
||||
&osd->o_con.peer_addr,
|
||||
sizeof(osd->o_con.peer_addr)) == 0 &&
|
||||
!ceph_con_opened(&osd->o_con)) {
|
||||
dout(" osd addr hasn't changed and connection never opened,"
|
||||
" letting msgr retry");
|
||||
/* touch each r_stamp for handle_timeout()'s benfit */
|
||||
list_for_each_entry(req, &osd->o_requests, r_osd_item)
|
||||
req->r_stamp = jiffies;
|
||||
ret = -EAGAIN;
|
||||
} else {
|
||||
ceph_con_close(&osd->o_con);
|
||||
ceph_con_open(&osd->o_con, &osdc->osdmap->osd_addr[osd->o_osd]);
|
||||
|
@ -862,7 +873,9 @@ static int __kick_requests(struct ceph_osd_client *osdc,
|
|||
|
||||
dout("kick_requests osd%d\n", kickosd ? kickosd->o_osd : -1);
|
||||
if (kickosd) {
|
||||
__reset_osd(osdc, kickosd);
|
||||
err = __reset_osd(osdc, kickosd);
|
||||
if (err == -EAGAIN)
|
||||
return 1;
|
||||
} else {
|
||||
for (p = rb_first(&osdc->osds); p; p = n) {
|
||||
struct ceph_osd *osd =
|
||||
|
|
Loading…
Reference in a new issue