diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c index 983285540945451149c1363ea65a098d4f27c2ca..a32f0f896d9f3c8d29b6d5758df000ae556b8683 100644 --- a/fs/ceph/messenger.c +++ b/fs/ceph/messenger.c @@ -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 */ diff --git a/fs/ceph/messenger.h b/fs/ceph/messenger.h index 4caaa5911110372510946678dc62b1ac181fcc38..a343dae73cdcf4f6f458480e4b910e5b9889093e 100644 --- a/fs/ceph/messenger.h +++ b/fs/ceph/messenger.h @@ -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); diff --git a/fs/ceph/osd_client.c b/fs/ceph/osd_client.c index 04359217ea6c2665802c6a67dbf5963bc2047688..c7b4dedaace674d60112326531d0d467dd69d122 100644 --- a/fs/ceph/osd_client.c +++ b/fs/ceph/osd_client.c @@ -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 =