The recent change to the recovery daemon to keep track of and

verify that all nodes agree on the most recent ip address assignments
broke "ctdb moveip ..." since that call would never trigger
a full takeover run and thus would immediately trigger an inconsistency.

Add a new message to the recovery daemon where we can tell the recovery daemon to update its assignments.

BZ62782

diff --git a/include/ctdb.h b/include/ctdb.h
index 3633751ac41ffa791ed7f7ca607fc31e63e8b985..c380c3d33a3fb2bde867eb521514f0e002fd40f5 100644 (file)
--- a/include/ctdb.h
+++ b/include/ctdb.h
@@ -75,6 +75,12 @@ struct ctdb_call_info {
  */
 #define CTDB_SRVID_SET_NODE_FLAGS 0xF400000000000000LL
 
+/* 
+   a message ID to ask the recovery daemon to update the expected node
+   assignment for a public ip
+ */
+#define CTDB_SRVID_RECD_UPDATE_IP 0xF500000000000000LL
+
 /*
   a message to tell the recovery daemon to fetch a set of records
  */

diff --git a/include/ctdb_private.h b/include/ctdb_private.h
index 06985a3ce9823712b6da9e98699194d31fe3d9fd..6c70623263d8b3897ca4f05156de187a88621b04 100644 (file)
--- a/include/ctdb_private.h
+++ b/include/ctdb_private.h
@@ -1566,5 +1566,7 @@ int ctdb_recheck_persistent_health(struct ctdb_context *ctdb);
 
 int verify_remote_ip_allocation(struct ctdb_context *ctdb, 
                                struct ctdb_all_public_ips *ips);
+int update_ip_assignment_tree(struct ctdb_context *ctdb,
+                               struct ctdb_public_ip *ip);
 
 #endif

diff --git a/server/ctdb_recoverd.c b/server/ctdb_recoverd.c
index 6ceb95e2edcd42169239da7024ee86cbab289af3..c2f441bdfd0e2868112bb7986a901d453a6feea1 100644 (file)
--- a/server/ctdb_recoverd.c
+++ b/server/ctdb_recoverd.c
@@ -1814,6 +1814,29 @@ static void reenable_ip_check(struct event_context *ev, struct timed_event *te,
        rec->ip_check_disable_ctx = NULL;
 }
 
+
+static void recd_update_ip_handler(struct ctdb_context *ctdb, uint64_t srvid, 
+                            TDB_DATA data, void *private_data)
+{
+       struct ctdb_recoverd *rec = talloc_get_type(private_data, struct ctdb_recoverd);
+       struct ctdb_public_ip *ip;
+
+       if (rec->recmaster != rec->ctdb->pnn) {
+               DEBUG(DEBUG_INFO,("Not recmaster, ignore update ip message\n"));
+               return;
+       }
+
+       if (data.dsize != sizeof(struct ctdb_public_ip)) {
+               DEBUG(DEBUG_ERR,(__location__ " Incorrect size of recd update ip message. Was %zd but expected %zd bytes\n", data.dsize, sizeof(struct ctdb_public_ip)));
+               return;
+       }
+
+       ip = (struct ctdb_public_ip *)data.dptr;
+
+       update_ip_assignment_tree(rec->ctdb, ip);
+}
+
+
 static void disable_ip_check_handler(struct ctdb_context *ctdb, uint64_t srvid, 
                             TDB_DATA data, void *private_data)
 {
@@ -2807,6 +2830,9 @@ static void monitor_cluster(struct ctdb_context *ctdb)
        /* register a message port for disabling the ip check for a short while */
        ctdb_set_message_handler(ctdb, CTDB_SRVID_DISABLE_IP_CHECK, disable_ip_check_handler, rec);
 
+       /* register a message port for updating the recovery daemons node assignment for an ip */
+       ctdb_set_message_handler(ctdb, CTDB_SRVID_RECD_UPDATE_IP, recd_update_ip_handler, rec);
+
 again:
        if (mem_ctx) {
                talloc_free(mem_ctx);

diff --git a/server/ctdb_takeover.c b/server/ctdb_takeover.c
index eb40357178092bc7a776ce9bf0c3cf7f95187c25..0288dd2796ddf1ba24fbd2fb3c19b55dc7fc202a 100644 (file)
--- a/server/ctdb_takeover.c
+++ b/server/ctdb_takeover.c
@@ -2192,3 +2192,24 @@ int verify_remote_ip_allocation(struct ctdb_context *ctdb, struct ctdb_all_publi
 
        return 0;
 }
+
+int update_ip_assignment_tree(struct ctdb_context *ctdb, struct ctdb_public_ip *ip)
+{
+       struct ctdb_public_ip_list *tmp_ip; 
+
+       if (ctdb->ip_tree == NULL) {
+               DEBUG(DEBUG_ERR,("No ctdb->ip_tree yet. Failed to update ip assignment\n"));
+               return -1;
+       }
+
+       tmp_ip = trbt_lookuparray32(ctdb->ip_tree, IP_KEYLEN, ip_key(&ip->addr));
+       if (tmp_ip == NULL) {
+               DEBUG(DEBUG_ERR,(__location__ " Could not find record for address %s, update ip\n", ctdb_addr_to_str(&ip->addr)));
+               return -1;
+       }
+
+       DEBUG(DEBUG_NOTICE,("Updated ip assignment tree for ip : %s from node %u to node %u\n", ctdb_addr_to_str(&ip->addr), tmp_ip->pnn, ip->pnn));
+       tmp_ip->pnn = ip->pnn;
+
+       return 0;
+}

diff --git a/tools/ctdb.c b/tools/ctdb.c
index b2284b2156fa717fb899062bd6f52f2e26e02ab4..f91c77de80f181ef2c76455b8379c174a1d4f35d 100644 (file)
--- a/tools/ctdb.c
+++ b/tools/ctdb.c
@@ -1032,6 +1032,15 @@ static int move_ip(struct ctdb_context *ctdb, ctdb_sock_addr *addr, uint32_t pnn
                return -1;
        }
 
+       /* update the recovery daemon so it now knows to expect the new
+          node assignment for this ip.
+       */
+       ret = ctdb_send_message(ctdb, CTDB_BROADCAST_CONNECTED, CTDB_SRVID_RECD_UPDATE_IP, data);
+       if (ret != 0) {
+               DEBUG(DEBUG_ERR,("Failed to send message to update the ip on the recovery master.\n"));
+               return -1;
+       }
+
        talloc_free(tmp_ctx);
        return 0;
 }