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
(cherry picked from commit e7069082e5f0380dcddee247db8754218ce18cab)

diff --git a/include/ctdb.h b/include/ctdb.h
index 7f0ff2fc4c6012cdaf803fb88c425cfb4e771241..ff798c8e72e45861e6f88f5b0f4fe92112146901 100644 (file)
--- a/include/ctdb.h
+++ b/include/ctdb.h
@@ -76,6 +76,12 @@ 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 beaf125f2eb6c86e0309eda0775b1c1e2a290197..e381c5b9fba3f87c8b5eac93c3e6433fdb75aa6f 100644 (file)
--- a/include/ctdb_private.h
+++ b/include/ctdb_private.h
@@ -1683,6 +1683,8 @@ void ctdb_fault_setup(void);
 
 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);
 
 /**
  * structure to pass to a schedule_for_deletion_control

diff --git a/server/ctdb_recoverd.c b/server/ctdb_recoverd.c
index 7dcc29a6c6cca195b1c55c2259169e2dd0c0f023..f91bcd0a1a2d37e5204807c22885509ea47b1015 100644 (file)
--- a/server/ctdb_recoverd.c
+++ b/server/ctdb_recoverd.c
@@ -1899,6 +1899,29 @@ 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)
 {
@@ -2870,6 +2893,9 @@ 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 c06c595bfaabd4bb54d9685d0438031464f259c7..62f54d88168f7ad4ca3a70f5a12ca998863685b7 100644 (file)
--- a/server/ctdb_takeover.c
+++ b/server/ctdb_takeover.c
@@ -2854,3 +2854,24 @@ 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 28fa676c42f104457633eb338eb23d940257c3c0..ada9b47e5e1675c235b30bdcf3237429f3c0870b 100644 (file)
--- a/tools/ctdb.c
+++ b/tools/ctdb.c
@@ -1092,6 +1092,15 @@ 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;
 }