ctdb-recoverd: Freeze databases whenever the node is INACTIVE

If the node becomes stopped or banned after recovery is marked
active, then it will never freeze the databases, and hence the
node will keep banning itself indefinitely, until ctdbd is restarted.

This is a regression from 4.3, introduced with

b4357a79d916b1f8ade8fa78563fbef0ce670aa9

and

d8f3b490bbb691c9916eed0df5b980c1aef23c85

BUG: https://bugzilla.samba.org/show_bug.cgi?id=11945

Signed-off-by: Amitay Isaacs <amitay@gmail.com>
Reviewed-by: Michael Adam <obnox@samba.org>
Reviewed-by: Martin Schwenke <martin@meltin.net>
Autobuild-User(master): Michael Adam <obnox@samba.org>
Autobuild-Date(master): Wed Jun  1 17:36:12 CEST 2016 on sn-devel-144

diff --git a/ctdb/server/ctdb_recoverd.c b/ctdb/server/ctdb_recoverd.c
index 09940dc32f881b05a277b5299510fa9bf576e8f0..cb5f8a34fd78a43fe38a3e1a252b30c02573e87d 100644 (file)
--- a/ctdb/server/ctdb_recoverd.c
+++ b/ctdb/server/ctdb_recoverd.c
@@ -257,6 +257,7 @@ struct ctdb_recoverd {
        struct ctdb_iface_list_old *ifaces;
        uint32_t *force_rebalance_nodes;
        struct ctdb_node_capabilities *caps;
+       bool frozen_on_inactive;
 };
 
 #define CONTROL_TIMEOUT() timeval_current_ofs(ctdb->tunable.recover_timeout, 0)
@@ -3550,11 +3551,18 @@ static void main_loop(struct ctdb_context *ctdb, struct ctdb_recoverd *rec,
 
                                return;
                        }
-                       ret = ctdb_ctrl_freeze(ctdb, CONTROL_TIMEOUT(), CTDB_CURRENT_NODE);
+               }
+               if (! rec->frozen_on_inactive) {
+                       ret = ctdb_ctrl_freeze(ctdb, CONTROL_TIMEOUT(),
+                                              CTDB_CURRENT_NODE);
                        if (ret != 0) {
-                               DEBUG(DEBUG_ERR,(__location__ " Failed to freeze node in STOPPED or BANNED state\n"));
+                               DEBUG(DEBUG_ERR,
+                                     (__location__ " Failed to freeze node "
+                                      "in STOPPED or BANNED state\n"));
                                return;
                        }
+
+                       rec->frozen_on_inactive = true;
                }
 
                /* If this node is stopped or banned then it is not the recovery
@@ -3564,6 +3572,8 @@ static void main_loop(struct ctdb_context *ctdb, struct ctdb_recoverd *rec,
                return;
        }
 
+       rec->frozen_on_inactive = false;
+
        /* Retrieve capabilities from all connected nodes */
        ret = update_capabilities(rec, nodemap);
        if (ret != 0) {
@@ -3901,6 +3911,7 @@ static void monitor_cluster(struct ctdb_context *ctdb)
        CTDB_NO_MEMORY_FATAL(ctdb, rec->recovery);
 
        rec->priority_time = timeval_current();
+       rec->frozen_on_inactive = false;
 
        /* register a message port for sending memory dumps */
        ctdb_client_set_message_handler(ctdb, CTDB_SRVID_MEM_DUMP, mem_dump_handler, rec);