cluster show: differentiate unreachable status

Differentiate between unreachable nodes and nodes which are running
but rejecting connections.

HISTORY

@@ -2,6 +2,8 @@
         repmgr: add "daemon (start|stop)" command; GitHub #528 (Ian)
         repmgr: add --version-number command line option (Ian)
         repmgr: add --compact option to "cluster show"; GitHub #521 (Ian)
+		repmgr: cluster show - differentiate between unreachable nodes
+		  and nodes which are running but rejecting connections (Ian)
         repmgr: add --dry-run option to "standby promote"; GitHub #522 (Ian)
         repmgr: add "node check --data-directory-config"; GitHub #523 (Ian)
         repmgr: prevent potential race condition in "standby switchover"

dbutils.h

@@ -80,7 +80,8 @@ typedef enum
 	NODE_STATUS_UP,
 	NODE_STATUS_SHUTTING_DOWN,
 	NODE_STATUS_DOWN,
-	NODE_STATUS_UNCLEAN_SHUTDOWN
+	NODE_STATUS_UNCLEAN_SHUTDOWN,
+	NODE_STATUS_REJECTED
 } NodeStatus;
 
 typedef enum

doc/appendix-release-notes.sgml

@@ -88,6 +88,18 @@ REPMGRD_OPTS="--daemonize=false"</programlisting>
             </para>
           </listitem>
 
+          <listitem>
+            <para>
+              <command><link linkend="repmgr-cluster-show">repmgr cluster show</link></command>:
+			  differentiate between unreachable nodes and nodes which are running but rejecting connections.
+            </para>
+            <para>
+			  This makes it possible to see whether a node is unreachable at network level,
+			  or if it is running but rejecting connections for some reason.
+            </para>
+          </listitem>
+
+
           <listitem>
             <para>
               Add <option>--dry-run</option> to <command><link linkend="repmgr-standby-promote">repmgr standby promote</link></command> (GitHub #522).

doc/repmgr-cluster-show.sgml

@@ -22,6 +22,14 @@
       directly and can be run on any node in the cluster; this is also useful when analyzing
       connectivity from a particular node.
     </para>
+
+    <para>
+      Node availability is tested by connecting from the node where
+      <command>repmgr cluster show</command> is executed, and does not necessarily imply the node
+      is down. See <xref linkend="repmgr-cluster-matrix"> and <xref linkend="repmgr-cluster-crosscheck"> to get
+      better overviews of connections between nodes.
+    </para>
+
   </refsect1>
 
   <refsect1>
@@ -55,30 +63,48 @@
     <title>Notes</title>
     <para>
       The column <literal>Role</literal> shows the expected server role according to the
-      &repmgr; metadata. <literal>Status</literal> shows whether the server is running or unreachable.
+      &repmgr; metadata.
+	</para>
+	<para>
+	  <literal>Status</literal> shows whether the server is running or unreachable.
       If the node has an unexpected role not reflected in the &repmgr; metadata, e.g. a node was manually
-      promoted to primary, this will be highlighted with an exclamation mark, e.g.:
+      promoted to primary, this will be highlighted with an exclamation mark.
+	  If a connection to the node cannot be made, this will be highlighted with a question mark.
+	  Note that the node will only be shown as <literal>? unreachable</literal>
+	  if a connection is not possible at network level; if the PostgreSQL instance on the
+	  node is pingable but not accepting connections, it will be shown as <literal>? running</literal>.
+	</para>
+	<para>
+	  In the following example, executed on <literal>node3</literal>, <literal>node1</literal> is not reachable
+	  at network level and assumed to be down; <literal>node2</literal> has been promoted to primary
+	  (but <literal>node3</literal> is not attached to it, and its metadata has not yet been updated);
+	  <literal>node4</literal> is running but rejecting connections (from <literal>node3</literal> at least).
       <programlisting>
-    $ repmgr -f /etc/repmgr.conf cluster show
-
 	 ID | Name  | Role    | Status               | Upstream | Location | Priority | Connection string
 	----+-------+---------+----------------------+----------+----------+----------+-----------------------------------------
 	 1  | node1 | primary | ? unreachable        |          | default  | 100      | host=db_node1 dbname=repmgr user=repmgr
 	 2  | node2 | standby | ! running as primary | node1    | default  | 100      | host=db_node2 dbname=repmgr user=repmgr
 	 3  | node3 | standby |   running            | node1    | default  | 100      | host=db_node3 dbname=repmgr user=repmgr
+	 4  | node4 | standby | ? running            | node1    | default  | 100      | host=db_node4 dbname=repmgr user=repmgr
 
 	WARNING: following issues were detected
 	  - unable to connect to node "node1" (ID: 1)
 	  - node "node1" (ID: 1) is registered as an active primary but is unreachable
 	  - node "node2" (ID: 2) is registered as standby but running as primary
+	  - unable to connect to node "node4" (ID: 4)
     HINT: execute with --verbose option to see connection error messages</programlisting>
     </para>
 	<para>
-      Node availability is tested by connecting from the node where
-      <command>repmgr cluster show</command> is executed, and does not necessarily imply the node
-      is down. See <xref linkend="repmgr-cluster-matrix"> and <xref linkend="repmgr-cluster-crosscheck"> to get
-      better overviews of connections between nodes.
+	  To diagnose connection issues, execute <command>repmgr cluster show</command>
+	  with the <option>--verbose</option> option; this will display the error message
+	  for each failed connection attempt.
 	</para>
+	<tip>
+	  <para>
+		Use <xref linkend="repmgr-cluster-matrix"> and <xref linkend="repmgr-cluster-crosscheck">
+		to diagnose connection issues across the whole replication cluster.
+	  </para>
+	</tip>
   </refsect1>
 
   <refsect1>

repmgr-action-cluster.c

@@ -155,7 +155,12 @@ do_cluster_show(void)
 		}
 		else
 		{
+			/* check if node is reachable, but just not letting us in */
+			if (is_server_available(cell->node_info->conninfo))
+				cell->node_info->node_status = NODE_STATUS_REJECTED;
+			else
 				cell->node_info->node_status = NODE_STATUS_DOWN;
+
 			cell->node_info->recovery_type = RECTYPE_UNKNOWN;
 
 			connection_error_found = true;
@@ -230,6 +235,19 @@ do_cluster_show(void)
 							}
 						}
 					}
+					/* node is up but cannot connect */
+					else if (cell->node_info->node_status == NODE_STATUS_REJECTED)
+					{
+						if (cell->node_info->active == true)
+						{
+							appendPQExpBufferStr(&details, "? running");
+						}
+						else
+						{
+							appendPQExpBufferStr(&details, "! running");
+								error_found = true;
+						}
+					}
 					/* node is unreachable */
 					else
 					{
@@ -303,6 +321,19 @@ do_cluster_show(void)
 													cell->node_info->node_name, cell->node_info->node_id);
 						}
 					}
+					/* node is up but cannot connect */
+					else if (cell->node_info->node_status == NODE_STATUS_REJECTED)
+					{
+						if (cell->node_info->active == true)
+						{
+							appendPQExpBufferStr(&details, "? running");
+						}
+						else
+						{
+							appendPQExpBufferStr(&details, "! running");
+								error_found = true;
+						}
+					}
 					/* node is unreachable */
 					else
 					{
@@ -320,7 +351,6 @@ do_cluster_show(void)
 								error_found = true;
 						}
 					}
-
 				}
 
 				break;
@@ -340,6 +370,20 @@ do_cluster_show(void)
 							error_found = true;
 						}
 					}
+					/* node is up but cannot connect */
+					else if (cell->node_info->node_status == NODE_STATUS_REJECTED)
+					{
+						if (cell->node_info->active == true)
+						{
+							appendPQExpBufferStr(&details, "? rejected");
+						}
+						else
+						{
+							appendPQExpBufferStr(&details, "! failed");
+							error_found = true;
+						}
+
+					}
 					/* node is unreachable */
 					else
 					{