QPID-3603: Minor improvements to HA tests, documentation and examples.

git-svn-id: https://svn.apache.org/repos/asf/qpid/trunk@1326755 13f79535-47bb-0310-9956-ffa450edef68

7 files changed, 38 insertions, 56 deletions

diff --git a/qpid/cpp/etc/cluster.conf-example.xml.in b/qpid/cpp/etc/cluster.conf-example.xml.in
index eb70ebbb1e..14b961a363 100644
--- a/qpid/cpp/etc/cluster.conf-example.xml.in
+++ b/qpid/cpp/etc/cluster.conf-example.xml.in
@@ -2,36 +2,33 @@
 <!--
 This is an example of a cluster.conf file to run qpidd HA under rgmanager.
 This example assumes a 3 node cluster, with nodes named node1, node2 and node3.
+
+NOTE: fencing is not shown, it should be configured in a real cluster configuration.
 -->
 
 <cluster name="qpid-test" config_version="18">
-  <!-- The cluster has 3 nodes. Each has a unique nodid and one vote for quorum. -->
+  <!-- The cluster has 3 nodes. Each has a unique nodid and one vote
+       for quorum. -->
   <clusternodes>
-    <clusternode name="node1" nodeid="1">
-      <fence/>
-    </clusternode>
-    <clusternode name="node2" nodeid="2">
-      <fence/>
-    </clusternode>
-    <clusternode name="node3" nodeid="3">
-      <fence/>
-    </clusternode>
+    <clusternode name="node1.example.com" nodeid="1"/>
+    <clusternode name="node2.example.com" nodeid="2"/>
+    <clusternode name="node3.example.com" nodeid="3"/>
   </clusternodes>
   <!-- Resouce Manager configuration. -->
-  <rm log_level="7">		<!-- Verbose logging -->
+  <rm>
     <!--
 	There is a failoverdomain for each node containing just that node.
-	This lets us stipulate that the qpidd service should always run on all nodes.
+	This lets us stipulate that the qpidd service should always run on each node.
     -->
     <failoverdomains>
       <failoverdomain name="node1-domain" restricted="1">
-	<failoverdomainnode name="node1"/>
+	<failoverdomainnode name="node1.example.com"/>
       </failoverdomain>
       <failoverdomain name="node2-domain" restricted="1">
-	<failoverdomainnode name="node2"/>
+	<failoverdomainnode name="node2.example.com"/>
       </failoverdomain>
       <failoverdomain name="node3-domain" restricted="1">
-	<failoverdomainnode name="node3"/>
+	<failoverdomainnode name="node3.example.com"/>
       </failoverdomain>
     </failoverdomains>
 
diff --git a/qpid/cpp/etc/qpidd.in b/qpid/cpp/etc/qpidd.in
index 23c15283dc..2b43625b7d 100755
--- a/qpid/cpp/etc/qpidd.in
+++ b/qpid/cpp/etc/qpidd.in
@@ -39,13 +39,14 @@ prog=qpidd
 lockfile=/var/lock/subsys/$prog
 pidfile=/var/run/qpidd.pid
 
-# Source function library.
-. /etc/rc.d/init.d/functions
-
+# Source configuration
 if [ -f !!sysconfdir!!/sysconfig/$prog ] ; then
 	. !!sysconfdir!!/sysconfig/$prog
 fi
 
+# Source function library.
+. /etc/rc.d/init.d/functions
+
 RETVAL=0
 
 #ensure binary is present and executable
diff --git a/qpid/cpp/src/tests/cluster.mk b/qpid/cpp/src/tests/cluster.mk
index 199d1e7b57..df24f021ba 100644
--- a/qpid/cpp/src/tests/cluster.mk
+++ b/qpid/cpp/src/tests/cluster.mk
@@ -25,8 +25,7 @@
 CLUSTER_TEST_SCRIPTS_LIST=			\
 	allhosts rsynchosts			\
 	qpid-build-rinstall qpid-src-rinstall	\
-	qpid-test-cluster			\
-	qpid-cluster-benchmark
+	qpid-test-cluster
 
 EXTRA_DIST +=					\
 	$(CLUSTER_TEST_SCRIPTS_LIST)		\
diff --git a/qpid/cpp/src/tests/cluster_failover b/qpid/cpp/src/tests/cluster_failover
index 2a68d1ec79..43170c731a 100755
--- a/qpid/cpp/src/tests/cluster_failover
+++ b/qpid/cpp/src/tests/cluster_failover
@@ -11,8 +11,9 @@ echo $SEND $RECV
 
 seq 1000000 > $SEND
 
-qpid-receive -f -a 'q;{create:always}' -b $URL --connection-options "{reconnect:true}"  | tee $RECV &
-
-qpid-send -a 'q;{create:always}' -b $URL --connection-options "{reconnect:true}" --send-rate 10 --content-stdin < $SEND &
+qpid-send -a 'cluster_failover;{create:always}' -b $URL --connection-options "{reconnect:true}" --send-rate 10 --content-stdin < $SEND &
 
+while msg=$(qpid-receive -m1 -f -a 'cluster_failover;{create:always}' -b $URL --connection-options "{reconnect:true,heartbeat:1}"); do
+    echo -n $msg; date
+done
 wait
diff --git a/qpid/cpp/src/tests/qpid-cluster-benchmark b/qpid/cpp/src/tests/qpid-cluster-benchmark
index 10b751c46d..fec2eb0e96 100755
--- a/qpid/cpp/src/tests/qpid-cluster-benchmark
+++ b/qpid/cpp/src/tests/qpid-cluster-benchmark
@@ -57,11 +57,12 @@ done
 shift $(($OPTIND-1))
 
 CONNECTION_OPTIONS="--connection-options {tcp-nodelay:$TCP_NODELAY,reconnect:$RECONNECT,heartbeat:$HEARTBEAT}"
+CREATE_OPTIONS="node:{x-declare:{arguments:{'qpid.replicate':all}}}"
 
-REPLICATE="node:{x-declare:{arguments:{'qpid.replicate':all}}}"
 BROKER=$(echo $BROKERS | sed s/,.*//)
 run_test() { echo $*; shift; "$@"; echo; echo; echo; }
 
 OPTS="$OPTS $REPEAT $BROKERS --summarize $QUEUES $SENDERS $RECEIVERS $MESSAGES $CLIENT_HOSTS $SAVE_RECEIVED $CONNECTION_OPTIONS $NO_DELETE"
-OPTS="$OPTS --create-option $REPLICATE"
+OPTS="$OPTS --create-option $CREATE_OPTIONS"
+
 run_test "Benchmark:" qpid-cpp-benchmark $OPTS "$@"
diff --git a/qpid/cpp/src/tests/qpid-cpp-benchmark b/qpid/cpp/src/tests/qpid-cpp-benchmark
index 19c01dd08a..1c649b333a 100755
--- a/qpid/cpp/src/tests/qpid-cpp-benchmark
+++ b/qpid/cpp/src/tests/qpid-cpp-benchmark
@@ -169,18 +169,6 @@ def first_line(p):
         raise Exception("Process exit %d: %s"%(p.returncode, error_msg(out,err)))
     return out.split("\n")[0]
 
-def queue_exists(queue,broker):
-    c = qpid.messaging.Connection(broker)
-    c.open()
-    try:
-        s = c.session()
-        try:
-            s.sender(queue)
-            return True
-        except qpid.messaging.exceptions.NotFound:
-            return False
-    finally: c.close()
-
 def recreate_queues(queues, brokers, no_delete, opts):
     c = qpid.messaging.Connection(brokers[0])
     c.open()
@@ -189,15 +177,9 @@ def recreate_queues(queues, brokers, no_delete, opts):
         if not no_delete:
             try: s.sender("%s;{delete:always}"%(q)).close()
             except qpid.messaging.exceptions.NotFound: pass
-            # FIXME aconway 2011-05-04: new cluster async wiring, wait for changes to propagate
-            for b in brokers:
-                while queue_exists(q,b): time.sleep(0.1);
         address = "%s;{%s}"%(q, ",".join(opts.create_option + ["create:always"]))
         if opts.verbose: print "Creating", address
         s.sender(address)
-        # FIXME aconway 2011-05-04: new cluster async wiring, wait for changes to propagate
-        for b in brokers:
-            while not queue_exists(q,b): time.sleep(0.1);
     c.close()
 
 def print_header(timestamp):
diff --git a/qpid/doc/book/src/Active-Passive-Cluster.xml b/qpid/doc/book/src/Active-Passive-Cluster.xml
index ffec584679..5f5823bdd2 100644
--- a/qpid/doc/book/src/Active-Passive-Cluster.xml
+++ b/qpid/doc/book/src/Active-Passive-Cluster.xml
@@ -316,39 +316,42 @@ under the License.
 <!--
 This is an example of a cluster.conf file to run qpidd HA under rgmanager.
 This example assumes a 3 node cluster, with nodes named node1, node2 and node3.
+
+NOTE: fencing is not shown, you must configure fencing appropriately for your cluster.
 -->
 
 <cluster name="qpid-test" config_version="18">
-  <!-- The cluster has 3 nodes. Each has a unique nodid and one vote for quorum. -->
+  <!-- The cluster has 3 nodes. Each has a unique nodid and one vote
+       for quorum. -->
   <clusternodes>
-    <clusternode name="node1" nodeid="1"/>
-    <clusternode name="node2" nodeid="2"/>
-    <clusternode name="node3" nodeid="3"/>
+    <clusternode name="node1.example.com" nodeid="1"/>
+    <clusternode name="node2.example.com" nodeid="2"/>
+    <clusternode name="node3.example.com" nodeid="3"/>
   </clusternodes>
   <!-- Resouce Manager configuration. -->
-  <rm log_level="7">		<!-- Verbose logging -->
+  <rm>
     <!--
 	There is a failoverdomain for each node containing just that node.
-	This lets us stipulate that the qpidd service should always run on all nodes.
+	This lets us stipulate that the qpidd service should always run on each node.
     -->
     <failoverdomains>
       <failoverdomain name="node1-domain" restricted="1">
-	<failoverdomainnode name="node1"/>
+	<failoverdomainnode name="node1.example.com"/>
       </failoverdomain>
       <failoverdomain name="node2-domain" restricted="1">
-	<failoverdomainnode name="node2"/>
+	<failoverdomainnode name="node2.example.com"/>
       </failoverdomain>
       <failoverdomain name="node3-domain" restricted="1">
-	<failoverdomainnode name="node3"/>
+	<failoverdomainnode name="node3.example.com"/>
       </failoverdomain>
     </failoverdomains>
 
     <resources>
       <!-- This script starts a qpidd broker acting as a backup. -->
-      <script file="!!sysconfdir!!/init.d/qpidd" name="qpidd"/>
+      <script file="/etc/init.d/qpidd" name="qpidd"/>
 
       <!-- This script promotes the qpidd broker on this node to primary. -->
-      <script file="!!sysconfdir!!/init.d/qpidd-primary" name="qpidd-primary"/>
+      <script file="/etc/init.d/qpidd-primary" name="qpidd-primary"/>
 
       <!-- This is a virtual IP address for broker replication traffic. -->
       <ip address="20.0.10.200" monitor_link="1"/>
@@ -376,8 +379,6 @@ This example assumes a 3 node cluster, with nodes named node1, node2 and node3.
       <ip ref="20.0.20.200"/>
     </service>
   </rm>
-  <fencedevices/>
-  <fence_daemon clean_start="0" post_fail_delay="0" post_join_delay="3"/>
 </cluster>
       ]]>
     </programlisting>