X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=extraconfig%2Ftasks%2Fyum_update.sh;h=c6313d9d5cdbb0a284b36b6cfc63e029654d9978;hb=1e157766e4430aed80526056ede19d22c03ee5f3;hp=e3e9545d7d96804d40da86b8fb1b59fc7350f6c1;hpb=80d929c75f979d99d4e608aae790f38786b4e055;p=apex-tripleo-heat-templates.git

diff --git a/extraconfig/tasks/yum_update.sh b/extraconfig/tasks/yum_update.sh
index e3e9545d..c6313d9d 100755
--- a/extraconfig/tasks/yum_update.sh
+++ b/extraconfig/tasks/yum_update.sh
@@ -24,6 +24,7 @@ update_identifier=${update_identifier//[^a-zA-Z0-9-_]/}
 # seconds to wait for this node to rejoin the cluster after update
 cluster_start_timeout=600
 galera_sync_timeout=360
+cluster_settle_timeout=1800
 
 timestamp_file="$timestamp_dir/$update_identifier"
 if [[ -a "$timestamp_file" ]]; then
@@ -45,6 +46,35 @@ pacemaker_status=$(systemctl is-active pacemaker)
 pacemaker_dumpfile=$(mktemp)
 
 if [[ "$pacemaker_status" == "active" ]] ; then
+SERVICES="memcached
+httpd
+neutron-dhcp-agent
+neutron-l3-agent
+neutron-metadata-agent
+neutron-openvswitch-agent
+neutron-server
+openstack-ceilometer-alarm-evaluator
+openstack-ceilometer-alarm-notifier
+openstack-ceilometer-api
+openstack-ceilometer-central
+openstack-ceilometer-collector
+openstack-ceilometer-notification
+openstack-cinder-api
+openstack-cinder-scheduler
+openstack-cinder-volume
+openstack-glance-api
+openstack-glance-registry
+openstack-heat-api
+openstack-heat-api-cfn
+openstack-heat-api-cloudwatch
+openstack-heat-engine
+openstack-keystone
+openstack-nova-api
+openstack-nova-conductor
+openstack-nova-consoleauth
+openstack-nova-novncproxy
+openstack-nova-scheduler"
+
     echo "Dumping Pacemaker config"
     pcs cluster cib $pacemaker_dumpfile
 
@@ -62,8 +92,11 @@ if [[ "$pacemaker_status" == "active" ]] ; then
         pcs -f $pacemaker_dumpfile constraint order promote galera-master then openstack-keystone-clone
     fi
 
-    if ! pcs constraint order show | grep "start haproxy-clone then start openstack-keystone-clone"; then
-        pcs -f $pacemaker_dumpfile constraint order start haproxy-clone then openstack-keystone-clone
+    if pcs resource | grep "haproxy-clone"; then
+        SERVICES="$SERVICES haproxy"
+        if ! pcs constraint order show | grep "start haproxy-clone then start openstack-keystone-clone"; then
+            pcs -f $pacemaker_dumpfile constraint order start haproxy-clone then openstack-keystone-clone
+        fi
     fi
 
     if ! pcs constraint order show | grep "start memcached-clone then start openstack-keystone-clone"; then
@@ -89,44 +122,17 @@ if [[ "$pacemaker_status" == "active" ]] ; then
     fi
 
     echo "Setting resource start/stop timeouts"
-    SERVICES="
-haproxy
-memcached
-httpd
-neutron-dhcp-agent
-neutron-l3-agent
-neutron-metadata-agent
-neutron-openvswitch-agent
-neutron-server
-openstack-ceilometer-alarm-evaluator
-openstack-ceilometer-alarm-notifier
-openstack-ceilometer-api
-openstack-ceilometer-central
-openstack-ceilometer-collector
-openstack-ceilometer-notification
-openstack-cinder-api
-openstack-cinder-scheduler
-openstack-cinder-volume
-openstack-glance-api
-openstack-glance-registry
-openstack-heat-api
-openstack-heat-api-cfn
-openstack-heat-api-cloudwatch
-openstack-heat-engine
-openstack-keystone
-openstack-nova-api
-openstack-nova-conductor
-openstack-nova-consoleauth
-openstack-nova-novncproxy
-openstack-nova-scheduler"
     for service in $SERVICES; do
-        pcs -f $pacemaker_dumpfile resource update $service op start timeout=100s op stop timeout=100s
+        pcs -f $pacemaker_dumpfile resource update $service op start timeout=200s op stop timeout=200s
     done
     # mongod start timeout is higher, setting only stop timeout
-    pcs resource update mongod op stop timeout=100s
+    pcs -f $pacemaker_dumpfile resource update mongod op start timeout=370s op  stop timeout=200s
 
     echo "Applying new Pacemaker config"
-    pcs cluster cib-push $pacemaker_dumpfile
+    if ! pcs cluster cib-push $pacemaker_dumpfile; then
+        echo "ERROR failed to apply new pacemaker config"
+        exit 1
+    fi
 
     echo "Pacemaker running, stopping cluster node and doing full package update"
     node_count=$(pcs status xml | grep -o "<nodes_configured.*/>" | grep -o 'number="[0-9]*"' | grep -o "[0-9]*")
@@ -186,6 +192,12 @@ if [[ "$pacemaker_status" == "active" ]] ; then
         fi
     done
 
+    echo "Waiting for pacemaker cluster to settle"
+    if ! timeout -k 10 $cluster_settle_timeout crm_resource --wait; then
+        echo "ERROR timed out while waiting for the cluster to settle"
+        exit 1
+    fi
+
     pcs status
 
 else