# seconds to wait for this node to rejoin the cluster after update
cluster_start_timeout=600
-galera_sync_timeout=360
+galera_sync_timeout=1800
cluster_settle_timeout=1800
timestamp_file="$timestamp_dir/$update_identifier"
fi
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-api
-openstack-ceilometer-central
-openstack-ceilometer-collector
-openstack-ceilometer-notification
-openstack-aodh-evaluator
-openstack-aodh-notifier
-openstack-aodh-listener
-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
-
- echo "Checking for missing constraints"
-
- if ! pcs constraint order show | grep "start openstack-nova-novncproxy-clone then start openstack-nova-api-clone"; then
- pcs -f $pacemaker_dumpfile constraint order start openstack-nova-novncproxy-clone then openstack-nova-api-clone
- fi
-
- if ! pcs constraint order show | grep "start rabbitmq-clone then start openstack-keystone-clone"; then
- pcs -f $pacemaker_dumpfile constraint order start rabbitmq-clone then openstack-keystone-clone
- fi
-
- if ! pcs constraint order show | grep "promote galera-master then start openstack-keystone-clone"; then
- pcs -f $pacemaker_dumpfile constraint order promote galera-master then openstack-keystone-clone
- fi
-
- if pcs resource | grep "haproxy-clone"; then
- SERVICES="$SERVICES haproxy"
- if ! pcs constraint order show | grep "start haproxy-clone then start openstack-keystone-clone"; then
- pcs -f $pacemaker_dumpfile constraint order start haproxy-clone then openstack-keystone-clone
- fi
+# Fix the redis/rabbit resource start/stop timeouts. See https://bugs.launchpad.net/tripleo/+bug/1633455
+# and https://bugs.launchpad.net/tripleo/+bug/1634851
+if [[ "$pacemaker_status" == "active" && \
+ "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)" ]] ; then
+ if pcs resource show rabbitmq | grep -E "start.*timeout=100"; then
+ pcs resource update rabbitmq op start timeout=200s
fi
-
- if ! pcs constraint order show | grep "start memcached-clone then start openstack-keystone-clone"; then
- pcs -f $pacemaker_dumpfile constraint order start memcached-clone then openstack-keystone-clone
+ if pcs resource show rabbitmq | grep -E "stop.*timeout=90"; then
+ pcs resource update rabbitmq op stop timeout=200s
fi
-
- if ! pcs constraint order show | grep "promote redis-master then start openstack-ceilometer-central-clone"; then
- pcs -f $pacemaker_dumpfile constraint order promote redis-master then start openstack-ceilometer-central-clone require-all=false
+ if pcs resource show redis | grep -E "start.*timeout=120"; then
+ pcs resource update redis op start timeout=200s
fi
-
- if ! pcs constraint order show | grep "promote redis-master then start openstack-aodh-evaluator-clone"; then
- pcs -f $pacemaker_dumpfile constraint order promote redis-master then start openstack-aodh-evaluator-clone require-all=false
+ if pcs resource show redis | grep -E "stop.*timeout=120"; then
+ pcs resource update redis op stop timeout=200s
fi
- # ensure neutron constraints https://review.openstack.org/#/c/229466
- # remove ovs-cleanup after server and add openvswitch-agent instead
- if pcs constraint order show | grep "start neutron-server-clone then start neutron-ovs-cleanup-clone"; then
- pcs -f $pacemaker_dumpfile constraint remove order-neutron-server-clone-neutron-ovs-cleanup-clone-mandatory
- fi
- if ! pcs constraint order show | grep "start neutron-server-clone then start neutron-openvswitch-agent-clone"; then
- pcs -f $pacemaker_dumpfile constraint order start neutron-server-clone then neutron-openvswitch-agent-clone
- fi
-
-
- if ! pcs resource defaults | grep "resource-stickiness: INFINITY"; then
- pcs -f $pacemaker_dumpfile resource defaults resource-stickiness=INFINITY
- fi
-
- echo "Setting resource start/stop timeouts"
- for service in $SERVICES; do
- 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 -f $pacemaker_dumpfile resource update mongod op start timeout=370s op stop timeout=200s
+fi
- echo "Making sure rabbitmq has the notify=true meta parameter"
- pcs -f $pacemaker_dumpfile resource update rabbitmq meta notify=true
-
- echo "Applying new Pacemaker config"
- if ! pcs cluster cib-push $pacemaker_dumpfile; then
- echo "ERROR failed to apply new pacemaker config"
- exit 1
- fi
+if [[ "$pacemaker_status" == "active" ]] ; then
echo "Pacemaker running, stopping cluster node and doing full package update"
node_count=$(pcs status xml | grep -o "<nodes_configured.*/>" | grep -o 'number="[0-9]*"' | grep -o "[0-9]*")
if [[ "$node_count" == "1" ]] ; then
else
pcs cluster stop
fi
-
- # clean leftover keepalived and radvd instances from neutron
- # (can be removed when we remove neutron-netns-cleanup from cluster services)
- # see https://review.gerrithub.io/#/c/248931/1/neutron-netns-cleanup.init
- killall neutron-keepalived-state-change 2>/dev/null || :
- kill $(ps ax | grep -e "keepalived.*\.pid-vrrp" | awk '{print $1}') 2>/dev/null || :
- kill $(ps ax | grep -e "radvd.*\.pid\.radvd" | awk '{print $1}') 2>/dev/null || :
else
- echo "Upgrading openstack-puppet-modules"
+ echo "Upgrading openstack-puppet-modules and its dependencies"
yum -q -y update openstack-puppet-modules
+ yum deplist openstack-puppet-modules | awk '/dependency/{print $2}' | xargs yum -q -y update
echo "Upgrading other packages is handled by config management tooling"
echo -n "true" > $heat_outputs_path.update_managed_packages
exit 0
fi
+# Special-case OVS for https://bugs.launchpad.net/tripleo/+bug/1635205
+if [[ -n $(rpm -q --scripts openvswitch | awk '/postuninstall/,/*/' | grep "systemctl.*try-restart") ]]; then
+ echo "Manual upgrade of openvswitch - restart in postun detected"
+ mkdir OVS_UPGRADE || true
+ pushd OVS_UPGRADE
+ echo "Attempting to downloading latest openvswitch with yumdownloader"
+ yumdownloader --resolve openvswitch
+ echo "Updating openvswitch with nopostun option"
+ rpm -U --replacepkgs --nopostun ./*.rpm
+ popd
+else
+ echo "Skipping manual upgrade of openvswitch - no restart in postun detected"
+fi
+
command=${command:-update}
full_command="yum -q -y $command $command_arguments"
echo "Running: $full_command"
Code Review / apex-tripleo-heat-templates.git / blobdiff