4.16. 回滚 control plane 采用

流程

1. 要将源云恢复到工作状态，请启动之前在采用过程中停止的 RHOSP control plane 服务：

   ServicesToStart=("tripleo_horizon.service"
                    "tripleo_keystone.service"
                    "tripleo_barbican_api.service"
                    "tripleo_barbican_worker.service"
                    "tripleo_barbican_keystone_listener.service"
                    "tripleo_cinder_api.service"
                    "tripleo_cinder_api_cron.service"
                    "tripleo_cinder_scheduler.service"
                    "tripleo_cinder_volume.service"
                    "tripleo_cinder_backup.service"
                    "tripleo_glance_api.service"
                    "tripleo_manila_api.service"
                    "tripleo_manila_api_cron.service"
                    "tripleo_manila_scheduler.service"
                    "tripleo_neutron_api.service"
                    "tripleo_placement_api.service"
                    "tripleo_nova_api_cron.service"
                    "tripleo_nova_api.service"
                    "tripleo_nova_conductor.service"
                    "tripleo_nova_metadata.service"
                    "tripleo_nova_scheduler.service"
                    "tripleo_nova_vnc_proxy.service"
                    "tripleo_aodh_api.service"
                    "tripleo_aodh_api_cron.service"
                    "tripleo_aodh_evaluator.service"
                    "tripleo_aodh_listener.service"
                    "tripleo_aodh_notifier.service"
                    "tripleo_ceilometer_agent_central.service"
                    "tripleo_ceilometer_agent_compute.service"
                    "tripleo_ceilometer_agent_ipmi.service"
                    "tripleo_ceilometer_agent_notification.service"
                    "tripleo_ovn_cluster_north_db_server.service"
                    "tripleo_ovn_cluster_south_db_server.service"
                    "tripleo_ovn_cluster_northd.service"
                    "tripleo_octavia_api.service"
                    "tripleo_octavia_health_manager.service"
                    "tripleo_octavia_rsyslog.service"
                    "tripleo_octavia_driver_agent.service"
                    "tripleo_octavia_housekeeping.service"
                    "tripleo_octavia_worker.service")
   
   PacemakerResourcesToStart=("galera-bundle"
                              "haproxy-bundle"
                              "rabbitmq-bundle"
                              "openstack-cinder-volume"
                              "openstack-cinder-backup"
                              "openstack-manila-share")
   
   echo "Starting systemd OpenStack services"
   for service in ${ServicesToStart[*]}; do
       for i in {1..3}; do
           SSH_CMD=CONTROLLER${i}_SSH
           if [ ! -z "${!SSH_CMD}" ]; then
               if ${!SSH_CMD} sudo systemctl is-enabled $service &> /dev/null; then
                   echo "Starting the $service in controller $i"
                   ${!SSH_CMD} sudo systemctl start $service
               fi
           fi
       done
   done
   
   echo "Checking systemd OpenStack services"
   for service in ${ServicesToStart[*]}; do
       for i in {1..3}; do
           SSH_CMD=CONTROLLER${i}_SSH
           if [ ! -z "${!SSH_CMD}" ]; then
               if ${!SSH_CMD} sudo systemctl is-enabled $service &> /dev/null; then
                   if ! ${!SSH_CMD} systemctl show $service | grep ActiveState=active >/dev/null; then
                       echo "ERROR: Service $service is not running on controller $i"
                   else
                       echo "OK: Service $service is running in controller $i"
                   fi
               fi
           fi
       done
   done
   
   echo "Starting pacemaker OpenStack services"
   for i in {1..3}; do
       SSH_CMD=CONTROLLER${i}_SSH
       if [ ! -z "${!SSH_CMD}" ]; then
           echo "Using controller $i to run pacemaker commands"
           for resource in ${PacemakerResourcesToStart[*]}; do
               if ${!SSH_CMD} sudo pcs resource config $resource &>/dev/null; then
                   echo "Starting $resource"
                   ${!SSH_CMD} sudo pcs resource enable $resource
               else
                   echo "Service $resource not present"
               fi
           done
           break
       fi
   done
   
   echo "Checking pacemaker OpenStack services"
   for i in {1..3}; do
       SSH_CMD=CONTROLLER${i}_SSH
       if [ ! -z "${!SSH_CMD}" ]; then
           echo "Using controller $i to run pacemaker commands"
           for resource in ${PacemakerResourcesToStop[*]}; do
               if ${!SSH_CMD} sudo pcs resource config $resource &>/dev/null; then
                   if ${!SSH_CMD} sudo pcs resource status $resource | grep Started >/dev/null; then
                       echo "OK: Service $resource is started"
                   else
                       echo "ERROR: Service $resource is stopped"
                   fi
               fi
           done
           break
       fi
   done

   Copy to Clipboard Toggle word wrap

2. 如果 Ceph NFS 服务在作为共享文件系统服务(manila)后端部署上运行，您必须为 openstack-manila-share 服务恢复 Pacemaker 顺序和 colocation 约束：

   $ sudo pcs constraint order start ceph-nfs then openstack-manila-share kind=Optional id=order-ceph-nfs-openstack-manila-share-Optional
   $ sudo pcs constraint colocation add openstack-manila-share with ceph-nfs score=INFINITY id=colocation-openstack-manila-share-ceph-nfs-INFINITY

   Copy to Clipboard Toggle word wrap
3. 验证源云是否可再次运行，例如，您可以运行 openstack CLI 命令，如 openstack server list，或检查您可以访问 Dashboard 服务(horizon)。

4. 删除部分或完全部署的 control plane，以便以后可以再次尝试采用：

   $ oc delete --ignore-not-found=true --wait=false openstackcontrolplane/openstack
   $ oc patch openstackcontrolplane openstack --type=merge --patch '
   metadata:
     finalizers: []
   ' || true
   
   while oc get pod | grep rabbitmq-server-0; do
       sleep 2
   done
   while oc get pod | grep openstack-galera-0; do
       sleep 2
   done
   
   $ oc delete --ignore-not-found=true --wait=false pod mariadb-copy-data
   $ oc delete --ignore-not-found=true --wait=false pvc mariadb-data
   $ oc delete --ignore-not-found=true --wait=false pod ovn-copy-data
   $ oc delete --ignore-not-found=true secret osp-secret

   Copy to Clipboard Toggle word wrap