Replace ceilometer-dbsync by ceilometer-upgrade

[apex-tripleo-heat-templates.git] / extraconfig / tasks / major_upgrade_controller_pacemaker_1.sh

diff --git a/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh b/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh
index 2cbdc53..739c01d 100755 (executable)
--- a/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh
+++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh
@@ -2,52 +2,35 @@
 
 set -eu
 
-cluster_sync_timeout=600
-
-if pcs status 2>&1 | grep -E '(cluster is not currently running)|(OFFLINE:)'; then
-    echo_error "ERROR: upgrade cannot start with some cluster nodes being offline"
-    exit 1
-fi
-
-if [ "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)" ]; then
-    pcs resource disable httpd
-    check_resource httpd stopped 1800
-    pcs resource disable openstack-core
-    check_resource openstack-core stopped 1800
-    pcs resource disable redis
-    check_resource redis stopped 600
-    pcs resource disable mongod
-    check_resource mongod stopped 600
-    pcs resource disable rabbitmq
-    check_resource rabbitmq stopped 600
-    pcs resource disable memcached
-    check_resource memcached stopped 600
-    pcs resource disable galera
-    check_resource galera stopped 600
-    pcs cluster stop --all
+check_cluster
+check_pcsd
+if [[ -n $(is_bootstrap_node) ]]; then
+    check_clean_cluster
 fi
-
-# Swift isn't controled by pacemaker
-systemctl_swift stop
-
-tstart=$(date +%s)
-while systemctl is-active pacemaker; do
-    sleep 5
-    tnow=$(date +%s)
-    if (( tnow-tstart > cluster_sync_timeout )) ; then
-        echo_error "ERROR: cluster shutdown timed out"
-        exit 1
+check_python_rpm
+check_galera_root_password
+check_disk_for_mysql_dump
+
+# We want to disable fencing during the cluster --stop as it might fence
+# nodes where a service fails to stop, which could be fatal during an upgrade
+# procedure. So we remember the stonith state. If it was enabled we reenable it
+# at the end of this script
+if [[ -n $(is_bootstrap_node) ]]; then
+    STONITH_STATE=$(pcs property show stonith-enabled | grep "stonith-enabled" | awk '{ print $2 }')
+    # We create this empty file if stonith was set to true so we can reenable stonith in step2
+    rm -f /var/tmp/stonith-true
+    if [ $STONITH_STATE == "true" ]; then
+        touch /var/tmp/stonith-true
     fi
-done
+    pcs property set stonith-enabled=false
+fi
 
-yum -y install python-zaqarclient  # needed for os-collect-config
-yum -y -q update
+# Migrate to HA NG and fix up rabbitmq queues
+# We fix up the rabbitmq ha queues after the migration because it will
+# restart the rabbitmq resource. Doing it after the migration means no other
+# services will be restart as there are no other constraints
+if [[ -n $(is_bootstrap_node) ]]; then
+    migrate_full_to_ng_ha
+    rabbitmq_mitaka_newton_upgrade
+fi
 
-# Pin messages sent to compute nodes to kilo, these will be upgraded later
-crudini  --set /etc/nova/nova.conf upgrade_levels compute "$upgrade_level_nova_compute"
-# https://bugzilla.redhat.com/show_bug.cgi?id=1284047
-# Change-Id: Ib3f6c12ff5471e1f017f28b16b1e6496a4a4b435
-crudini  --set /etc/ceilometer/ceilometer.conf DEFAULT rpc_backend rabbit
-# https://bugzilla.redhat.com/show_bug.cgi?id=1284058
-# Ifd1861e3df46fad0e44ff9b5cbd58711bbc87c97 Swift Ceilometer middleware no longer exists
-crudini --set /etc/swift/proxy-server.conf pipeline:main pipeline "catch_errors healthcheck cache ratelimit tempurl formpost authtoken keystone staticweb proxy-logging proxy-server"