Merge "j2 template per-role things in default registry"

[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 e0d5aa7..d4200e5 100755 (executable)
--- a/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh
+++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh
@@ -6,7 +6,9 @@ cluster_sync_timeout=1800
 
 check_cluster
 check_pcsd
-check_clean_cluster
+if [[ -n $(is_bootstrap_node) ]]; then
+    check_clean_cluster
+fi
 check_python_rpm
 check_galera_root_password
 check_disk_for_mysql_dump
@@ -19,7 +21,7 @@ STONITH_STATE=$(pcs property show stonith-enabled | grep "stonith-enabled" | awk
 pcs property set stonith-enabled=false
 
 # Migrate to HA NG
-if [ "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)" ]; then
+if [[ -n $(is_bootstrap_node) ]]; then
     migrate_full_to_ng_ha
 fi
 
@@ -29,9 +31,26 @@ fi
 # is going to take a long time because rabbit is down. By having the service stopped
 # systemctl try-restart is a noop
 
-for $service in $(services_to_migrate); do
+for service in $(services_to_migrate); do
     manage_systemd_service stop "${service%%-clone}"
-    check_resource_systemd "${service%%-clone}" stopped 600
+    # So the reason for not reusing check_resource_systemd is that
+    # I have observed systemctl is-active returning unknown with at least
+    # one service that was stopped (See LP 1627254)
+    timeout=600
+    tstart=$(date +%s)
+    tend=$(( $tstart + $timeout ))
+    check_interval=3
+    while (( $(date +%s) < $tend )); do
+      if [[ "$(systemctl is-active ${service%%-clone})" = "active" ]]; then
+        echo "$service still active, sleeping $check_interval seconds."
+        sleep $check_interval
+      else
+        # we do not care if it is inactive, unknown or failed as long as it is
+        # not running
+        break
+      fi
+
+    done
 done
 
 # In case the mysql package is updated, the database on disk must be
@@ -46,7 +65,7 @@ done
 # on mysql package versionning, but this can be overriden manually
 # to support specific upgrade scenario
 
-if [ "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)" ]; then
+if [[ -n $(is_bootstrap_node) ]]; then
     if [ $DO_MYSQL_UPGRADE -eq 1 ]; then
         mysqldump $backup_flags > "$MYSQL_BACKUP_DIR/openstack_database.sql"
         cp -rdp /etc/my.cnf* "$MYSQL_BACKUP_DIR"
@@ -58,6 +77,8 @@ if [ "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)
     check_resource rabbitmq stopped 600
     pcs resource disable galera
     check_resource galera stopped 600
+    pcs resource disable openstack-cinder-volume
+    check_resource openstack-cinder-volume stopped 600
     # Disable all VIPs before stopping the cluster, so that pcs doesn't use one as a source address:
     #   https://bugzilla.redhat.com/show_bug.cgi?id=1330688
     for vip in $(pcs resource show | grep ocf::heartbeat:IPaddr2 | grep Started | awk '{ print $1 }'); do
@@ -68,7 +89,7 @@ if [ "$(hiera -c /etc/puppet/hiera.yaml bootstrap_nodeid)" = "$(facter hostname)
 fi
 
 
-# Swift isn't controled by pacemaker
+# Swift isn't controlled by pacemaker
 systemctl_swift stop
 
 tstart=$(date +%s)
@@ -159,5 +180,7 @@ crudini  --set /etc/ceilometer/ceilometer.conf DEFAULT rpc_backend rabbit
 crudini --set /etc/swift/proxy-server.conf pipeline:main pipeline "catch_errors healthcheck cache ratelimit tempurl formpost authtoken keystone staticweb proxy-logging proxy-server"
 # LP: 1615035, required only for M/N upgrade.
 crudini --set /etc/nova/nova.conf DEFAULT scheduler_host_manager host_manager
+# LP: 1627450, required only for M/N upgrade
+crudini --set /etc/nova/nova.conf DEFAULT scheduler_driver filter_scheduler
 
 crudini --set /etc/sahara/sahara.conf DEFAULT plugins ambari,cdh,mapr,vanilla,spark,storm