diff options
Diffstat (limited to 'extraconfig')
-rw-r--r-- | extraconfig/tasks/major_upgrade_block_storage.sh | 14 | ||||
-rw-r--r-- | extraconfig/tasks/major_upgrade_ceph_storage.sh | 14 | ||||
-rw-r--r-- | extraconfig/tasks/major_upgrade_compute.sh | 14 | ||||
-rwxr-xr-x | extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh | 26 | ||||
-rwxr-xr-x | extraconfig/tasks/major_upgrade_controller_pacemaker_2.sh | 1 | ||||
-rwxr-xr-x | extraconfig/tasks/major_upgrade_controller_pacemaker_3.sh | 15 | ||||
-rwxr-xr-x | extraconfig/tasks/major_upgrade_controller_pacemaker_4.sh | 8 | ||||
-rwxr-xr-x | extraconfig/tasks/major_upgrade_controller_pacemaker_5.sh | 15 | ||||
-rw-r--r-- | extraconfig/tasks/major_upgrade_object_storage.sh | 13 | ||||
-rw-r--r-- | extraconfig/tasks/major_upgrade_pacemaker.yaml | 47 | ||||
-rwxr-xr-x | extraconfig/tasks/pacemaker_common_functions.sh | 2 | ||||
-rwxr-xr-x | extraconfig/tasks/yum_update.sh | 36 |
12 files changed, 181 insertions, 24 deletions
diff --git a/extraconfig/tasks/major_upgrade_block_storage.sh b/extraconfig/tasks/major_upgrade_block_storage.sh index 07666245..39861826 100644 --- a/extraconfig/tasks/major_upgrade_block_storage.sh +++ b/extraconfig/tasks/major_upgrade_block_storage.sh @@ -4,5 +4,19 @@ # set -eu +# 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 + yum -y install python-zaqarclient # needed for os-collect-config yum -y -q update diff --git a/extraconfig/tasks/major_upgrade_ceph_storage.sh b/extraconfig/tasks/major_upgrade_ceph_storage.sh index 56b54e22..d84cad45 100644 --- a/extraconfig/tasks/major_upgrade_ceph_storage.sh +++ b/extraconfig/tasks/major_upgrade_ceph_storage.sh @@ -49,6 +49,20 @@ timeout 60 bash -c "while kill -0 ${OSD_PIDS} 2> /dev/null; do sleep 2; done" +# 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 + # Update (Ceph to Jewel) yum -y install python-zaqarclient # needed for os-collect-config yum -y update diff --git a/extraconfig/tasks/major_upgrade_compute.sh b/extraconfig/tasks/major_upgrade_compute.sh index a1df695f..f5105a1a 100644 --- a/extraconfig/tasks/major_upgrade_compute.sh +++ b/extraconfig/tasks/major_upgrade_compute.sh @@ -18,6 +18,20 @@ set -eu crudini --set /etc/nova/nova.conf upgrade_levels compute $upgrade_level_nova_compute +# Special-case OVS for https://bugs.launchpad.net/tripleo/+bug/1635205 +if [[ -n \$(rpm -q --scripts openvswitch | awk '/postuninstall/,/*/' | grep "systemctl.*try-restart") ]]; then + echo "Manual upgrade of openvswitch - restart in postun detected" + mkdir OVS_UPGRADE || true + pushd OVS_UPGRADE + echo "Attempting to downloading latest openvswitch with yumdownloader" + yumdownloader --resolve openvswitch + echo "Updating openvswitch with nopostun option" + rpm -U --replacepkgs --nopostun ./*.rpm + popd +else + echo "Skipping manual upgrade of openvswitch - no restart in postun detected" +fi + yum -y install python-zaqarclient # needed for os-collect-config yum -y update diff --git a/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh b/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh index 23074fcb..fbdbc30b 100755 --- a/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh +++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_1.sh @@ -17,8 +17,10 @@ check_disk_for_mysql_dump # nodes where a service fails to stop, which could be fatal during an upgrade # procedure. So we remember the stonith state. If it was enabled we reenable it # at the end of this script -STONITH_STATE=$(pcs property show stonith-enabled | grep "stonith-enabled" | awk '{ print $2 }') -pcs property set stonith-enabled=false +if [[ -n $(is_bootstrap_node) ]]; then + STONITH_STATE=$(pcs property show stonith-enabled | grep "stonith-enabled" | awk '{ print $2 }') + pcs property set stonith-enabled=false +fi # Migrate to HA NG and fix up rabbitmq queues # We fix up the rabbitmq ha queues after the migration because it will @@ -120,6 +122,20 @@ if [ $DO_MYSQL_UPGRADE -eq 1 ]; then mv /var/lib/mysql $MYSQL_TEMP_UPGRADE_BACKUP_DIR 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 + yum -y install python-zaqarclient # needed for os-collect-config yum -y -q update @@ -170,8 +186,10 @@ if [ $DO_MYSQL_UPGRADE -eq 1 ]; then fi # Let's reset the stonith back to true if it was true, before starting the cluster -if [ $STONITH_STATE == "true" ]; then - pcs -f /var/lib/pacemaker/cib/cib.xml property set stonith-enabled=true +if [[ -n $(is_bootstrap_node) ]]; then + if [ $STONITH_STATE == "true" ]; then + pcs -f /var/lib/pacemaker/cib/cib.xml property set stonith-enabled=true + fi fi # Pin messages sent to compute nodes to kilo, these will be upgraded later diff --git a/extraconfig/tasks/major_upgrade_controller_pacemaker_2.sh b/extraconfig/tasks/major_upgrade_controller_pacemaker_2.sh index b3a0098c..37061512 100755 --- a/extraconfig/tasks/major_upgrade_controller_pacemaker_2.sh +++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_2.sh @@ -64,6 +64,5 @@ if [[ -n $(is_bootstrap_node) ]]; then nova-manage db sync nova-manage api_db sync nova-manage db online_data_migrations - gnocchi-upgrade sahara-db-manage --config-file /etc/sahara/sahara.conf upgrade head fi diff --git a/extraconfig/tasks/major_upgrade_controller_pacemaker_3.sh b/extraconfig/tasks/major_upgrade_controller_pacemaker_3.sh index b653c7c7..d2cb9553 100755 --- a/extraconfig/tasks/major_upgrade_controller_pacemaker_3.sh +++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_3.sh @@ -9,18 +9,9 @@ check_resource redis started 600 start_or_enable_service openstack-cinder-volume check_resource openstack-cinder-volume started 600 +# start httpd so keystone is available for gnocchi +# upgrade to run. +systemctl start httpd # Swift isn't controled by pacemaker systemctl_swift start - -# We need to start the systemd services we explicitely stopped at step _1.sh -# FIXME: Should we let puppet during the convergence step do the service enabling or -# should we add it here? -services=$(services_to_migrate) -if [[ ${keep_sahara_services_on_upgrade} =~ [Ff]alse ]] ; then - services=${services%%openstack-sahara*} -fi -for service in $services; do - manage_systemd_service start "${service%%-clone}" - check_resource_systemd "${service%%-clone}" started 600 -done diff --git a/extraconfig/tasks/major_upgrade_controller_pacemaker_4.sh b/extraconfig/tasks/major_upgrade_controller_pacemaker_4.sh new file mode 100755 index 00000000..fa95f1f8 --- /dev/null +++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_4.sh @@ -0,0 +1,8 @@ +#!/bin/bash + +set -eu + +if [[ -n $(is_bootstrap_node) ]]; then + # run gnocchi upgrade + gnocchi-upgrade +fi diff --git a/extraconfig/tasks/major_upgrade_controller_pacemaker_5.sh b/extraconfig/tasks/major_upgrade_controller_pacemaker_5.sh new file mode 100755 index 00000000..d569084d --- /dev/null +++ b/extraconfig/tasks/major_upgrade_controller_pacemaker_5.sh @@ -0,0 +1,15 @@ +#!/bin/bash + +set -eu + +# We need to start the systemd services we explicitely stopped at step _1.sh +# FIXME: Should we let puppet during the convergence step do the service enabling or +# should we add it here? +services=$(services_to_migrate) +if [[ ${keep_sahara_services_on_upgrade} =~ [Ff]alse ]] ; then + services=${services%%openstack-sahara*} +fi +for service in $services; do + manage_systemd_service start "${service%%-clone}" + check_resource_systemd "${service%%-clone}" started 600 +done diff --git a/extraconfig/tasks/major_upgrade_object_storage.sh b/extraconfig/tasks/major_upgrade_object_storage.sh index f82457ce..2667bb16 100644 --- a/extraconfig/tasks/major_upgrade_object_storage.sh +++ b/extraconfig/tasks/major_upgrade_object_storage.sh @@ -23,6 +23,19 @@ function systemctl_swift { done } +# 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 systemctl_swift stop diff --git a/extraconfig/tasks/major_upgrade_pacemaker.yaml b/extraconfig/tasks/major_upgrade_pacemaker.yaml index 7c78d5ad..e13aada3 100644 --- a/extraconfig/tasks/major_upgrade_pacemaker.yaml +++ b/extraconfig/tasks/major_upgrade_pacemaker.yaml @@ -132,6 +132,44 @@ resources: config: list_join: - '' + - - get_file: pacemaker_common_functions.sh + - get_file: major_upgrade_pacemaker_migrations.sh + - get_file: major_upgrade_controller_pacemaker_3.sh + + ControllerPacemakerUpgradeDeployment_Step3: + type: OS::Heat::SoftwareDeploymentGroup + depends_on: ControllerPacemakerUpgradeDeployment_Step2 + properties: + servers: {get_param: [servers, Controller]} + config: {get_resource: ControllerPacemakerUpgradeConfig_Step3} + input_values: {get_param: input_values} + + ControllerPacemakerUpgradeConfig_Step4: + type: OS::Heat::SoftwareConfig + properties: + group: script + config: + list_join: + - '' + - - get_file: pacemaker_common_functions.sh + - get_file: major_upgrade_pacemaker_migrations.sh + - get_file: major_upgrade_controller_pacemaker_4.sh + + ControllerPacemakerUpgradeDeployment_Step4: + type: OS::Heat::SoftwareDeploymentGroup + depends_on: ControllerPacemakerUpgradeDeployment_Step3 + properties: + servers: {get_param: [servers, Controller]} + config: {get_resource: ControllerPacemakerUpgradeConfig_Step4} + input_values: {get_param: input_values} + + ControllerPacemakerUpgradeConfig_Step5: + type: OS::Heat::SoftwareConfig + properties: + group: script + config: + list_join: + - '' - - str_replace: template: | #!/bin/bash @@ -140,13 +178,12 @@ resources: KEEP_SAHARA_SERVICES_ON_UPGRADE: {get_param: KeepSaharaServicesOnUpgrade} - get_file: pacemaker_common_functions.sh - get_file: major_upgrade_pacemaker_migrations.sh - - get_file: major_upgrade_controller_pacemaker_3.sh + - get_file: major_upgrade_controller_pacemaker_5.sh - ControllerPacemakerUpgradeDeployment_Step3: + ControllerPacemakerUpgradeDeployment_Step5: type: OS::Heat::SoftwareDeploymentGroup - depends_on: ControllerPacemakerUpgradeDeployment_Step2 + depends_on: ControllerPacemakerUpgradeDeployment_Step4 properties: servers: {get_param: [servers, Controller]} - config: {get_resource: ControllerPacemakerUpgradeConfig_Step3} + config: {get_resource: ControllerPacemakerUpgradeConfig_Step5} input_values: {get_param: input_values} - diff --git a/extraconfig/tasks/pacemaker_common_functions.sh b/extraconfig/tasks/pacemaker_common_functions.sh index 4f17b69a..2c7dfc35 100755 --- a/extraconfig/tasks/pacemaker_common_functions.sh +++ b/extraconfig/tasks/pacemaker_common_functions.sh @@ -284,7 +284,7 @@ function systemctl_swift { services=$(systemctl | grep openstack-swift- | grep running | awk '{print $1}') ;; start) - enable_swift_storage=$(hiera -c /etc/puppet/hiera.yaml 'enable_swift_storage') + enable_swift_storage=$(hiera -c /etc/puppet/hiera.yaml tripleo::profile::base::swift::storage::enable_swift_storage) if [[ $enable_swift_storage != "true" ]]; then services=( openstack-swift-proxy ) fi diff --git a/extraconfig/tasks/yum_update.sh b/extraconfig/tasks/yum_update.sh index b045e5ea..4612f197 100755 --- a/extraconfig/tasks/yum_update.sh +++ b/extraconfig/tasks/yum_update.sh @@ -44,6 +44,25 @@ fi pacemaker_status=$(systemctl is-active pacemaker) +# 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)" = "$(facter hostname)" ]] ; then + if pcs resource show rabbitmq | grep -E "start.*timeout=100"; then + pcs resource update rabbitmq op start timeout=200s + fi + if pcs resource show rabbitmq | grep -E "stop.*timeout=90"; then + pcs resource update rabbitmq op stop timeout=200s + fi + if pcs resource show redis | grep -E "start.*timeout=120"; then + pcs resource update redis op start timeout=200s + fi + if pcs resource show redis | grep -E "stop.*timeout=120"; then + pcs resource update redis op stop timeout=200s + fi +fi + + if [[ "$pacemaker_status" == "active" ]] ; then echo "Pacemaker running, stopping cluster node and doing full package update" node_count=$(pcs status xml | grep -o "<nodes_configured.*/>" | grep -o 'number="[0-9]*"' | grep -o "[0-9]*") @@ -54,13 +73,28 @@ if [[ "$pacemaker_status" == "active" ]] ; then pcs cluster stop fi 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" |