zuul: Introduce nova-evacuate

This change reworks the evacuation parts of the original
nova-live-migration job into a zuulv3 native ansible role and initial
job covering local ephemeral and iSCSI/LVM volume attached instance
evacuation. Future jobs will cover ceph and other storage backends.

Change-Id: I380e9ca1e6a84da2b2ae577fb48781bf5c740e23

5 files changed, 185 insertions, 0 deletions

diff --git a/roles/run-evacuate-hook/README.rst b/roles/run-evacuate-hook/README.rst
new file mode 100644
index 0000000000..e423455aee
--- /dev/null
+++ b/roles/run-evacuate-hook/README.rst
@@ -0,0 +1 @@
+Run Nova evacuation tests against a multinode environment.
diff --git a/roles/run-evacuate-hook/files/setup_evacuate_resources.sh b/roles/run-evacuate-hook/files/setup_evacuate_resources.sh
new file mode 100755
index 0000000000..c8c385d7ff
--- /dev/null
+++ b/roles/run-evacuate-hook/files/setup_evacuate_resources.sh
@@ -0,0 +1,34 @@
+#!/bin/bash
+source /opt/stack/devstack/openrc admin
+set -x
+set -e
+
+image_id=$(openstack image list -f value -c ID | awk 'NR==1{print $1}')
+flavor_id=$(openstack flavor list -f value -c ID | awk 'NR==1{print $1}')
+network_id=$(openstack network list --no-share -f value -c ID | awk 'NR==1{print $1}')
+
+echo "Creating ephemeral test server on subnode"
+openstack --os-compute-api-version 2.74 server create --image ${image_id} --flavor ${flavor_id} \
+--nic net-id=${network_id} --host $SUBNODE_HOSTNAME --wait evacuate-test
+
+# TODO(lyarwood) Use osc to launch the bfv volume
+echo "Creating boot from volume test server on subnode"
+nova --os-compute-api-version 2.74 boot --flavor ${flavor_id} --poll \
+--block-device id=${image_id},source=image,dest=volume,size=1,bootindex=0,shutdown=remove \
+--nic net-id=${network_id} --host ${SUBNODE_HOSTNAME} evacuate-bfv-test
+
+echo "Forcing down the subnode so we can evacuate from it"
+openstack --os-compute-api-version 2.11 compute service set --down ${SUBNODE_HOSTNAME} nova-compute
+
+count=0
+status=$(openstack compute service list --host ${SUBNODE_HOSTNAME} --service nova-compute -f value -c State)
+while [ "${status}" != "down" ]
+do
+    sleep 1
+    count=$((count+1))
+    if [ ${count} -eq 30 ]; then
+        echo "Timed out waiting for subnode compute service to be marked as down"
+        exit 5
+    fi
+    status=$(openstack compute service list --host ${SUBNODE_HOSTNAME} --service nova-compute -f value -c State)
+done
diff --git a/roles/run-evacuate-hook/files/test_evacuate.sh b/roles/run-evacuate-hook/files/test_evacuate.sh
new file mode 100755
index 0000000000..bdf8d92441
--- /dev/null
+++ b/roles/run-evacuate-hook/files/test_evacuate.sh
@@ -0,0 +1,55 @@
+#!/bin/bash
+# Source tempest to determine the build timeout configuration.
+source /opt/stack/devstack/lib/tempest
+source /opt/stack/devstack/openrc admin
+set -x
+set -e
+
+# Wait for the controller compute service to be enabled.
+count=0
+status=$(openstack compute service list --host ${CONTROLLER_HOSTNAME} --service nova-compute -f value -c Status)
+while [ "${status}" != "enabled" ]
+do
+    sleep 1
+    count=$((count+1))
+    if [ ${count} -eq 30 ]; then
+        echo "Timed out waiting for controller compute service to be enabled"
+        exit 5
+    fi
+    status=$(openstack compute service list --host ${CONTROLLER_HOSTNAME} --service nova-compute -f value -c Status)
+done
+
+function evacuate_and_wait_for_active() {
+    local server="$1"
+
+    nova evacuate ${server}
+    # Wait for the instance to go into ACTIVE state from the evacuate.
+    count=0
+    status=$(openstack server show ${server} -f value -c status)
+    while [ "${status}" != "ACTIVE" ]
+    do
+        sleep 1
+        count=$((count+1))
+        if [ ${count} -eq ${BUILD_TIMEOUT} ]; then
+            echo "Timed out waiting for server ${server} to go to ACTIVE status"
+            exit 6
+        fi
+        status=$(openstack server show ${server} -f value -c status)
+    done
+}
+
+evacuate_and_wait_for_active evacuate-test
+evacuate_and_wait_for_active evacuate-bfv-test
+
+# Make sure the servers moved.
+for server in evacuate-test evacuate-bfv-test; do
+    host=$(openstack server show ${server} -f value -c OS-EXT-SRV-ATTR:host)
+    if [[ ${host} != ${CONTROLLER_HOSTNAME} ]]; then
+        echo "Unexpected host ${host} for server ${server} after evacuate."
+        exit 7
+    fi
+done
+
+# Cleanup test servers
+openstack server delete --wait evacuate-test
+openstack server delete --wait evacuate-bfv-test
diff --git a/roles/run-evacuate-hook/files/test_negative_evacuate.sh b/roles/run-evacuate-hook/files/test_negative_evacuate.sh
new file mode 100755
index 0000000000..b1f5f7a4af
--- /dev/null
+++ b/roles/run-evacuate-hook/files/test_negative_evacuate.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+# Source tempest to determine the build timeout configuration.
+source /opt/stack/devstack/lib/tempest
+source /opt/stack/devstack/openrc admin
+set -x
+set -e
+
+# Now force the evacuation to the controller; we have to force to bypass the
+# scheduler since we killed libvirtd which will trigger the libvirt compute
+# driver to auto-disable the nova-compute service and then the ComputeFilter
+# would filter out this host and we'd get NoValidHost. Normally forcing a host
+# during evacuate and bypassing the scheduler is a very bad idea, but we're
+# doing a negative test here.
+
+function evacuate_and_wait_for_error() {
+    local server="$1"
+
+    echo "Forcing evacuate of ${server} to local host"
+    # TODO(mriedem): Use OSC when it supports evacuate.
+    nova --os-compute-api-version "2.67" evacuate --force ${server} ${CONTROLLER_HOSTNAME}
+    # Wait for the instance to go into ERROR state from the failed evacuate.
+    count=0
+    status=$(openstack server show ${server} -f value -c status)
+    while [ "${status}" != "ERROR" ]
+    do
+        sleep 1
+        count=$((count+1))
+        if [ ${count} -eq ${BUILD_TIMEOUT} ]; then
+            echo "Timed out waiting for server ${server} to go to ERROR status"
+            exit 4
+        fi
+        status=$(openstack server show ${server} -f value -c status)
+    done
+}
+
+evacuate_and_wait_for_error evacuate-test
+evacuate_and_wait_for_error evacuate-bfv-test
diff --git a/roles/run-evacuate-hook/tasks/main.yaml b/roles/run-evacuate-hook/tasks/main.yaml
new file mode 100644
index 0000000000..755dcdf02d
--- /dev/null
+++ b/roles/run-evacuate-hook/tasks/main.yaml
@@ -0,0 +1,58 @@
+- name: Setup resources and mark the subnode as forced down
+  become: true
+  become_user: stack
+  shell: "/opt/stack/nova/roles/run-evacuate-hook/files/setup_evacuate_resources.sh"
+  environment:
+    SUBNODE_HOSTNAME: "{{ hostvars['compute1']['ansible_hostname'] }}"
+
+- name: Fence subnode by stopping q-agt and n-cpu
+  delegate_to: compute1
+  become: true
+  systemd:
+    name: "{{ item }}"
+    state: stopped
+  with_items:
+    - devstack@q-agt
+    - devstack@n-cpu
+
+- name: Register running domains on subnode
+  delegate_to: compute1
+  become: true
+  virt:
+    command: list_vms
+    state: running
+  register: subnode_vms
+
+- name: Destroy running domains on subnode
+  delegate_to: compute1
+  become: true
+  virt:
+    name: "{{ item }}"
+    state: destroyed
+  with_items: "{{ subnode_vms.list_vms }}"
+
+- name: Stop libvirtd on "{{ inventory_hostname }}"
+  become: true
+  systemd:
+    name: libvirtd
+    state: stopped
+
+- name: Run negative evacuate tests
+  become: true
+  become_user: stack
+  shell: "/opt/stack/nova/roles/run-evacuate-hook/files/test_negative_evacuate.sh"
+  environment:
+    CONTROLLER_HOSTNAME: "{{ hostvars['controller']['ansible_hostname'] }}"
+
+- name: Start libvirtd on "{{ inventory_hostname }}"
+  become: true
+  systemd:
+    name: libvirtd
+    state: started
+
+- name: Run evacuate tests
+  become: true
+  become_user: stack
+  shell: "/opt/stack/nova/roles/run-evacuate-hook/files/test_evacuate.sh"
+  environment:
+    CONTROLLER_HOSTNAME: "{{ hostvars['controller']['ansible_hostname'] }}"