Multinode xena (#248)

* feat:  copy `ci-multinode` from PR `#246`

* feat: copy `ansible` from PR `#246`

* revert: configure-aio-resources.yml to `da05599`

* feat: actually copy contents of `ci-multinode`

For some reason the previous commit does not contain the important
changes to the configuration. This commit fixes that.

* feat: include `.automation.conf` from PR `#246`

* revert: `stackhpc-ci` back to `stackhpc/xena`

* feat: update address of `pulp-server`

* feat: bump `stackhpc.cephadm` version

* feat: `haproxy` group has been replaced with `loadbalancer`

* fix: ensure `cephadm_host_labels` is defined

* feat: reduce concurrency and remove load list

* feat: increase `max_microversion`

* fix: restore order to `requirements.yml`

* fix: README has been moved

* fix: remove unused collection

* fix: add missing new line

* feat: disable some unwanted service within ci-multinode

* fix: remove extra blank lines

* feat: revert `TEMPEST_CONCURRENCY` to two

* feat: load `ci-multinode` tempest settings conditionally

Firstly, the skip-list has been renamed from `tempest-full` to `ci-multinode` as this
list would be environment specific. Secondly the `config.sh` script now contains a
conditional for the `ci-multinode` environment allowing for the test list and
concurrency settings to be loaded without impacting other environments.

* fix: use `HTTP` dashboard URL over `HTTPS`

* fix: reduce multinode tempest concurrency

* feat: bump `stackhpc.cephadm` collection version

* feat: remove unecessary comment

Author: jackhodgkiss

.automation.conf/config.sh

@@ -19,6 +19,10 @@ if [ ! -z ${KAYOBE_ENVIRONMENT:+x} ]; then
     # Seem to get servers failing to spawn with higher concurrency
     export TEMPEST_CONCURRENCY=1
   fi
+  if [[ "$KAYOBE_ENVIRONMENT" =~ "ci-multinode" ]]; then
+      export KAYOBE_AUTOMATION_TEMPEST_LOADLIST=tempest-full
+      export KAYOBE_AUTOMATION_TEMPEST_SKIPLIST=ci-multinode
+  fi
 fi
 
 if [[ -z "${KAYOBE_AUTOMATION_TEMPEST_CONF_OVERRIDES:+x}" ]] || [[ ! -e "${KAYOBE_AUTOMATION_TEMPEST_CONF_OVERRIDES}" ]]; then

.automation.conf/tempest/load-lists/tempest-full

@@ -0,0 +1 @@
+tempest.scenario.test_network_basic_ops.TestNetworkBasicOps.test_subnet_details.*: "Cirros image doesn't have '/var/run/udhcpc.eth0.pid"

.automation.conf/tempest/skip-lists/ci-multinode

@@ -0,0 +1,30 @@
+[DEFAULT]
+openstack_client_http_timeout = 300
+
+[auth]
+compute_quotas = cores:-1,ram:-1
+
+[identity]
+v3_endpoint_type = publicURL
+
+[compute]
+min_compute_nodes = 2
+min_microversion = 2.1
+max_microversion = 2.88
+
+[service-clients]
+http_timeout = 600
+
+[compute-feature-enabled]
+resize = true
+live_migration = true
+block_migration_for_live_migration = false
+volume_backed_live_migration = true
+console_output = true
+
+[volume]
+min_microversion = 3.0
+max_microversion = 3.66
+
+[dashboard]
+dashboard_url = http://192.168.39.2

.automation.conf/tempest/tempest-ci-multinode.overrides.conf

@@ -1,6 +1,6 @@
 ---
 - name: Configure VXLAN
-  hosts: storage,seed,controllers,compute
+  hosts: controllers,compute,seed,storage
   gather_facts: false
   vars:
     ansible_user: "{{ bootstrap_user }}"
@@ -11,10 +11,3 @@
     ansible_ssh_common_args: "-o StrictHostKeyChecking=no"
   roles:
     - role: stackhpc.vxlan
-      vars:
-        vxlan_phys_dev: "{{ admin_oc_net_name | net_interface }}"
-        vxlan_dstport: 4790
-        vxlan_interfaces:
-          - device: vxlan10
-            group: 224.0.0.10
-            bridge: breth1

etc/kayobe/ansible/configure-vxlan.yml

@@ -0,0 +1,23 @@
+---
+- name: Fix hostname on storage nodes for cephadm
+  hosts: storage
+  gather_facts: false
+  vars:
+    ansible_user: "{{ bootstrap_user }}"
+    # We can't assume that a virtualenv exists at this point, so use the system
+    # python interpreter.
+    ansible_python_interpreter: /usr/bin/python3
+    # Work around no known_hosts entry on first boot.
+    ansible_ssh_common_args: "-o StrictHostKeyChecking=no"
+  tasks:
+    - name: Get current hostname
+      ansible.builtin.command:
+        cmd: hostname
+      changed_when: false
+      register: current_hostname
+
+    - name: Set hostname to a non FQDN
+      ansible.builtin.command:
+        cmd: hostnamectl set-hostname "{{ inventory_hostname }}"
+      when: current_hostname.stdout != inventory_hostname
+      become: true

etc/kayobe/ansible/fix-hostname.yml

@@ -0,0 +1,21 @@
+---
+- name: Fix networking
+  hosts: seed,compute,controllers,storage
+  gather_facts: false
+  vars:
+    ansible_user: "{{ bootstrap_user }}"
+    # We can't assume that a virtualenv exists at this point, so use the system
+    # python interpreter.
+    ansible_python_interpreter: /usr/bin/python3
+    # Work around no known_hosts entry on first boot.
+    ansible_ssh_common_args: "-o StrictHostKeyChecking=no"
+  tasks:
+    - name: Ensure `hosts` file contains pulp entries
+      ansible.builtin.copy:
+        content: |
+          127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
+          ::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
+          10.0.0.34 pelican pelican.service.compute.sms-lab.cloud
+          10.205.3.187 pulp-server pulp-server.internal.sms-cloud
+        dest: /etc/hosts
+      become: true

etc/kayobe/ansible/fix-networking.yml

@@ -1,7 +1,7 @@
 ---
 collections:
   - name: stackhpc.cephadm
-    version: 1.10.0
+    version: 1.12.2
   - name: stackhpc.pulp
     version: 0.4.1
 roles:

etc/kayobe/ansible/requirements.yml

@@ -1,4 +1,5 @@
 ---
+compute_bootstrap_user: "{{ os_distribution if os_distribution == 'ubuntu' else 'cloud-user' }}"
 # List of storage volume groups. See mrlesmithjr.manage-lvm role for
 # format.
 compute_lvm_groups:

etc/kayobe/environments/ci-multinode/compute.yml

@@ -1,4 +1,5 @@
 ---
+controller_bootstrap_user: "{{ os_distribution if os_distribution == 'ubuntu' else 'cloud-user' }}"
 # List of storage volume groups. See mrlesmithjr.manage-lvm role for
 # format.
 controller_lvm_groups: