Merge stackhpc/zed into stackhpc/2023.1

Author: markgoddard

doc/source/configuration/monitoring.rst

@@ -126,6 +126,8 @@ depending on your configuration, you may need set the
 ``kolla_enable_prometheus_ceph_mgr_exporter`` variable to ``true`` in order to
 enable the ceph mgr exporter.
 
+.. _os-capacity:
+
 OpenStack Capacity
 ==================
 
@@ -149,9 +151,19 @@ project domain name in ``stackhpc-monitoring.yml``:
     stackhpc_os_capacity_openstack_region_name: <openstack_region_name>
 
 Additionally, you should ensure these credentials have the correct permissions
-for the exporter. If you are deploying in a cloud with internal TLS, you may be required
-to disable certificate verification for the OpenStack Capacity exporter
-if your certificate is not signed by a trusted CA.
+for the exporter.
+
+If you are deploying in a cloud with internal TLS, you may be required
+to provide a CA certificate for the OpenStack Capacity exporter if your
+certificate is not signed by a trusted CA. For example, to use a CA certificate
+named ``vault.crt`` that is also added to the Kolla containers:
+
+.. code-block:: yaml
+
+    stackhpc_os_capacity_openstack_cacert: "{{ kayobe_env_config_path }}/kolla/certificates/ca/vault.crt"
+
+Alternatively, to disable certificate verification for the OpenStack Capacity
+exporter:
 
 .. code-block:: yaml
 

doc/source/configuration/release-train.rst

@@ -147,6 +147,33 @@ By default, HashiCorp images (Consul and Vault) are not synced from Docker Hub
 to the local Pulp. To sync these images, set ``stackhpc_sync_hashicorp_images``
 to ``true``.
 
+Custom container images
+-----------------------
+
+A custom list of container images can be synced to the local Pulp using the
+``stackhpc_pulp_repository_container_repos_extra`` and
+``stackhpc_pulp_distribution_container_extra`` variables.
+
+.. code-block:: yaml
+
+   # List of extra container image repositories.
+   stackhpc_pulp_repository_container_repos_extra:
+     - name: "certbot/certbot"
+       url: "https://registry-1.docker.io"
+       policy: on_demand
+       proxy_url: "{{ pulp_proxy_url }}"
+       state: present
+       include_tags: "nightly"
+       required: True
+
+   # List of extra container image distributions.
+   stackhpc_pulp_distribution_container_extra:
+     - name: certbot
+       repository: certbot/certbot
+       base_path: certbot/certbot
+       state: present
+       required: True
+
 Usage
 =====
 

doc/source/configuration/vault.rst

@@ -241,6 +241,8 @@ Enable the required TLS variables in kayobe and kolla
       # Whether TLS is enabled for the internal API endpoints. Default is 'no'.
       kolla_enable_tls_internal: yes
 
+   See :ref:`os-capacity` for information on adding CA certificates to the trust store when deploying the OpenStack Capacity exporter.
+
 3. Set the following in etc/kayobe/kolla/globals.yml or if environments are being used etc/kayobe/environments/$KAYOBE_ENVIRONMENT/kolla/globals.yml
 
    .. code-block::

doc/source/operations/secret-rotation.rst

@@ -46,7 +46,7 @@ process easier.
 
    This was previously mitigated with a change to the StackHPC fork of
    Kolla-Ansible, which has since been reverted due to an unforeseen issue. See
-   `here <https://github.com/stackhpc/kolla-ansible/pull/503>` for more
+   `here <https://github.com/stackhpc/kolla-ansible/pull/503>`__ for more
    details.
 
 #. A change to Nova, to automate :ref:`this<nova-change>` step to change the

etc/kayobe/ansible/deploy-os-capacity-exporter.yml

@@ -27,6 +27,7 @@
       delegate_to: localhost
       register: credential
       when: stackhpc_enable_os_capacity
+      changed_when: false
 
     - name: Set facts for admin credentials
       ansible.builtin.set_fact:
@@ -43,6 +44,16 @@
         src: templates/os_capacity-clouds.yml.j2
         dest: /opt/kayobe/os-capacity/clouds.yaml
       when: stackhpc_enable_os_capacity
+      register: clouds_yaml_result
+
+    - name: Copy CA certificate to OpenStack Capacity nodes
+      ansible.builtin.copy:
+        src: "{{ stackhpc_os_capacity_openstack_cacert }}"
+        dest: /opt/kayobe/os-capacity/cacert.pem
+      when:
+        - stackhpc_enable_os_capacity
+        - stackhpc_os_capacity_openstack_cacert | length > 0
+      register: cacert_result
 
     - name: Ensure os_capacity container is running
       community.docker.docker_container:
@@ -56,6 +67,7 @@
             source: /opt/kayobe/os-capacity/
             target: /etc/openstack/
         network_mode: host
+        restart: "{{ clouds_yaml_result is changed or cacert_result is changed }}"
         restart_policy: unless-stopped
       become: true
       when: stackhpc_enable_os_capacity

etc/kayobe/ansible/templates/os_capacity-clouds.yml.j2

@@ -10,6 +10,9 @@ clouds:
     interface: "internal"
     identity_api_version: 3
     auth_type: "password"
+{% if stackhpc_os_capacity_openstack_cacert | length > 0 %}
+    cacert: /etc/openstack/cacert.pem
+{% endif %}
 {% if not stackhpc_os_capacity_openstack_verify | bool %}
     verify: False
 {% endif %}

etc/kayobe/environments/ci-multinode/stackhpc-monitoring.yml

@@ -0,0 +1,3 @@
+---
+# Path to a CA certificate file to trust in the OpenStack Capacity exporter.
+stackhpc_os_capacity_openstack_cacert: "{{ kayobe_env_config_path }}/kolla/certificates/ca/vault.crt"

etc/kayobe/kolla.yml

@@ -420,7 +420,6 @@ kolla_build_blocks:
     ARG prometheus_url=https://github.com/prometheus/prometheus/releases/download/v${prometheus_version}/prometheus-${prometheus_version}.linux-{{debian_arch}}.tar.gz
     {% endraw %}
 
-
 # Dict mapping image customization variable names to their values.
 # Each variable takes the form:
 # <image name>_<customization>_<operation>

etc/kayobe/kolla/config/prometheus/system.rules

@@ -24,6 +24,24 @@ groups:
       summary: "Prometheus exporter at {{ $labels.instance }} reports low memory"
       description: "Available memory is {{ $value }} GiB."
 
+  - alert: LowSwapSpace
+    expr: (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes) < {% endraw %}{{ alertmanager_node_free_swap_warning_threshold_ratio }}{% raw %}
+    for: 1m
+    labels:
+      severity: warning
+    annotations:
+      summary: "Swap space at {{ $labels.instance }} reports low memory"
+      description: "Available swap space is {{ $value | humanizePercentage }}. Running out of swap space causes OOM Kills."
+
+  - alert: LowSwapSpace
+    expr: (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes) < {% endraw %}{{ alertmanager_node_free_swap_critical_threshold_ratio }}{% raw %}
+    for: 1m
+    labels:
+      severity: critical
+    annotations:
+      summary: "Swap space at {{ $labels.instance }} reports low memory"
+      description: "Available swap space is {{ $value | humanizePercentage }}. Running out of swap space causes OOM Kills."
+
   - alert: HostOomKillDetected
     expr: increase(node_vmstat_oom_kill[5m]) > 0
     for: 5m

etc/kayobe/pulp.yml

@@ -652,14 +652,22 @@ stackhpc_pulp_distribution_container_hashicorp:
     state: present
     required: "{{ stackhpc_sync_hashicorp_images | bool }}"
 
+# List of extra container image repositories.
+stackhpc_pulp_repository_container_repos_extra: []
+
+# List of extra container image distributions.
+stackhpc_pulp_distribution_container_extra: []
+
 # List of container image repositories.
 stackhpc_pulp_repository_container_repos: >-
   {{ (stackhpc_pulp_repository_container_repos_kolla +
       stackhpc_pulp_repository_container_repos_ceph +
-      stackhpc_pulp_repository_container_repos_hashicorp) | selectattr('required') }}
+      stackhpc_pulp_repository_container_repos_hashicorp +
+      stackhpc_pulp_repository_container_repos_extra) | selectattr('required') }}
 
 # List of container image distributions.
 stackhpc_pulp_distribution_container: >-
   {{ (stackhpc_pulp_distribution_container_kolla +
       stackhpc_pulp_distribution_container_ceph +
-      stackhpc_pulp_distribution_container_hashicorp) | selectattr('required') }}
+      stackhpc_pulp_distribution_container_hashicorp +
+      stackhpc_pulp_distribution_container_extra) | selectattr('required') }}