Apply 2024.1 backports from 2023.1

doc/source/user/index.rst

@@ -463,6 +463,12 @@ the table are linked to more details elsewhere in the user guide.
 +---------------------------------------+--------------------+---------------+
 | `octavia_lb_healthcheck`_             | see bellow         | true          |
 +---------------------------------------+--------------------+---------------+
+| `extra_network`_                      | see below          | ""            |
++---------------------------------------+--------------------+---------------+
+| `extra_subnet`_                       | see below          | ""            |
++---------------------------------------+--------------------+---------------+
+| `extra_security_group`_               | see below          | see below     |
++---------------------------------------+--------------------+---------------+
 
 .. _cluster:
 
@@ -1175,13 +1181,14 @@ _`container_infra_prefix`
 
   Images that might be needed if 'monitoring_enabled' is 'true':
 
-  * quay.io/prometheus/alertmanager:v0.20.0
-  * docker.io/squareup/ghostunnel:v1.5.2
-  * docker.io/jettech/kube-webhook-certgen:v1.0.0
-  * quay.io/coreos/prometheus-operator:v0.37.0
-  * quay.io/coreos/configmap-reload:v0.0.1
-  * quay.io/coreos/prometheus-config-reloader:v0.37.0
-  * quay.io/prometheus/prometheus:v2.15.2
+  * quay.io/prometheus/alertmanager:v0.21.0
+  * docker.io/jettech/kube-webhook-certgen:v1.5.0
+  * quay.io/prometheus-operator/prometheus-operator:v0.44.0
+  * docker.io/jimmidyson/configmap-reload:v0.4.0
+  * quay.io/prometheus-operator/prometheus-config-reloader:v0.44.0
+  * quay.io/prometheus/prometheus:v2.22.1
+  * quay.io/prometheus/node-exporter:v1.0.1
+  * docker.io/directxman12/k8s-prometheus-adapter:v0.8.2
 
   Images that might be needed if 'cinder_csi_enabled' is 'true':
 
@@ -1548,6 +1555,22 @@ _`octavia_lb_healthcheck`
   If true, enable Octavia load balancer healthcheck
   Default: true
 
+_`extra_network`
+  Optional additional network name or UUID to add to cluster nodes.
+  When not specified, additional networks are not added. Optionally specify
+  'extra_subnet' if you wish to use a specific subnet on the network.
+  Default: ""
+
+_`extra_subnet`
+  Optional additional subnet name or UUID to add to cluster nodes.
+  Only used when 'extra_network' is defined.
+  Default: ""
+
+_`extra_security_group`
+  Optional additional group name or UUID to add to network port.
+  Only used when 'extra_network' is defined.
+  Default: cluster node default security group.
+
 Supported versions
 ------------------
 
@@ -2297,7 +2320,6 @@ _`calico_tag`
   Victoria default: v3.13.1
   Wallaby default: v3.13.1
 
-
 Besides, the Calico network driver needs kube_tag with v1.9.3 or later, because
 Calico needs extra mounts for the kubelet container. See `commit
 <https://github.com/projectatomic/atomic-system-containers/commit/54ab8abc7fa1bfb6fa674f55cd0c2fa0c812fd36>`_

doc/source/user/monitoring.rst

@@ -33,13 +33,15 @@ _`metrics_server_enabled`
 
 _`monitoring_enabled`
   Enable installation of cluster monitoring solution provided by the
-  stable/prometheus-operator helm chart.
+  prometheus-community/kube-prometheus-stack helm chart.
+  To use this service tiller_enabled must be true when using
+  helm_client_tag<v3.0.0.
   Default: false
 
 _`prometheus_adapter_enabled`
   Enable installation of cluster custom metrics provided by the
-  stable/prometheus-adapter helm chart. This service depends on
-  monitoring_enabled.
+  prometheus-community/prometheus-adapter helm chart.
+  This service depends on monitoring_enabled.
   Default: true
 
 To control deployed versions, extra labels are available:
@@ -52,14 +54,17 @@ _`metrics_server_chart_tag`
 
 _`prometheus_operator_chart_tag`
   Add prometheus_operator_chart_tag to select version of the
-  stable/prometheus-operator chart to install. When installing the chart,
-  helm will use the default values of the tag defined and overwrite them based
-  on the prometheus-operator-config ConfigMap currently defined. You must
-  certify that the versions are compatible.
+  prometheus-community/kube-prometheus-stack chart to install.
+  When installing the chart, helm will use the default values of the tag
+  defined and overwrite them based on the prometheus-operator-config
+  ConfigMap currently defined.
+  You must certify that the versions are compatible.
+  Wallaby-default: 17.2.0
 
 _`prometheus_adapter_chart_tag`
-  The stable/prometheus-adapter helm chart version to use.
+  The prometheus-community/prometheus-adapter helm chart version to use.
   Train-default: 1.4.0
+  Wallaby-default: 2.12.1
 
 Full fledged cluster monitoring
 +++++++++++++++++++++++++++++++

magnum/drivers/common/templates/kubernetes/fragments/configure-kubernetes-master.sh

@@ -271,7 +271,7 @@ CERT_DIR=/etc/kubernetes/certs
 
 # kube-proxy config
 PROXY_KUBECONFIG=/etc/kubernetes/proxy-kubeconfig.yaml
-KUBE_PROXY_ARGS="--kubeconfig=${PROXY_KUBECONFIG} --cluster-cidr=${PODS_NETWORK_CIDR} --hostname-override=${INSTANCE_NAME}"
+KUBE_PROXY_ARGS="--kubeconfig=${PROXY_KUBECONFIG} --cluster-cidr=${PODS_NETWORK_CIDR} --hostname-override=${INSTANCE_NAME} --metrics-bind-address=0.0.0.0"
 cat > /etc/kubernetes/proxy << EOF
 KUBE_PROXY_ARGS="${KUBE_PROXY_ARGS} ${KUBEPROXY_OPTIONS}"
 EOF
@@ -406,6 +406,8 @@ KUBE_CONTROLLER_MANAGER_ARGS="--leader-elect=true --kubeconfig=/etc/kubernetes/a
 KUBE_CONTROLLER_MANAGER_ARGS="$KUBE_CONTROLLER_MANAGER_ARGS --cluster-name=${CLUSTER_UUID}"
 KUBE_CONTROLLER_MANAGER_ARGS="${KUBE_CONTROLLER_MANAGER_ARGS} --allocate-node-cidrs=true"
 KUBE_CONTROLLER_MANAGER_ARGS="${KUBE_CONTROLLER_MANAGER_ARGS} --cluster-cidr=${PODS_NETWORK_CIDR}"
+KUBE_CONTROLLER_MANAGER_ARGS="${KUBE_CONTROLLER_MANAGER_ARGS} --secure-port=10257"
+KUBE_CONTROLLER_MANAGER_ARGS="${KUBE_CONTROLLER_MANAGER_ARGS} --authorization-always-allow-paths=/healthz,/readyz,/livez,/metrics"
 KUBE_CONTROLLER_MANAGER_ARGS="$KUBE_CONTROLLER_MANAGER_ARGS $KUBECONTROLLER_OPTIONS"
 if [ -n "${ADMISSION_CONTROL_LIST}" ] && [ "${TLS_DISABLED}" == "False" ]; then
     KUBE_CONTROLLER_MANAGER_ARGS="$KUBE_CONTROLLER_MANAGER_ARGS --service-account-private-key-file=$CERT_DIR/service_account_private.key --root-ca-file=$CERT_DIR/ca.crt"
@@ -428,7 +430,7 @@ sed -i '
     /^KUBE_CONTROLLER_MANAGER_ARGS=/ s#\(KUBE_CONTROLLER_MANAGER_ARGS\).*#\1="'"${KUBE_CONTROLLER_MANAGER_ARGS}"'"#
 ' /etc/kubernetes/controller-manager
 
-sed -i '/^KUBE_SCHEDULER_ARGS=/ s#=.*#="--leader-elect=true --kubeconfig=/etc/kubernetes/admin.conf"#' /etc/kubernetes/scheduler
+sed -i '/^KUBE_SCHEDULER_ARGS=/ s#=.*#="--leader-elect=true --kubeconfig=/etc/kubernetes/admin.conf --authorization-always-allow-paths=/healthz,/readyz,/livez,/metrics "#' /etc/kubernetes/scheduler
 
 $ssh_cmd mkdir -p /etc/kubernetes/manifests
 KUBELET_ARGS="--register-node=true --pod-manifest-path=/etc/kubernetes/manifests --hostname-override=${INSTANCE_NAME}"
@@ -497,7 +499,14 @@ KUBELET_ARGS="${KUBELET_ARGS} --client-ca-file=${CERT_DIR}/ca.crt --tls-cert-fil
 
 # specified cgroup driver
 KUBELET_ARGS="${KUBELET_ARGS} --cgroup-driver=${CGROUP_DRIVER}"
+
 if [ ${CONTAINER_RUNTIME} = "containerd"  ] ; then
+    # check kubelet version, 1.27.0 dropped docker shim and --container-runtime command line option
+    KUBELET_VERSION=$($ssh_cmd podman run --rm ${CONTAINER_INFRA_PREFIX:-${HYPERKUBE_PREFIX}}hyperkube:${KUBE_TAG} kubelet --version | awk '{print $2}')
+    CONTAINER_RUNTIME_REMOTE_DROPPED="v1.27.0"
+    if [[ "${CONTAINER_RUNTIME_REMOTE_DROPPED}" != $(echo -e "${CONTAINER_RUNTIME_REMOTE_DROPPED}\n${KUBELET_VERSION}" | sort -V | head -n1) && "${KUBELET_VERSION}" != "devel" ]]; then
+        KUBELET_ARGS="${KUBELET_ARGS} --container-runtime=remote"
+    fi
     KUBELET_ARGS="${KUBELET_ARGS} --runtime-cgroups=/system.slice/containerd.service"
     KUBELET_ARGS="${KUBELET_ARGS} --runtime-request-timeout=15m"
     KUBELET_ARGS="${KUBELET_ARGS} --container-runtime-endpoint=unix:///run/containerd/containerd.sock"

magnum/drivers/common/templates/kubernetes/fragments/configure-kubernetes-minion.sh

@@ -278,6 +278,12 @@ KUBELET_ARGS="${KUBELET_ARGS} --client-ca-file=${CERT_DIR}/ca.crt --tls-cert-fil
 # specified cgroup driver
 KUBELET_ARGS="${KUBELET_ARGS} --cgroup-driver=${CGROUP_DRIVER}"
 if [ ${CONTAINER_RUNTIME} = "containerd"  ] ; then
+    # check kubelet version, 1.27.0 dropped docker shim and --container-runtime command line option
+    KUBELET_VERSION=$($ssh_cmd podman run --rm ${CONTAINER_INFRA_PREFIX:-${HYPERKUBE_PREFIX}}hyperkube:${KUBE_TAG} kubelet --version | awk '{print $2}')
+    CONTAINER_RUNTIME_REMOTE_DROPPED="v1.27.0"
+    if [[ "${CONTAINER_RUNTIME_REMOTE_DROPPED}" != $(echo -e "${CONTAINER_RUNTIME_REMOTE_DROPPED}\n${KUBELET_VERSION}" | sort -V | head -n1) && "${KUBELET_VERSION}" != "devel" ]]; then
+        KUBELET_ARGS="${KUBELET_ARGS} --container-runtime=remote"
+    fi
     KUBELET_ARGS="${KUBELET_ARGS} --runtime-cgroups=/system.slice/containerd.service"
     KUBELET_ARGS="${KUBELET_ARGS} --runtime-request-timeout=15m"
     KUBELET_ARGS="${KUBELET_ARGS} --container-runtime-endpoint=unix:///run/containerd/containerd.sock"

magnum/drivers/common/templates/kubernetes/fragments/core-dns-service.sh

@@ -74,14 +74,17 @@ data:
   Corefile: |
     .:53 {
         errors
-        log
-        health
+        log stdout
+        health {
+            lameduck 5s
+        }
+        ready
         kubernetes ${DNS_CLUSTER_DOMAIN} ${PORTAL_NETWORK_CIDR} ${PODS_NETWORK_CIDR} {
            pods verified
            fallthrough in-addr.arpa ip6.arpa
         }
         prometheus :9153
-        forward . /etc/resolv.conf
+        forward . /run/systemd/resolve/resolv.conf
         cache 30
         loop
         reload
@@ -141,6 +144,9 @@ spec:
           readOnly: true
         - name: tmp
           mountPath: /tmp
+        - name: resolvconf
+          mountPath: /run/systemd/resolve/resolv.conf
+          readOnly: true
         ports:
         - containerPort: 53
           name: dns
@@ -183,6 +189,10 @@ spec:
             items:
             - key: Corefile
               path: Corefile
+        - name: resolvconf
+          hostPath:
+            path: /run/systemd/resolve/resolv.conf
+            type: File
 ---
 apiVersion: v1
 kind: Service

magnum/drivers/common/templates/kubernetes/fragments/enable-auto-scaling.sh

@@ -30,54 +30,50 @@ rules:
     resources: ["leases"]
     resourceNames: ["cluster-autoscaler"]
     verbs: ["get", "update", "patch", "delete"]
-  # TODO: remove in 1.18; CA uses lease objects for leader election since 1.17
   - apiGroups: [""]
-    resources: ["endpoints"]
+    resources: ["events", "endpoints"]
+    verbs: ["create", "patch"]
+  - apiGroups: [""]
+    resources: ["pods/eviction"]
     verbs: ["create"]
+  - apiGroups: [""]
+    resources: ["pods/status"]
+    verbs: ["update"]
   - apiGroups: [""]
     resources: ["endpoints"]
     resourceNames: ["cluster-autoscaler"]
-    verbs: ["get", "update", "patch", "delete"]
-  # accessing & modifying cluster state (nodes & pods)
+    verbs: ["get", "update"]
   - apiGroups: [""]
     resources: ["nodes"]
-    verbs: ["get", "list", "watch", "update", "patch"]
-  - apiGroups: [""]
-    resources: ["pods"]
-    verbs: ["get", "list", "watch"]
+    verbs: ["watch", "list", "get", "update"]
   - apiGroups: [""]
-    resources: ["pods/eviction"]
-    verbs: ["create"]
-  # read-only access to cluster state
-  - apiGroups: [""]
-    resources: ["services", "replicationcontrollers", "persistentvolumes", "persistentvolumeclaims"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: ["apps"]
-    resources: ["daemonsets", "replicasets"]
-    verbs: ["get", "list", "watch"]
-  - apiGroups: ["apps"]
-    resources: ["statefulsets"]
-    verbs: ["get", "list", "watch"]
+    resources:
+      - "namespaces"
+      - "pods"
+      - "services"
+      - "replicationcontrollers"
+      - "persistentvolumeclaims"
+      - "persistentvolumes"
+    verbs: ["watch", "list", "get"]
   - apiGroups: ["batch"]
     resources: ["jobs"]
-    verbs: ["get", "list", "watch"]
+    verbs: ["watch", "list", "get"]
   - apiGroups: ["policy"]
     resources: ["poddisruptionbudgets"]
-    verbs: ["get", "list", "watch"]
+    verbs: ["watch", "list"]
+  - apiGroups: ["apps"]
+    resources: ["daemonsets", "replicasets", "statefulsets"]
+    verbs: ["watch", "list", "get"]
   - apiGroups: ["storage.k8s.io"]
-    resources: ["storageclasses", "csinodes"]
-    verbs: ["get", "list", "watch"]
-  # misc access
-  - apiGroups: [""]
-    resources: ["events"]
-    verbs: ["create", "update", "patch"]
+    resources: ["storageclasses", "csinodes", "csidrivers", "csistoragecapacities"]
+    verbs: ["watch", "list", "get"]
   - apiGroups: [""]
     resources: ["configmaps"]
-    verbs: ["create"]
+    verbs: ["create","list","watch"]
   - apiGroups: [""]
     resources: ["configmaps"]
-    resourceNames: ["cluster-autoscaler-status"]
-    verbs: ["get", "update", "patch", "delete"]
+    resourceNames: ["cluster-autoscaler-status", "cluster-autoscaler-priority-expander"]
+    verbs: ["delete", "get", "update"]
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding

magnum/drivers/common/templates/kubernetes/fragments/make-cert-client.sh

@@ -82,7 +82,7 @@ EOF
     curl $VERIFY_CA -X GET \
         -H "X-Auth-Token: $USER_TOKEN" \
         -H "OpenStack-API-Version: container-infra latest" \
-        $MAGNUM_URL/certificates/$CLUSTER_UUID | python -c 'import sys, json; print(json.load(sys.stdin)["pem"])' >> $CA_CERT
+        $MAGNUM_URL/certificates/$CLUSTER_UUID | python -c 'import sys, json; print(json.load(sys.stdin)["pem"])' > $CA_CERT
 
     # Generate client's private key and csr
     $ssh_cmd openssl genrsa -out "${_KEY}" 4096

magnum/drivers/common/templates/kubernetes/helm/prometheus-adapter.sh

@@ -21,10 +21,11 @@ EOF
     cat << EOF >> ${HELM_CHART_DIR}/values.yaml
 prometheus-adapter:
   image:
-    repository: ${CONTAINER_INFRA_PREFIX:-docker.io/directxman12/}k8s-prometheus-adapter-${ARCH}
+    repository: ${CONTAINER_INFRA_PREFIX:-k8s.gcr.io/prometheus-adapter/}prometheus-adapter
   priorityClassName: "system-cluster-critical"
   prometheus:
-    url: http://web.tcp.prometheus-prometheus.kube-system.svc.cluster.local
+    url: http://web.tcp.magnum-kube-prometheus-sta-prometheus.kube-system.svc.cluster.local
+    path: /prometheus
   resources:
     requests:
       cpu: 150m