chore(deps): update helm release gateway to v1.24.2

Dockerfile

@@ -1,9 +1,9 @@
-ARG ALPINE_VERSION=3.21
+ARG ALPINE_VERSION=3.20
 
 FROM docker.io/alpine:${ALPINE_VERSION}
 
 ARG ALPINE_VERSION
-ARG KUBE_VERSION=1.31.4
+ARG KUBE_VERSION=1.30.6
 
 ARG SOPS_VERSION="3.9.1"
 ARG VALS_VERSION="0.37.6"
@@ -12,7 +12,7 @@ ARG HELM_SECRETS_VERSION="4.6.2"
 RUN cd /etc/apk/keys && \
     wget "https://cdn.zero-downtime.net/alpine/stefan@zero-downtime.net-61bb6bfb.rsa.pub" && \
     echo "@kubezero https://cdn.zero-downtime.net/alpine/v${ALPINE_VERSION}/kubezero" >> /etc/apk/repositories && \
-    echo "@testing http://dl-cdn.alpinelinux.org/alpine/edge/testing" >> /etc/apk/repositories && \
+    echo "@edge-testing http://dl-cdn.alpinelinux.org/alpine/edge/testing" >> /etc/apk/repositories && \
     echo "@edge-community http://dl-cdn.alpinelinux.org/alpine/edge/community" >> /etc/apk/repositories && \
     apk upgrade -U -a --no-cache && \
     apk --no-cache add \
@@ -24,7 +24,6 @@ RUN cd /etc/apk/keys && \
       py3-yaml \
       restic \
       helm \
-      ytt@testing \
       etcd-ctl@edge-community \
       cri-tools@kubezero \
       etcdhelper@kubezero \

admin/kubezero.sh

@@ -69,9 +69,9 @@ render_kubeadm() {
   fi
 
   # "uncloak" the json patches after they got processed by helm
-  for s in kube-apiserver kube-controller-manager kube-scheduler corednsdeployment; do
-    yq eval '.json' ${WORKDIR}/kubeadm/templates/patches/${s}1\+json.yaml > /tmp/_tmp.yaml && \
-      mv /tmp/_tmp.yaml ${WORKDIR}/kubeadm/templates/patches/${s}1\+json.yaml
+  for s in apiserver controller-manager scheduler; do
+    yq eval '.json' ${WORKDIR}/kubeadm/templates/patches/kube-${s}1\+json.yaml > /tmp/_tmp.yaml && \
+      mv /tmp/_tmp.yaml ${WORKDIR}/kubeadm/templates/patches/kube-${s}1\+json.yaml
   done
 }
 
@@ -117,12 +117,40 @@ post_kubeadm() {
   for f in ${WORKDIR}/kubeadm/templates/resources/*.yaml; do
     kubectl apply -f $f $LOG
   done
+
+  # Patch coreDNS addon, ideally we prevent kubeadm to reset coreDNS to its defaults
+  kubectl patch deployment coredns -n kube-system --patch-file ${WORKDIR}/kubeadm/templates/patches/coredns0.yaml $LOG
 }
 
 
 kubeadm_upgrade() {
   # pre upgrade hook
 
+  ### Remove with 1.31
+  # migrate kubezero CM to kubezero NS
+  # migrate ArgoCD app from values to valuesObject
+  create_ns kubezero
+
+  if [ "$ARGOCD" == "True" ]; then
+    kubectl get app kubezero -n argocd -o yaml > $WORKDIR/kubezero-argo-app.yaml
+    if [ "$(yq '(.spec.source.helm | has "values")' $WORKDIR/kubezero-argo-app.yaml)" == "true" ]; then
+      yq '.spec.source.helm.valuesObject = (.spec.source.helm.values | from_yaml)' \
+        $WORKDIR/kubezero-argo-app.yaml | kubectl apply --server-side --force-conflicts -f -
+
+      kubectl patch app kubezero -n argocd --type json -p='[{"op": "remove", "path": "/spec/source/helm/values"}]'
+      kubectl delete cm kubezero-values -n kube-system > /dev/null || true
+      kubectl create configmap -n kubezero kubezero-values || true
+    fi
+
+  else
+    kubectl get cm kubezero-values -n kubezero > /dev/null || \
+      { kubectl get cm kubezero-values -n kube-system -o yaml | \
+        sed 's/^  namespace: kube-system/  namespace: kubezero/' | \
+        kubectl create -f - && \
+        kubectl delete cm kubezero-values -n kube-system ; }
+  fi
+  ###
+
   # get current values, argo app over cm
   get_kubezero_values $ARGOCD
 
@@ -163,6 +191,14 @@ kubeadm_upgrade() {
 
   # post upgrade
 
+  # Update kubezero-values CM
+  kubectl get cm -n kube-system kubelet-config -o=yaml | \
+    yq e '.data.kubelet' | yq e '.containerRuntimeEndpoint = "unix:///run/containerd/containerd.sock"' > $WORKDIR/new-kubelet.cm
+
+  kubectl get cm -n kube-system kubelet-config -o=yaml | \
+    yq e '.data.kubelet |= load_str("/tmp/kubezero/new-kubelet.cm")' | \
+    kubectl apply --server-side --force-conflicts -f -
+
   # Cleanup after kubeadm on the host
   rm -rf ${HOSTFS}/etc/kubernetes/tmp
 

admin/libhelm.sh

@@ -46,16 +46,6 @@ function get_kubezero_values() {
 }
 
 
-# Update kubezero-values CM
-function update_kubezero_cm() {
-  kubectl get application kubezero -n argocd -o yaml | yq .spec.source.helm.valuesObject > ${WORKDIR}/kubezero-values.yaml
-
-  kubectl get cm -n kubezero kubezero-values -o=yaml | \
-    yq e '.data."values.yaml" |= load_str("/tmp/kubezero/kubezero-values.yaml")' | \
-    kubectl apply --server-side --force-conflicts -f -
-}
-
-
 function disable_argo() {
   cat > _argoapp_patch.yaml <<EOF
 spec:

admin/upgrade_cluster.sh

@@ -2,7 +2,7 @@
 set -eE
 set -o pipefail
 
-KUBE_VERSION=v1.31
+KUBE_VERSION=v1.30
 
 ARGO_APP=${1:-/tmp/new-kubezero-argoapp.yaml}
 
@@ -19,6 +19,11 @@ echo "Checking that all pods in kube-system are running ..."
 
 [ "$ARGOCD" == "True" ] && disable_argo
 
+# 1.30 fix for the missing kubeadm socket annotations
+for c in $(kubectl get nodes -l "node-role.kubernetes.io/control-plane=" | grep v1.29 | awk {'print $1}'); do
+  kubectl annotate node $c 'kubeadm.alpha.kubernetes.io/cri-socket=unix:///var/run/crio/crio.sock'
+done
+
 control_plane_upgrade kubeadm_upgrade
 
 echo "Control plane upgraded, <Return> to continue"
@@ -28,7 +33,8 @@ read -r
 # shellcheck disable=SC2015
 #[ "$ARGOCD" == "True" ] && kubectl edit app kubezero -n argocd || kubectl edit cm kubezero-values -n kubezero
 
-### v1.31
+### v1.30
+kubectl delete runtimeclass crio || true
 
 # upgrade modules
 #
@@ -37,8 +43,9 @@ read -r
 
 control_plane_upgrade "apply_network, apply_addons, apply_storage, apply_operators"
 
-echo "Checking that all pods in kube-system are running ..."
-waitSystemPodsRunning
+# Disabled during 1.30 due to nvidia runtime deadlock
+#echo "Checking that all pods in kube-system are running ..."
+#waitSystemPodsRunning
 
 echo "Applying remaining KubeZero modules..."
 

charts/kubeadm/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: kubeadm
 description: KubeZero Kubeadm cluster config
 type: application
-version: 1.31.4
+version: 1.30.6
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:

charts/kubeadm/templates/_helpers.tpl

@@ -3,7 +3,7 @@
 {{- /* v1.28: PodAndContainerStatsFromCRI still not working */ -}}
 {{- /* v1.28: UnknownVersionInteroperabilityProxy requires StorageVersionAPI which is still alpha in 1.30 */ -}}
 {{- define "kubeadm.featuregates" }}
-{{- $gates := list "CustomCPUCFSQuotaPeriod" "AuthorizeWithSelectors" "AuthorizeNodeWithSelectors" "ConsistentListFromCache" "VolumeAttributesClass" "WatchList"}}
+{{- $gates := list "CustomCPUCFSQuotaPeriod" }}
 {{- if eq .return "csv" }}
 {{- range $key := $gates }}
 {{- $key }}=true,

charts/kubeadm/templates/patches/coredns0.yaml

@@ -1,4 +1,5 @@
 spec:
+  replicas: {{ ternary 3 1 .Values.global.highAvailable }}
   template:
     spec:
       containers:

charts/kubeadm/templates/patches/corednsdeployment1+json.yaml

@@ -1,4 +0,0 @@
-json:
-  - op: replace
-    path: /spec/replicas
-    value: {{ ternary 3 1 .Values.global.highAvailable }}

charts/kubezero-addons/Chart.yaml

@@ -33,11 +33,6 @@ dependencies:
     # https://github.com/NVIDIA/k8s-device-plugin
     repository: https://nvidia.github.io/k8s-device-plugin
     condition: nvidia-device-plugin.enabled
-  - name: neuron-helm-chart
-    version: 1.1.1
-    # https://github.com/aws-neuron/neuron-helm-charts/tree/main/charts/neuron-helm-chart
-    repository: oci://public.ecr.aws/neuron #/neuron-helm-chart
-    condition: neuron-helm-chart.enabled
   - name: sealed-secrets
     version: 2.16.2
     repository: https://bitnami-labs.github.io/sealed-secrets

charts/kubezero-addons/README.md

@@ -25,7 +25,6 @@ Kubernetes: `>= 1.26.0`
 | https://nvidia.github.io/k8s-device-plugin | nvidia-device-plugin | 0.17.0 |
 | https://twin.github.io/helm-charts | aws-eks-asg-rolling-update-handler | 1.5.0 |
 | oci://public.ecr.aws/aws-ec2/helm | aws-node-termination-handler | 0.24.1 |
-| oci://public.ecr.aws/neuron | neuron-helm-chart | 1.1.1 |
 
 # MetalLB   
    
@@ -101,11 +100,13 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | aws-node-termination-handler.tolerations[0].effect | string | `"NoSchedule"` |  |
 | aws-node-termination-handler.tolerations[0].key | string | `"node-role.kubernetes.io/control-plane"` |  |
 | aws-node-termination-handler.useProviderId | bool | `true` |  |
+| awsNeuron.enabled | bool | `false` |  |
+| awsNeuron.image.name | string | `"public.ecr.aws/neuron/neuron-device-plugin"` |  |
+| awsNeuron.image.tag | string | `"2.22.4.0"` |  |
 | cluster-autoscaler.autoDiscovery.clusterName | string | `""` |  |
 | cluster-autoscaler.awsRegion | string | `"us-west-2"` |  |
 | cluster-autoscaler.enabled | bool | `false` |  |
 | cluster-autoscaler.extraArgs.balance-similar-node-groups | bool | `true` |  |
-| cluster-autoscaler.extraArgs.ignore-daemonsets-utilization | bool | `true` |  |
 | cluster-autoscaler.extraArgs.ignore-taint | string | `"node.cilium.io/agent-not-ready"` |  |
 | cluster-autoscaler.extraArgs.scan-interval | string | `"30s"` |  |
 | cluster-autoscaler.extraArgs.skip-nodes-with-local-storage | bool | `false` |  |
@@ -140,24 +141,22 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | fuseDevicePlugin.enabled | bool | `false` |  |
 | fuseDevicePlugin.image.name | string | `"public.ecr.aws/zero-downtime/fuse-device-plugin"` |  |
 | fuseDevicePlugin.image.tag | string | `"v1.2.0"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[0].key | string | `"CriticalAddonsOnly"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[0].operator | string | `"Exists"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[1].effect | string | `"NoSchedule"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[1].key | string | `"aws.amazon.com/neuron"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[1].operator | string | `"Exists"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[2].effect | string | `"NoSchedule"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[2].key | string | `"kubezero-workergroup"` |  |
-| neuron-helm-chart.devicePlugin.tolerations[2].operator | string | `"Exists"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[0].mountPath | string | `"/var/lib/kubelet/device-plugins"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[0].name | string | `"device-plugin"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[1].mountPath | string | `"/run"` |  |
-| neuron-helm-chart.devicePlugin.volumeMounts[1].name | string | `"infa-map"` |  |
-| neuron-helm-chart.devicePlugin.volumes[0].hostPath.path | string | `"/var/lib/kubelet/device-plugins"` |  |
-| neuron-helm-chart.devicePlugin.volumes[0].name | string | `"device-plugin"` |  |
-| neuron-helm-chart.devicePlugin.volumes[1].hostPath.path | string | `"/run"` |  |
-| neuron-helm-chart.devicePlugin.volumes[1].name | string | `"infa-map"` |  |
-| neuron-helm-chart.enabled | bool | `false` |  |
-| neuron-helm-chart.npd.enabled | bool | `false` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].key | string | `"node.kubernetes.io/instance-type"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].operator | string | `"In"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[0] | string | `"g5.xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[10] | string | `"g4dn.4xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[11] | string | `"g4dn.8xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[12] | string | `"g4dn.12xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[13] | string | `"g4dn.16xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[1] | string | `"g5.2xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[2] | string | `"g5.4xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[3] | string | `"g5.8xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[4] | string | `"g5.12xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[5] | string | `"g5.16xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[6] | string | `"g5.24xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[7] | string | `"g5.48xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[8] | string | `"g4dn.xlarge"` |  |
+| nvidia-device-plugin.affinity.nodeAffinity.requiredDuringSchedulingIgnoredDuringExecution.nodeSelectorTerms[0].matchExpressions[0].values[9] | string | `"g4dn.2xlarge"` |  |
 | nvidia-device-plugin.cdi.nvidiaHookPath | string | `"/usr/bin"` |  |
 | nvidia-device-plugin.deviceDiscoveryStrategy | string | `"nvml"` |  |
 | nvidia-device-plugin.enabled | bool | `false` |  |
@@ -168,23 +167,6 @@ Device plugin for [AWS Neuron](https://aws.amazon.com/machine-learning/neuron/)
 | nvidia-device-plugin.tolerations[1].effect | string | `"NoSchedule"` |  |
 | nvidia-device-plugin.tolerations[1].key | string | `"kubezero-workergroup"` |  |
 | nvidia-device-plugin.tolerations[1].operator | string | `"Exists"` |  |
-| py-kube-downscaler.enabled | bool | `false` |  |
-| py-kube-downscaler.excludedNamespaces[0] | string | `"kube-system"` |  |
-| py-kube-downscaler.excludedNamespaces[1] | string | `"operators"` |  |
-| py-kube-downscaler.excludedNamespaces[2] | string | `"monitoring"` |  |
-| py-kube-downscaler.excludedNamespaces[3] | string | `"logging"` |  |
-| py-kube-downscaler.excludedNamespaces[4] | string | `"telemetry"` |  |
-| py-kube-downscaler.excludedNamespaces[5] | string | `"istio-system"` |  |
-| py-kube-downscaler.excludedNamespaces[6] | string | `"istio-ingress"` |  |
-| py-kube-downscaler.excludedNamespaces[7] | string | `"cert-manager"` |  |
-| py-kube-downscaler.excludedNamespaces[8] | string | `"argocd"` |  |
-| py-kube-downscaler.nodeSelector."node-role.kubernetes.io/control-plane" | string | `""` |  |
-| py-kube-downscaler.resources.limits.cpu | string | `nil` |  |
-| py-kube-downscaler.resources.limits.memory | string | `"256Mi"` |  |
-| py-kube-downscaler.resources.requests.cpu | string | `"20m"` |  |
-| py-kube-downscaler.resources.requests.memory | string | `"48Mi"` |  |
-| py-kube-downscaler.tolerations[0].effect | string | `"NoSchedule"` |  |
-| py-kube-downscaler.tolerations[0].key | string | `"node-role.kubernetes.io/control-plane"` |  |
 | sealed-secrets.enabled | bool | `false` |  |
 | sealed-secrets.fullnameOverride | string | `"sealed-secrets-controller"` |  |
 | sealed-secrets.keyrenewperiod | string | `"0"` |  |

charts/kubezero-addons/templates/device-plugins/aws-neuron-ds.yaml

@@ -0,0 +1,80 @@
+{{- if .Values.awsNeuron.enabled }}
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: neuron-device-plugin
+  namespace: kube-system
+spec:
+  selector:
+    matchLabels:
+      name:  neuron-device-plugin-ds
+  updateStrategy:
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        name: neuron-device-plugin-ds
+    spec:
+      serviceAccount: neuron-device-plugin
+      tolerations:
+      - key: CriticalAddonsOnly
+        operator: Exists
+      - key: aws.amazon.com/neuron
+        operator: Exists
+        effect: NoSchedule
+      - key: kubezero-workergroup
+        effect: NoSchedule
+        operator: Exists
+      # Mark this pod as a critical add-on; when enabled, the critical add-on
+      # scheduler reserves resources for critical add-on pods so that they can
+      # be rescheduled after a failure.
+      # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
+      priorityClassName: "system-node-critical"
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                  - key: "node.kubernetes.io/instance-type"
+                    operator: In
+                    values:
+                      - inf1.xlarge
+                      - inf1.2xlarge
+                      - inf1.6xlarge
+                      - inf1.24xlarge
+                      - inf2.xlarge
+                      - inf2.4xlarge
+                      - inf2.8xlarge
+                      - inf2.24xlarge
+                      - inf2.48xlarge
+                      - trn1.2xlarge
+                      - trn1.32xlarge
+                      - trn1n.32xlarge
+      containers:
+      - image: "{{ .Values.awsNeuron.image.name }}:{{ .Values.awsNeuron.image.tag }}"
+        imagePullPolicy: IfNotPresent
+        name: neuron-device-plugin
+        env:
+        - name: KUBECONFIG
+          value: /etc/kubernetes/kubelet.conf
+        - name: NODE_NAME
+          valueFrom:
+            fieldRef:
+              fieldPath: spec.nodeName
+        securityContext:
+          allowPrivilegeEscalation: false
+          capabilities:
+            drop: ["ALL"]
+        volumeMounts:
+          - name: device-plugin
+            mountPath: /var/lib/kubelet/device-plugins
+          - name: infa-map
+            mountPath: /run
+      volumes:
+        - name: device-plugin
+          hostPath:
+            path: /var/lib/kubelet/device-plugins
+        - name: infa-map
+          hostPath:
+            path: /run
+{{- end }}

charts/kubezero-addons/templates/device-plugins/aws-neuron-rbac.yaml

@@ -0,0 +1,59 @@
+{{- if .Values.awsNeuron.enabled }}
+kind: ClusterRole
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: neuron-device-plugin
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - nodes
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - events
+  verbs:
+  - create
+  - patch
+- apiGroups:
+  - ""
+  resources:
+  - pods
+  verbs:
+  - update
+  - patch
+  - get
+  - list
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - nodes/status
+  verbs:
+  - patch
+  - update
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: neuron-device-plugin
+  namespace: kube-system
+---
+kind: ClusterRoleBinding
+apiVersion: rbac.authorization.k8s.io/v1
+metadata:
+  name: neuron-device-plugin
+  namespace: kube-system
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: neuron-device-plugin
+subjects:
+- kind: ServiceAccount
+  name: neuron-device-plugin
+  namespace: kube-system
+{{- end }}

charts/kubezero-addons/values.yaml

@@ -155,35 +155,12 @@ fuseDevicePlugin:
     name: public.ecr.aws/zero-downtime/fuse-device-plugin
     tag: v1.2.0
 
-neuron-helm-chart:
+awsNeuron:
   enabled: false
 
-  npd:
-    enabled: false
-
-  devicePlugin:
-    tolerations:
-      - key: CriticalAddonsOnly
-        operator: Exists
-      - key: aws.amazon.com/neuron
-        operator: Exists
-        effect: NoSchedule
-      - key: kubezero-workergroup
-        effect: NoSchedule
-        operator: Exists
-
-    volumeMounts:
-      - name: device-plugin
-        mountPath: /var/lib/kubelet/device-plugins
-      - name: infa-map
-        mountPath: /run
-    volumes:
-      - name: device-plugin
-        hostPath:
-          path: /var/lib/kubelet/device-plugins
-      - name: infa-map
-        hostPath:
-          path: /run
+  image:
+    name: public.ecr.aws/neuron/neuron-device-plugin
+    tag: 2.22.4.0
 
 nvidia-device-plugin:
   enabled: false
@@ -201,6 +178,29 @@ nvidia-device-plugin:
     effect: NoSchedule
     operator: Exists
 
+  affinity:
+    nodeAffinity:
+      requiredDuringSchedulingIgnoredDuringExecution:
+        nodeSelectorTerms:
+          - matchExpressions:
+              - key: "node.kubernetes.io/instance-type"
+                operator: In
+                values:
+                  - g5.xlarge
+                  - g5.2xlarge
+                  - g5.4xlarge
+                  - g5.8xlarge
+                  - g5.12xlarge
+                  - g5.16xlarge
+                  - g5.24xlarge
+                  - g5.48xlarge
+                  - g4dn.xlarge
+                  - g4dn.2xlarge
+                  - g4dn.4xlarge
+                  - g4dn.8xlarge
+                  - g4dn.12xlarge
+                  - g4dn.16xlarge
+
 cluster-autoscaler:
   enabled: false
 

charts/kubezero-argo/README.md

@@ -1,6 +1,6 @@
 # kubezero-argo
 
-![Version: 0.2.7](https://img.shields.io/badge/Version-0.2.7-informational?style=flat-square)
+![Version: 0.2.6](https://img.shields.io/badge/Version-0.2.6-informational?style=flat-square)
 
 KubeZero Argo - Events, Workflow, CD
 
@@ -18,8 +18,8 @@ Kubernetes: `>= 1.26.0-0`
 
 | Repository | Name | Version |
 |------------|------|---------|
-| https://argoproj.github.io/argo-helm | argo-cd | 7.7.7 |
-| https://argoproj.github.io/argo-helm | argo-events | 2.4.9 |
+| https://argoproj.github.io/argo-helm | argo-cd | 7.7.2 |
+| https://argoproj.github.io/argo-helm | argo-events | 2.4.8 |
 | https://argoproj.github.io/argo-helm | argocd-apps | 2.0.2 |
 | https://argoproj.github.io/argo-helm | argocd-image-updater | 0.11.2 |
 | https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
@@ -28,13 +28,12 @@ Kubernetes: `>= 1.26.0-0`
 
 | Key | Type | Default | Description |
 |-----|------|---------|-------------|
-| argo-cd.configs.cm."application.resourceTrackingMethod" | string | `"annotation"` |  |
 | argo-cd.configs.cm."resource.customizations" | string | `"cert-manager.io/Certificate:\n  # Lua script for customizing the health status assessment\n  health.lua: |\n    hs = {}\n    if obj.status ~= nil then\n      if obj.status.conditions ~= nil then\n        for i, condition in ipairs(obj.status.conditions) do\n          if condition.type == \"Ready\" and condition.status == \"False\" then\n            hs.status = \"Degraded\"\n            hs.message = condition.message\n            return hs\n          end\n          if condition.type == \"Ready\" and condition.status == \"True\" then\n            hs.status = \"Healthy\"\n            hs.message = condition.message\n            return hs\n          end\n        end\n      end\n    end\n    hs.status = \"Progressing\"\n    hs.message = \"Waiting for certificate\"\n    return hs\n"` |  |
 | argo-cd.configs.cm."timeout.reconciliation" | string | `"300s"` |  |
-| argo-cd.configs.cm."ui.bannercontent" | string | `"KubeZero v1.31 - Release notes"` |  |
+| argo-cd.configs.cm."ui.bannercontent" | string | `"KubeZero v1.30 - Release notes"` |  |
 | argo-cd.configs.cm."ui.bannerpermanent" | string | `"true"` |  |
 | argo-cd.configs.cm."ui.bannerposition" | string | `"bottom"` |  |
-| argo-cd.configs.cm."ui.bannerurl" | string | `"https://kubezero.com/releases/v1.31"` |  |
+| argo-cd.configs.cm."ui.bannerurl" | string | `"https://kubezero.com/releases/v1.30"` |  |
 | argo-cd.configs.cm.url | string | `"https://argocd.example.com"` |  |
 | argo-cd.configs.params."controller.diff.server.side" | string | `"true"` |  |
 | argo-cd.configs.params."controller.operation.processors" | string | `"5"` |  |
@@ -52,9 +51,8 @@ Kubernetes: `>= 1.26.0-0`
 | argo-cd.dex.enabled | bool | `false` |  |
 | argo-cd.enabled | bool | `false` |  |
 | argo-cd.global.image.repository | string | `"public.ecr.aws/zero-downtime/zdt-argocd"` |  |
-| argo-cd.global.image.tag | string | `"v2.13.1"` |  |
+| argo-cd.global.image.tag | string | `"v2.12.4"` |  |
 | argo-cd.global.logging.format | string | `"json"` |  |
-| argo-cd.global.networkPolicy.create | bool | `true` |  |
 | argo-cd.istio.enabled | bool | `false` |  |
 | argo-cd.istio.gateway | string | `"istio-ingress/ingressgateway"` |  |
 | argo-cd.istio.ipBlocks | list | `[]` |  |

charts/kubezero-argo/values.yaml

@@ -66,10 +66,6 @@ argo-cd:
 
       timeout.reconciliation: 300s
 
-      application.resourceTrackingMethod: annotation
-      installationID: "KubeZero-ArgoCD"
-      application.instanceLabelKey: Null
-
       resource.customizations: |
         cert-manager.io/Certificate:
           # Lua script for customizing the health status assessment

charts/kubezero-graph/.helmignore

@@ -1,23 +0,0 @@
-# Patterns to ignore when building packages.
-# This supports shell glob matching, relative path matching, and
-# negation (prefixed with !). Only one pattern per line.
-.DS_Store
-# Common VCS dirs
-.git/
-.gitignore
-.bzr/
-.bzrignore
-.hg/
-.hgignore
-.svn/
-# Common backup files
-*.swp
-*.bak
-*.tmp
-*.orig
-*~
-# Various IDEs
-.project
-.idea/
-*.tmproj
-.vscode/

charts/kubezero-graph/Chart.yaml

@@ -1,23 +0,0 @@
-apiVersion: v2
-name: kubezero-graph
-description: KubeZero GraphQL and GraphDB
-type: application
-version: 0.1.0
-home: https://kubezero.com
-icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
-keywords:
-  - kubezero
-  - neo4j
-maintainers:
-  - name: Stefan Reimer
-    email: stefan@zero-downtime.net
-dependencies:
-  - name: kubezero-lib
-    version: ">= 0.2.1"
-    repository: https://cdn.zero-downtime.net/charts/
-  - name: neo4j
-    version: 5.26.0
-    repository: https://helm.neo4j.com/neo4j
-    condition: neo4j.enabled
-
-kubeVersion: ">= 1.29.0-0"

charts/kubezero-graph/README.md

@@ -1,44 +0,0 @@
-# kubezero-graph
-
-![Version: 0.1.0](https://img.shields.io/badge/Version-0.1.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)
-
-KubeZero GraphQL and GraphDB
-
-**Homepage:** <https://kubezero.com>
-
-## Maintainers
-
-| Name | Email | Url |
-| ---- | ------ | --- |
-| Stefan Reimer | <stefan@zero-downtime.net> |  |
-
-## Requirements
-
-Kubernetes: `>= 1.29.0-0`
-
-| Repository | Name | Version |
-|------------|------|---------|
-| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.2.1 |
-| https://helm.neo4j.com/neo4j | neo4j | 5.26.0 |
-
-## Values
-
-| Key | Type | Default | Description |
-|-----|------|---------|-------------|
-| neo4j.disableLookups | bool | `true` |  |
-| neo4j.enabled | bool | `false` |  |
-| neo4j.neo4j.name | string | `"test-db"` |  |
-| neo4j.serviceMonitor.enabled | bool | `false` |  |
-| neo4j.services.neo4j.enabled | bool | `false` |  |
-| neo4j.volumes.data.mode | string | `"defaultStorageClass"` |  |
-
-# Dashboards
-https://grafana.com/grafana/dashboards/11835
-
-## Redis
-
-# Resources
-- https://ot-container-kit.github.io/redis-operator/
-- https://github.com/helm/charts/tree/master/stable/redis
-- https://github.com/rustudorcalin/deploying-redis-cluster
--

charts/kubezero-graph/README.md.gotmpl

@@ -1,27 +0,0 @@
-{{ template "chart.header" . }}
-{{ template "chart.deprecationWarning" . }}
-
-{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
-
-{{ template "chart.description" . }}
-
-{{ template "chart.homepageLine" . }}
-
-{{ template "chart.maintainersSection" . }}
-
-{{ template "chart.sourcesSection" . }}
-
-{{ template "chart.requirementsSection" . }}
-
-{{ template "chart.valuesSection" . }}
-
-# Dashboards
-https://grafana.com/grafana/dashboards/11835
-
-## Redis
-
-# Resources
-- https://ot-container-kit.github.io/redis-operator/
-- https://github.com/helm/charts/tree/master/stable/redis
-- https://github.com/rustudorcalin/deploying-redis-cluster
-- 

charts/kubezero-graph/update.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-set -ex
-
-. ../../scripts/lib-update.sh
-
-#login_ecr_public
-update_helm
-
-update_docs

charts/kubezero-graph/values.yaml

@@ -1,18 +0,0 @@
-neo4j:
-  enabled: false
-
-  disableLookups: true
-
-  neo4j:
-    name: test-db
-
-  volumes:
-    data:
-      mode: defaultStorageClass
-
-  services:
-    neo4j:
-      enabled: false
-
-  serviceMonitor:
-    enabled: false

charts/kubezero-istio-gateway/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: kubezero-istio-gateway
 description: KubeZero Umbrella Chart for Istio gateways
 type: application
-version: 0.23.2
+version: 0.23.3
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
@@ -17,6 +17,6 @@ dependencies:
     version: ">= 0.1.6"
     repository: https://cdn.zero-downtime.net/charts/
   - name: gateway
-    version: 1.23.2
+    version: 1.24.2
     repository: https://istio-release.storage.googleapis.com/charts
 kubeVersion: ">= 1.26.0-0"

charts/kubezero-keyvalue/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v2
-name: kubezero-cache
-description: KubeZero Cache module
+name: kubezero-keyvalue
+description: KubeZero KeyValue Module
 type: application
 version: 0.1.0
 home: https://kubezero.com
@@ -14,7 +14,7 @@ maintainers:
     email: stefan@zero-downtime.net
 dependencies:
   - name: kubezero-lib
-    version: ">= 0.2.1"
+    version: ">= 0.1.6"
     repository: https://cdn.zero-downtime.net/charts/
   - name: redis
     version: 20.0.3
@@ -25,4 +25,4 @@ dependencies:
     repository: https://charts.bitnami.com/bitnami
     condition: redis-cluster.enabled
 
-kubeVersion: ">= 1.29.0-0"
+kubeVersion: ">= 1.26.0"

charts/kubezero-keyvalue/README.md

@@ -1,8 +1,8 @@
-# kubezero-cache
+# kubezero-keyvalue
 
 ![Version: 0.1.0](https://img.shields.io/badge/Version-0.1.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)
 
-KubeZero Cache module
+KubeZero KeyValue Module
 
 **Homepage:** <https://kubezero.com>
 
@@ -14,11 +14,11 @@ KubeZero Cache module
 
 ## Requirements
 
-Kubernetes: `>= 1.29.0-0`
+Kubernetes: `>= 1.26.0`
 
 | Repository | Name | Version |
 |------------|------|---------|
-| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.2.1 |
+| https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
 | https://charts.bitnami.com/bitnami | redis | 20.0.3 |
 | https://charts.bitnami.com/bitnami | redis-cluster | 11.0.2 |
 

charts/kubezero-network/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: kubezero-network
 description: KubeZero umbrella chart for all things network
 type: application
-version: 0.5.6
+version: 0.5.5
 home: https://kubezero.com
 icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png
 keywords:
@@ -19,11 +19,11 @@ dependencies:
     version: ">= 0.1.6"
     repository: https://cdn.zero-downtime.net/charts/
   - name: cilium
-    version: 1.16.5
+    version: 1.16.3
     repository: https://helm.cilium.io/
     condition: cilium.enabled
   - name: metallb
-    version: 0.14.9
+    version: 0.14.8
     repository: https://metallb.github.io/metallb
     condition: metallb.enabled
   - name: haproxy

charts/kubezero-network/README.md

@@ -1,6 +1,6 @@
 # kubezero-network
 
-![Version: 0.5.6](https://img.shields.io/badge/Version-0.5.6-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)
+![Version: 0.5.5](https://img.shields.io/badge/Version-0.5.5-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square)
 
 KubeZero umbrella chart for all things network
 
@@ -20,8 +20,8 @@ Kubernetes: `>= 1.26.0`
 |------------|------|---------|
 | https://cdn.zero-downtime.net/charts/ | kubezero-lib | >= 0.1.6 |
 | https://haproxytech.github.io/helm-charts | haproxy | 1.23.0 |
-| https://helm.cilium.io/ | cilium | 1.16.5 |
-| https://metallb.github.io/metallb | metallb | 0.14.9 |
+| https://helm.cilium.io/ | cilium | 1.16.3 |
+| https://metallb.github.io/metallb | metallb | 0.14.8 |
 
 ## Values
 

charts/kubezero-operators/values.yaml

@@ -29,22 +29,18 @@ cloudnative-pg:
 strimzi-kafka-operator:
   enabled: false
 
-  revisionHistoryLimit: 2
+  revisionHistoryLimit: 3
   watchAnyNamespace: true
 
   leaderElection:
     enable: false
 
-# extraEnvs:
-#   - name: JAVA_OPTS
-#     value: "-XX:MaxRAMPercentage=75 -XX:+UseParallelGC -XX:ActiveProcessorCount=2"
-
-# resources:
-#   requests:
-#     cpu: 10m
-#     memory: 256Mi
-#   limits:
-#     memory: 256Mi
+  resources:
+    requests:
+      cpu: 20m
+      memory: 256Mi
+    limits:
+      memory: 384Mi
 
   monitoring:
     podMonitorEnabled: false

charts/kubezero/values.yaml

@@ -36,7 +36,7 @@ addons:
 network:
   enabled: true
   retain: true
-  targetRevision: 0.5.6
+  targetRevision: 0.5.5
   cilium:
     cluster: {}
 

docs/v1.31.md

@@ -1,16 +1,15 @@
 # ![k8s-v1.31](images/k8s-1.31.png)  KubeZero 1.31 - Elli
 
 ## What's new - Major themes
-- all KubeZero and support AMIs based on [Alpine 3.21](https://alpinelinux.org/posts/Alpine-3.21.0-released.html)
-- network policies for ArgoCD
+- all KubeZero and support AMIs based on Alpine 3.21
 
 ## Features and fixes
-- ArgoCD now tracks ownership by annotations rather than labels
 
 ## Version upgrades
+<WIP>
 - cilium 1.16.3
 - istio 1.22.3
-- ArgoCD 2.13.1 [custom ZDT image](https://git.zero-downtime.net/ZeroDownTime/zdt-argocd)
+- ArgoCD 2.13.0 [custom ZDT image](https://git.zero-downtime.net/ZeroDownTime/zdt-argocd)
 - Prometheus 2.55.1 / Grafana 11.3.0
 - Nvidia container toolkit 1.17, drivers  565.57.01, Cuda 12.7