devel: Useful kubectl plugins

chore: update npins dependencies

See merge request oceanbox/manifests!67

.envrc

@@ -1,6 +1,7 @@
 #!/usr/bin/env bash
 # the shebang is ignored, but nice for editors
 watch_file nix/sources.json
+watch_file nix/checks.nix
 
 # Load .env file if it exists
 dotenv_if_exists

.gitignore

@@ -1,6 +1,7 @@
 *.tgz
 _*/
 .direnv/
+.env
 .pre-commit-config.yaml
 _*.yaml
 backup/

.gitlab-ci.yml

@@ -1,46 +1,54 @@
-image:
+# yaml-language-server: $schema=https://gitlab.com/gitlab-org/gitlab/-/raw/master/app/assets/javascripts/editor/schema/ci.json
-  name: alpine/helm:latest
+default:
-  entrypoint: [ "/bin/bash", "-c" ]
+  tags:
+    - nix
 
-stages:
+include:
-  - release
+  - project: oceanbox/gitlab-ci
+    ref: v4.5
+    file: template/Base.gitlab-ci.yml
+# stages:
+# - release
 
-release:
+# image:
-  stage: release
+# name: alpine/helm:latest
-  rules:
+# entrypoint: ["/bin/bash", "-c"]
-  - if: '$CI_COMMIT_BRANCH =~ /^main/'
-    when: always
-  - when: never
-  script:
-    - |
-      cd $CI_PROJECT_DIR
-      for i in $(git show --pretty="" --name-only | grep '^charts/.*/Chart.yaml' | cut -d/ -f2); do
-        pack=$(helm package ./charts/$i | sed 's/Success.*: \(.*\)/\1/')
-        if [ ! -z $pack ]; then
-          chart=$(basename $pack)
-          curl --request POST \
-               --user gitlab-ci-token:$CI_JOB_TOKEN \
-               --form "chart=@${chart}" \
-               "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/helm/api/stable/charts"
-        fi
-      done
 
-rebuild:
+# release:
-  stage: release
+# stage: release
-  rules:
+# rules:
-    - when: manual
+# - if: "$CI_COMMIT_BRANCH =~ /^main/"
-      allow_failure: true
+# when: always
-  script:
+# - when: never
-    - |
+# script:
-      cd $CI_PROJECT_DIR
+# - |
-      for i in $(find ./charts -maxdepth 2 -name Chart.yaml | cut -d/ -f3); do
+# cd $CI_PROJECT_DIR
-        pack=$(helm package ./charts/$i | sed 's/Success.*: \(.*\)/\1/')
+# for i in $(git show --pretty="" --name-only | grep '^charts/.*/Chart.yaml' | cut -d/ -f2); do
-        if [ ! -z $pack ]; then
+# pack=$(helm package ./charts/$i | sed 's/Success.*: \(.*\)/\1/')
-          chart=$(basename $pack)
+# if [ ! -z $pack ]; then
-          curl --request POST \
+# chart=$(basename $pack)
-               --user gitlab-ci-token:$CI_JOB_TOKEN \
+# curl --request POST \
-               --form "chart=@${chart}" \
+# --user gitlab-ci-token:$CI_JOB_TOKEN \
-               "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/helm/api/stable/charts"
+# --form "chart=@${chart}" \
-        fi
+# "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/helm/api/stable/charts"
-      done
+# fi
+# done
 
+# rebuild:
+# stage: release
+# rules:
+# - when: manual
+# allow_failure: true
+# script:
+# - |
+# cd $CI_PROJECT_DIR
+# for i in $(find ./charts -maxdepth 2 -name Chart.yaml | cut -d/ -f3); do
+# pack=$(helm package ./charts/$i | sed 's/Success.*: \(.*\)/\1/')
+# if [ ! -z $pack ]; then
+# chart=$(basename $pack)
+# curl --request POST \
+# --user gitlab-ci-token:$CI_JOB_TOKEN \
+# --form "chart=@${chart}" \
+# "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/helm/api/stable/charts"
+# fi
+# done

attic/nix/atlantis.nix

@@ -9,20 +9,29 @@ let
     extraValues = { };
   };
 
-  kustomize = r:
+  kustomize =
+    r:
     if r.kind == "Deployment" then
       lib.attrsets.recursiveUpdate r {
-        spec.template.spec.containers =
+        spec.template.spec.containers = builtins.map (
-        builtins.map (x:
+          x:
-        x // {
+          x
+          // {
             livenessProbe.httpGet.path = "/healthz";
             readinessProble.httpGet.path = "/healthz";
-            env = x.env ++ [ { name = "INERNAL_PORT"; value = 8000; } ];
+            env = x.env ++ [
-        }) r.spec.template.spec.containers;
+              {
+                name = "INERNAL_PORT";
+                value = 8000;
+              }
+            ];
+          }
+        ) r.spec.template.spec.containers;
       }
     else if r.kind == "Service" then
       { }
-    else r;
+    else
+      r;
 in
 {
   options.apps.atlantis = lib.apps.appOptions {
@@ -34,9 +43,7 @@ in
 
     hostname = lib.mkOption {
       type = lib.types.str;
-        default = if env == "prod"
+      default = if env == "prod" then "maps.oceanbox.io" else "atlantis.beta.oceanbox.io";
-          then "maps.oceanbox.io"
-          else "atlantis.beta.oceanbox.io";
       description = "Revision";
     };
   };

attic/nix/openfga.nix

@@ -9,10 +9,8 @@ let
     extraValues = { };
   };
 
-  kustomize = r:
+  kustomize =
-    if r.kind == "Job" then
+    r: if r.kind == "Job" then lib.attrsets.recursiveUpdate r { spec.backoffLimit = 2; } else r;
-      lib.attrsets.recursiveUpdate r { spec.backoffLimit = 2; }
-    else r;
 
 in
 {

attic/values/dex/templates/.vscode/launch.json

@@ -1,7 +1,4 @@
 {
-    // Use IntelliSense to learn about possible attributes.
-    // Hover to view descriptions of existing attributes.
-    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
     "version": "0.2.0",
     "configurations": [
         {

attic/values/dex/templates/deploy.sh

@@ -2,16 +2,16 @@
 
 server="root@fs1-0"
 path="/vol/brick0/nfs0/k1/pv-oceanbox-dex"
-dest="$server:$path"
+dest="${server}:${path}"
 
 index=$(basename dist/assets/index-*.js)
 
-ssh $server -- rm $path/static/js/*.js
+ssh "${server}" -- rm "${path}"/static/js/*.js
-scp dist/assets/*.js $dest/static/js/
+scp dist/assets/*.js "${dest}"/static/js/
 
-sed -r "s/@index@/$index/" ./dex/templates/login.html > login.html.$$
+sed -r "s/@index@/${index}/" ./dex/templates/login.html > login.html.$$
-scp ./dex/templates/* $dest/templates/
+scp ./dex/templates/* "${dest}"/templates/
-scp ./dex/static/*.* $dest/static/
+scp ./dex/static/*.* "${dest}"/static/
-scp login.html.$$ $dest/templates/login.html
+scp login.html.$$ "${dest}"/templates/login.html
 rm login.html.$$
 ssh admin@k1-0.itpartner.intern -- kubectl rollout restart -n oceanbox deployment/dex

bin/generate.sh

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# shellcheck disable=SC2034  # Unused variables left for readability
 
 helmfile () {
 
@@ -10,30 +11,30 @@ bases:
  - ../envs/environments.yaml.gotmpl
 
 commonLabels:
-  tier: $tier
+  tier: ${tier}
 
 releases:
-- name: $name
+- name: ${name}
-  namespace: {{ .Environment.Name }}-$name
+  namespace: {{ .Environment.Name }}-${name}
-  chart: ../charts/$name
+  chart: ../charts/${name}
-  condition: $name.enabled
+  condition: ${name}.enabled
   values:
-  - ../values/$name/values/values.yaml.gotmpl
+  - ../values/${name}/values/values.yaml.gotmpl
-  - ../values/$name/values/values-{{ .Environment.Name }}.yaml
+  - ../values/${name}/values/values-{{ .Environment.Name }}.yaml
   postRenderer: ../bin/kustomizer
   postRendererArgs:
-  - ../values/$name/kustomize/{{ .Environment.Name }}
+  - ../values/${name}/kustomize/{{ .Environment.Name }}
   missingFileHandler: Info
 - name: manifests
-  namespace: {{ .Environment.Name }}-$name
+  namespace: {{ .Environment.Name }}-${name}
   chart: manifests
-  condition: $name.enabled
+  condition: ${name}.enabled
   missingFileHandler: Info
   values:
   - ../values/env.yaml
   - ../values/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
-  - ../values/$name/env.yaml.gotmpl
+  - ../values/${name}/env.yaml.gotmpl
-  - ../values/$name/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
+  - ../values/${name}/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
   hooks:
   - events: [ prepare, cleanup ]
     showlogs: true
@@ -42,7 +43,7 @@ releases:
     - '{{\`{{ if eq .Event.Name "prepare" }}build{{ else }}clean{{ end }}\`}}'
     - '{{\`{{ .Release.Chart }}\`}}'
     - '{{\`{{ .Environment.Name }}\`}}'
-    - ../values/$name/manifests
+    - ../values/${name}/manifests
     - manifests
 EOF
 }
@@ -59,10 +60,10 @@ done
 
 name=$1
 tier=$2
-if [ -n "$ns" ]; then
+if [[ -n "${ns}" ]]; then
-    namespace="namespace: {{ .Environment.Name }}-$name"
+    namespace="namespace: {{ .Environment.Name }}-${name}"
 else
-    namespace="namespace: $name"
+    namespace="namespace: ${name}"
 fi
 
-helmfile $1 $2
+helmfile "$1" "$2"

bin/helmify

@@ -4,39 +4,38 @@ set -o pipefail
 
 cmd=$1
 chart=$2
-env=$3
 manifests=${4:-manifests}
 outdir=${5:-_manifests}
 
 build() {
-  mkdir -p $outdir/templates
+  mkdir -p "${outdir}"/templates
-  echo "Creating $outdir/templates"
+  echo "Creating ${outdir}/templates"
 
-  echo "generating $outdir/Chart.yaml" 1>&2
+  echo "generating ${outdir}/Chart.yaml" 1>&2
 
-  cat <<EOF > $outdir/Chart.yaml
+  cat <<EOF > "${outdir}"/Chart.yaml
 apiVersion: v1
 appVersion: "1.0"
 # description: A Helm chart for Kubernetes
-name: $chart
+name: ${chart}
 version: 0.1.0
 EOF
 
-if [ -d $manifests ]; then
+if [[ -d "${manifests}" ]]; then
-    cp -r $manifests/* $outdir/templates
+    cp -r "${manifests}"/* "${outdir}"/templates
-elif [ -f $manifests ]; then
+elif [[ -f "${manifests}" ]]; then
-    cp $manifests $outdir/templates
+    cp "${manifests}" "${outdir}"/templates
 fi
 }
 
 clean() {
-  echo "cleaning $outdir" 1>&2
+  echo "cleaning ${outdir}" 1>&2
-  rm -rf $outdir
+  rm -rf "${outdir}"
 }
 
-case "$cmd" in
+case "${cmd}" in
   "build" ) build ;;
   "clean" ) clean ;;
-  * ) echo "unsupported command: $cmd" 1>&2; exit 1 ;;
+  * ) echo "unsupported command: ${cmd}" 1>&2; exit 1 ;;
 esac
 

bin/kustomizer

@@ -1,13 +1,13 @@
 #!/usr/bin/env bash
 
-[ $# != 1 ] && exit 1
+[[ $# != 1 ]] && exit 1
 
 dir=$1
-base=$dir/../base
+base=${dir}/../base
 
-if [ -f $base/kustomization.yaml -a -f $dir/kustomization.yaml ]; then
+if [[ -f "${base}"/kustomization.yaml ]] && [[ -f "${dir}"/kustomization.yaml ]]; then
-    cat > $base/_manifest.yaml
+    cat > "${base}"/_manifest.yaml
-    kubectl kustomize $dir
+    kubectl kustomize "${dir}"
 else
     cat
 fi

bootstrap/argocd-cluster-admin.yaml

@@ -4,15 +4,15 @@ metadata:
   name: argocd-cluster-admin
 rules:
   - apiGroups:
-  - '*'
+      - "*"
     resources:
-  - '*'
+      - "*"
     verbs:
-  - '*'
+      - "*"
   - nonResourceURLs:
-  - '*'
+      - "*"
     verbs:
-  - '*'
+      - "*"
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding

bootstrap/cluster-admin-token.yaml

@@ -6,5 +6,3 @@ metadata:
   name: cluster-admin-token
   namespace: kube-system
 type: kubernetes.io/service-account-token
-
-

bootstrap/cluster-ekman.yaml

@@ -10,5 +10,3 @@ metadata:
   name: cluster-ekman
   namespace: argocd
 type: Opaque
-
-

bootstrap/helm-kustomize-cmp/deploy.sh

@@ -3,5 +3,5 @@
 img=registry.gitlab.com/oceanbox/manifests/helm-kustomize-cmp
 tag=${1:-latest}
 
-docker build -t $img:$tag .
+docker build -t "${img}":"${tag}" .
-docker push $img:$tag
+docker push "${img}":"${tag}"

bootstrap/helm-kustomize-cmp/generate.sh

@@ -1,14 +1,15 @@
 #!/bin/sh
+# shellcheck disable=SC2154
 
 export HOME=/plugin
 
-env > /tmp/$ARGOCD_APP_NAME.env
+env > /tmp/"${ARGOCD_APP_NAME}".env
 
-echo "$ARGOCD_APP_PARAMETERS" | jq '.[] | select(.name == "helm-parameters") | .map' | yq -P -oy > parameters.yaml
+echo "${ARGOCD_APP_PARAMETERS}" | jq '.[] | select(.name == "helm-parameters") | .map' | yq -P -oy > parameters.yaml
-cp parameters.yaml /tmp/$ARGOCD_APP_NAME-parameters.yaml
+cp parameters.yaml /tmp/"${ARGOCD_APP_NAME}"-parameters.yaml
 
-if [ -n "$PARAM_CHART" -a "$PARAM_CHART" != "." ]; then
+if [ -n "${PARAM_CHART}" ] && [ "${PARAM_CHART}" != "." ]; then
-    CHART=$PARAM_CHART
+    CHART=${PARAM_CHART}
 elif [ -d chart ]; then
     CHART=chart
 elif [ -f chart ]; then
@@ -18,19 +19,19 @@ else
 fi
 
 [ -f chart/values.yaml ] && VALUES="-f chart/values.yaml"
-[ -f values-chart.yaml ] && VALUES="$VALUES -f values-chart.yaml"
+[ -f values-chart.yaml ] && VALUES="${VALUES} -f values-chart.yaml"
-[ -f values.yaml ] && VALUES="$VALUES -f values.yaml"
+[ -f values.yaml ] && VALUES="${VALUES} -f values.yaml"
-[ -f values-$PARAM_ENV.yaml ] && VALUES="$VALUES -f values-$PARAM_ENV.yaml"
+[ -f values-"${PARAM_ENV}".yaml ] && VALUES="${VALUES} -f values-${PARAM_ENV}.yaml"
-VALUES="$VALUES -f parameters.yaml"
+VALUES="${VALUES} -f parameters.yaml"
 
-helm dependency update $CHART >/tmp/$ARGOCD_APP_NAME-helm-dependency-build.out
+helm dependency update "${CHART}" >/tmp/"${ARGOCD_APP_NAME}"-helm-dependency-build.out
 
 mkdir -p base
-echo "helm template -n $ARGOCD_APP_NAMESPACE $PARAM_FLAGS $VALUES $ARGOCD_APP_NAME $CHART" > /tmp/$ARGOCD_APP_NAME-helm.sh
+echo "helm template -n ${ARGOCD_APP_NAMESPACE} ${PARAM_FLAGS} ${VALUES} ${ARGOCD_APP_NAME} ${CHART}" > /tmp/"${ARGOCD_APP_NAME}"-helm.sh
-helm template -n $ARGOCD_APP_NAMESPACE $PARAM_FLAGS $VALUES $ARGOCD_APP_NAME $CHART > ./base/_manifest.yaml
+helm template -n "${ARGOCD_APP_NAMESPACE}" "${PARAM_FLAGS}" "${VALUES}" "${ARGOCD_APP_NAME}" "${CHART}" > ./base/_manifest.yaml
 
-cp ./base/_manifest.yaml /tmp/$ARGOCD_APP_NAME-manifest.yaml
+cp ./base/_manifest.yaml /tmp/"${ARGOCD_APP_NAME}"-manifest.yaml
 
-[ -d "$PARAM_ENV" ] && kubectl kustomize $PARAM_ENV > /tmp/$ARGOCD_APP_NAME-manifest.yaml
+[ -d "${PARAM_ENV}" ] && kubectl kustomize "${PARAM_ENV}" > /tmp/"${ARGOCD_APP_NAME}"-manifest.yaml
 
-cat /tmp/$ARGOCD_APP_NAME-manifest.yaml
+cat /tmp/"${ARGOCD_APP_NAME}"-manifest.yaml

bootstrap/helm-kustomize-cmp/get-values.sh

@@ -18,7 +18,7 @@ EOF
     exit 0
 fi
 
-yq e -o=p $VALUES | jq --slurp --raw-input '
+yq e -o=p "${VALUES}" | jq --slurp --raw-input '
   [{
     name: "helm-parameters",
     title: "Helm Parameters",

bootstrap/helm-kustomize-cmp/init-helm-repos.sh

@@ -1,8 +1,9 @@
 #!/bin/sh
+# shellcheck disable=SC2154
 
 export HOME=/plugin
 
-helm repo add --username argocd-helm --password "$OCEANBOX_HELM_ACCESS_TOKEN" oceanbox \
+helm repo add --username argocd-helm --password "${OCEANBOX_HELM_ACCESS_TOKEN}" oceanbox \
     https://gitlab.com/api/v4/projects/54396343/packages/helm/stable
 
 helm repo add bitnami https://charts.bitnami.com/bitnami

bootstrap/helm-kustomize-cmp/init.sh

@@ -4,9 +4,9 @@ export HOME=/plugin
 
 helm repo update oceanbox
 
-if [ -n "$PARAM_CHART" -a "$PARAM_CHART" != "." ]; then
+if [ -n "${PARAM_CHART}" ] && [ "${PARAM_CHART}" != "." ]; then
-    helm show values $PARAM_CHART > values-chart.yaml
+    helm show values "${PARAM_CHART}" > values-chart.yaml
 elif [ -f chart ]; then
     CHART=$(cat chart)
-    helm show values $CHART > values-chart.yaml
+    helm show values "${CHART}" > values-chart.yaml
 fi

bootstrap/helm-kustomize-cmp/plugin.yaml

@@ -66,7 +66,7 @@ spec:
         itemType: string
         collectionType: string
         string: ""
-      # All the fields above besides "string" apply to both the array and map type parameter announcements.
+        # All the fields above besides 'string' apply to both the array and map type parameter announcements.
         # - name: array-param
         #   # This field communicates the parameter's default value to the UI. Setting this field is optional.
         #   array: [default, items]
@@ -84,4 +84,3 @@ spec:
     # If set to `true` then the plugin receives repository files with original file mode. Dangerous since the repository
     # might have executable files. Set to true only if you trust the CMP plugin authors.
     preserveFileMode: false
-

bootstrap/helmfile-cmp/Dockerfile

@@ -1,4 +1,4 @@
-FROM ghcr.io/helmfile/helmfile:v1.0.0
+FROM ghcr.io/helmfile/helmfile:v1.1.9
 
 RUN mkdir -p /home/argocd/cmp-server/config/
 COPY plugin.yaml /home/argocd/cmp-server/config/

bootstrap/helmfile-cmp/deploy.sh

@@ -3,5 +3,5 @@
 img=registry.gitlab.com/oceanbox/manifests/helmfile-cmp
 tag=${1:-latest}
 
-docker build -t $img:$tag .
+docker build -t "${img}":"${tag}" .
-docker push $img:$tag
+docker push "${img}":"${tag}"

bootstrap/helmfile-cmp/generate.sh

@@ -1,4 +1,5 @@
 #!/bin/sh
+# shellcheck disable=SC2154
 
 # NOTE: Ensure errors are part of exitcode
 # set -o pipefail
@@ -10,7 +11,7 @@ export HELM_CONFIG_HOME=/tmp/helm/config
 export HELMFILE_CACHE_HOME=/tmp/helmfile/cache
 export HELMFILE_TEMPDIR=/tmp/helmfile/tmp
 
-test -n ARGOCD_ENV_HELMFILE_ENVIRONMENT && export HELMFILE_ENVIRONMENT=$ARGOCD_ENV_HELMFILE_ENVIRONMENT
+test -n ARGOCD_ENV_HELMFILE_ENVIRONMENT && export HELMFILE_ENVIRONMENT="${ARGOCD_ENV_HELMFILE_ENVIRONMENT}"
-test -n ARGOCD_ENV_HELMFILE_FILE_PATH && export HELMFILE_FILE_PATH=$ARGOCD_ENV_HELMFILE_FILE_PATH
+test -n ARGOCD_ENV_HELMFILE_FILE_PATH && export HELMFILE_FILE_PATH="${ARGOCD_ENV_HELMFILE_FILE_PATH}"
 
-helmfile -n "$ARGOCD_APP_NAMESPACE" $ARGS template --include-crds -q
+helmfile -n "${ARGOCD_APP_NAMESPACE}" "${ARGS}" template -q --include-crds

bootstrap/kustomize-helm-with-rewrite/argo-repo-server.yaml

@@ -422,4 +422,3 @@ spec:
                 path: ca.crt
             optional: true
             secretName: argocd-repo-server-tls
-

bootstrap/reset-ekman-cluster.sh

@@ -13,7 +13,7 @@ kubectl --context ekman apply -f cluster-admin-token.yaml
 # kubectl --context oceanbox apply -f _cluster-ekman.yaml
 
 token=$(kubectl --context ekman get secret -n kube-system argocd-manager-token -o yaml | grep ' token:' | cut -d' ' -f4 | base64 -d)
-sed "s/@token@/$token/" cluster-ekman.yaml > _cluster-ekman.yaml
+sed "s/@token@/${token}/" cluster-ekman.yaml > _cluster-ekman.yaml
 echo "configure argocd ekman-cluster..."
 cat _cluster-ekman.yaml
 kubectl --context oceanbox apply -f _cluster-ekman.yaml

bootstrap/staging-vcluster.yaml

@@ -13,4 +13,3 @@ stringData:
   name: staging-vcluster
   server: https://staging-vcluster.staging-vcluster
 type: Opaque
-

bootstrap/values.yaml

@@ -32,12 +32,12 @@ projects:
     additionalAnnotations: {}
     description: sys components project
     sourceRepos:
-    - '*'
+      - "*"
     destinations:
-    - namespace: '*'
+      - namespace: "*"
         server: https://kubernetes.default.svc
     clusterResourceWhitelist:
-    - group: '*'
+      - group: "*"
-      kind: '*'
+        kind: "*"
     orphanedResources:
       warn: false

charts/atlantis/Chart.yaml

@@ -8,3 +8,8 @@ version: v1.35.2
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: v1.35.2
+dependencies:
+  - name: diagrid-dashboard
+    version: "0.1.0"
+    repository: "file://../diagrid-dashboard"
+    condition: diagrid-dashboard.enabled

charts/atlantis/values.yaml

@@ -116,3 +116,6 @@ serviceMonitor:
 nodeSelector: {}
 tolerations: []
 affinity: {}
+
+diagrid-dashboard:
+  enabled: false

charts/diagrid-dashboard/.helmignore

@@ -0,0 +1,23 @@
+# 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/diagrid-dashboard/Chart.yaml

@@ -0,0 +1,24 @@
+apiVersion: v2
+name: diagrid-dashboard
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.16.0"

charts/diagrid-dashboard/templates/NOTES.txt

@@ -0,0 +1,35 @@
+1. Get the application URL by running these commands:
+{{- if .Values.httpRoute.enabled }}
+{{- if .Values.httpRoute.hostnames }}
+    export APP_HOSTNAME={{ .Values.httpRoute.hostnames | first }}
+{{- else }}
+    export APP_HOSTNAME=$(kubectl get --namespace {{(first .Values.httpRoute.parentRefs).namespace | default .Release.Namespace }} gateway/{{ (first .Values.httpRoute.parentRefs).name }} -o jsonpath="{.spec.listeners[0].hostname}")
+  {{- end }}
+{{- if and .Values.httpRoute.rules (first .Values.httpRoute.rules).matches (first (first .Values.httpRoute.rules).matches).path.value }}
+    echo "Visit http://$APP_HOSTNAME{{ (first (first .Values.httpRoute.rules).matches).path.value }} to use your application"
+
+    NOTE: Your HTTPRoute depends on the listener configuration of your gateway and your HTTPRoute rules.
+    The rules can be set for path, method, header and query parameters.
+    You can check the gateway configuration with 'kubectl get --namespace {{(first .Values.httpRoute.parentRefs).namespace | default .Release.Namespace }} gateway/{{ (first .Values.httpRoute.parentRefs).name }} -o yaml'
+{{- end }}
+{{- else if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "diagrid-dashboard.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "diagrid-dashboard.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "diagrid-dashboard.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "diagrid-dashboard.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}

charts/diagrid-dashboard/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "diagrid-dashboard.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "diagrid-dashboard.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "diagrid-dashboard.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "diagrid-dashboard.labels" -}}
+helm.sh/chart: {{ include "diagrid-dashboard.chart" . }}
+{{ include "diagrid-dashboard.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "diagrid-dashboard.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "diagrid-dashboard.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "diagrid-dashboard.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "diagrid-dashboard.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

charts/diagrid-dashboard/templates/deployment.yaml

@@ -0,0 +1,87 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "diagrid-dashboard.fullname" . }}
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "diagrid-dashboard.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "diagrid-dashboard.labels" . | nindent 8 }}
+        {{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "diagrid-dashboard.serviceAccountName" . }}
+      {{- with .Values.podSecurityContext }}
+      securityContext:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      containers:
+        - name: {{ .Chart.Name }}
+          {{- with .Values.securityContext }}
+          securityContext:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          env:
+            - name: COMPONENT_FILE
+              value: /app/components/statestore.yaml
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          {{- with .Values.livenessProbe }}
+          livenessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.readinessProbe }}
+          readinessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.resources }}
+          resources:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          volumeMounts:
+            - name: statestore
+              mountPath: /app/components/statestore.yaml
+              subPath: statestore.yaml
+          {{- with .Values.volumeMounts }}
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+      volumes:
+        - name: statestore
+          configMap:
+            name: {{ include "diagrid-dashboard.fullname" . }}-statestore
+      {{- with .Values.volumes }}
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}

charts/diagrid-dashboard/templates/hpa.yaml

@@ -0,0 +1,32 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "diagrid-dashboard.fullname" . }}
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "diagrid-dashboard.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+{{- end }}

charts/diagrid-dashboard/templates/httproute.yaml

@@ -0,0 +1,38 @@
+{{- if .Values.httpRoute.enabled -}}
+{{- $fullName := include "diagrid-dashboard.fullname" . -}}
+{{- $svcPort := .Values.service.port -}}
+apiVersion: gateway.networking.k8s.io/v1
+kind: HTTPRoute
+metadata:
+  name: {{ $fullName }}
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+  {{- with .Values.httpRoute.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  parentRefs:
+    {{- with .Values.httpRoute.parentRefs }}
+      {{- toYaml . | nindent 4 }}
+    {{- end }}
+  {{- with .Values.httpRoute.hostnames }}
+  hostnames:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+  rules:
+    {{- range .Values.httpRoute.rules }}
+    {{- with .matches }}
+    - matches:
+      {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .filters }}
+      filters:
+      {{- toYaml . | nindent 8 }}
+    {{- end }}
+      backendRefs:
+        - name: {{ $fullName }}
+          port: {{ $svcPort }}
+          weight: 1
+    {{- end }}
+{{- end }}

charts/diagrid-dashboard/templates/ingress.yaml

@@ -0,0 +1,43 @@
+{{- if .Values.ingress.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "diagrid-dashboard.fullname" . }}
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- with .Values.ingress.className }}
+  ingressClassName: {{ . }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- with .pathType }}
+            pathType: {{ . }}
+            {{- end }}
+            backend:
+              service:
+                name: {{ include "diagrid-dashboard.fullname" $ }}
+                port:
+                  number: {{ $.Values.service.port }}
+          {{- end }}
+    {{- end }}
+{{- end }}

charts/diagrid-dashboard/templates/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "diagrid-dashboard.fullname" . }}
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    {{- include "diagrid-dashboard.selectorLabels" . | nindent 4 }}

charts/diagrid-dashboard/templates/serviceaccount.yaml

@@ -0,0 +1,13 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "diagrid-dashboard.serviceAccountName" . }}
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
+{{- end }}

charts/diagrid-dashboard/templates/statestore.yaml

@@ -0,0 +1,26 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "diagrid-dashboard.fullname" . }}-statestore
+data:
+  statestore.yaml: |
+    apiVersion: dapr.io/v1alpha1
+    kind: Component
+    metadata:
+      name: statestore
+    scopes:
+      - {{ .Values.statestore.scope }}
+    spec:
+      metadata:
+        - name: redisHost
+          value: {{ .Values.statestore.redis }}:6379
+        - name: redisUsername
+          value: default
+        - name: redisPassword
+          value: secret
+        - name: actorStateStore
+          value: "true"
+        - name: redisDB
+          value: "1"
+      type: state.redis
+      version: v1

charts/diagrid-dashboard/templates/tests/test-connection.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "diagrid-dashboard.fullname" . }}-test-connection"
+  labels:
+    {{- include "diagrid-dashboard.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args: ['{{ include "diagrid-dashboard.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never

charts/diagrid-dashboard/values.yaml

@@ -0,0 +1,160 @@
+# Default values for diagrid-dashboard.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+statestore:
+  scope: my-scope
+  redis: my-redis
+
+# This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
+replicaCount: 1
+
+# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
+image:
+  repository: ghcr.io/diagridio/diagrid-dashboard
+  # This sets the pull policy for images.
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: "latest"
+
+# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
+imagePullSecrets: []
+# This is to override the chart name.
+nameOverride: ""
+fullnameOverride: ""
+
+# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Automatically mount a ServiceAccount's API credentials?
+  automount: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+
+# This is for setting Kubernetes Annotations to a Pod.
+# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
+podAnnotations: {}
+# This is for setting Kubernetes Labels to a Pod.
+# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
+podLabels: {}
+
+podSecurityContext: {}
+  # fsGroup: 2000
+
+securityContext: {}
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  # runAsNonRoot: true
+  # runAsUser: 1000
+
+# This is for setting up a service more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/
+service:
+  # This sets the service type more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
+  type: ClusterIP
+  # This sets the ports more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports
+  port: 8080
+
+# This block is for setting up the ingress for more information can be found here: https://kubernetes.io/docs/concepts/services-networking/ingress/
+ingress:
+  enabled: true
+  className: "nginx"
+  annotations:
+    cert-manager.io/cluster-issuer: ca-issuer
+    nginx.ingress.kubernetes.io/backend-protocol: HTTP
+    nginx.ingress.kubernetes.io/ssl-redirect: "true"
+    oceanbox.io/expose: internal
+  hosts:
+    - host: diadash.dev.vtn.obx
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls:
+    - secretName: diadash-tls
+      hosts:
+        - diadash.dev.vtn.obx
+
+# -- Expose the service via gateway-api HTTPRoute
+# Requires Gateway API resources and suitable controller installed within the cluster
+# (see: https://gateway-api.sigs.k8s.io/guides/)
+httpRoute:
+  # HTTPRoute enabled.
+  enabled: false
+  # HTTPRoute annotations.
+  annotations: {}
+  # Which Gateways this Route is attached to.
+  parentRefs:
+    - name: gateway
+      sectionName: http
+      # namespace: default
+  # Hostnames matching HTTP header.
+  hostnames:
+    - chart-example.local
+  # List of rules and filters applied.
+  rules:
+    - matches:
+        - path:
+            type: PathPrefix
+            value: /headers
+  #   filters:
+  #   - type: RequestHeaderModifier
+  #     requestHeaderModifier:
+  #       set:
+  #       - name: My-Overwrite-Header
+  #         value: this-is-the-only-value
+  #       remove:
+  #       - User-Agent
+  # - matches:
+  #   - path:
+  #       type: PathPrefix
+  #       value: /echo
+  #     headers:
+  #     - name: version
+  #       value: v2
+
+resources: {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 100m
+  #   memory: 128Mi
+
+# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
+livenessProbe:
+  httpGet:
+    path: /
+    port: http
+readinessProbe:
+  httpGet:
+    path: /
+    port: http
+
+# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 100
+  targetCPUUtilizationPercentage: 80
+  # targetMemoryUtilizationPercentage: 80
+
+# Additional volumes on the output Deployment definition.
+volumes: {}
+
+# Additional volumeMounts on the output Deployment definition.
+volumeMounts: {}
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}

charts/fornix/.helmignore

@@ -0,0 +1,23 @@
+# 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/fornix/Chart.yaml

@@ -0,0 +1,21 @@
+apiVersion: v2
+name: fornix
+description: A Helm chart for Kubernetes
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: v1.6.0
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "v1.6.0"

charts/fornix/templates/NOTES.txt

@@ -0,0 +1,22 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "fornix.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "fornix.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "fornix.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "fornix.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}

charts/fornix/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "fornix.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "fornix.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "fornix.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "fornix.labels" -}}
+helm.sh/chart: {{ include "fornix.chart" . }}
+{{ include "fornix.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "fornix.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "fornix.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "fornix.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "fornix.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

charts/fornix/templates/deployment.yaml

@@ -0,0 +1,83 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "fornix.fullname" . }}
+  labels:
+    {{- include "fornix.labels" . | nindent 4 }}
+spec:
+  {{- if not .Values.autoscaling.enabled }}
+  replicas: {{ .Values.replicaCount }}
+  {{- end }}
+  selector:
+    matchLabels:
+      {{- include "fornix.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "fornix.labels" . | nindent 8 }}
+        {{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "fornix.serviceAccountName" . }}
+      {{- with .Values.podSecurityContext }}
+      securityContext:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      containers:
+        - name: {{ .Chart.Name }}
+          {{- with .Values.securityContext }}
+          securityContext:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          env:
+          - name: DRUPAL_URL
+            value: {{ .Values.drupalUrl }}
+          - name: BASE_URL
+            value: {{ .Values.baseUrl }}
+          {{- with .Values.livenessProbe }}
+          livenessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.readinessProbe }}
+          readinessProbe:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.resources }}
+          resources:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+          {{- with .Values.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
+      {{- with .Values.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}

charts/fornix/templates/ingress.yaml

@@ -0,0 +1,43 @@
+{{- if .Values.ingress.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "fornix.fullname" . }}
+  labels:
+    {{- include "fornix.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- with .Values.ingress.className }}
+  ingressClassName: {{ . }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- with .pathType }}
+            pathType: {{ . }}
+            {{- end }}
+            backend:
+              service:
+                name: {{ include "fornix.fullname" $ }}
+                port:
+                  number: {{ $.Values.service.port }}
+          {{- end }}
+    {{- end }}
+{{- end }}

charts/fornix/templates/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "fornix.fullname" . }}
+  labels:
+    {{- include "fornix.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    {{- include "fornix.selectorLabels" . | nindent 4 }}

charts/fornix/templates/serviceaccount.yaml

@@ -0,0 +1,13 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "fornix.serviceAccountName" . }}
+  labels:
+    {{- include "fornix.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
+{{- end }}

charts/fornix/templates/tests/test-connection.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: "{{ include "fornix.fullname" . }}-test-connection"
+  labels:
+    {{- include "fornix.labels" . | nindent 4 }}
+  annotations:
+    "helm.sh/hook": test
+spec:
+  containers:
+    - name: wget
+      image: busybox
+      command: ['wget']
+      args: ['{{ include "fornix.fullname" . }}:{{ .Values.service.port }}']
+  restartPolicy: Never

charts/fornix/values.yaml

@@ -0,0 +1,100 @@
+# Default values for fornix.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+drupalUrl: http://drupal
+baseUrl: https://oceanbox.io
+# This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
+replicaCount: 1
+# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
+image:
+  repository: registry.gitlab.com/oceanbox/fornix
+  # This sets the pull policy for images.
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: v1.6.0
+# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
+imagePullSecrets:
+  - name: gitlab-pull-secret
+# This is to override the chart name.
+nameOverride: ""
+fullnameOverride: ""
+# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Automatically mount a ServiceAccount's API credentials?
+  automount: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+# This is for setting Kubernetes Annotations to a Pod.
+# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
+podAnnotations: {}
+# This is for setting Kubernetes Labels to a Pod.
+# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
+podLabels: {}
+podSecurityContext:
+  fsGroup: 2000
+securityContext:
+  capabilities:
+    drop:
+      - ALL
+  readOnlyRootFilesystem: false
+  runAsNonRoot: true
+  runAsUser: 1000
+# This is for setting up a service more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/
+service:
+  # This sets the service type more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
+  type: ClusterIP
+  # This sets the ports more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports
+  port: 8085
+# This block is for setting up the ingress for more information can be found here: https://kubernetes.io/docs/concepts/services-networking/ingress/
+ingress:
+  enabled: false
+resources: {}
+# We usually recommend not to specify default resources and to leave this as a conscious
+# choice for the user. This also increases chances charts run on environments with little
+# resources, such as Minikube. If you do want to specify resources, uncomment the following
+# lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+# limits:
+#   cpu: 100m
+#   memory: 128Mi
+# requests:
+#   cpu: 100m
+#   memory: 128Mi
+
+# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
+livenessProbe:
+  httpGet:
+    path: /
+    port: http
+readinessProbe:
+  httpGet:
+    path: /
+    port: http
+# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 100
+  targetCPUUtilizationPercentage: 80
+  # targetMemoryUtilizationPercentage: 80
+# Additional volumes on the output Deployment definition.
+volumes: []
+# - name: foo
+#   secret:
+#     secretName: mysecret
+#     optional: false
+
+# Additional volumeMounts on the output Deployment definition.
+volumeMounts: []
+# - name: foo
+#   mountPath: "/etc/foo"
+#   readOnly: true
+
+nodeSelector: {}
+tolerations: []
+affinity: {}

charts/makai/values.yaml

@@ -3,7 +3,7 @@
 # Declare variables to be passed into your templates.
 replicaCount: 1
 image:
-  repository: registry.gitlab.com/oceanbox/makai/makai
+  repository: registry.gitlab.com/oceanbox/makai
   tag: v0.1.0
   pullPolicy: IfNotPresent
 init:

charts/plume/templates/redis.yaml

@@ -45,6 +45,7 @@ spec:
     persistentVolumeClaimSpec:
       accessModes:
       - ReadWriteOnce
+      storageClass: {{ .Values.redis.storageClass | default "managed-nfs-storage" }}
       resources:
         requests:
           storage: {{ .Values.redis.size | default "1Gi" }}

charts/plume/values.yaml

@@ -3,7 +3,7 @@
 # Declare variables to be passed into your templates.
 replicaCount: 1
 image:
-  repository: registry.gitlab.com/oceanbox/plume/plume
+  repository: registry.gitlab.com/oceanbox/plume
   tag: v1.6.7
   pullPolicy: IfNotPresent
 init:

charts/sorcerer/Chart.lock

@@ -0,0 +1,6 @@
+dependencies:
+- name: diagrid-dashboard
+  repository: file://../diagrid-dashboard
+  version: 0.1.0
+digest: sha256:4fdb3148a2a6439223d7844a3083da2de324dd47e5cb3ac4a5d9c436e6e2c775
+generated: "2025-12-16T19:38:21.939708629+01:00"

charts/sorcerer/Chart.yaml

@@ -8,3 +8,8 @@ version: v1.35.2
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
 appVersion: v1.35.2
+dependencies:
+  - name: diagrid-dashboard
+    version: "0.1.0"
+    repository: "file://../diagrid-dashboard"
+    condition: diagrid-dashboard.enabled

charts/sorcerer/values.yaml

@@ -108,3 +108,9 @@ serviceMonitor:
 nodeSelector: {}
 tolerations: []
 affinity: {}
+
+diagrid-dashboard:
+  enabled: false
+  statestore:
+    scope: sorcerer
+    redis: sorcerer-redis

charts/yolo-registry/values.yaml

@@ -5,7 +5,7 @@
 replicaCount: 1
 image:
   repository: registry
-  tag: 2
+  tag: 3
   pullPolicy: IfNotPresent
 init:
   enabled: false

helmfile.d/argo.yaml.gotmpl

@@ -27,7 +27,7 @@ releases:
 - name: argocd-apps
   namespace: argocd
   chart: argo/argocd-apps
-  version: 0.0.9
+  version: 2.0.3
   condition: argo.apps.enabled
   values:
   - ../values/argo/values/apps.yaml.gotmpl

helmfile.d/cert-manager.yaml.gotmpl

@@ -3,7 +3,8 @@ bases:
 
 repositories:
   - name: cert-manager
-    url: 'https://charts.jetstack.io'
+    oci: true
+    url: 'quay.io/jetstack/charts'
 
 commonLabels:
   tier: system
@@ -12,7 +13,7 @@ releases:
 - name: cert-manager
   namespace: cert-manager
   chart: cert-manager/cert-manager
-  version: 1.12.13
+  version: v1.19.2
   condition: cert_manager.enabled
   values:
   - ../values/cert-manager/values/cert-manager.yaml.gotmpl

helmfile.d/forgejo.yaml.gotmpl

@@ -0,0 +1,44 @@
+bases:
+ - ../envs/environments.yaml.gotmpl
+
+repositories:
+- name: forgejo
+  oci: true
+  url: code.forgejo.org/forgejo-helm
+
+commonLabels:
+  tier: system
+
+releases:
+- name: forgejo
+  namespace: forgejo
+  chart: forgejo/forgejo
+  version: 16.0.0
+  condition: forgejo.enabled
+  values:
+  - ../values/forgejo/values/values.yaml
+  - ../values/forgejo/values/values-{{ .Environment.Name }}.yaml
+  postRenderer: ../bin/kustomizer
+  postRendererArgs:
+  - ../values/forgejo/kustomize/{{ .Environment.Name }}
+  missingFileHandler: Info
+- name: manifests
+  namespace: forgejo
+  chart: manifests
+  condition: forgejo.enabled
+  missingFileHandler: Info
+  values:
+  - ../values/env.yaml
+  - ../values/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
+  - ../values/forgejo/env.yaml.gotmpl
+  - ../values/forgejo/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
+  hooks:
+  - events: [ prepare, cleanup ]
+    showlogs: true
+    command: ../bin/helmify
+    args:
+    - '{{`{{ if eq .Event.Name "prepare" }}build{{ else }}clean{{ end }}`}}'
+    - '{{`{{ .Release.Chart }}`}}'
+    - '{{`{{ .Environment.Name }}`}}'
+    - ../values/forgejo/manifests
+    - manifests

helmfile.d/fornix.yaml.gotmpl

@@ -0,0 +1,37 @@
+bases:
+ - ../envs/environments.yaml.gotmpl
+
+commonLabels:
+  tier: oceanbox
+
+releases:
+- name: fornix
+  namespace: fornix
+  chart: ../charts/fornix
+  condition: fornix.enabled
+  values:
+  - ../values/fornix/values/values.yaml
+  postRenderer: ../bin/kustomizer
+  postRendererArgs:
+  - ../values/fornix/kustomize/{{ .Environment.Name }}
+  missingFileHandler: Info
+- name: manifests
+  namespace: fornix
+  chart: manifests
+  condition: fornix.enabled
+  missingFileHandler: Info
+  values:
+  - ../values/env.yaml
+  - ../values/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
+  - ../values/fornix/env.yaml.gotmpl
+  - ../values/fornix/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
+  hooks:
+  - events: [ prepare, cleanup ]
+    showlogs: true
+    command: ../bin/helmify
+    args:
+    - '{{`{{ if eq .Event.Name "prepare" }}build{{ else }}clean{{ end }}`}}'
+    - '{{`{{ .Release.Chart }}`}}'
+    - '{{`{{ .Environment.Name }}`}}'
+    - ../values/fornix/manifests
+    - manifests

helmfile.d/ingress-nginx.yaml.gotmpl

@@ -12,7 +12,7 @@ releases:
 - name: ingress-nginx
   namespace: ingress-nginx
   chart: ingress-nginx/ingress-nginx
-  version: 4.8.3
+  version: 4.14.1
   condition: nginx.enabled
   values:
   - ../values/ingress-nginx/values/ingress-nginx.yaml.gotmpl

helmfile.d/kueue.yaml.gotmpl

@@ -0,0 +1,40 @@
+bases:
+ - ../envs/environments.yaml.gotmpl
+
+commonLabels:
+  tier: system
+
+releases:
+- name: kueue
+  namespace: kueue-system
+  chart: oci://registry.k8s.io/kueue/charts/kueue
+  version: 0.15.0
+  condition: kueue.enabled
+  values:
+  - ../values/kueue/values/values.yaml
+  - ../values/kueue/values/values-{{ .Environment.Name }}.yaml
+  - ../values/kueue/values/values-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
+  postRenderer: ../bin/kustomizer
+  postRendererArgs:
+  - ../values/kueue/kustomize/{{ .Environment.Name }}
+  missingFileHandler: Info
+- name: manifests
+  namespace: kueue-system
+  chart: manifests
+  condition: kueue.enabled
+  missingFileHandler: Info
+  values:
+  - ../values/env.yaml
+  - ../values/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
+  - ../values/kueue/env.yaml.gotmpl
+  - ../values/kueue/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
+  hooks:
+  - events: [ prepare, cleanup ]
+    showlogs: true
+    command: ../bin/helmify
+    args:
+    - '{{`{{ if eq .Event.Name "prepare" }}build{{ else }}clean{{ end }}`}}'
+    - '{{`{{ .Release.Chart }}`}}'
+    - '{{`{{ .Environment.Name }}`}}'
+    - ../values/kueue/manifests
+    - manifests

helmfile.d/kyverno.yaml.gotmpl

@@ -15,7 +15,7 @@ releases:
 - name: kyverno
   namespace: kyverno
   chart: kyverno/kyverno
-  version: 3.5.1
+  version: 3.6.1
   condition: kyverno.enabled
   values:
   - ../values/kyverno/values/kyverno.yaml.gotmpl

helmfile.d/mariadb-operator.yaml.gotmpl

@@ -12,7 +12,7 @@ releases:
 - name: mariadb-operator
   namespace: mariadb-operator
   chart: mariadb-operator/mariadb-operator
-  version: 25.8.4
+  version: 25.10.3
   condition: mariadb_operator.enabled
   values:
   - ../values/mariadb-operator/values/mariadb-operator.yaml.gotmpl

helmfile.d/openfga.yaml.gotmpl

@@ -16,7 +16,7 @@ releases:
   namespace: {{ .Environment.Name }}-openfga
   {{- end }}
   chart: openfga/openfga
-  version: 0.2.45
+  version: 0.2.50
   condition: openfga.enabled
   values:
   - ../values/openfga/values/values.yaml

helmfile.d/opentelemetry-collector.yaml.gotmpl

@@ -12,7 +12,7 @@ releases:
 - name: opentelemetry-collector
   namespace: otel
   chart: open-telemetry/opentelemetry-collector
-  version: 0.134.1
+  version: 0.142.1
   condition: otel.enabled
   values:
   - ../values/opentelemetry-collector/values/values.yaml

helmfile.d/postgres-operator.yaml.gotmpl

@@ -15,7 +15,7 @@ releases:
 - name: postgres-operator
   namespace: cnpg
   chart: cloudnative-pg/cloudnative-pg
-  version: 0.26.1
+  version: 0.27.0
   condition: postgres_operator.enabled
   values:
   - ../values/postgres-operator/values/postgres-operator.yaml.gotmpl

helmfile.d/rabbitmq.yaml.gotmpl

@@ -13,7 +13,7 @@ releases:
 - name: {{ .Environment.Name }}-rabbitmq
   namespace: rabbitmq
   chart: bitnami/rabbitmq
-  version: 12.9.0
+  version: 13.0.3
   condition: rabbitmq.enabled
   values:
   - ../values/rabbitmq/values/values.yaml

helmfile.d/slurm-operator.yaml.gotmpl

@@ -13,7 +13,7 @@ releases:
 - name: slurm-operator
   namespace: slinky
   chart: slurm-operator/slurm-operator
-  version: 0.4.0
+  version: 0.4.1
   condition: slurm_operator.enabled
   values:
   - ../values/slurm-operator/values/slurm-operator.yaml.gotmpl

helmfile.d/spegel.yaml.gotmpl

@@ -13,7 +13,7 @@ releases:
 - name: spegel
   namespace: spegel
   chart: spegel/spegel
-  version: 0.5.1
+  version: 0.6.0
   condition: spegel.enabled
   values:
   - ../values/spegel/values/spegel.yaml.gotmpl

helmfile.d/velero.yaml.gotmpl

@@ -15,7 +15,7 @@ releases:
 - name: velero
   namespace: velero
   chart: velero/velero
-  version: 11.1.1
+  version: 11.3.2
   condition: velero.enabled
   values:
   - ../values/velero/values/velero.yaml.gotmpl

nix/checks.nix

@@ -0,0 +1,70 @@
+let
+  sources = import ./default.nix;
+  pkgs = import sources.nixpkgs { };
+  pre-commit = import sources.git-hooks;
+
+  globalExcludes = [
+    "nix/default.nix"
+    "attic"
+    "vcluster"
+    ".*vendor"
+    ".*chart/.*"
+    ".*schema.json"
+  ];
+
+in
+pre-commit.run {
+  src = pkgs.nix-gitignore.gitignoreSource [ ] ../.;
+  # Do not run at pre-commit time
+  default_stages = [
+    "pre-push"
+  ];
+  # TODO(mrtz): Remove when default
+  package = pkgs.prek;
+  # Linters From https://github.com/cachix/pre-commit-hooks.nix
+  hooks = {
+    nixfmt-rfc-style = {
+      enable = true;
+      excludes = globalExcludes;
+    };
+
+    trim-trailing-whitespace.enable = true;
+
+    shellcheck = {
+      enable = true;
+      excludes = [
+        "vcluster/"
+        "attic/"
+      ];
+      args = [
+        "-x"
+        "-o"
+        "all"
+      ];
+    };
+
+    yamllint = {
+      enable = true;
+      excludes = [
+        "attic/"
+        "charts/templates/"
+        "charts/"
+        "values/"
+        "vcluster/"
+      ];
+      settings = {
+        strict = true;
+        configData = ''{ extends: default, rules: { document-start: disable, line-length: {max: 300} } }'';
+      };
+    };
+
+    check-json.enable = true;
+
+    renovate-config-validator = {
+      enable = true;
+      files = "renovate.json$";
+      entry = "renovate-config-validator";
+    };
+
+  };
+}

nix/default.nix

@@ -9,8 +9,15 @@
 */
 # Generated by npins. Do not modify; will be overwritten regularly
 let
-  data = builtins.fromJSON (builtins.readFile ./sources.json);
+  # Backwards-compatibly make something that previously didn't take any arguments take some
-  version = data.version;
+  # The function must return an attrset, and will unfortunately be eagerly evaluated
+  # Same thing, but it catches eval errors on the default argument so that one may still call it with other arguments
+  mkFunctor =
+    fn:
+    let
+      e = builtins.tryEval (fn { });
+    in
+    (if e.success then e.value else { error = fn { }; }) // { __functor = _self: fn; };
 
   # https://github.com/NixOS/nixpkgs/blob/0258808f5744ca980b9a1f24fe0b1e6f0fecee9c/lib/lists.nix#L295
   range =
@@ -21,7 +28,6 @@ let
 
   # https://github.com/NixOS/nixpkgs/blob/0258808f5744ca980b9a1f24fe0b1e6f0fecee9c/lib/strings.nix#L269
   stringAsChars = f: s: concatStrings (map f (stringToCharacters s));
-  concatMapStrings = f: list: concatStrings (map f list);
   concatStrings = builtins.concatStringsSep "";
 
   # If the environment variable NPINS_OVERRIDE_${name} is set, then use
@@ -48,41 +54,87 @@ let
 
   mkSource =
     name: spec:
+    {
+      pkgs ? null,
+    }:
     assert spec ? type;
     let
+      # Unify across builtin and pkgs fetchers.
+      # `fetchGit` requires a wrapper because of slight API differences.
+      fetchers =
+        if pkgs == null then
+          {
+            inherit (builtins) fetchTarball fetchurl;
+            # For some fucking reason, fetchGit has a different signature than the other builtin fetchers …
+            fetchGit = args: (builtins.fetchGit args).outPath;
+          }
+        else
+          {
+            fetchTarball =
+              {
+                url,
+                sha256,
+              }:
+              pkgs.fetchzip {
+                inherit url sha256;
+                extension = "tar";
+              };
+            inherit (pkgs) fetchurl;
+            fetchGit =
+              {
+                url,
+                submodules,
+                rev,
+                name,
+                narHash,
+              }:
+              pkgs.fetchgit {
+                inherit url rev name;
+                fetchSubmodules = submodules;
+                hash = narHash;
+              };
+          };
+
+      # Dispatch to the correct code path based on the type
       path =
         if spec.type == "Git" then
-          mkGitSource spec
+          mkGitSource fetchers spec
         else if spec.type == "GitRelease" then
-          mkGitSource spec
+          mkGitSource fetchers spec
         else if spec.type == "PyPi" then
-          mkPyPiSource spec
+          mkPyPiSource fetchers spec
         else if spec.type == "Channel" then
-          mkChannelSource spec
+          mkChannelSource fetchers spec
         else if spec.type == "Tarball" then
-          mkTarballSource spec
+          mkTarballSource fetchers spec
+        else if spec.type == "Container" then
+          mkContainerSource pkgs spec
         else
           builtins.throw "Unknown source type ${spec.type}";
     in
     spec // { outPath = mayOverride name path; };
 
   mkGitSource =
+    {
+      fetchTarball,
+      fetchGit,
+      ...
+    }:
     {
       repository,
       revision,
       url ? null,
       submodules,
       hash,
-      branch ? null,
       ...
     }:
     assert repository ? type;
     # At the moment, either it is a plain git repository (which has an url), or it is a GitHub/GitLab repository
     # In the latter case, there we will always be an url to the tarball
     if url != null && !submodules then
-      builtins.fetchTarball {
+      fetchTarball {
         inherit url;
-        sha256 = hash; # FIXME: check nix version & use SRI hashes
+        sha256 = hash;
       }
     else
       let
@@ -93,6 +145,8 @@ let
             "https://github.com/${repository.owner}/${repository.repo}.git"
           else if repository.type == "GitLab" then
             "${repository.server}/${repository.repo_path}.git"
+          else if repository.type == "Forgejo" then
+            "${repository.server}/${repository.owner}/${repository.repo}.git"
           else
             throw "Unrecognized repository type ${repository.type}";
         urlToName =
@@ -107,40 +161,89 @@ let
           "${if matched == null then "source" else builtins.head matched}${appendShort}";
         name = urlToName url revision;
       in
-      builtins.fetchGit {
+      fetchGit {
         rev = revision;
-        inherit name;
+        narHash = hash;
-        # hash = hash;
+
-        inherit url submodules;
+        inherit name submodules url;
       };
 
   mkPyPiSource =
-    { url, hash, ... }:
+    { fetchurl, ... }:
-    builtins.fetchurl {
+    {
+      url,
+      hash,
+      ...
+    }:
+    fetchurl {
       inherit url;
       sha256 = hash;
     };
 
   mkChannelSource =
-    { url, hash, ... }:
+    { fetchTarball, ... }:
-    builtins.fetchTarball {
+    {
+      url,
+      hash,
+      ...
+    }:
+    fetchTarball {
       inherit url;
       sha256 = hash;
     };
 
   mkTarballSource =
+    { fetchTarball, ... }:
     {
       url,
       locked_url ? url,
       hash,
       ...
     }:
-    builtins.fetchTarball {
+    fetchTarball {
       url = locked_url;
       sha256 = hash;
     };
+
+  mkContainerSource =
+    pkgs:
+    {
+      image_name,
+      image_tag,
+      image_digest,
+      ...
+    }:
+    if pkgs == null then
+      builtins.throw "container sources require passing in a Nixpkgs value: https://github.com/andir/npins/blob/master/README.md#using-the-nixpkgs-fetchers"
+    else
+      pkgs.dockerTools.pullImage {
+        imageName = image_name;
+        imageDigest = image_digest;
+        finalImageTag = image_tag;
+      };
 in
-if version == 5 then
+mkFunctor (
-  builtins.mapAttrs mkSource data.pins
+  {
+    input ? ./sources.json,
+  }:
+  let
+    data =
+      if builtins.isPath input then
+        # while `readFile` will throw an error anyways if the path doesn't exist,
+        # we still need to check beforehand because *our* error can be caught but not the one from the builtin
+        # *piegames sighs*
+        if builtins.pathExists input then
+          builtins.fromJSON (builtins.readFile input)
+        else
+          throw "Input path ${toString input} does not exist"
+      else if builtins.isAttrs input then
+        input
+      else
+        throw "Unsupported input type ${builtins.typeOf input}, must be a path or an attrset";
+    version = data.version;
+  in
+  if version == 7 then
+    builtins.mapAttrs (name: spec: mkFunctor (mkSource name spec)) data.pins
   else
     throw "Unsupported format version ${toString version} in sources.json. Try running `npins upgrade`"
+)

nix/sources.json

@@ -1,11 +1,24 @@
 {
   "pins": {
+    "git-hooks": {
+      "type": "Git",
+      "repository": {
+        "type": "GitHub",
+        "owner": "cachix",
+        "repo": "git-hooks.nix"
+      },
+      "branch": "master",
+      "submodules": false,
+      "revision": "f0927703b7b1c8d97511c4116eb9b4ec6645a0fa",
+      "url": "https://github.com/cachix/git-hooks.nix/archive/f0927703b7b1c8d97511c4116eb9b4ec6645a0fa.tar.gz",
+      "hash": "sha256-6MkqajPICgugsuZ92OMoQcgSHnD6sJHwk8AxvMcIgTE="
+    },
     "nixpkgs": {
       "type": "Channel",
       "name": "nixpkgs-unstable",
-      "url": "https://releases.nixos.org/nixpkgs/nixpkgs-26.05pre903996.59b6c96beacc/nixexprs.tar.xz",
+      "url": "https://releases.nixos.org/nixpkgs/nixpkgs-26.05pre927565.13868c071cc7/nixexprs.tar.xz",
-      "hash": "0b0yr9d1xyfwgpaj68bimsbjjbj7yis4whjvkrfdycfnasdf0gf0"
+      "hash": "sha256-wufp5c0nWh/87f9eK7xy1eZXms5zd4yl6S4SR+LfA08="
     }
   },
-  "version": 5
+  "version": 7
 }

raw/tos/oceanbox/database/upload-img.sh

@@ -3,7 +3,7 @@
 # Simple script for uploading a base64 encoded image into our database. For
 # grafana business image panels.
 
-if [ $# -ne 2 ]
+if [[ $# -ne 2 ]]
 then
 	echo "Usage: $0 <image-name> <file>.png"
 	exit 1
@@ -12,9 +12,9 @@ fi
 filename=$1
 file=$2
 
-if [ ! -e $file ]
+if [[ ! -e "${file}" ]]
 then
-	echo "file $file does not exist"
+	echo "file ${file} does not exist"
 	exit 1
 fi
 
@@ -22,9 +22,9 @@ function create_image() {
 	local filename=$1
 	local data=$2
 cat << EOF
-INSERT INTO images VALUES('$filename', '$data');
+INSERT INTO images VALUES('${filename}', '${data}');
 EOF
 }
 
-data=$(cat $file | base64 -w0)
+data=$(base64 -w0 < "${file}")
-create_image $filename $data
+create_image "${filename}" "${data}"

renovate.json

@@ -1,4 +1,3 @@
-// -*- mode: jsonc -*-
 {
   "$schema": "https://docs.renovatebot.com/renovate-schema.json",
   "extends": [

rules/etcd.yaml

@@ -3,7 +3,8 @@ groups:
     rules:
       - alert: etcdMembersDown
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": members are down ({{ $value
+          description:
+            'etcd cluster "{{ $labels.job }}": members are down ({{ $value
             }}).'
           summary: etcd cluster members are down.
         expr: |-
@@ -20,17 +21,20 @@ groups:
           severity: critical
       - alert: etcdInsufficientMembers
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value
+          description:
+            'etcd cluster "{{ $labels.job }}": insufficient members ({{ $value
             }}).'
           summary: etcd cluster has insufficient number of members.
-    expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"})
+        expr:
+          sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"})
           without (instance) + 1) / 2)
         for: 3m
         labels:
           severity: critical
       - alert: etcdNoLeader
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }}
+          description:
+            'etcd cluster "{{ $labels.job }}": member {{ $labels.instance }}
             has no leader.'
           summary: etcd cluster has no leader.
         expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
@@ -39,12 +43,14 @@ groups:
           severity: critical
       - alert: etcdHighNumberOfLeaderChanges
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes
+          description:
+            'etcd cluster "{{ $labels.job }}": {{ $value }} leader changes
             within the last 15 minutes. Frequent elections may be a sign of insufficient
             resources, high network latency, or disruptions by other components and should
             be investigated.'
           summary: etcd cluster has high number of leader changes.
-    expr: increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"})
+        expr:
+          increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"})
           or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m])
           >= 4
         for: 5m
@@ -52,7 +58,8 @@ groups:
           severity: warning
       - alert: etcdHighNumberOfFailedGRPCRequests
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for
+          description:
+            'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for
             {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
           summary: etcd cluster has high number of failed grpc requests.
         expr: |-
@@ -65,7 +72,8 @@ groups:
           severity: warning
       - alert: etcdHighNumberOfFailedGRPCRequests
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for
+          description:
+            'etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for
             {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.'
           summary: etcd cluster has high number of failed grpc requests.
         expr: |-
@@ -78,7 +86,8 @@ groups:
           severity: critical
       - alert: etcdGRPCRequestsSlow
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": 99th percentile of gRPC requests
+          description:
+            'etcd cluster "{{ $labels.job }}": 99th percentile of gRPC requests
             is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method
             }} method.'
           summary: etcd grpc requests are slow
@@ -90,7 +99,8 @@ groups:
           severity: critical
       - alert: etcdMemberCommunicationSlow
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": member communication with {{
+          description:
+            'etcd cluster "{{ $labels.job }}": member communication with {{
             $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance
             }}.'
           summary: etcd cluster member communication is slow.
@@ -102,7 +112,8 @@ groups:
           severity: warning
       - alert: etcdHighNumberOfFailedProposals
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures
+          description:
+            'etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures
             within the last 30 minutes on etcd instance {{ $labels.instance }}.'
           summary: etcd cluster has high number of proposal failures.
         expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
@@ -111,7 +122,8 @@ groups:
           severity: warning
       - alert: etcdHighFsyncDurations
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations
+          description:
+            'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations
             are {{ $value }}s on etcd instance {{ $labels.instance }}.'
           summary: etcd cluster 99th percentile fsync durations are too high.
         expr: |-
@@ -122,7 +134,8 @@ groups:
           severity: warning
       - alert: etcdHighFsyncDurations
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations
+          description:
+            'etcd cluster "{{ $labels.job }}": 99th percentile fsync durations
             are {{ $value }}s on etcd instance {{ $labels.instance }}.'
           summary: etcd cluster 99th percentile fsync durations are too high.
         expr: |-
@@ -133,7 +146,8 @@ groups:
           severity: critical
       - alert: etcdHighCommitDurations
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": 99th percentile commit durations
+          description:
+            'etcd cluster "{{ $labels.job }}": 99th percentile commit durations
             {{ $value }}s on etcd instance {{ $labels.instance }}.'
           summary: etcd cluster 99th percentile commit durations are too high.
         expr: |-
@@ -144,11 +158,13 @@ groups:
           severity: warning
       - alert: etcdDatabaseQuotaLowSpace
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": database size exceeds the defined
+          description:
+            'etcd cluster "{{ $labels.job }}": database size exceeds the defined
             quota on etcd instance {{ $labels.instance }}, please defrag or increase the
             quota as the writes to etcd will be disabled when it is full.'
           summary: etcd cluster database is running full.
-    expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m]) /
+        expr:
+          (last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m]) /
           last_over_time(etcd_server_quota_backend_bytes{job=~".*etcd.*"}[5m]))*100 >
           95
         for: 10m
@@ -156,26 +172,31 @@ groups:
           severity: critical
       - alert: etcdExcessiveDatabaseGrowth
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": Predicting running out of disk
+          description:
+            'etcd cluster "{{ $labels.job }}": Predicting running out of disk
             space in the next four hours, based on write observations within the past
             four hours on etcd instance {{ $labels.instance }}, please check as it might
             be disruptive.'
           summary: etcd cluster database growing very fast.
-    expr: predict_linear(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[4h], 4*60*60)
+        expr:
+          predict_linear(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[4h], 4*60*60)
           > etcd_server_quota_backend_bytes{job=~".*etcd.*"}
         for: 10m
         labels:
           severity: warning
       - alert: etcdDatabaseHighFragmentationRatio
         annotations:
-      description: 'etcd cluster "{{ $labels.job }}": database size in use on instance
+          description:
+            'etcd cluster "{{ $labels.job }}": database size in use on instance
             {{ $labels.instance }} is {{ $value | humanizePercentage }} of the actual
             allocated disk space, please run defragmentation (e.g. etcdctl defrag) to
             retrieve the unused fragmented disk space.'
           runbook_url: https://etcd.io/docs/v3.5/op-guide/maintenance/#defragmentation
-      summary: etcd database size in use is less than 50% of the actual allocated
+          summary:
+            etcd database size in use is less than 50% of the actual allocated
             storage.
-    expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"}[5m])
+        expr:
+          (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"}[5m])
           / last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m])) < 0.5
           and etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"} > 104857600
         for: 10m

rules/general.yaml

@@ -3,11 +3,13 @@ groups:
     rules:
       - alert: TargetDown
         annotations:
-      description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service
+          description:
+            '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service
             }} targets in {{ $labels.namespace }} namespace are down.'
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
           summary: One or more targets are unreachable.
-    expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up)
+        expr:
+          100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up)
           BY (cluster, job, namespace, service)) > 10
         for: 10m
         labels:
@@ -21,7 +23,8 @@ groups:
             mechanisms that send a notification when this alert is not firing. For example the
             "DeadMansSnitch" integration in PagerDuty.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
-      summary: An alert that should always be firing to certify that Alertmanager
+          summary:
+            An alert that should always be firing to certify that Alertmanager
             is working properly.
         expr: vector(1)
         labels:
@@ -37,7 +40,8 @@ groups:
             This alert should be routed to a null receiver and configured to inhibit alerts with severity="info".
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
           summary: Info-level alert inhibition.
-    expr: ALERTS{severity = "info"} == 1 unless on (namespace) ALERTS{alertname !=
+        expr:
+          ALERTS{severity = "info"} == 1 unless on (namespace) ALERTS{alertname !=
           "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1
         labels:
           severity: none

rules/kubernetes-apps.yaml

@@ -3,18 +3,21 @@ groups:
     rules:
       - alert: KubePodCrashLooping
         annotations:
-      description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
+          description:
+            'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
             }}) is in waiting state (reason: "CrashLoopBackOff").'
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping
           summary: Pod is crash looping.
-    expr: max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff",
+        expr:
+          max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff",
           job="kube-state-metrics", namespace=~".*"}[5m]) >= 1
         for: 15m
         labels:
           severity: warning
       - alert: KubePodNotReady
         annotations:
-      description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready
+          description:
+            Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready
             state for longer than 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready
           summary: Pod has been in a non-ready state for more than 15 minutes.
@@ -31,7 +34,8 @@ groups:
           severity: warning
       - alert: KubeDeploymentGenerationMismatch
         annotations:
-      description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment
+          description:
+            Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment
             }} does not match, this indicates that the Deployment has failed but has not
             been rolled back.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch
@@ -45,7 +49,8 @@ groups:
           severity: warning
       - alert: KubeDeploymentReplicasMismatch
         annotations:
-      description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has
+          description:
+            Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has
             not matched the expected number of replicas for longer than 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch
           summary: Deployment has not matched the expected number of replicas.
@@ -64,7 +69,8 @@ groups:
           severity: warning
       - alert: KubeDeploymentRolloutStuck
         annotations:
-      description: Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment
+          description:
+            Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment
             }} is not progressing for longer than 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck
           summary: Deployment rollout is not progressing.
@@ -76,7 +82,8 @@ groups:
           severity: warning
       - alert: KubeStatefulSetReplicasMismatch
         annotations:
-      description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has
+          description:
+            StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has
             not matched the expected number of replicas for longer than 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch
           summary: StatefulSet has not matched the expected number of replicas.
@@ -95,7 +102,8 @@ groups:
           severity: warning
       - alert: KubeStatefulSetGenerationMismatch
         annotations:
-      description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset
+          description:
+            StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset
             }} does not match, this indicates that the StatefulSet has failed but has
             not been rolled back.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch
@@ -109,7 +117,8 @@ groups:
           severity: warning
       - alert: KubeStatefulSetUpdateNotRolledOut
         annotations:
-      description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update
+          description:
+            StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update
             has not been rolled out.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout
           summary: StatefulSet update has not been rolled out.
@@ -136,7 +145,8 @@ groups:
           severity: warning
       - alert: KubeDaemonSetRolloutStuck
         annotations:
-      description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not
+          description:
+            DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not
             finished or progressed for at least 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck
           summary: DaemonSet rollout is stuck.
@@ -169,19 +179,22 @@ groups:
           severity: warning
       - alert: KubeContainerWaiting
         annotations:
-      description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container
+          description:
+            pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container
             {{ $labels.container}} has been in waiting state for longer than 1 hour.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
           summary: Pod container waiting longer than 1 hour
-    expr: sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics",
+        expr:
+          sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics",
           namespace=~".*"}) > 0
         for: 1h
         labels:
           severity: warning
       - alert: KubeDaemonSetNotScheduled
         annotations:
-      description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
+          description:
-        }} are not scheduled.'
+            "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
+            }} are not scheduled."
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled
           summary: DaemonSet pods are not scheduled.
         expr: |-
@@ -193,18 +206,21 @@ groups:
           severity: warning
       - alert: KubeDaemonSetMisScheduled
         annotations:
-      description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
+          description:
-        }} are running where they are not supposed to run.'
+            "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
+            }} are running where they are not supposed to run."
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled
           summary: DaemonSet pods are misscheduled.
-    expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"}
+        expr:
+          kube_daemonset_status_number_misscheduled{job="kube-state-metrics", namespace=~".*"}
           > 0
         for: 15m
         labels:
           severity: warning
       - alert: KubeJobNotCompleted
         annotations:
-      description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more
+          description:
+            Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more
             than {{ "43200" | humanizeDuration }} to complete.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted
           summary: Job did not complete in time
@@ -216,7 +232,8 @@ groups:
           severity: warning
       - alert: KubeJobFailed
         annotations:
-      description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
+          description:
+            Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
             Removing failed job after investigation should clear this alert.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed
           summary: Job failed to complete.
@@ -226,7 +243,8 @@ groups:
           severity: warning
       - alert: KubeHpaReplicasMismatch
         annotations:
-      description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler  }}
+          description:
+            HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler  }}
             has not matched the desired number of replicas for longer than 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch
           summary: HPA has not matched desired number of replicas.
@@ -249,7 +267,8 @@ groups:
           severity: warning
       - alert: KubeHpaMaxedOut
         annotations:
-      description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler  }}
+          description:
+            HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler  }}
             has been running at max replicas for longer than 15 minutes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout
           summary: HPA is running at max replicas

rules/kubernetes-resources.yaml

@@ -3,7 +3,8 @@ groups:
     rules:
       - alert: KubeCPUOvercommit
         annotations:
-      description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests
+          description:
+            Cluster {{ $labels.cluster }} has overcommitted CPU resource requests
             for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
           summary: Cluster has overcommitted CPU resource requests.
@@ -16,7 +17,8 @@ groups:
           severity: warning
       - alert: KubeMemoryOvercommit
         annotations:
-      description: Cluster {{ $labels.cluster }} has overcommitted memory resource
+          description:
+            Cluster {{ $labels.cluster }} has overcommitted memory resource
             requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node
             failure.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
@@ -30,7 +32,8 @@ groups:
           severity: warning
       - alert: KubeCPUQuotaOvercommit
         annotations:
-      description: Cluster {{ $labels.cluster }}  has overcommitted CPU resource requests
+          description:
+            Cluster {{ $labels.cluster }}  has overcommitted CPU resource requests
             for Namespaces.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
           summary: Cluster has overcommitted CPU resource requests.
@@ -44,7 +47,8 @@ groups:
           severity: warning
       - alert: KubeMemoryQuotaOvercommit
         annotations:
-      description: Cluster {{ $labels.cluster }}  has overcommitted memory resource
+          description:
+            Cluster {{ $labels.cluster }}  has overcommitted memory resource
             requests for Namespaces.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
           summary: Cluster has overcommitted memory resource requests.
@@ -58,7 +62,8 @@ groups:
           severity: warning
       - alert: KubeQuotaAlmostFull
         annotations:
-      description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
+          description:
+            Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
             }} of its {{ $labels.resource }} quota.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
           summary: Namespace quota is going to be full.
@@ -72,7 +77,8 @@ groups:
           severity: info
       - alert: KubeQuotaFullyUsed
         annotations:
-      description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
+          description:
+            Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
             }} of its {{ $labels.resource }} quota.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
           summary: Namespace quota is fully used.
@@ -86,7 +92,8 @@ groups:
           severity: info
       - alert: KubeQuotaExceeded
         annotations:
-      description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
+          description:
+            Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
             }} of its {{ $labels.resource }} quota.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
           summary: Namespace quota has exceeded the limits.
@@ -100,9 +107,10 @@ groups:
           severity: warning
       - alert: CPUThrottlingHigh
         annotations:
-      description: '{{ $value | humanizePercentage }} throttling of CPU in namespace
+          description:
+            "{{ $value | humanizePercentage }} throttling of CPU in namespace
             {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod
-        }}.'
+            }}."
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
           summary: Processes experience elevated CPU throttling.
         expr: |-

rules/kubernetes-storage.yaml

@@ -1,10 +1,10 @@
-
 groups:
   - name: kubernetes-storage
     rules:
       - alert: KubePersistentVolumeFillingUp
         annotations:
-      description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
+          description:
+            The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
             }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster
             {{ . }} {{- end }} is only {{ $value | humanizePercentage }} free.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
@@ -26,7 +26,8 @@ groups:
           severity: critical
       - alert: KubePersistentVolumeFillingUp
         annotations:
-      description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim
+          description:
+            Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim
             }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster
             {{ . }} {{- end }} is expected to fill up within four days. Currently {{ $value
             | humanizePercentage }} is available.
@@ -51,7 +52,8 @@ groups:
           severity: warning
       - alert: KubePersistentVolumeInodesFillingUp
         annotations:
-      description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
+          description:
+            The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
             }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster
             {{ . }} {{- end }} only has {{ $value | humanizePercentage }} free inodes.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup
@@ -73,7 +75,8 @@ groups:
           severity: critical
       - alert: KubePersistentVolumeInodesFillingUp
         annotations:
-      description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim
+          description:
+            Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim
             }} in Namespace {{ $labels.namespace }} {{ with $labels.cluster -}} on Cluster
             {{ . }} {{- end }} is expected to run out of inodes within four days. Currently
             {{ $value | humanizePercentage }} of its inodes are free.
@@ -98,11 +101,13 @@ groups:
           severity: warning
       - alert: KubePersistentVolumeErrors
         annotations:
-      description: The persistent volume {{ $labels.persistentvolume }} {{ with $labels.cluster
+          description:
+            The persistent volume {{ $labels.persistentvolume }} {{ with $labels.cluster
             -}} on Cluster {{ . }} {{- end }} has status {{ $labels.phase }}.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeerrors
           summary: PersistentVolume is having issues with provisioning.
-    expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"}
+        expr:
+          kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"}
           > 0
         for: 5m
         labels:

rules/node-exporter.yaml

@@ -3,7 +3,8 @@ groups:
     rules:
       - alert: NodeFilesystemSpaceFillingUp
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             space left and is filling up.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup
@@ -21,7 +22,8 @@ groups:
           severity: warning
       - alert: NodeFilesystemSpaceFillingUp
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             space left and is filling up fast.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup
@@ -39,7 +41,8 @@ groups:
           severity: critical
       - alert: NodeFilesystemAlmostOutOfSpace
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             space left.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace
@@ -55,7 +58,8 @@ groups:
           severity: warning
       - alert: NodeFilesystemAlmostOutOfSpace
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             space left.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace
@@ -71,7 +75,8 @@ groups:
           severity: critical
       - alert: NodeFilesystemFilesFillingUp
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             inodes left and is filling up.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup
@@ -89,7 +94,8 @@ groups:
           severity: warning
       - alert: NodeFilesystemFilesFillingUp
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             inodes left and is filling up fast.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup
@@ -107,7 +113,8 @@ groups:
           severity: critical
       - alert: NodeFilesystemAlmostOutOfFiles
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             inodes left.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles
@@ -123,7 +130,8 @@ groups:
           severity: warning
       - alert: NodeFilesystemAlmostOutOfFiles
         annotations:
-      description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
+          description:
+            Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
             }}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
             inodes left.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles
@@ -139,38 +147,44 @@ groups:
           severity: critical
       - alert: NodeNetworkReceiveErrs
         annotations:
-      description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
+          description:
+            '{{ $labels.instance }} interface {{ $labels.device }} has encountered
             {{ printf "%.0f" $value }} receive errors in the last two minutes.'
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworkreceiveerrs
           summary: Network interface is reporting many receive errors.
-    expr: rate(node_network_receive_errs_total{job="node-exporter"}[2m]) / rate(node_network_receive_packets_total{job="node-exporter"}[2m])
+        expr:
+          rate(node_network_receive_errs_total{job="node-exporter"}[2m]) / rate(node_network_receive_packets_total{job="node-exporter"}[2m])
           > 0.01
         for: 1h
         labels:
           severity: warning
       - alert: NodeNetworkTransmitErrs
         annotations:
-      description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
+          description:
+            '{{ $labels.instance }} interface {{ $labels.device }} has encountered
             {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworktransmiterrs
           summary: Network interface is reporting many transmit errors.
-    expr: rate(node_network_transmit_errs_total{job="node-exporter"}[2m]) / rate(node_network_transmit_packets_total{job="node-exporter"}[2m])
+        expr:
+          rate(node_network_transmit_errs_total{job="node-exporter"}[2m]) / rate(node_network_transmit_packets_total{job="node-exporter"}[2m])
           > 0.01
         for: 1h
         labels:
           severity: warning
       - alert: NodeHighNumberConntrackEntriesUsed
         annotations:
-      description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
+          description: "{{ $value | humanizePercentage }} of conntrack entries are used."
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused
           summary: Number of conntrack are getting close to the limit.
-    expr: (node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit)
+        expr:
+          (node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit)
           > 0.75
         labels:
           severity: warning
       - alert: NodeTextFileCollectorScrapeError
         annotations:
-      description: Node Exporter text file collector on {{ $labels.instance }} failed
+          description:
+            Node Exporter text file collector on {{ $labels.instance }} failed
             to scrape.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodetextfilecollectorscrapeerror
           summary: Node Exporter text file collector failed to scrape.
@@ -179,7 +193,8 @@ groups:
           severity: warning
       - alert: NodeClockSkewDetected
         annotations:
-      description: Clock at {{ $labels.instance }} is out of sync by more than 0.05s.
+          description:
+            Clock at {{ $labels.instance }} is out of sync by more than 0.05s.
             Ensure NTP is configured correctly on this host.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected
           summary: Clock skew detected.
@@ -200,7 +215,8 @@ groups:
           severity: warning
       - alert: NodeClockNotSynchronising
         annotations:
-      description: Clock at {{ $labels.instance }} is not synchronising. Ensure NTP
+          description:
+            Clock at {{ $labels.instance }} is not synchronising. Ensure NTP
             is configured on this host.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclocknotsynchronising
           summary: Clock not synchronising.
@@ -213,12 +229,14 @@ groups:
           severity: warning
       - alert: NodeRAIDDegraded
         annotations:
-      description: RAID array '{{ $labels.device }}' at {{ $labels.instance }} is
+          description:
+            RAID array '{{ $labels.device }}' at {{ $labels.instance }} is
             in degraded state due to one or more disks failures. Number of spare drives
             is insufficient to fix issue automatically.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddegraded
           summary: RAID Array is degraded.
-    expr: node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}
+        expr:
+          node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}
           - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"})
           > 0
         for: 15m
@@ -226,17 +244,20 @@ groups:
           severity: critical
       - alert: NodeRAIDDiskFailure
         annotations:
-      description: At least one device in RAID array at {{ $labels.instance }} failed.
+          description:
+            At least one device in RAID array at {{ $labels.instance }} failed.
             Array '{{ $labels.device }}' needs attention and possibly a disk swap.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddiskfailure
           summary: Failed device in RAID array.
-    expr: node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}
+        expr:
+          node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}
           > 0
         labels:
           severity: warning
       - alert: NodeFileDescriptorLimit
         annotations:
-      description: File descriptors limit at {{ $labels.instance }} is currently at
+          description:
+            File descriptors limit at {{ $labels.instance }} is currently at
             {{ printf "%.2f" $value }}%.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit
           summary: Kernel is predicted to exhaust file descriptors limit soon.
@@ -249,7 +270,8 @@ groups:
           severity: warning
       - alert: NodeFileDescriptorLimit
         annotations:
-      description: File descriptors limit at {{ $labels.instance }} is currently at
+          description:
+            File descriptors limit at {{ $labels.instance }} is currently at
             {{ printf "%.2f" $value }}%.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit
           summary: Kernel is predicted to exhaust file descriptors limit soon.
@@ -266,7 +288,8 @@ groups:
             CPU usage at {{ $labels.instance }} has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage
           summary: High CPU usage.
-    expr: sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter",
+        expr:
+          sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter",
           mode!="idle"}[2m]))) * 100 > 90
         for: 15m
         labels:
@@ -301,7 +324,8 @@ groups:
             Memory is filling up at {{ $labels.instance }}, has been above 90% for the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememoryhighutilization
           summary: Host is running out of memory.
-    expr: 100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"}
+        expr:
+          100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"}
           * 100) > 90
         for: 15m
         labels:
@@ -313,14 +337,16 @@ groups:
             This symptom might indicate disk saturation.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodediskiosaturation
           summary: Disk IO queue is high.
-    expr: rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
+        expr:
+          rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
           > 10
         for: 30m
         labels:
           severity: warning
       - alert: NodeSystemdServiceFailed
         annotations:
-      description: Systemd service {{ $labels.name }} has entered failed state at
+          description:
+            Systemd service {{ $labels.name }} has entered failed state at
             {{ $labels.instance }}
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed
           summary: Systemd service has entered failed state.
@@ -330,7 +356,8 @@ groups:
           severity: warning
       - alert: NodeBondingDegraded
         annotations:
-      description: Bonding interface {{ $labels.master }} on {{ $labels.instance }}
+          description:
+            Bonding interface {{ $labels.master }} on {{ $labels.instance }}
             is in degraded state due to one or more slave failures.
           runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodebondingdegraded
           summary: Bonding interface is degraded

rules/node-resource-utilization.yaml

@@ -8,14 +8,16 @@ groups:
               VALUE = {{ $value }}
               LABELS = {{ $labels }}
           summary: Host high CPU load (instance {{ $labels.instance }})
-    expr: (sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m])))
+        expr:
+          (sum by (instance) (avg by (mode, instance) (rate(node_cpu_seconds_total{mode!="idle"}[2m])))
           > 0.9) * on(instance) group_left (nodename) node_uname_info{nodename=~".+"}
         for: 10m
         labels:
           severity: critical
       - alert: MemoryUtilizationHighWarning
         annotations:
-      dashboard: https://grafana.ads1.itpartner.no/explore?orgId=1&left=%7B%22datasource%22:%22Prometheus%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22instant%22:true,%22range%22:true,%22exemplar%22:false,%22expr%22:%22topk(10,%20sum(container_memory_usage_bytes%7Bcontainer!%3D%5C%22%5C%22,%20container!%3D%5C%22POD%5{
+          dashboard:
+            https://grafana.ads1.itpartner.no/explore?orgId=1&left=%7B%22datasource%22:%22Prometheus%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22instant%22:true,%22range%22:true,%22exemplar%22:false,%22expr%22:%22topk(10,%20sum(container_memory_usage_bytes%7Bcontainer!%3D%5C%22%5C%22,%20container!%3D%5C%22POD%5{
             $labels.instance }}%5C%22%7D)%20by%20(container,%20pod,%20namespace))%22%7D%5D,%22range%22:%7B%22from%22:%22now-1h%22,%22to%22:%22now%22%7D%7D
           description: Node {{ $labels.instance }} has less than 10% available memory.
           summary: Node Memory utilization warning
@@ -25,7 +27,8 @@ groups:
           severity: critical
       - alert: MemoryUtilizationHighCritical
         annotations:
-      dashboard: https://grafana.ads1.itpartner.no/explore?orgId=1&left=%7B%22datasource%22:%22Prometheus%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22instant%22:true,%22range%22:true,%22exemplar%22:false,%22expr%22:%22topk(10,%20sum(container_memory_usage_bytes%7Bcontainer!%3D%5C%22%5C%22,%20container!%3D%5C%22POD%5{
+          dashboard:
+            https://grafana.ads1.itpartner.no/explore?orgId=1&left=%7B%22datasource%22:%22Prometheus%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22instant%22:true,%22range%22:true,%22exemplar%22:false,%22expr%22:%22topk(10,%20sum(container_memory_usage_bytes%7Bcontainer!%3D%5C%22%5C%22,%20container!%3D%5C%22POD%5{
             $labels.instance }}%5C%22%7D)%20by%20(container,%20pod,%20namespace))%22%7D%5D,%22range%22:%7B%22from%22:%22now-1h%22,%22to%22:%22now%22%7D%7D
           description: Node {{ $labels.instance }} has less than 5% available memory.
           summary: Node Memory utilization critical
@@ -37,7 +40,8 @@ groups:
         annotations:
           description: Node {{ $labels.node }} has CPU utilization over 90%.
           summary: Node has been in not-ready state for longer than 3 minutes
-    expr: (sum(max_over_time(kube_node_status_condition{condition="Ready",status="true"}[3m])
+        expr:
+          (sum(max_over_time(kube_node_status_condition{condition="Ready",status="true"}[3m])
           <= 0) by (node)) or (absent(kube_node_status_condition{condition="Ready",status="true"}))
           > 0
         for: 5m
@@ -50,7 +54,8 @@ groups:
               VALUE = {{ $value }}
               LABELS = {{ $labels }}
           summary: Kubernetes Node memory pressure (instance {{ $labels.instance }})
-    expr: kube_node_status_condition{condition="MemoryPressure",status="true"} ==
+        expr:
+          kube_node_status_condition{condition="MemoryPressure",status="true"} ==
           1
         for: 2m
         labels:
@@ -62,7 +67,8 @@ groups:
               VALUE = {{ $value }}
               LABELS = {{ $labels }}
           summary: Kubernetes Container oom killer (instance {{ $labels.instance }})
-    expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total
+        expr:
+          (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total
           offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m])
           == 1
         for: 0m

rules/velero.yaml

@@ -3,18 +3,22 @@ groups:
     rules:
       - alert: VeleroBackupPartialFailures
         annotations:
-      message: Velero backup  {{ $labels.schedule }}  has  {{$value | humanizePercentage}}  partialy
+          message:
+            Velero backup  {{ $labels.schedule }}  has  {{$value | humanizePercentage}}  partialy
             failed backups.
-    expr: velero_backup_partial_failure_total{schedule!=""} / velero_backup_attempt_total{schedule!=""}
+        expr:
+          velero_backup_partial_failure_total{schedule!=""} / velero_backup_attempt_total{schedule!=""}
           > 0.25
         for: 15m
         labels:
           severity: critical
       - alert: VeleroBackupFailures
         annotations:
-      message: Velero backup  {{$labels.schedule}}  has  {{$value | humanizePercentage}}  failed
+          message:
+            Velero backup  {{$labels.schedule}}  has  {{$value | humanizePercentage}}  failed
             backups.
-    expr: velero_backup_failure_total{schedule!=""} / velero_backup_attempt_total{schedule!=""}
+        expr:
+          velero_backup_failure_total{schedule!=""} / velero_backup_attempt_total{schedule!=""}
           > 0.25
         for: 15m
         labels:

rules/x509-exporter.yaml

@@ -3,7 +3,8 @@ groups:
     rules:
       - alert: X509ExporterReadErrors
         annotations:
-      description: Over the last 15 minutes, this x509-certificate-exporter instance
+          description:
+            Over the last 15 minutes, this x509-certificate-exporter instance
             has experienced errors reading certificate files or querying the Kubernetes
             API. This could be caused by a misconfiguration if triggered when the exporter
             starts.
@@ -14,7 +15,8 @@ groups:
           severity: warning
       - alert: CertificateError
         annotations:
-      description: Certificate could not be decoded {{if $labels.secret_name }} in
+          description:
+            Certificate could not be decoded {{if $labels.secret_name }} in
             Kubernetes secret "{{ $labels.secret_namespace }}/{{ $labels.secret_name }}"{{else}}at
             location "{{ $labels.filepath }}"{{end}}
           summary: Certificate cannot be decoded
@@ -24,22 +26,26 @@ groups:
           severity: warning
       - alert: CertificateRenewal
         annotations:
-      description: Certificate for "{{ $labels.subject_CN }}" should be renewed {{if
+          description:
+            Certificate for "{{ $labels.subject_CN }}" should be renewed {{if
             $labels.secret_name }}in Kubernetes secret "{{ $labels.secret_namespace }}/{{
             $labels.secret_name }}"{{else}}at location "{{ $labels.filepath }}"{{end}}
           summary: Certificate should be renewed
-    expr: ((x509_cert_not_after{secret_name!="linkerd-identity-issuer", issuer_O="",
+        expr:
+          ((x509_cert_not_after{secret_name!="linkerd-identity-issuer", issuer_O="",
           issuer_CN!="webhook.linkerd.cluster.local"} - time()) / 86400) < 28
         for: 15m
         labels:
           severity: warning
       - alert: CertificateExpiration
         annotations:
-      description: Certificate for "{{ $labels.subject_CN }}" is about to expire {{if
+          description:
+            Certificate for "{{ $labels.subject_CN }}" is about to expire {{if
             $labels.secret_name }}in Kubernetes secret "{{ $labels.secret_namespace }}/{{
             $labels.secret_name }}"{{else}}at location "{{ $labels.filepath }}"{{end}}
           summary: Certificate is about to expire
-    expr: ((x509_cert_not_after{secret_name!="linkerd-identity-issuer", issuer_O="",
+        expr:
+          ((x509_cert_not_after{secret_name!="linkerd-identity-issuer", issuer_O="",
           issuer_CN!="webhook.linkerd.cluster.local"} - time()) / 86400) < 14
         for: 15m
         labels:

shell.nix

@@ -6,11 +6,15 @@ let
     config = { };
     overlays = [ ];
   };
+  checks = import ./nix/checks.nix;
 in
 pkgs.mkShellNoCC {
   name = "clstr";
 
-  packages = with pkgs; [
+  packages =
+    with pkgs;
+    [
+      # dev tools
       just
       npins
 
@@ -24,17 +28,40 @@ pkgs.mkShellNoCC {
       kubelogin
       kubelogin-oidc
       kubectl-rook-ceph
+      kubectl-graph
+      kubectl-klock
+      graphviz
 
-    # other tools
+      # other tools activate when needed
-    step-cli
+      # step-cli
-    linkerd
+      # linkerd
-    velero
+      # cmctl
-    cmctl
+      # rclone
+      # velero
+      # renovate
 
       # dapr
       dapr-cli
+    ]
+    ++ checks.enabledPackages;
+
+  # Environment variables
+  ARGOCD_ENV_CLUSTER_NAME = "hel1";
+  HELM_GIT_ACCESS_TOKEN = "glpat-xxx";
+
+  shellHook = builtins.concatStringsSep "\n" [
+    checks.shellHook
   ];
 
-  ARGOCD_ENV_CLUSTER_NAME = "rossby";
+  # Alternative shells
-  HELM_GIT_ACCESS_TOKEN = "glpat-xxx";
+  passthru = pkgs.lib.mapAttrs (name: value: pkgs.mkShellNoCC (value // { inherit name; })) {
+    ci-shell = {
+      packages = [
+        pkgs.npins
+      ];
+      shellHook = ''
+        export NPINS_DIRECTORY="nix"
+      '';
+    };
+  };
 }

values/argo/manifests/sys-project.yaml

@@ -88,6 +88,8 @@ spec:
     server: https://kubernetes.default.svc
   - namespace: uptime
     server: https://kubernetes.default.svc
+  - namespace: forgejo
+    server: https://kubernetes.default.svc
   sourceRepos:
   - https://argoproj.github.io/argo-helm
   - https://kubernetes-sigs.github.io/metrics-server/
@@ -123,6 +125,7 @@ spec:
   - ghcr.io/slinkyproject/charts/slurm-operator-crds
   - ghcr.io/spegel-org/helm-charts
   - ghcr.io/dragonflydb/dragonfly-operator/helm/dragonfly-operator
+  - code.forgejo.org/forgejo-helm
   - https://operator.mariadb.com/mariadb-enterprise-operator
   - https://operator.mariadb.com
   - https://ot-container-kit.github.io/helm-charts

values/atlantis/kustomize/prod/appsettings.json

@@ -73,7 +73,7 @@
     "connString": "Username=postgres;Password=secret;Host=localhost;Port=5432;Database=app;Pooling=true;",
     "sorcerer" : "https://sorcerer.data.oceanbox.io",
     "allowedOrigins": [
-        "https://maps.oceanbox.io",
+        "https://maps.oceanbox.io"
     ],
     "appName": "atlantis",
     "appEnv": "prod",

values/atlantis/values/values-prod.yaml.gotmpl

@@ -79,3 +79,9 @@ resources:
   requests:
     cpu: 500m
     memory: 1Gi
+
+diagrid-dashboard:
+  enabled: false
+  statestore:
+    scope: prod-atlantis
+    redis: prod-atlantis-redis

values/atlantis/values/values-staging.yaml.gotmpl

@@ -1,6 +1,6 @@
 replicaCount: 1
 image:
-  tag: 369127e0-debug
+  tag: 503ccbb2-debug
 podAnnotations:
   dapr.io/app-id: "staging-atlantis"
 env:
@@ -26,12 +26,12 @@ env:
   - name: DB_USER
     valueFrom:
       secretKeyRef:
-        name: staging-atlantis-db-superuser
+        name: staging-atlantis-db-app
         key: username
   - name: DB_PASSWORD
     valueFrom:
       secretKeyRef:
-        name: staging-atlantis-db-superuser
+        name: staging-atlantis-db-app
         key: password
   - name: DAPR_API_TOKEN
     valueFrom:
@@ -116,9 +116,6 @@ cluster:
       db: prod-atlantis-db
       namespace: prod-atlantis
 resources:
-  limits:
-    cpu: 250m
-    memory: 1Gi
   requests:
     cpu: 250m
     memory: 1Gi
@@ -133,3 +130,8 @@ redis:
   resources:
     cpu: 150m
     memory: 256Mi
+diagrid-dashboard:
+  enabled: false
+  statestore:
+    scope: staging-atlantis
+    redis: staging-atlantis-redis

values/atlantis/values/values.yaml.gotmpl

@@ -10,3 +10,4 @@ podAnnotations:
   dapr.io/sidecar-memory-request: "50Mi"
   # dapr.io/sidecar-cpu-limit: "100m"
   # dapr.io/sidecar-memory-limit: "1000Mi"
+

values/codex/env.yaml.gotmpl

@@ -1,4 +1,8 @@
 codex:
   enabled: false
+  {{- if eq .Environment.Name "prod" }}
   autosync: false
+  {{- else }}
+  autosync: true
+  {{- end }}
   env: {{ .Environment.Name }}

values/codex/kustomize/prod/appsettings.json

@@ -0,0 +1,67 @@
+{
+    "Logging": {
+        "LogLevel": {
+            "Default": "Information",
+            "Microsoft": "Warning",
+            "Microsoft.Hosting": "Error"
+        }
+    },
+    "Debug": {
+        "LogLevel": {
+            "Default": "Debug"
+        }
+    },
+    "Console": {
+        "IncludeScopes": true,
+        "LogLevel": {
+            "Default": "Debug"
+        }
+    },
+    "OIDC": {
+        "issuer": "https://auth.oceanbox.io/realms/oceanbox",
+        "authorization_endpoint": "https://auth.oceanbox.io/realms/oceanbox/protocol/openid-connect/auth",
+        "token_endpoint": "https://auth.oceanbox.io/realms/oceanbox/protocol/openid-connect/token",
+        "jwks_uri": "https://auth.oceanbox.io/realms/oceanbox/protocol/openid-connect/certs",
+        "userinfo_endpoint": "https://auth.oceanbox.io/realms/oceanbox/protocol/openid-connect/userinfo",
+        "end_session_endpoint": "https://auth.oceanbox.io/realms/oceanbox/protocol/openid-connect/logout",
+        "device_authorization_endpoint": "https://auth.oceanbox.io/realms/oceanbox/protocol/openid-connect/auth/device",
+        "clientId": "atlantis",
+        "clientSecret": "",
+        "scopes": [
+            "openid",
+            "email",
+            "offline_access",
+            "profile"
+        ],
+        "audiences": [
+            "atlantis"
+        ]
+    },
+    "SSO": {
+        "cookieDomain": ".oceanbox.io",
+        "cookieName": ".obx.prod",
+        "ttl": 12.0,
+        "signedOutRedirectUri": "https://maps.oceanbox.io/",
+        "realm": "atlantis",
+        "environment": "prod",
+        "keyStore": {
+            "kind": "azure",
+            "uri": "https://atlantis.blob.core.windows.net",
+            "key": "dataprotection-keys"
+        },
+        "keyVault": {
+            "kind": "azure",
+            "uri": "https://atlantisvault.vault.azure.net",
+            "key": "dataencryption-keys"
+        }
+    },
+    "plainAuthUsers": [
+        {
+            "username": "admin",
+            "password": "en-to-tre-fire",
+            "groups": [ "/oceanbox" ],
+            "roles": [ "admin" ]
+        }
+    ]
+}
+

values/codex/kustomize/prod/deployment_patch.yaml

@@ -0,0 +1,66 @@
+- op: add
+  path: /spec/template/spec/containers/0/envFrom
+  value:
+    - secretRef:
+        name: azure-keyvault
+- op: add
+  path: /spec/template/spec/containers/0/env
+  value:
+    - name: APP_NAMESPACE
+      value: prod-atlantis
+    - name: DOTNET_ENVIRONMENT
+      value: Production
+    - name: ASPNETCORE_ENVIRONMENT
+      value: Production
+    - name: DB_HOST
+      valueFrom:
+        secretKeyRef:
+          name: prod-atlantis-db-app
+          key: host
+    - name: DB_PORT
+      valueFrom:
+        secretKeyRef:
+          name: prod-atlantis-db-app
+          key: port
+    - name: DB_DATABASE
+      valueFrom:
+        secretKeyRef:
+          name: prod-atlantis-db-app
+          key: dbname
+    - name: DB_USER
+      valueFrom:
+        secretKeyRef:
+          name: prod-atlantis-db-app
+          key: user
+    - name: DB_PASSWORD
+      valueFrom:
+        secretKeyRef:
+          name: prod-atlantis-db-app
+          key: password
+    - name: FGA_URL
+      value: http://prod-openfga.openfga.svc.cluster.local:8080
+    - name: FGA_DB_HOST
+      valueFrom:
+        secretKeyRef:
+          name: prod-openfga-db-app
+          key: host
+    - name: FGA_DB_PORT
+      valueFrom:
+        secretKeyRef:
+          name: prod-openfga-db-app
+          key: port
+    - name: FGA_DB_DATABASE
+      valueFrom:
+        secretKeyRef:
+          name: prod-openfga-db-app
+          key: dbname
+    - name: FGA_DB_USER
+      valueFrom:
+        secretKeyRef:
+          name: prod-openfga-db-app
+          key: user
+    - name: FGA_DB_PASSWORD
+      valueFrom:
+        secretKeyRef:
+          name: prod-openfga-db-app
+          key: password

values/codex/kustomize/prod/kustomization.yaml

@@ -0,0 +1,15 @@
+generatorOptions:
+  disableNameSuffixHash: true
+configMapGenerator:
+- name: prod-codex-appsettings
+  files:
+    - appsettings.json
+patches:
+  - target:
+      group: apps
+      version: v1
+      kind: Deployment
+    path: deployment_patch.yaml
+resources:
+  - ../base
+

values/codex/kustomize/staging/deployment_patch.yaml

@@ -62,4 +62,3 @@
         secretKeyRef:
           name: staging-openfga-db-app
           key: password
-  name: azure-keyvault

values/codex/manifests/network/allow-external-services.yaml

@@ -0,0 +1,14 @@
+{{- if .Values.clusterConfig.cilium.enabled }}
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: codex-allow-external-services
+  namespace: {{ .Release.Namespace }}
+spec:
+  egress:
+  - toFQDNs:
+    - matchName: cacerts.digicert.com
+  endpointSelector:
+    matchLabels: {}
+{{- end }}
+

values/codex/values/values-prod.yaml

@@ -0,0 +1,27 @@
+replicaCount: 1
+ingress:
+  enabled: true
+  className: "nginx"
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-production
+    nginx.ingress.kubernetes.io/backend-protocol: HTTP
+    nginx.ingress.kubernetes.io/ssl-redirect: "true"
+    oceanbox.io/expose: internal
+  hosts:
+    - host: codex.adm.oceanbox.io
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls:
+    - hosts:
+        - codex.adm.oceanbox.io
+      secretName: prod-codex-tls
+volumes:
+  - name: appsettings
+    configMap:
+      name: prod-codex-appsettings
+volumeMounts:
+  - name: appsettings
+    mountPath: "/app/appsettings.json"
+    readOnly: true
+    subPath: appsettings.json