Worker node upgrade chain

README.md

@@ -136,6 +136,11 @@ The currently tested upgrade chain is:
 - `1.33.10 -> 1.34.6`
 - `1.34.6 -> 1.35.3`
 
+Tested worker node upgrade chain:
+
+- `1.33.3 -> 1.34.1`
+- `1.33.1 -> 1.35.3`
+
 ---
 
 ## Current status

alpine/build-rootfs.sh

@@ -6,7 +6,7 @@ source /utils.sh
 
 /preload-k8s-images.sh || exit 1
 
-export CTL_BIN_LAYER=$( skopeo inspect docker-daemon:localhost/monok8s/node-control:dev | jq -r '.Layers[0] | sub("^sha256:"; "")' )
+export CTL_BIN_LAYER=$( skopeo inspect docker-daemon:localhost/monok8s/node-control:$TAG | jq -r '.Layers[0] | sub("^sha256:"; "")' )
 
 mkdir -p \
   "$ROOTFS/dev" \

build.env

@@ -43,3 +43,7 @@ BUILD_TAG=MONOK8S
 # Optional apt cache
 #   example: apt-cacher-ng.eco-system.svc.cluster.local:3142
 APT_PROXY=
+
+# remote image repository prefix to push to
+# e.g. ghcr.io/monok8s
+IMAGE_REPOSITORY=

clitools/docker/ctl-agent.Dockerfile

@@ -1,16 +1,41 @@
+ARG BASE_IMAGE=localhost/monok8s/ctl-build-base:dev
+
+FROM --platform=$BUILDPLATFORM ${BASE_IMAGE} AS build
+
+ARG VERSION=dev
+ARG TARGETOS
+ARG TARGETARCH
+
+WORKDIR /src
+
+COPY . .
+
+RUN test -f pkg/buildinfo/buildinfo_gen.go
+
+RUN mkdir -p /out && \
+    GOOS=${TARGETOS} GOARCH=${TARGETARCH} CGO_ENABLED=0 \
+    go build -trimpath -ldflags="-s -w" \
+      -o /out/ctl ./cmd/ctl
+
+
 FROM alpine:latest AS cacerts
+
+
 FROM scratch
 
 ARG VERSION
+ARG TARGETOS
+ARG TARGETARCH
 ENV VERSION=${VERSION}
 
 WORKDIR /
 
-COPY bin/ctl-linux-aarch64-${VERSION} ./ctl
-COPY out/fw_printenv ./
-COPY out/fw_setenv ./
+COPY --from=build /out/ctl /ctl
 COPY --from=cacerts /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
 
+COPY out/uboot-tools/${TARGETOS}_${TARGETARCH}/fw_printenv /fw_printenv
+COPY out/uboot-tools/${TARGETOS}_${TARGETARCH}/fw_setenv /fw_setenv
+
 ENV PATH=/
 
 ENTRYPOINT ["/ctl"]

clitools/docker/ctl-builder-local.Dockerfile

@@ -1,24 +0,0 @@
-FROM golang:1.26-alpine AS build
-
-ARG VERSION
-ARG KUBE_VERSION
-ARG GIT_REV=unknown
-
-WORKDIR /src
-
-RUN apk add --no-cache git build-base
-
-COPY go.mod go.sum ./
-RUN go mod download
-
-COPY . .
-
-RUN test -f pkg/buildinfo/buildinfo_gen.go
-
-RUN mkdir -p /out && \
-    GOOS=darwin GOARCH=arm64 CGO_ENABLED=0 \
-    go build -trimpath -ldflags="-s -w" \
-      -o /out/ctl-${VERSION} ./cmd/ctl
-
-FROM scratch
-COPY --from=build /out/ /

clitools/docker/ctl-builder.Dockerfile

@@ -1,20 +0,0 @@
-ARG BASE_IMAGE=localhost/monok8s/ctl-build-base:dev
-FROM ${BASE_IMAGE} AS build
-
-ARG VERSION=dev
-ARG TARGETOS=linux
-ARG TARGETARCH=arm64
-
-WORKDIR /src
-
-COPY . .
-
-RUN test -f pkg/buildinfo/buildinfo_gen.go
-
-RUN mkdir -p /out && \
-    GOOS=${TARGETOS} GOARCH=${TARGETARCH} CGO_ENABLED=0 \
-    go build -trimpath -ldflags="-s -w" \
-      -o /out/ctl-linux-aarch64-${VERSION} ./cmd/ctl
-
-FROM scratch
-COPY --from=build /out/ /

clitools/makefile

@@ -1,4 +1,6 @@
 include ../build.env
+-include ../build.env.work
+export
 
 BUILD_PLATFORM ?= linux/amd64
 
@@ -11,30 +13,29 @@ KUBE_VERSION ?= v1.33.3
 
 GIT_REV := $(shell git rev-parse HEAD)
 
-PACKAGES_DIR := packages
-BIN_DIR      := bin
-OUT_DIR      := out
+PACKAGES_DIR    := packages
+OUT_DIR         := out
+UBOOT_TOOLS_OUT := $(OUT_DIR)/uboot-tools
 
 UBOOT_TAR      := $(PACKAGES_DIR)/uboot-$(UBOOT_VERSION).tar.gz
 BUILDINFO_FILE := pkg/buildinfo/buildinfo_gen.go
-CRD_PATHS      := ./pkg/apis/...
-
+ASSETS_PATH      := ./pkg/assets
 
 BUILDX_BUILDER      := container-builder
 LOCAL_REGISTRY      := registry
 LOCAL_REGISTRY_PORT := 5000
 
-CTL_BUILD_BASE_IMAGE := localhost:5000/monok8s/ctl-build-base:$(VERSION)
-CTL_BINARY           := ctl-linux-aarch64-$(VERSION)
+CTL_BUILD_BASE_REPO  := localhost:5000/monok8s/ctl-build-base
+CTL_IMAGE_REPO       := localhost:5000/monok8s/node-control
+
+CTL_BUILD_BASE_IMAGE := $(CTL_BUILD_BASE_REPO):$(VERSION)
+CTL_IMAGE            := $(CTL_IMAGE_REPO):$(VERSION)
 
 DOWNLOAD_PACKAGES_STAMP := $(PACKAGES_DIR)/.download-packages.stamp
 
 $(PACKAGES_DIR):
 	mkdir -p $@
 
-$(BIN_DIR):
-	mkdir -p $@
-
 $(OUT_DIR):
 	mkdir -p $@
 
@@ -88,11 +89,14 @@ $(DOWNLOAD_PACKAGES_STAMP): docker/download-packages.Dockerfile makefile | $(PAC
 	@touch $@
 
 uboot-tools: $(DOWNLOAD_PACKAGES_STAMP)
-	docker buildx build --platform linux/arm64 \
+	rm -rf "$(UBOOT_TOOLS_OUT)"
+	mkdir -p "$(UBOOT_TOOLS_OUT)"
+	docker buildx build \
+		--platform linux/amd64,linux/arm64 \
 		-f docker/uboot-tools.Dockerfile \
 		--build-arg UBOOT_VERSION=$(UBOOT_VERSION) \
 		--build-arg UBOOT_TAR=$(UBOOT_TAR) \
-		--output type=local,dest=./$(OUT_DIR) .
+		--output type=local,dest=./$(UBOOT_TOOLS_OUT),platform-split=true .
 
 ctl-build-base: ensure-buildx ensure-registry
 	docker buildx build \
@@ -101,16 +105,6 @@ ctl-build-base: ensure-buildx ensure-registry
 		-t $(CTL_BUILD_BASE_IMAGE) \
 		--output type=image,push=true,registry.insecure=true .
 
-build-bin: .buildinfo ctl-build-base | $(BIN_DIR)
-	docker buildx build \
-		--platform $(BUILD_PLATFORM) \
-		-f docker/ctl-builder.Dockerfile \
-		--build-arg BASE_IMAGE=$(CTL_BUILD_BASE_IMAGE) \
-		--build-arg VERSION=$(VERSION) \
-		--build-arg TARGETOS=linux \
-		--build-arg TARGETARCH=arm64 \
-		--output type=local,dest=./$(BIN_DIR) .
-
 build-crds: ctl-build-base | $(OUT_DIR)
 	mkdir -p "$(OUT_DIR)/crds"
 	docker buildx build \
@@ -118,35 +112,47 @@ build-crds: ctl-build-base | $(OUT_DIR)
 		-f docker/crdgen.Dockerfile \
 		--build-arg BASE_IMAGE=$(CTL_BUILD_BASE_IMAGE) \
 		--output type=local,dest=./$(OUT_DIR)/crds .
+	rm -rf "$(ASSETS_PATH)/crds"
+	mkdir -p "$(ASSETS_PATH)/crds"
+	cp -R "$(OUT_DIR)/crds/." "$(ASSETS_PATH)/crds/"
 
-build-agent: build uboot-tools
+build-agent: .buildinfo build-crds uboot-tools
+	docker buildx build \
+		--platform linux/amd64,linux/arm64 \
+		-f docker/ctl-agent.Dockerfile \
+		--build-arg BASE_IMAGE=$(CTL_BUILD_BASE_IMAGE) \
+		--build-arg VERSION=$(VERSION) \
+		-t $(CTL_IMAGE) \
+		--output type=image,push=true,registry.insecure=true .
+
+build-local: .buildinfo build-crds uboot-tools
 	docker buildx build \
 		--platform linux/arm64 \
 		-f docker/ctl-agent.Dockerfile \
+		--build-arg BASE_IMAGE=$(CTL_BUILD_BASE_IMAGE) \
 		--build-arg VERSION=$(VERSION) \
 		--load \
 		-t localhost/monok8s/node-control:$(VERSION) .
 
-build-local: .buildinfo | $(BIN_DIR)
+push-agent: .buildinfo build-crds uboot-tools
+	test -n "$(IMAGE_REPOSITORY)"
 	docker buildx build \
-		-f docker/ctl-builder-local.Dockerfile \
+		--platform linux/amd64,linux/arm64 \
+		-f docker/ctl-agent.Dockerfile \
+		--build-arg BASE_IMAGE=$(CTL_BUILD_BASE_IMAGE) \
 		--build-arg VERSION=$(VERSION) \
-		--build-arg KUBE_VERSION=$(KUBE_VERSION) \
-		--build-arg GIT_REV=$(GIT_REV) \
-		--output type=local,dest=./$(BIN_DIR) .
+		-t $(IMAGE_REPOSITORY)/node-control:$(VERSION) \
+		--push .
 
 run-agent:
 	docker run --rm \
 		-v "$$(pwd)/out:/work/out" \
-		localhost/monok8s/node-control:$(VERSION) \
+		$(CTL_IMAGE) \
 		agent --env-file /work/out/cluster.env
 
-build: build-bin build-crds
-
 clean:
 	-docker image rm localhost/monok8s/node-control:$(VERSION) >/dev/null 2>&1 || true
 	rm -rf \
-		$(BIN_DIR) \
 		$(OUT_DIR)/crds \
 		$(BUILDINFO_FILE)
 
@@ -158,7 +164,6 @@ dockerclean:
 	- docker rmi \
 		localhost/monok8s/ctl-build-base:$(VERSION) \
 		localhost/monok8s/node-control:$(VERSION) \
-		localhost/monok8s/ctl-builder:$(VERSION) \
 		localhost/monok8s/crdgen:$(VERSION) \
 		2>/dev/null || true
 
@@ -169,10 +174,10 @@ dockerclean:
 pkgclean:
 	rm -rf $(PACKAGES_DIR)
 
-all: build build-agent build-local
+all: build-agent build-local
 
 .PHONY: \
 	all clean dockerclean \
 	.buildinfo ensure-buildx ensure-registry \
-	build build-bin build-crds build-local build-agent \
-	uboot-tools run-agent
+	build-crds build-local build-agent build-agent-local push-agent \
+	uboot-tools run-agent run-agent-local

clitools/pkg/assets/crds/monok8s.io_monoksconfigs.yaml

@@ -0,0 +1,178 @@
+---
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  annotations:
+    controller-gen.kubebuilder.io/version: v0.20.1
+  name: monoksconfigs.monok8s.io
+spec:
+  group: monok8s.io
+  names:
+    kind: MonoKSConfig
+    listKind: MonoKSConfigList
+    plural: monoksconfigs
+    singular: monoksconfig
+  scope: Namespaced
+  versions:
+  - name: v1alpha1
+    schema:
+      openAPIV3Schema:
+        properties:
+          apiVersion:
+            description: |-
+              APIVersion defines the versioned schema of this representation of an object.
+              Servers should convert recognized schemas to the latest internal value, and
+              may reject unrecognized values.
+              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
+            type: string
+          kind:
+            description: |-
+              Kind is a string value representing the REST resource this object represents.
+              Servers may infer this from the endpoint the client submits requests to.
+              Cannot be updated.
+              In CamelCase.
+              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
+            type: string
+          metadata:
+            type: object
+          spec:
+            properties:
+              allowSchedulingOnControlPlane:
+                type: boolean
+              apiServerAdvertiseAddress:
+                type: string
+              apiServerEndpoint:
+                type: string
+              bootstrapToken:
+                type: string
+              clusterDomain:
+                type: string
+              clusterName:
+                type: string
+              clusterRole:
+                type: string
+              cniPlugin:
+                type: string
+              containerRuntimeEndpoint:
+                type: string
+              controlPlaneCertKey:
+                type: string
+              discoveryTokenCACertHash:
+                type: string
+              enableNodeControl:
+                type: boolean
+              initControlPlane:
+                type: boolean
+              kubeProxyNodePortAddresses:
+                items:
+                  type: string
+                type: array
+              kubernetesVersion:
+                type: string
+              network:
+                properties:
+                  dnsNameservers:
+                    items:
+                      type: string
+                    type: array
+                  dnsSearchDomains:
+                    items:
+                      type: string
+                    type: array
+                  hostname:
+                    type: string
+                  managementCIDR:
+                    type: string
+                  managementGateway:
+                    type: string
+                  managementIface:
+                    type: string
+                type: object
+              nodeLabels:
+                additionalProperties:
+                  type: string
+                type: object
+              nodeName:
+                type: string
+              podSubnet:
+                type: string
+              serviceSubnet:
+                type: string
+              skipImageCheck:
+                type: boolean
+              subjectAltNames:
+                items:
+                  type: string
+                type: array
+            type: object
+          status:
+            properties:
+              appliedSteps:
+                items:
+                  type: string
+                type: array
+              conditions:
+                items:
+                  description: Condition contains details for one aspect of the current
+                    state of this API Resource.
+                  properties:
+                    lastTransitionTime:
+                      description: |-
+                        lastTransitionTime is the last time the condition transitioned from one status to another.
+                        This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
+                      format: date-time
+                      type: string
+                    message:
+                      description: |-
+                        message is a human readable message indicating details about the transition.
+                        This may be an empty string.
+                      maxLength: 32768
+                      type: string
+                    observedGeneration:
+                      description: |-
+                        observedGeneration represents the .metadata.generation that the condition was set based upon.
+                        For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
+                        with respect to the current state of the instance.
+                      format: int64
+                      minimum: 0
+                      type: integer
+                    reason:
+                      description: |-
+                        reason contains a programmatic identifier indicating the reason for the condition's last transition.
+                        Producers of specific condition types may define expected values and meanings for this field,
+                        and whether the values are considered a guaranteed API.
+                        The value should be a CamelCase string.
+                        This field may not be empty.
+                      maxLength: 1024
+                      minLength: 1
+                      pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
+                      type: string
+                    status:
+                      description: status of the condition, one of True, False, Unknown.
+                      enum:
+                      - "True"
+                      - "False"
+                      - Unknown
+                      type: string
+                    type:
+                      description: type of condition in CamelCase or in foo.example.com/CamelCase.
+                      maxLength: 316
+                      pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
+                      type: string
+                  required:
+                  - lastTransitionTime
+                  - message
+                  - reason
+                  - status
+                  - type
+                  type: object
+                type: array
+              observedGeneration:
+                format: int64
+                type: integer
+              phase:
+                type: string
+            type: object
+        type: object
+    served: true
+    storage: true

clitools/pkg/assets/crds/monok8s.io_osupgradeprogresses.yaml

@@ -0,0 +1,124 @@
+---
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  annotations:
+    controller-gen.kubebuilder.io/version: v0.20.1
+  name: osupgradeprogresses.monok8s.io
+spec:
+  group: monok8s.io
+  names:
+    kind: OSUpgradeProgress
+    listKind: OSUpgradeProgressList
+    plural: osupgradeprogresses
+    shortNames:
+    - osup
+    singular: osupgradeprogress
+  scope: Namespaced
+  versions:
+  - additionalPrinterColumns:
+    - jsonPath: .spec.nodeName
+      name: Node
+      type: string
+    - jsonPath: .spec.sourceRef.name
+      name: Source
+      type: string
+    - jsonPath: .status.currentVersion
+      name: Current
+      type: string
+    - jsonPath: .status.targetVersion
+      name: Target
+      type: string
+    - jsonPath: .status.phase
+      name: Phase
+      type: string
+    name: v1alpha1
+    schema:
+      openAPIV3Schema:
+        properties:
+          apiVersion:
+            description: |-
+              APIVersion defines the versioned schema of this representation of an object.
+              Servers should convert recognized schemas to the latest internal value, and
+              may reject unrecognized values.
+              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
+            type: string
+          kind:
+            description: |-
+              Kind is a string value representing the REST resource this object represents.
+              Servers may infer this from the endpoint the client submits requests to.
+              Cannot be updated.
+              In CamelCase.
+              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
+            type: string
+          metadata:
+            type: object
+          spec:
+            description: Specification of the desired behavior of the OSUpgradeProgress.
+            properties:
+              nodeName:
+                type: string
+              retryNonce:
+                description: |-
+                  RetryNonce triggers a retry when its value changes.
+                  Users can update this field (for example, set it to the current time)
+                  to request a retry of a failed OS upgrade.
+                type: string
+              sourceRef:
+                properties:
+                  name:
+                    type: string
+                  namespace:
+                    type: string
+                type: object
+            type: object
+          status:
+            description: Most recently observed status of the OSUpgradeProgress.
+            properties:
+              completedAt:
+                format: date-time
+                type: string
+              currentFrom:
+                type: string
+              currentStep:
+                format: int32
+                type: integer
+              currentTo:
+                type: string
+              currentVersion:
+                type: string
+              failureReason:
+                type: string
+              inactivePartition:
+                type: string
+              lastUpdatedAt:
+                format: date-time
+                type: string
+              message:
+                type: string
+              observedRetryNonce:
+                description: |-
+                  ObservedRetryNonce records the last retryNonce value the agent accepted.
+                  When spec.retryNonce is changed by the user and differs from this value,
+                  the agent may retry a failed upgrade.
+                type: string
+              phase:
+                type: string
+              plannedPath:
+                items:
+                  type: string
+                type: array
+              retryCount:
+                format: int32
+                type: integer
+              startedAt:
+                format: date-time
+                type: string
+              targetVersion:
+                type: string
+            type: object
+        type: object
+    served: true
+    storage: true
+    subresources:
+      status: {}

clitools/pkg/assets/crds/monok8s.io_osupgrades.yaml

@@ -0,0 +1,202 @@
+---
+apiVersion: apiextensions.k8s.io/v1
+kind: CustomResourceDefinition
+metadata:
+  annotations:
+    controller-gen.kubebuilder.io/version: v0.20.1
+  name: osupgrades.monok8s.io
+spec:
+  group: monok8s.io
+  names:
+    kind: OSUpgrade
+    listKind: OSUpgradeList
+    plural: osupgrades
+    shortNames:
+    - osu
+    singular: osupgrade
+  scope: Namespaced
+  versions:
+  - additionalPrinterColumns:
+    - jsonPath: .spec.desiredVersion
+      name: Desired
+      type: string
+    - jsonPath: .status.resolvedVersion
+      name: Resolved
+      type: string
+    - jsonPath: .status.phase
+      name: Phase
+      type: string
+    name: v1alpha1
+    schema:
+      openAPIV3Schema:
+        properties:
+          apiVersion:
+            description: |-
+              APIVersion defines the versioned schema of this representation of an object.
+              Servers should convert recognized schemas to the latest internal value, and
+              may reject unrecognized values.
+              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
+            type: string
+          kind:
+            description: |-
+              Kind is a string value representing the REST resource this object represents.
+              Servers may infer this from the endpoint the client submits requests to.
+              Cannot be updated.
+              In CamelCase.
+              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
+            type: string
+          metadata:
+            type: object
+          spec:
+            description: Specification of the desired behavior of the OSUpgrade.
+            properties:
+              catalog:
+                properties:
+                  configMapRef:
+                    type: string
+                  inline:
+                    type: string
+                  url:
+                    type: string
+                type: object
+              desiredVersion:
+                minLength: 1
+                type: string
+              flashProfile:
+                default: balanced
+                description: |-
+                  Profiles (TODO)
+                     safe     - api-server can be responsive most of the time
+                     balanced - api-server can sometimes be unresponsive
+                     fast     - disable throttling. Good for worker node.
+                enum:
+                - fast
+                - balanced
+                - safe
+                type: string
+              nodeSelector:
+                description: |-
+                  A label selector is a label query over a set of resources. The result of matchLabels and
+                  matchExpressions are ANDed. An empty label selector matches all objects. A null
+                  label selector matches no objects.
+                properties:
+                  matchExpressions:
+                    description: matchExpressions is a list of label selector requirements.
+                      The requirements are ANDed.
+                    items:
+                      description: |-
+                        A label selector requirement is a selector that contains values, a key, and an operator that
+                        relates the key and values.
+                      properties:
+                        key:
+                          description: key is the label key that the selector applies
+                            to.
+                          type: string
+                        operator:
+                          description: |-
+                            operator represents a key's relationship to a set of values.
+                            Valid operators are In, NotIn, Exists and DoesNotExist.
+                          type: string
+                        values:
+                          description: |-
+                            values is an array of string values. If the operator is In or NotIn,
+                            the values array must be non-empty. If the operator is Exists or DoesNotExist,
+                            the values array must be empty. This array is replaced during a strategic
+                            merge patch.
+                          items:
+                            type: string
+                          type: array
+                          x-kubernetes-list-type: atomic
+                      required:
+                      - key
+                      - operator
+                      type: object
+                    type: array
+                    x-kubernetes-list-type: atomic
+                  matchLabels:
+                    additionalProperties:
+                      type: string
+                    description: |-
+                      matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels
+                      map is equivalent to an element of matchExpressions, whose key field is "key", the
+                      operator is "In", and the values array contains only "value". The requirements are ANDed.
+                    type: object
+                type: object
+                x-kubernetes-map-type: atomic
+            type: object
+          status:
+            description: Most recently observed status of the OSUpgrade.
+            properties:
+              conditions:
+                items:
+                  description: Condition contains details for one aspect of the current
+                    state of this API Resource.
+                  properties:
+                    lastTransitionTime:
+                      description: |-
+                        lastTransitionTime is the last time the condition transitioned from one status to another.
+                        This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
+                      format: date-time
+                      type: string
+                    message:
+                      description: |-
+                        message is a human readable message indicating details about the transition.
+                        This may be an empty string.
+                      maxLength: 32768
+                      type: string
+                    observedGeneration:
+                      description: |-
+                        observedGeneration represents the .metadata.generation that the condition was set based upon.
+                        For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
+                        with respect to the current state of the instance.
+                      format: int64
+                      minimum: 0
+                      type: integer
+                    reason:
+                      description: |-
+                        reason contains a programmatic identifier indicating the reason for the condition's last transition.
+                        Producers of specific condition types may define expected values and meanings for this field,
+                        and whether the values are considered a guaranteed API.
+                        The value should be a CamelCase string.
+                        This field may not be empty.
+                      maxLength: 1024
+                      minLength: 1
+                      pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
+                      type: string
+                    status:
+                      description: status of the condition, one of True, False, Unknown.
+                      enum:
+                      - "True"
+                      - "False"
+                      - Unknown
+                      type: string
+                    type:
+                      description: type of condition in CamelCase or in foo.example.com/CamelCase.
+                      maxLength: 316
+                      pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
+                      type: string
+                  required:
+                  - lastTransitionTime
+                  - message
+                  - reason
+                  - status
+                  - type
+                  type: object
+                type: array
+              message:
+                type: string
+              observedGeneration:
+                format: int64
+                type: integer
+              phase:
+                type: string
+              reason:
+                type: string
+              resolvedVersion:
+                type: string
+            type: object
+        type: object
+    served: true
+    storage: true
+    subresources:
+      status: {}

clitools/pkg/assets/embed.go

@@ -0,0 +1,6 @@
+package assets
+
+import "embed"
+
+//go:embed crds/*.yaml
+var CRDs embed.FS

clitools/pkg/assets/render.go

@@ -0,0 +1,49 @@
+package assets
+
+import (
+	"fmt"
+	"io"
+	"path/filepath"
+	"sort"
+)
+
+func PrintCRDs(out io.Writer) error {
+	entries, err := CRDs.ReadDir("crds")
+	if err != nil {
+		return err
+	}
+
+	names := make([]string, 0, len(entries))
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		if filepath.Ext(entry.Name()) != ".yaml" {
+			continue
+		}
+		names = append(names, entry.Name())
+	}
+
+	sort.Strings(names)
+
+	for _, name := range names {
+		b, err := CRDs.ReadFile("crds/" + name)
+		if err != nil {
+			return err
+		}
+
+		if _, err := fmt.Fprintln(out, "---"); err != nil {
+			return err
+		}
+		if _, err := out.Write(b); err != nil {
+			return err
+		}
+		if len(b) == 0 || b[len(b)-1] != '\n' {
+			if _, err := fmt.Fprintln(out); err != nil {
+				return err
+			}
+		}
+	}
+
+	return nil
+}

clitools/pkg/bootstrap/runner.go

@@ -112,6 +112,11 @@ func NewRunner(cfg *monov1alpha1.MonoKSConfig) *Runner {
 				Name:   "Wait for existing cluster",
 				Desc:   "Block until control plane is reachable when joining or reconciling an existing cluster",
 			},
+			{
+				RegKey: "CheckForVersionSkew",
+				Name:   "Check for version skew",
+				Desc:   "Validate wether version satisfy the requirements againts current cluster if any",
+			},
 			{
 				RegKey: "ReconcileControlPlane",
 				Name:   "Reconcile control plane",
@@ -122,11 +127,6 @@ func NewRunner(cfg *monov1alpha1.MonoKSConfig) *Runner {
 				Name:   "Reconcile worker node",
 				Desc:   "Reconcile the worker node",
 			},
-			{
-				RegKey: "CheckForVersionSkew",
-				Name:   "Check for version skew",
-				Desc:   "Validate wether version satisfy the requirements againts current cluster if any",
-			},
 			{
 				RegKey: "RunKubeadmUpgradeApply",
 				Name:   "Run kubeadm upgrade apply",

clitools/pkg/cmd/create/create.go

@@ -6,7 +6,9 @@ import (
 	"github.com/spf13/cobra"
 	"k8s.io/cli-runtime/pkg/genericclioptions"
 	"os"
+	"strings"
 
+	assets "example.com/monok8s/pkg/assets"
 	render "example.com/monok8s/pkg/render"
 )
 
@@ -42,13 +44,20 @@ func NewCmdCreate(flags *genericclioptions.ConfigFlags) *cobra.Command {
 				return err
 			},
 		},
+		&cobra.Command{
+			Use:   "crds",
+			Short: "Print the bundled CRDs",
+			RunE: func(cmd *cobra.Command, _ []string) error {
+				return assets.PrintCRDs(cmd.OutOrStdout())
+			},
+		},
 	)
 
 	var authorizedKeysPath string
 
 	sshdcmd := cobra.Command{
 		Use:   "sshd",
-		Short: "Print sshd deployment template",
+		Short: "Print sshd deployments template",
 		RunE: func(cmd *cobra.Command, _ []string) error {
 			ns, _, err := flags.ToRawKubeConfigLoader().Namespace()
 			if err != nil {
@@ -77,8 +86,12 @@ func NewCmdCreate(flags *genericclioptions.ConfigFlags) *cobra.Command {
 	cconf := render.ControllerConf{}
 	controllercmd := cobra.Command{
 		Use:   "controller",
-		Short: "Print controller deployment template",
+		Short: "Print controller deployments template",
 		RunE: func(cmd *cobra.Command, _ []string) error {
+			if len(cconf.ImagePullSecrets) > 0 && strings.TrimSpace(cconf.Image) == "" {
+				return fmt.Errorf("--image-pull-secret requires --image")
+			}
+
 			ns, _, err := flags.ToRawKubeConfigLoader().Namespace()
 			if err != nil {
 				return err
@@ -102,9 +115,56 @@ func NewCmdCreate(flags *genericclioptions.ConfigFlags) *cobra.Command {
 		"",
 		"Controller image, including optional registry and tag",
 	)
+	controllercmd.Flags().StringSliceVar(
+		&cconf.ImagePullSecrets,
+		"image-pull-secret",
+		nil,
+		"Image pull secret name for the agent image; may be specified multiple times or as a comma-separated list",
+	)
 
 	cmd.AddCommand(&controllercmd)
 
+	aconf := render.AgentConf{}
+	agentcmd := cobra.Command{
+		Use:   "agent",
+		Short: "Print agent daemonsets template",
+		RunE: func(cmd *cobra.Command, _ []string) error {
+			if len(aconf.ImagePullSecrets) > 0 && strings.TrimSpace(aconf.Image) == "" {
+				return fmt.Errorf("--image-pull-secret requires --image")
+			}
+
+			ns, _, err := flags.ToRawKubeConfigLoader().Namespace()
+			if err != nil {
+				return err
+			}
+
+			aconf.Namespace = ns
+
+			out, err := render.RenderAgentDaemonSets(aconf)
+			if err != nil {
+				return err
+			}
+
+			_, err = fmt.Fprint(cmd.OutOrStdout(), out)
+			return err
+		},
+	}
+
+	agentcmd.Flags().StringVar(
+		&aconf.Image,
+		"image",
+		"",
+		"Agent image, including optional registry and tag",
+	)
+	agentcmd.Flags().StringSliceVar(
+		&aconf.ImagePullSecrets,
+		"image-pull-secret",
+		nil,
+		"Image pull secret name for the agent image; may be specified multiple times or as a comma-separated list",
+	)
+
+	cmd.AddCommand(&agentcmd)
+
 	return cmd
 }
 

clitools/pkg/controller/osupgrade/watch.go

@@ -272,11 +272,17 @@ func listTargetNodeNames(
 	})
 
 	if osu.Spec.NodeSelector != nil {
-		sel, err := metav1.LabelSelectorAsSelector(osu.Spec.NodeSelector)
+		userSelector, err := metav1.LabelSelectorAsSelector(osu.Spec.NodeSelector)
 		if err != nil {
 			return nil, fmt.Errorf("invalid nodeSelector: %w", err)
 		}
-		selector = sel
+
+		reqs, selectable := userSelector.Requirements()
+		if !selectable {
+			selector = labels.Nothing()
+		} else {
+			selector = selector.Add(reqs...)
+		}
 	}
 
 	list, err := clients.Kubernetes.CoreV1().

clitools/pkg/crds/crds.go

@@ -1,76 +0,0 @@
-package crds
-
-import (
-	monov1alpha1 "example.com/monok8s/pkg/apis/monok8s/v1alpha1"
-	apiextensionsv1 "k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-)
-
-func Definitions() []*apiextensionsv1.CustomResourceDefinition {
-	return []*apiextensionsv1.CustomResourceDefinition{
-		monoKSConfigCRD(),
-		osUpgradeCRD(),
-	}
-}
-
-func monoKSConfigCRD() *apiextensionsv1.CustomResourceDefinition {
-	return &apiextensionsv1.CustomResourceDefinition{
-		ObjectMeta: metav1.ObjectMeta{
-			Name: monov1alpha1.MonoKSConfigCRD,
-		},
-		Spec: apiextensionsv1.CustomResourceDefinitionSpec{
-			Group: monov1alpha1.Group,
-			Scope: apiextensionsv1.NamespaceScoped,
-			Names: apiextensionsv1.CustomResourceDefinitionNames{
-				Plural:     "monoksconfigs",
-				Singular:   "monoksconfig",
-				Kind:       "MonoKSConfig",
-				ShortNames: []string{"mkscfg"},
-			},
-			Versions: []apiextensionsv1.CustomResourceDefinitionVersion{{
-				Name:    "v1alpha1",
-				Served:  true,
-				Storage: true,
-				Schema: &apiextensionsv1.CustomResourceValidation{OpenAPIV3Schema: &apiextensionsv1.JSONSchemaProps{
-					Type: "object",
-					Properties: map[string]apiextensionsv1.JSONSchemaProps{
-						"spec":   {Type: "object", XPreserveUnknownFields: boolPtr(true)},
-						"status": {Type: "object", XPreserveUnknownFields: boolPtr(true)},
-					},
-				}},
-			}},
-		},
-	}
-}
-
-func osUpgradeCRD() *apiextensionsv1.CustomResourceDefinition {
-	return &apiextensionsv1.CustomResourceDefinition{
-		ObjectMeta: metav1.ObjectMeta{
-			Name: monov1alpha1.OSUpgradeCRD,
-		},
-		Spec: apiextensionsv1.CustomResourceDefinitionSpec{
-			Group: monov1alpha1.Group,
-			Scope: apiextensionsv1.NamespaceScoped,
-			Names: apiextensionsv1.CustomResourceDefinitionNames{
-				Plural:     "osupgrades",
-				Singular:   "osupgrade",
-				Kind:       "OSUpgrade",
-				ShortNames: []string{"osup"},
-			},
-			Versions: []apiextensionsv1.CustomResourceDefinitionVersion{{
-				Name:    "v1alpha1",
-				Served:  true,
-				Storage: true,
-				Schema: &apiextensionsv1.CustomResourceValidation{OpenAPIV3Schema: &apiextensionsv1.JSONSchemaProps{
-					Type: "object",
-					Properties: map[string]apiextensionsv1.JSONSchemaProps{
-						"spec":   {Type: "object", XPreserveUnknownFields: boolPtr(true)},
-						"status": {Type: "object", XPreserveUnknownFields: boolPtr(true)},
-					},
-				}},
-			}},
-		},
-	}
-}
-
-func boolPtr(v bool) *bool { return &v }

clitools/pkg/node/agent.go

@@ -3,37 +3,27 @@ package node
 import (
 	"context"
 	"fmt"
-	"reflect"
 	"strings"
 
-	appsv1 "k8s.io/api/apps/v1"
-	corev1 "k8s.io/api/core/v1"
-	rbacv1 "k8s.io/api/rbac/v1"
-	apierrors "k8s.io/apimachinery/pkg/api/errors"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-	"k8s.io/client-go/kubernetes"
 	"k8s.io/klog/v2"
 
-	monov1alpha1 "example.com/monok8s/pkg/apis/monok8s/v1alpha1"
 	"example.com/monok8s/pkg/kube"
+	"example.com/monok8s/pkg/render"
 	templates "example.com/monok8s/pkg/templates"
 )
 
-const (
-	controlAgentImage = "localhost/monok8s/node-control:dev"
-	kubeconfig        = "/etc/kubernetes/admin.conf"
-)
+const kubeconfig = "/etc/kubernetes/admin.conf"
 
 func ApplyNodeControlDaemonSetResources(ctx context.Context, n *NodeContext) error {
-	// Only the control-plane should bootstrap this DaemonSet definition.
-	// And only when the feature is enabled.
 	if strings.TrimSpace(n.Config.Spec.ClusterRole) != "control-plane" || !n.Config.Spec.EnableNodeControl {
-		klog.InfoS("skipped for", "clusterRole", n.Config.Spec.ClusterRole, "enableNodeAgent", n.Config.Spec.EnableNodeControl)
+		klog.InfoS("skipped for",
+			"clusterRole", n.Config.Spec.ClusterRole,
+			"enableNodeAgent", n.Config.Spec.EnableNodeControl,
+		)
 		return nil
 	}
 
-	err := ApplyCRDs(ctx, n)
-	if err != nil {
+	if err := ApplyCRDs(ctx, n); err != nil {
 		return err
 	}
 
@@ -47,363 +37,13 @@ func ApplyNodeControlDaemonSetResources(ctx context.Context, n *NodeContext) err
 		return fmt.Errorf("build kube clients from %s: %w", kubeconfig, err)
 	}
 
-	labels := map[string]string{
-		"app.kubernetes.io/name":       monov1alpha1.NodeAgentName,
-		"app.kubernetes.io/component":  "agent",
-		"app.kubernetes.io/part-of":    "monok8s",
-		"app.kubernetes.io/managed-by": monov1alpha1.NodeControlName,
+	conf := render.AgentConf{
+		Namespace: namespace,
 	}
 
-	kubeClient := clients.Kubernetes
-
-	if err := ensureNamespace(ctx, kubeClient, namespace, labels); err != nil {
-		return fmt.Errorf("ensure namespace %q: %w", namespace, err)
-	}
-	if err := applyNodeAgentServiceAccount(ctx, kubeClient, namespace, labels); err != nil {
-		return fmt.Errorf("apply serviceaccount: %w", err)
-	}
-	if err := applyNodeAgentClusterRole(ctx, kubeClient, labels); err != nil {
-		return fmt.Errorf("apply clusterrole: %w", err)
-	}
-	if err := applyNodeAgentClusterRoleBinding(ctx, kubeClient, namespace, labels); err != nil {
-		return fmt.Errorf("apply clusterrolebinding: %w", err)
-	}
-	if err := applyNodeAgentDaemonSet(ctx, kubeClient, namespace, labels); err != nil {
-		return fmt.Errorf("apply daemonset: %w", err)
+	if err := render.ApplyAgentDaemonSets(ctx, clients.Kubernetes, conf); err != nil {
+		return fmt.Errorf("apply node agent daemonset resources: %w", err)
 	}
 
 	return nil
 }
-
-func ensureNamespace(
-	ctx context.Context,
-	kubeClient kubernetes.Interface,
-	namespace string,
-	labels map[string]string,
-) error {
-	_, err := kubeClient.CoreV1().Namespaces().Get(ctx, namespace, metav1.GetOptions{})
-	if err == nil {
-		return nil
-	}
-	if !apierrors.IsNotFound(err) {
-		return fmt.Errorf("get namespace: %w", err)
-	}
-
-	ns := &corev1.Namespace{
-		ObjectMeta: metav1.ObjectMeta{
-			Name:   namespace,
-			Labels: copyStringMap(labels),
-		},
-	}
-
-	_, err = kubeClient.CoreV1().Namespaces().Create(ctx, ns, metav1.CreateOptions{})
-	if err != nil && !apierrors.IsAlreadyExists(err) {
-		return fmt.Errorf("create namespace: %w", err)
-	}
-
-	return nil
-}
-
-func copyStringMap(in map[string]string) map[string]string {
-	if len(in) == 0 {
-		return nil
-	}
-	out := make(map[string]string, len(in))
-	for k, v := range in {
-		out[k] = v
-	}
-	return out
-}
-
-func applyNodeAgentServiceAccount(ctx context.Context, kubeClient kubernetes.Interface, namespace string, labels map[string]string) error {
-	want := &corev1.ServiceAccount{
-		ObjectMeta: metav1.ObjectMeta{
-			Name:      monov1alpha1.NodeAgentName,
-			Namespace: namespace,
-			Labels:    labels,
-		},
-	}
-
-	existing, err := kubeClient.CoreV1().ServiceAccounts(namespace).Get(ctx, monov1alpha1.NodeAgentName, metav1.GetOptions{})
-	if apierrors.IsNotFound(err) {
-		_, err = kubeClient.CoreV1().ServiceAccounts(namespace).Create(ctx, want, metav1.CreateOptions{})
-		return err
-	}
-	if err != nil {
-		return err
-	}
-
-	changed := false
-	if !reflect.DeepEqual(existing.Labels, want.Labels) {
-		existing.Labels = want.Labels
-		changed = true
-	}
-
-	if !changed {
-		return nil
-	}
-
-	_, err = kubeClient.CoreV1().ServiceAccounts(namespace).Update(ctx, existing, metav1.UpdateOptions{})
-	return err
-}
-
-func applyNodeAgentClusterRole(ctx context.Context, kubeClient kubernetes.Interface, labels map[string]string) error {
-	wantRules := []rbacv1.PolicyRule{
-		{
-			APIGroups: []string{monov1alpha1.Group},
-			Resources: []string{"osupgrades"},
-			Verbs:     []string{"get"},
-		},
-		{
-			APIGroups: []string{monov1alpha1.Group},
-			Resources: []string{"osupgradeprogresses"},
-			Verbs:     []string{"get", "list", "watch", "create", "patch", "update"},
-		},
-		{
-			APIGroups: []string{monov1alpha1.Group},
-			Resources: []string{"osupgradeprogresses/status"},
-			Verbs:     []string{"get", "list", "watch", "create", "patch", "update"},
-		},
-		{
-			APIGroups: []string{""},
-			Resources: []string{"nodes"},
-			Verbs:     []string{"get", "list", "watch"},
-		},
-	}
-
-	want := &rbacv1.ClusterRole{
-		ObjectMeta: metav1.ObjectMeta{
-			Name:   monov1alpha1.NodeAgentName,
-			Labels: labels,
-		},
-		Rules: wantRules,
-	}
-
-	existing, err := kubeClient.RbacV1().ClusterRoles().Get(ctx, monov1alpha1.NodeAgentName, metav1.GetOptions{})
-	if apierrors.IsNotFound(err) {
-		_, err = kubeClient.RbacV1().ClusterRoles().Create(ctx, want, metav1.CreateOptions{})
-		return err
-	}
-	if err != nil {
-		return err
-	}
-
-	changed := false
-	if !reflect.DeepEqual(existing.Labels, want.Labels) {
-		existing.Labels = want.Labels
-		changed = true
-	}
-	if !reflect.DeepEqual(existing.Rules, want.Rules) {
-		existing.Rules = want.Rules
-		changed = true
-	}
-
-	if !changed {
-		return nil
-	}
-
-	_, err = kubeClient.RbacV1().ClusterRoles().Update(ctx, existing, metav1.UpdateOptions{})
-	return err
-}
-
-func applyNodeAgentClusterRoleBinding(ctx context.Context, kubeClient kubernetes.Interface, namespace string, labels map[string]string) error {
-	wantRoleRef := rbacv1.RoleRef{
-		APIGroup: rbacv1.GroupName,
-		Kind:     "ClusterRole",
-		Name:     monov1alpha1.NodeAgentName,
-	}
-	wantSubjects := []rbacv1.Subject{
-		{
-			Kind:      "ServiceAccount",
-			Name:      monov1alpha1.NodeAgentName,
-			Namespace: namespace,
-		},
-	}
-
-	want := &rbacv1.ClusterRoleBinding{
-		ObjectMeta: metav1.ObjectMeta{
-			Name:   monov1alpha1.NodeAgentName,
-			Labels: labels,
-		},
-		RoleRef:  wantRoleRef,
-		Subjects: wantSubjects,
-	}
-
-	existing, err := kubeClient.RbacV1().ClusterRoleBindings().Get(ctx, monov1alpha1.NodeAgentName, metav1.GetOptions{})
-	if apierrors.IsNotFound(err) {
-		_, err = kubeClient.RbacV1().ClusterRoleBindings().Create(ctx, want, metav1.CreateOptions{})
-		return err
-	}
-	if err != nil {
-		return err
-	}
-
-	// roleRef is immutable. If it differs, fail loudly instead of pretending we can patch it.
-	if !reflect.DeepEqual(existing.RoleRef, want.RoleRef) {
-		return fmt.Errorf("existing ClusterRoleBinding %q has different roleRef and must be recreated", monov1alpha1.NodeAgentName)
-	}
-
-	changed := false
-	if !reflect.DeepEqual(existing.Labels, want.Labels) {
-		existing.Labels = want.Labels
-		changed = true
-	}
-	if !reflect.DeepEqual(existing.Subjects, want.Subjects) {
-		existing.Subjects = want.Subjects
-		changed = true
-	}
-
-	if !changed {
-		return nil
-	}
-
-	_, err = kubeClient.RbacV1().ClusterRoleBindings().Update(ctx, existing, metav1.UpdateOptions{})
-	return err
-}
-
-func applyNodeAgentDaemonSet(ctx context.Context, kubeClient kubernetes.Interface, namespace string, labels map[string]string) error {
-	privileged := true
-
-	dsLabels := monov1alpha1.NodeAgentLabels()
-
-	want := &appsv1.DaemonSet{
-		ObjectMeta: metav1.ObjectMeta{
-			Name:      monov1alpha1.NodeAgentName,
-			Namespace: namespace,
-			Labels:    labels,
-		},
-		Spec: appsv1.DaemonSetSpec{
-			Selector: &metav1.LabelSelector{
-				MatchLabels: map[string]string{
-					"app.kubernetes.io/name": monov1alpha1.NodeAgentName,
-				},
-			},
-			Template: corev1.PodTemplateSpec{
-				ObjectMeta: metav1.ObjectMeta{
-					Labels: dsLabels,
-				},
-				Spec: corev1.PodSpec{
-					ServiceAccountName: monov1alpha1.NodeAgentName,
-					HostNetwork:        true,
-					HostPID:            true,
-					DNSPolicy:          corev1.DNSClusterFirstWithHostNet,
-					NodeSelector: map[string]string{
-						monov1alpha1.NodeControlKey: "true",
-					},
-					Tolerations: []corev1.Toleration{
-						{Operator: corev1.TolerationOpExists},
-					},
-					Containers: []corev1.Container{
-						{
-							Name:            "agent",
-							Image:           controlAgentImage,
-							ImagePullPolicy: corev1.PullNever,
-							Args:            []string{"agent", "--env-file", "$(CLUSTER_ENV_FILE)"},
-							Env: []corev1.EnvVar{
-								{
-									Name: "NODE_NAME",
-									ValueFrom: &corev1.EnvVarSource{
-										FieldRef: &corev1.ObjectFieldSelector{
-											APIVersion: "v1",
-											FieldPath:  "spec.nodeName",
-										},
-									},
-								},
-								{
-									Name:  "CLUSTER_ENV_FILE",
-									Value: "/host/opt/monok8s/config/cluster.env",
-								},
-								{
-									Name:  "FW_ENV_CONFIG_FILE",
-									Value: "/host/etc/fw_env.config",
-								},
-							},
-							SecurityContext: &corev1.SecurityContext{
-								Privileged: &privileged,
-							},
-							VolumeMounts: []corev1.VolumeMount{
-								{
-									Name:      "host-dev",
-									MountPath: "/dev",
-								},
-								{
-									Name:      "host-etc",
-									MountPath: "/host/etc",
-									ReadOnly:  true,
-								},
-								{
-									Name:      "host-config",
-									MountPath: "/host/opt/monok8s/config",
-									ReadOnly:  true,
-								},
-							},
-						},
-					},
-					Volumes: []corev1.Volume{
-						{
-							Name: "host-dev",
-							VolumeSource: corev1.VolumeSource{
-								HostPath: &corev1.HostPathVolumeSource{
-									Path: "/dev",
-									Type: hostPathType(corev1.HostPathDirectory),
-								},
-							},
-						},
-						{
-							Name: "host-etc",
-							VolumeSource: corev1.VolumeSource{
-								HostPath: &corev1.HostPathVolumeSource{
-									Path: "/etc",
-									Type: hostPathType(corev1.HostPathDirectory),
-								},
-							},
-						},
-						{
-							Name: "host-config",
-							VolumeSource: corev1.VolumeSource{
-								HostPath: &corev1.HostPathVolumeSource{
-									Path: "/opt/monok8s/config",
-									Type: hostPathType(corev1.HostPathDirectory),
-								},
-							},
-						},
-					},
-				},
-			},
-		},
-	}
-
-	existing, err := kubeClient.AppsV1().DaemonSets(namespace).Get(ctx, monov1alpha1.NodeAgentName, metav1.GetOptions{})
-	if apierrors.IsNotFound(err) {
-		_, err = kubeClient.AppsV1().DaemonSets(namespace).Create(ctx, want, metav1.CreateOptions{})
-		return err
-	}
-	if err != nil {
-		return err
-	}
-
-	changed := false
-	if !reflect.DeepEqual(existing.Labels, want.Labels) {
-		existing.Labels = want.Labels
-		changed = true
-	}
-	if !reflect.DeepEqual(existing.Spec, want.Spec) {
-		existing.Spec = want.Spec
-		changed = true
-	}
-
-	if !changed {
-		return nil
-	}
-
-	_, err = kubeClient.AppsV1().DaemonSets(namespace).Update(ctx, existing, metav1.UpdateOptions{})
-	return err
-}
-
-func hostPathType(t corev1.HostPathType) *corev1.HostPathType {
-	return &t
-}
-
-func mountPropagationMode(m corev1.MountPropagationMode) *corev1.MountPropagationMode {
-	return &m
-}

clitools/pkg/node/kubeadm.go

@@ -12,9 +12,6 @@ import (
 	"time"
 
 	"gopkg.in/yaml.v3"
-	"k8s.io/client-go/discovery"
-	"k8s.io/client-go/kubernetes"
-	"k8s.io/client-go/tools/clientcmd"
 	"k8s.io/klog/v2"
 
 	monov1alpha1 "example.com/monok8s/pkg/apis/monok8s/v1alpha1"
@@ -27,6 +24,16 @@ const (
 	tmpKubeadmInitConf    = "/tmp/kubeadm-init.yaml"
 )
 
+func chooseVersionKubeconfig(state *LocalClusterState) string {
+	if state.HasAdminKubeconfig {
+		return adminKubeconfigPath
+	}
+	if state.HasKubeletKubeconfig {
+		return kubeletKubeconfigPath
+	}
+	return ""
+}
+
 func DetectLocalClusterState(ctx context.Context, nctx *NodeContext) error {
 	_ = ctx
 
@@ -259,110 +266,6 @@ func waitForAPIViaKubeconfig(ctx context.Context, kubeconfigPath string, timeout
 	}
 }
 
-func getServerVersion(ctx context.Context, kubeconfigPath string) (string, error) {
-	restCfg, err := clientcmd.BuildConfigFromFlags("", kubeconfigPath)
-	if err != nil {
-		return "", fmt.Errorf("build kubeconfig %s: %w", kubeconfigPath, err)
-	}
-
-	// Keep this short. This is a probe, not a long-running client.
-	restCfg.Timeout = 5 * time.Second
-
-	clientset, err := kubernetes.NewForConfig(restCfg)
-	if err != nil {
-		return "", fmt.Errorf("create clientset: %w", err)
-	}
-
-	disc := clientset.Discovery()
-	return discoverServerVersion(ctx, disc)
-}
-
-func discoverServerVersion(ctx context.Context, disc discovery.DiscoveryInterface) (string, error) {
-	info, err := disc.ServerVersion()
-	if err != nil {
-		return "", err
-	}
-	if info == nil || strings.TrimSpace(info.GitVersion) == "" {
-		return "", errors.New("server version is empty")
-	}
-	return normalizeKubeVersion(info.GitVersion), nil
-}
-
-type kubeVersion struct {
-	Major int
-	Minor int
-	Patch int
-}
-
-func parseKubeVersion(s string) (kubeVersion, error) {
-	s = strings.TrimSpace(s)
-	s = strings.TrimPrefix(s, "v")
-
-	var v kubeVersion
-	n, err := fmt.Sscanf(s, "%d.%d.%d", &v.Major, &v.Minor, &v.Patch)
-	// Accepts "1.29" or "1.29.3"
-	if err != nil || n < 2 {
-		return kubeVersion{}, fmt.Errorf("invalid kubernetes version %q", s)
-	}
-	return v, nil
-}
-
-// Control-plane: keep this strict.
-// Accept same version, or a one-minor step where the node binary is newer than the current cluster.
-// That covers normal control-plane upgrade flow but blocks nonsense.
-func isSupportedControlPlaneSkew(clusterVersion, nodeVersion string) bool {
-	cv, err := parseKubeVersion(clusterVersion)
-	if err != nil {
-		return false
-	}
-	nv, err := parseKubeVersion(nodeVersion)
-	if err != nil {
-		return false
-	}
-
-	if cv.Major != nv.Major {
-		return false
-	}
-	if cv.Minor == nv.Minor {
-		return true
-	}
-	if nv.Minor == cv.Minor+1 {
-		return true
-	}
-	return false
-}
-
-// Worker: kubelet generally must not be newer than the apiserver.
-// Older kubelets are allowed within supported skew range.
-// Your requirement says unsupported worker skew should still proceed, so this
-// only classifies support status and must NOT be used to block this function.
-func isSupportedWorkerSkew(clusterVersion, nodeVersion string) bool {
-	cv, err := parseKubeVersion(clusterVersion)
-	if err != nil {
-		return false
-	}
-	nv, err := parseKubeVersion(nodeVersion)
-	if err != nil {
-		return false
-	}
-
-	if cv.Major != nv.Major {
-		return false
-	}
-
-	// kubelet newer than apiserver => unsupported
-	if nv.Minor > cv.Minor {
-		return false
-	}
-
-	// kubelet up to 3 minors older than apiserver => supported
-	if cv.Minor-nv.Minor <= 3 {
-		return true
-	}
-
-	return false
-}
-
 func ValidateRequiredImagesPresent(ctx context.Context, n *NodeContext) error {
 	if n.Config.Spec.SkipImageCheck {
 		klog.Infof("skipping image check (skipImageCheck=true)")
@@ -419,31 +322,6 @@ func checkImagePresent(ctx context.Context, n *NodeContext, image string) error
 	return nil
 }
 
-func chooseVersionKubeconfig(state *LocalClusterState) string {
-	if state.HasAdminKubeconfig {
-		return adminKubeconfigPath
-	}
-	if state.HasKubeletKubeconfig {
-		return kubeletKubeconfigPath
-	}
-	return ""
-}
-
-func versionEq(a, b string) bool {
-	return normalizeKubeVersion(a) == normalizeKubeVersion(b)
-}
-
-func normalizeKubeVersion(v string) string {
-	v = strings.TrimSpace(v)
-	if v == "" {
-		return ""
-	}
-	if !strings.HasPrefix(v, "v") {
-		v = "v" + v
-	}
-	return v
-}
-
 func buildNodeRegistration(spec monov1alpha1.MonoKSConfigSpec) NodeRegistrationOptions {
 	nodeName := strings.TrimSpace(spec.NodeName)
 	criSocket := strings.TrimSpace(spec.ContainerRuntimeEndpoint)
@@ -781,11 +659,6 @@ func RunKubeadmJoin(ctx context.Context, nctx *NodeContext) error {
 	return nil
 }
 
-func RunKubeadmUpgradeNode(context.Context, *NodeContext) error {
-	klog.Info("run_kubeadm_upgrade_node: TODO implement kubeadm upgrade node")
-	return nil
-}
-
 func ReconcileControlPlane(ctx context.Context, nctx *NodeContext) error {
 	if nctx.BootstrapState == nil {
 		return errors.New("BootstrapState is nil, call ClassifyBootstrapAction() first")

clitools/pkg/node/kubeadm_compat.go

@@ -0,0 +1,108 @@
+package node
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"strings"
+
+	"k8s.io/klog/v2"
+
+	"example.com/monok8s/pkg/system"
+)
+
+const kubeadmUpgradeNodeHostnameBugFixedIn = "v1.35.0"
+
+// COMPAT(kubeadm-upgrade-node-hostname)
+// Affects: Kubernetes/kubeadm < v1.35.0
+// Upstream: kubernetes/kubeadm#3244, kubernetes/kubernetes#134319
+// RemoveWhen: minimum supported Kubernetes version >= v1.35.0
+//
+// Affected kubeadm versions can derive the target Node name for
+// `kubeadm upgrade node` from the local OS hostname instead of the existing
+// kubeadm NodeRegistration / kubelet --hostname-override state.
+func needsKubeadmUpgradeNodeHostnameWorkaround(kubeadmVersion string) bool {
+	lt, err := versionLt(kubeadmVersion, kubeadmUpgradeNodeHostnameBugFixedIn)
+	if err != nil {
+		klog.Warningf(
+			"could not parse kubeadm version %q; enabling kubeadm upgrade node hostname workaround: %v",
+			kubeadmVersion,
+			err,
+		)
+		return true
+	}
+	return lt
+}
+
+// runWithTemporaryHostname works around kubernetes/kubeadm#3244, fixed by
+// kubernetes/kubernetes#134319 in Kubernetes v1.35.0.
+//
+// Affected kubeadm versions can derive the target Node name for
+// `kubeadm upgrade node` from the local OS hostname instead of the existing
+// kubeadm NodeRegistration / kubelet --hostname-override state. That breaks
+// valid setups where the machine hostname differs from the Kubernetes Node
+// name: kubeadm may authenticate as one node but try to get/patch another Node,
+// and the Node authorizer correctly rejects it.
+//
+// Keep this workaround scoped to affected kubeadm versions only. Set the
+// temporary hostname to the Kubernetes Node name, run kubeadm, then restore the
+// configured machine hostname immediately afterward.
+func runWithTemporaryHostname(ctx context.Context, nctx *NodeContext, fn func(context.Context) error) error {
+	if nctx == nil {
+		return errors.New("node context is nil")
+	}
+
+	temporaryHostname := strings.TrimSpace(nctx.Config.Spec.NodeName)
+	if temporaryHostname == "" {
+		return errors.New("temporary hostname is required")
+	}
+
+	originalHostname, err := os.Hostname()
+	if err != nil {
+		return fmt.Errorf("get current hostname: %w", err)
+	}
+
+	if originalHostname == temporaryHostname {
+		return fn(ctx)
+	}
+
+	restoreHostname := strings.TrimSpace(nctx.Config.Spec.Network.Hostname)
+	if restoreHostname == "" {
+		restoreHostname = originalHostname
+	}
+
+	klog.Warningf(
+		"temporarily changing hostname for kubeadm upgrade node: current=%q temporary=%q restore=%q",
+		originalHostname,
+		temporaryHostname,
+		restoreHostname,
+	)
+
+	if err := system.SetHostname(temporaryHostname); err != nil {
+		return fmt.Errorf("set temporary hostname to %q: %w", temporaryHostname, err)
+	}
+
+	defer func() {
+		if err := system.SetHostname(restoreHostname); err != nil {
+			klog.Errorf("failed to restore hostname to %q: %v", restoreHostname, err)
+		}
+	}()
+
+	return fn(ctx)
+}
+
+// COMPAT(kubeadm-upgrade-node-hostname)
+// RemoveWhen: minimum supported Kubernetes version >= v1.35.0
+func runKubeadmUpgradeNodeWithCompat(
+	ctx context.Context,
+	nctx *NodeContext,
+	kubeadmVersion string,
+	fn func(context.Context) error,
+) error {
+	if needsKubeadmUpgradeNodeHostnameWorkaround(kubeadmVersion) {
+		return runWithTemporaryHostname(ctx, nctx, fn)
+	}
+
+	return fn(ctx)
+}

clitools/pkg/node/kubeadm_upgrade.go

@@ -257,3 +257,102 @@ func describeHealthCheckFailure(ctx context.Context, kubeClient kubernetes.Inter
 
 	return nil
 }
+
+func RunKubeadmUpgradeNode(ctx context.Context, nctx *NodeContext) error {
+	if nctx == nil {
+		return errors.New("node context is nil")
+	}
+	if nctx.Config == nil {
+		return errors.New("node config is nil")
+	}
+	if nctx.LocalClusterState == nil {
+		return errors.New("LocalClusterState is nil. Please run earlier steps first")
+	}
+	if nctx.BootstrapState == nil {
+		return errors.New("BootstrapState is nil. Please run earlier steps first")
+	}
+
+	switch nctx.BootstrapState.Action {
+	case BootstrapActionUpgradeWorker:
+		// continue
+	default:
+		klog.V(4).Infof("RunKubeadmUpgradeNode skipped for action %q", nctx.BootstrapState.Action)
+		return nil
+	}
+
+	wantVersion := normalizeKubeVersion(strings.TrimSpace(nctx.Config.Spec.KubernetesVersion))
+	if wantVersion == "" {
+		return errors.New("spec.kubernetesVersion is required")
+	}
+
+	kubeconfigPath := chooseVersionKubeconfig(nctx.LocalClusterState)
+	if kubeconfigPath == "" {
+		return errors.New("no kubeconfig available for detecting cluster version")
+	}
+
+	clusterVersion := strings.TrimSpace(nctx.BootstrapState.DetectedClusterVersion)
+	if clusterVersion == "" {
+		var err error
+		clusterVersion, err = getServerVersion(ctx, kubeconfigPath)
+		if err != nil {
+			if nctx.BootstrapState.UnsupportedWorkerVersionSkew {
+				klog.Warningf(
+					"cluster version unavailable but worker skew was marked unsupported/permissive, continuing: reason=%s",
+					nctx.BootstrapState.VersionSkewReason,
+				)
+			} else {
+				return fmt.Errorf("get cluster version via %s: %w", kubeconfigPath, err)
+			}
+		}
+	}
+
+	if clusterVersion != "" && !isSupportedWorkerSkew(clusterVersion, wantVersion) {
+		klog.Warningf(
+			"unsupported worker version skew detected, continuing anyway: cluster=%s node=%s",
+			clusterVersion,
+			wantVersion,
+		)
+	}
+
+	klog.Infof(
+		"running kubeadm upgrade node: role=%s clusterVersion=%s nodeVersion=%s kubeconfig=%s",
+		strings.TrimSpace(nctx.Config.Spec.ClusterRole),
+		clusterVersion,
+		wantVersion,
+		kubeconfigPath,
+	)
+
+	args := []string{
+		"upgrade",
+		"node",
+		"--kubeconfig",
+		kubeconfigPath,
+	}
+
+	runKubeadm := func(ctx context.Context) error {
+		_, err := nctx.SystemRunner.RunWithOptions(
+			ctx,
+			"kubeadm",
+			args,
+			system.RunOptions{
+				Timeout: 10 * time.Minute,
+				OnStdoutLine: func(line string) {
+					klog.Infof("[kubeadm] %s", line)
+				},
+				OnStderrLine: func(line string) {
+					klog.Infof("[kubeadm] %s", line)
+				},
+			},
+		)
+		return err
+	}
+
+	// COMPAT(kubeadm-upgrade-node-hostname)
+	// RemoveWhen: minimum supported Kubernetes version >= v1.35.0
+	// Replace this wrapper with direct runKubeadm(ctx).
+	if err := runKubeadmUpgradeNodeWithCompat(ctx, nctx, wantVersion, runKubeadm); err != nil {
+		return fmt.Errorf("run kubeadm upgrade node: %w", err)
+	}
+
+	return nil
+}

clitools/pkg/node/prereqs.go

@@ -8,9 +8,18 @@ import (
 	"strings"
 	"time"
 
+	"k8s.io/client-go/discovery"
+	"k8s.io/client-go/kubernetes"
+	"k8s.io/client-go/tools/clientcmd"
 	"k8s.io/klog/v2"
 )
 
+type kubeVersion struct {
+	Major int
+	Minor int
+	Patch int
+}
+
 func ValidateNodeIPAndAPIServerReachability(ctx context.Context, nct *NodeContext) error {
 	requireLocalIP := func(wantedIP string) error {
 		wantedIP = strings.TrimSpace(wantedIP)
@@ -189,3 +198,136 @@ func CheckForVersionSkew(ctx context.Context, nctx *NodeContext) error {
 
 	return nil
 }
+
+func versionEq(a, b string) bool {
+	return normalizeKubeVersion(a) == normalizeKubeVersion(b)
+}
+
+func versionLt(a, b string) (bool, error) {
+	av, err := parseKubeVersion(a)
+	if err != nil {
+		return false, err
+	}
+
+	bv, err := parseKubeVersion(b)
+	if err != nil {
+		return false, err
+	}
+
+	if av.Major != bv.Major {
+		return av.Major < bv.Major, nil
+	}
+	if av.Minor != bv.Minor {
+		return av.Minor < bv.Minor, nil
+	}
+	return av.Patch < bv.Patch, nil
+}
+
+func normalizeKubeVersion(v string) string {
+	v = strings.TrimSpace(v)
+	if v == "" {
+		return ""
+	}
+	if !strings.HasPrefix(v, "v") {
+		v = "v" + v
+	}
+	return v
+}
+
+func parseKubeVersion(s string) (kubeVersion, error) {
+	s = strings.TrimSpace(s)
+	s = strings.TrimPrefix(s, "v")
+
+	var v kubeVersion
+	n, err := fmt.Sscanf(s, "%d.%d.%d", &v.Major, &v.Minor, &v.Patch)
+	// Accepts "1.29" or "1.29.3"
+	if err != nil || n < 2 {
+		return kubeVersion{}, fmt.Errorf("invalid kubernetes version %q", s)
+	}
+	return v, nil
+}
+
+// Control-plane: keep this strict.
+// Accept same version, or a one-minor step where the node binary is newer than the current cluster.
+// That covers normal control-plane upgrade flow but blocks nonsense.
+func isSupportedControlPlaneSkew(clusterVersion, nodeVersion string) bool {
+	cv, err := parseKubeVersion(clusterVersion)
+	if err != nil {
+		return false
+	}
+	nv, err := parseKubeVersion(nodeVersion)
+	if err != nil {
+		return false
+	}
+
+	if cv.Major != nv.Major {
+		return false
+	}
+	if cv.Minor == nv.Minor {
+		return true
+	}
+	if nv.Minor == cv.Minor+1 {
+		return true
+	}
+	return false
+}
+
+// Worker: kubelet generally must not be newer than the apiserver.
+// Older kubelets are allowed within supported skew range.
+// Your requirement says unsupported worker skew should still proceed, so this
+// only classifies support status and must NOT be used to block this function.
+func isSupportedWorkerSkew(clusterVersion, nodeVersion string) bool {
+	cv, err := parseKubeVersion(clusterVersion)
+	if err != nil {
+		return false
+	}
+	nv, err := parseKubeVersion(nodeVersion)
+	if err != nil {
+		return false
+	}
+
+	if cv.Major != nv.Major {
+		return false
+	}
+
+	// kubelet newer than apiserver => unsupported
+	if nv.Minor > cv.Minor {
+		return false
+	}
+
+	// kubelet up to 3 minors older than apiserver => supported
+	if cv.Minor-nv.Minor <= 3 {
+		return true
+	}
+
+	return false
+}
+
+func getServerVersion(ctx context.Context, kubeconfigPath string) (string, error) {
+	restCfg, err := clientcmd.BuildConfigFromFlags("", kubeconfigPath)
+	if err != nil {
+		return "", fmt.Errorf("build kubeconfig %s: %w", kubeconfigPath, err)
+	}
+
+	// Keep this short. This is a probe, not a long-running client.
+	restCfg.Timeout = 5 * time.Second
+
+	clientset, err := kubernetes.NewForConfig(restCfg)
+	if err != nil {
+		return "", fmt.Errorf("create clientset: %w", err)
+	}
+
+	disc := clientset.Discovery()
+	return discoverServerVersion(ctx, disc)
+}
+
+func discoverServerVersion(ctx context.Context, disc discovery.DiscoveryInterface) (string, error) {
+	info, err := disc.ServerVersion()
+	if err != nil {
+		return "", err
+	}
+	if info == nil || strings.TrimSpace(info.GitVersion) == "" {
+		return "", errors.New("server version is empty")
+	}
+	return normalizeKubeVersion(info.GitVersion), nil
+}

clitools/pkg/render/agent.go

@@ -0,0 +1,284 @@
+package render
+
+import (
+	"fmt"
+	"strings"
+
+	appsv1 "k8s.io/api/apps/v1"
+	corev1 "k8s.io/api/core/v1"
+	rbacv1 "k8s.io/api/rbac/v1"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/apimachinery/pkg/runtime"
+
+	monov1alpha1 "example.com/monok8s/pkg/apis/monok8s/v1alpha1"
+	buildinfo "example.com/monok8s/pkg/buildinfo"
+)
+
+type AgentConf struct {
+	Namespace        string
+	Image            string
+	ImagePullSecrets []string
+	Labels           map[string]string
+}
+
+func RenderAgentDaemonSets(conf AgentConf) (string, error) {
+	objs, err := buildAgentDaemonSetObjects(conf)
+	if err != nil {
+		return "", err
+	}
+
+	return renderObjects(objs)
+}
+
+func buildAgentDaemonSetObjects(conf AgentConf) ([]runtime.Object, error) {
+	if strings.TrimSpace(conf.Namespace) == "" {
+		return nil, fmt.Errorf("namespace is required")
+	}
+
+	conf.Labels = map[string]string{
+		"app.kubernetes.io/name":       monov1alpha1.NodeAgentName,
+		"app.kubernetes.io/component":  "agent",
+		"app.kubernetes.io/part-of":    "monok8s",
+		"app.kubernetes.io/managed-by": monov1alpha1.NodeControlName,
+	}
+
+	return []runtime.Object{
+		buildAgentServiceAccount(conf),
+		buildAgentClusterRole(conf),
+		buildAgentClusterRoleBinding(conf),
+		buildAgentDaemonSet(conf),
+	}, nil
+}
+
+func buildAgentNamespace(conf AgentConf) *corev1.Namespace {
+	return &corev1.Namespace{
+		TypeMeta: metav1.TypeMeta{
+			APIVersion: "v1",
+			Kind:       "Namespace",
+		},
+		ObjectMeta: metav1.ObjectMeta{
+			Name:   conf.Namespace,
+			Labels: copyStringMap(conf.Labels),
+		},
+	}
+}
+
+func buildAgentServiceAccount(conf AgentConf) *corev1.ServiceAccount {
+	return &corev1.ServiceAccount{
+		TypeMeta: metav1.TypeMeta{
+			APIVersion: "v1",
+			Kind:       "ServiceAccount",
+		},
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      monov1alpha1.NodeAgentName,
+			Namespace: conf.Namespace,
+			Labels:    copyStringMap(conf.Labels),
+		},
+	}
+}
+
+func buildAgentClusterRole(conf AgentConf) *rbacv1.ClusterRole {
+	wantRules := []rbacv1.PolicyRule{
+		{
+			APIGroups: []string{monov1alpha1.Group},
+			Resources: []string{"osupgrades"},
+			Verbs:     []string{"get"},
+		},
+		{
+			APIGroups: []string{monov1alpha1.Group},
+			Resources: []string{"osupgradeprogresses"},
+			Verbs:     []string{"get", "list", "watch", "create", "patch", "update"},
+		},
+		{
+			APIGroups: []string{monov1alpha1.Group},
+			Resources: []string{"osupgradeprogresses/status"},
+			Verbs:     []string{"get", "list", "watch", "create", "patch", "update"},
+		},
+		{
+			APIGroups: []string{""},
+			Resources: []string{"nodes"},
+			Verbs:     []string{"get", "list", "watch"},
+		},
+	}
+
+	return &rbacv1.ClusterRole{
+		TypeMeta: metav1.TypeMeta{
+			APIVersion: "rbac.authorization.k8s.io/v1",
+			Kind:       "ClusterRole",
+		},
+		ObjectMeta: metav1.ObjectMeta{
+			Name:   monov1alpha1.NodeAgentName,
+			Labels: copyStringMap(conf.Labels),
+		},
+		Rules: wantRules,
+	}
+}
+
+func buildAgentClusterRoleBinding(conf AgentConf) *rbacv1.ClusterRoleBinding {
+	return &rbacv1.ClusterRoleBinding{
+		TypeMeta: metav1.TypeMeta{
+			APIVersion: "rbac.authorization.k8s.io/v1",
+			Kind:       "ClusterRoleBinding",
+		},
+		ObjectMeta: metav1.ObjectMeta{
+			Name:   monov1alpha1.NodeAgentName,
+			Labels: copyStringMap(conf.Labels),
+		},
+		RoleRef: rbacv1.RoleRef{
+			APIGroup: rbacv1.GroupName,
+			Kind:     "ClusterRole",
+			Name:     monov1alpha1.NodeAgentName,
+		},
+		Subjects: []rbacv1.Subject{
+			{
+				Kind:      "ServiceAccount",
+				Name:      monov1alpha1.NodeAgentName,
+				Namespace: conf.Namespace,
+			},
+		},
+	}
+}
+
+func buildAgentDaemonSet(conf AgentConf) *appsv1.DaemonSet {
+	privileged := true
+	dsLabels := monov1alpha1.NodeAgentLabels()
+
+	image, pullPolicy := agentImage(conf)
+
+	return &appsv1.DaemonSet{
+		TypeMeta: metav1.TypeMeta{
+			APIVersion: "apps/v1",
+			Kind:       "DaemonSet",
+		},
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      monov1alpha1.NodeAgentName,
+			Namespace: conf.Namespace,
+			Labels:    copyStringMap(conf.Labels),
+		},
+		Spec: appsv1.DaemonSetSpec{
+			Selector: &metav1.LabelSelector{
+				MatchLabels: map[string]string{
+					"app.kubernetes.io/name": monov1alpha1.NodeAgentName,
+				},
+			},
+			Template: corev1.PodTemplateSpec{
+				ObjectMeta: metav1.ObjectMeta{
+					Labels: dsLabels,
+				},
+				Spec: corev1.PodSpec{
+					ServiceAccountName: monov1alpha1.NodeAgentName,
+					HostNetwork:        true,
+					HostPID:            true,
+					DNSPolicy:          corev1.DNSClusterFirstWithHostNet,
+					ImagePullSecrets:   imagePullSecrets(conf.ImagePullSecrets),
+					NodeSelector: map[string]string{
+						monov1alpha1.NodeControlKey: "true",
+					},
+					Tolerations: []corev1.Toleration{
+						{Operator: corev1.TolerationOpExists},
+					},
+					Containers: []corev1.Container{
+						{
+							Name:            "agent",
+							Image:           image,
+							ImagePullPolicy: pullPolicy,
+							Args:            []string{"agent", "--env-file", "$(CLUSTER_ENV_FILE)"},
+							Env: []corev1.EnvVar{
+								{
+									Name: "NODE_NAME",
+									ValueFrom: &corev1.EnvVarSource{
+										FieldRef: &corev1.ObjectFieldSelector{
+											APIVersion: "v1",
+											FieldPath:  "spec.nodeName",
+										},
+									},
+								},
+								{
+									Name:  "CLUSTER_ENV_FILE",
+									Value: "/host/opt/monok8s/config/cluster.env",
+								},
+								{
+									Name:  "FW_ENV_CONFIG_FILE",
+									Value: "/host/etc/fw_env.config",
+								},
+							},
+							SecurityContext: &corev1.SecurityContext{
+								Privileged: &privileged,
+							},
+							VolumeMounts: []corev1.VolumeMount{
+								{
+									Name:      "host-dev",
+									MountPath: "/dev",
+								},
+								{
+									Name:      "host-etc",
+									MountPath: "/host/etc",
+									ReadOnly:  true,
+								},
+								{
+									Name:      "host-config",
+									MountPath: "/host/opt/monok8s/config",
+									ReadOnly:  true,
+								},
+							},
+						},
+					},
+					Volumes: []corev1.Volume{
+						{
+							Name: "host-dev",
+							VolumeSource: corev1.VolumeSource{
+								HostPath: &corev1.HostPathVolumeSource{
+									Path: "/dev",
+									Type: hostPathType(corev1.HostPathDirectory),
+								},
+							},
+						},
+						{
+							Name: "host-etc",
+							VolumeSource: corev1.VolumeSource{
+								HostPath: &corev1.HostPathVolumeSource{
+									Path: "/etc",
+									Type: hostPathType(corev1.HostPathDirectory),
+								},
+							},
+						},
+						{
+							Name: "host-config",
+							VolumeSource: corev1.VolumeSource{
+								HostPath: &corev1.HostPathVolumeSource{
+									Path: "/opt/monok8s/config",
+									Type: hostPathType(corev1.HostPathDirectory),
+								},
+							},
+						},
+					},
+				},
+			},
+		},
+	}
+}
+
+func agentImage(conf AgentConf) (string, corev1.PullPolicy) {
+	if conf.Image != "" {
+		return conf.Image, corev1.PullIfNotPresent
+	}
+
+	return fmt.Sprintf("localhost/monok8s/node-control:%s", buildinfo.Version), corev1.PullNever
+}
+
+func copyStringMap(in map[string]string) map[string]string {
+	if len(in) == 0 {
+		return nil
+	}
+
+	out := make(map[string]string, len(in))
+	for k, v := range in {
+		out[k] = v
+	}
+
+	return out
+}
+
+func hostPathType(t corev1.HostPathType) *corev1.HostPathType {
+	return &t
+}

clitools/pkg/render/agent_apply.go

@@ -0,0 +1,203 @@
+package render
+
+import (
+	"context"
+	"fmt"
+	"reflect"
+
+	appsv1 "k8s.io/api/apps/v1"
+	corev1 "k8s.io/api/core/v1"
+	rbacv1 "k8s.io/api/rbac/v1"
+	apierrors "k8s.io/apimachinery/pkg/api/errors"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/apimachinery/pkg/runtime"
+	"k8s.io/client-go/kubernetes"
+)
+
+func ApplyAgentDaemonSets(ctx context.Context, kubeClient kubernetes.Interface, conf AgentConf) error {
+	objs, err := buildAgentDaemonSetObjects(conf)
+	if err != nil {
+		return err
+	}
+
+	if err := applyAgentNamespace(ctx, kubeClient, buildAgentNamespace(conf)); err != nil {
+		return fmt.Errorf("apply namespace: %w", err)
+	}
+
+	for _, obj := range objs {
+		if err := applyAgentObject(ctx, kubeClient, obj); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+func applyAgentObject(ctx context.Context, kubeClient kubernetes.Interface, obj runtime.Object) error {
+	switch want := obj.(type) {
+	case *corev1.ServiceAccount:
+		return applyAgentServiceAccount(ctx, kubeClient, want)
+	case *rbacv1.ClusterRole:
+		return applyAgentClusterRole(ctx, kubeClient, want)
+	case *rbacv1.ClusterRoleBinding:
+		return applyAgentClusterRoleBinding(ctx, kubeClient, want)
+	case *appsv1.DaemonSet:
+		return applyAgentDaemonSet(ctx, kubeClient, want)
+	default:
+		return fmt.Errorf("unsupported agent object type %T", obj)
+	}
+}
+
+func applyAgentNamespace(ctx context.Context, kubeClient kubernetes.Interface, want *corev1.Namespace) error {
+	existing, err := kubeClient.CoreV1().Namespaces().Get(ctx, want.Name, metav1.GetOptions{})
+	if apierrors.IsNotFound(err) {
+		_, err = kubeClient.CoreV1().Namespaces().Create(ctx, want, metav1.CreateOptions{})
+		return err
+	}
+	if err != nil {
+		return err
+	}
+
+	labels, changed := mergeStringMapsInto(existing.Labels, want.Labels)
+	if !changed {
+		return nil
+	}
+
+	existing.Labels = labels
+	_, err = kubeClient.CoreV1().Namespaces().Update(ctx, existing, metav1.UpdateOptions{})
+	return err
+}
+
+func applyAgentServiceAccount(ctx context.Context, kubeClient kubernetes.Interface, want *corev1.ServiceAccount) error {
+	existing, err := kubeClient.CoreV1().ServiceAccounts(want.Namespace).Get(ctx, want.Name, metav1.GetOptions{})
+	if apierrors.IsNotFound(err) {
+		_, err = kubeClient.CoreV1().ServiceAccounts(want.Namespace).Create(ctx, want, metav1.CreateOptions{})
+		return err
+	}
+	if err != nil {
+		return err
+	}
+
+	changed := false
+	if !reflect.DeepEqual(existing.Labels, want.Labels) {
+		existing.Labels = want.Labels
+		changed = true
+	}
+
+	if !changed {
+		return nil
+	}
+
+	_, err = kubeClient.CoreV1().ServiceAccounts(want.Namespace).Update(ctx, existing, metav1.UpdateOptions{})
+	return err
+}
+
+func applyAgentClusterRole(ctx context.Context, kubeClient kubernetes.Interface, want *rbacv1.ClusterRole) error {
+	existing, err := kubeClient.RbacV1().ClusterRoles().Get(ctx, want.Name, metav1.GetOptions{})
+	if apierrors.IsNotFound(err) {
+		_, err = kubeClient.RbacV1().ClusterRoles().Create(ctx, want, metav1.CreateOptions{})
+		return err
+	}
+	if err != nil {
+		return err
+	}
+
+	changed := false
+	if !reflect.DeepEqual(existing.Labels, want.Labels) {
+		existing.Labels = want.Labels
+		changed = true
+	}
+	if !reflect.DeepEqual(existing.Rules, want.Rules) {
+		existing.Rules = want.Rules
+		changed = true
+	}
+
+	if !changed {
+		return nil
+	}
+
+	_, err = kubeClient.RbacV1().ClusterRoles().Update(ctx, existing, metav1.UpdateOptions{})
+	return err
+}
+
+func applyAgentClusterRoleBinding(ctx context.Context, kubeClient kubernetes.Interface, want *rbacv1.ClusterRoleBinding) error {
+	existing, err := kubeClient.RbacV1().ClusterRoleBindings().Get(ctx, want.Name, metav1.GetOptions{})
+	if apierrors.IsNotFound(err) {
+		_, err = kubeClient.RbacV1().ClusterRoleBindings().Create(ctx, want, metav1.CreateOptions{})
+		return err
+	}
+	if err != nil {
+		return err
+	}
+
+	// roleRef is immutable. If it differs, fail loudly instead of pretending we can patch it.
+	if !reflect.DeepEqual(existing.RoleRef, want.RoleRef) {
+		return fmt.Errorf("existing ClusterRoleBinding %q has different roleRef and must be recreated", want.Name)
+	}
+
+	changed := false
+	if !reflect.DeepEqual(existing.Labels, want.Labels) {
+		existing.Labels = want.Labels
+		changed = true
+	}
+	if !reflect.DeepEqual(existing.Subjects, want.Subjects) {
+		existing.Subjects = want.Subjects
+		changed = true
+	}
+
+	if !changed {
+		return nil
+	}
+
+	_, err = kubeClient.RbacV1().ClusterRoleBindings().Update(ctx, existing, metav1.UpdateOptions{})
+	return err
+}
+
+func applyAgentDaemonSet(ctx context.Context, kubeClient kubernetes.Interface, want *appsv1.DaemonSet) error {
+	existing, err := kubeClient.AppsV1().DaemonSets(want.Namespace).Get(ctx, want.Name, metav1.GetOptions{})
+	if apierrors.IsNotFound(err) {
+		_, err = kubeClient.AppsV1().DaemonSets(want.Namespace).Create(ctx, want, metav1.CreateOptions{})
+		return err
+	}
+	if err != nil {
+		return err
+	}
+
+	changed := false
+	if !reflect.DeepEqual(existing.Labels, want.Labels) {
+		existing.Labels = want.Labels
+		changed = true
+	}
+	if !reflect.DeepEqual(existing.Spec, want.Spec) {
+		existing.Spec = want.Spec
+		changed = true
+	}
+
+	if !changed {
+		return nil
+	}
+
+	_, err = kubeClient.AppsV1().DaemonSets(want.Namespace).Update(ctx, existing, metav1.UpdateOptions{})
+	return err
+}
+
+func mergeStringMapsInto(dst map[string]string, src map[string]string) (map[string]string, bool) {
+	if len(src) == 0 {
+		return dst, false
+	}
+
+	changed := false
+	if dst == nil {
+		dst = map[string]string{}
+		changed = true
+	}
+
+	for k, v := range src {
+		if dst[k] != v {
+			dst[k] = v
+			changed = true
+		}
+	}
+
+	return dst, changed
+}

clitools/pkg/render/controller.go

@@ -1,7 +1,6 @@
 package render
 
 import (
-	"bytes"
 	"fmt"
 
 	appsv1 "k8s.io/api/apps/v1"
@@ -9,7 +8,6 @@ import (
 	rbacv1 "k8s.io/api/rbac/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/runtime"
-	"k8s.io/apimachinery/pkg/runtime/serializer/json"
 	"k8s.io/apimachinery/pkg/util/intstr"
 
 	monov1alpha1 "example.com/monok8s/pkg/apis/monok8s/v1alpha1"
@@ -17,9 +15,10 @@ import (
 )
 
 type ControllerConf struct {
-	Namespace string
-	Image     string
-	Labels    map[string]string
+	Namespace        string
+	Image            string
+	ImagePullSecrets []string
+	Labels           map[string]string
 }
 
 func RenderControllerDeployments(conf ControllerConf) (string, error) {
@@ -41,27 +40,7 @@ func RenderControllerDeployments(conf ControllerConf) (string, error) {
 		buildControllerDeployment(conf),
 	}
 
-	s := runtime.NewScheme()
-	_ = corev1.AddToScheme(s)
-	_ = rbacv1.AddToScheme(s)
-	_ = appsv1.AddToScheme(s)
-
-	serializer := json.NewYAMLSerializer(json.DefaultMetaFactory, s, s)
-
-	var buf bytes.Buffer
-
-	for i, obj := range objs {
-		if i > 0 {
-			if _, err := fmt.Fprintln(&buf, "---"); err != nil {
-				return "", err
-			}
-		}
-		if err := serializer.Encode(obj, &buf); err != nil {
-			return "", err
-		}
-	}
-
-	return buf.String(), nil
+	return renderObjects(objs)
 }
 
 func buildControllerServiceAccount(conf ControllerConf) *corev1.ServiceAccount {
@@ -191,6 +170,7 @@ func buildControllerDeployment(conf ControllerConf) *appsv1.Deployment {
 				},
 				Spec: corev1.PodSpec{
 					ServiceAccountName: monov1alpha1.ControllerName,
+					ImagePullSecrets:   imagePullSecrets(conf.ImagePullSecrets),
 					Containers: []corev1.Container{
 						{
 							Name:            "controller",

clitools/pkg/render/helpers.go

@@ -0,0 +1,74 @@
+package render
+
+import (
+	"bytes"
+	"fmt"
+	"strings"
+
+	corev1 "k8s.io/api/core/v1"
+	"k8s.io/apimachinery/pkg/runtime"
+	"sigs.k8s.io/yaml"
+)
+
+func renderObjects(objs []runtime.Object) (string, error) {
+	var buf bytes.Buffer
+
+	for i, obj := range objs {
+		if i > 0 {
+			if _, err := fmt.Fprintln(&buf, "---"); err != nil {
+				return "", err
+			}
+		}
+
+		b, err := renderObjectYAML(obj)
+		if err != nil {
+			return "", err
+		}
+
+		if _, err := buf.Write(b); err != nil {
+			return "", err
+		}
+	}
+
+	return buf.String(), nil
+}
+
+func renderObjectYAML(obj runtime.Object) ([]byte, error) {
+	b, err := yaml.Marshal(obj)
+	if err != nil {
+		return nil, err
+	}
+
+	var m map[string]any
+	if err := yaml.Unmarshal(b, &m); err != nil {
+		return nil, err
+	}
+
+	delete(m, "status")
+
+	return yaml.Marshal(m)
+}
+
+func imagePullSecrets(names []string) []corev1.LocalObjectReference {
+	if len(names) == 0 {
+		return nil
+	}
+
+	refs := make([]corev1.LocalObjectReference, 0, len(names))
+	for _, name := range names {
+		name = strings.TrimSpace(name)
+		if name == "" {
+			continue
+		}
+
+		refs = append(refs, corev1.LocalObjectReference{
+			Name: name,
+		})
+	}
+
+	if len(refs) == 0 {
+		return nil
+	}
+
+	return refs
+}

clitools/pkg/render/sshd.go

@@ -1,16 +1,11 @@
 package render
 
 import (
-	"bytes"
-	"fmt"
-
 	appsv1 "k8s.io/api/apps/v1"
 	corev1 "k8s.io/api/core/v1"
-	rbacv1 "k8s.io/api/rbac/v1"
 	"k8s.io/apimachinery/pkg/api/resource"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/runtime"
-	"k8s.io/apimachinery/pkg/runtime/serializer/json"
 	"k8s.io/apimachinery/pkg/util/intstr"
 
 	monov1alpha1 "example.com/monok8s/pkg/apis/monok8s/v1alpha1"
@@ -39,27 +34,7 @@ func RenderSSHDDeployments(namespace, authKeys string) (string, error) {
 		buildSSHDDeployment(vals, namespace, labels),
 	}
 
-	s := runtime.NewScheme()
-	_ = corev1.AddToScheme(s)
-	_ = rbacv1.AddToScheme(s)
-	_ = appsv1.AddToScheme(s)
-
-	serializer := json.NewYAMLSerializer(json.DefaultMetaFactory, s, s)
-
-	var buf bytes.Buffer
-
-	for i, obj := range objs {
-		if i > 0 {
-			if _, err := fmt.Fprintln(&buf, "---"); err != nil {
-				return "", err
-			}
-		}
-		if err := serializer.Encode(obj, &buf); err != nil {
-			return "", err
-		}
-	}
-
-	return buf.String(), nil
+	return renderObjects(objs)
 }
 
 func buildSSHDConfigMap(

makefile

@@ -181,7 +181,7 @@ $(INITRAMFS): $(INITRAMFS_DEPS) $(DOWNLOAD_PACKAGES_STAMP) | $(OUT_DIR)
 	test -f $@
 
 $(CLITOOLS_BIN): $(CLITOOLS_SRCS)
-	$(MAKE) -C clitools build-agent
+	$(MAKE) -C clitools build-local VERSION="$(TAG)"
 
 vpp: $(BUILD_BASE_STAMP) $(VPP_TAR) $(DPDK_TAR) $(FMLIB_TAR) $(FMC_TAR) $(NXP_TAR)
 	@build_base_tag=$$(docker image inspect \