feat: add support for arm

.github/workflows/build-deploy.yaml

@@ -1,13 +1,42 @@
 name: build slurm-operator
 
 on:
-  pull_request: []
+  pull_request: {}
   push:
     branches:
     - main
   workflow_dispatch:
 
 jobs:
+  build-arm:
+    if: (github.event_name != 'pull_request')    
+    runs-on: ubuntu-latest
+    name: make and build arm
+    steps:
+    - name: Checkout Repository
+      uses: actions/checkout@v3
+    - uses: actions/setup-go@v3
+      with:
+        go-version: ^1.24
+    - name: GHCR Login
+      if: (github.event_name != 'pull_request')
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Add custom buildx ARM builder
+      if: (github.event_name != 'pull_request')
+      run: |
+       docker buildx create --name armbuilder
+       docker buildx use armbuilder
+       docker buildx inspect --bootstrap
+
+    - name: Deploy Container
+      if: (github.event_name != 'pull_request')
+      run: make arm-deploy
+
   build:
     runs-on: ubuntu-latest
     strategy:
@@ -21,7 +50,7 @@ jobs:
       uses: actions/checkout@v4
     - uses: actions/setup-go@v3
       with:
-        go-version: ^1.23
+        go-version: ^1.24
     - name: GHCR Login
       if: (github.event_name != 'pull_request')
       uses: docker/login-action@v2

.github/workflows/main.yaml

@@ -1,7 +1,7 @@
 name: test slurm-operator
 
 on:
-  pull_request: []
+  pull_request: {}
 
 jobs:
   formatting:
@@ -27,7 +27,7 @@ jobs:
     - name: Setup Go
       uses: actions/setup-go@v3
       with:
-        go-version: ^1.23
+        go-version: ^1.24
     - name: fmt check
       run: make fmt
 
@@ -60,7 +60,7 @@ jobs:
     - name: Setup Go
       uses: actions/setup-go@v3
       with:
-        go-version: ^1.23
+        go-version: ^1.24
 
     - name: Start minikube
       uses: medyagh/setup-minikube@697f2b7aaed5f70bf2a94ee21a4ec3dde7b12f92 # v0.0.9

.github/workflows/slurm-containers.yaml

@@ -1,13 +1,74 @@
 name: build slurm-containers
 
 on:
-  pull_request: []
+  pull_request: {}
   push:
     branches:
     - main
   workflow_dispatch:
 
 jobs:
+  build-arm-ubuntu:
+    env:
+      container: ghcr.io/converged-computing/slurm
+    runs-on: ubuntu-latest
+    name: build arm slurm ubuntu
+    steps:
+    - name: Checkout Repository
+      uses: actions/checkout@v3
+    - uses: actions/setup-go@v3
+      with:
+        go-version: ^1.24
+    - name: GHCR Login
+      if: (github.event_name != 'pull_request')
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Add custom buildx ARM builder
+      if: (github.event_name != 'pull_request')
+      run: |
+       docker buildx create --name armbuilder
+       docker buildx use armbuilder
+       docker buildx inspect --bootstrap
+
+    - name: Build and Deploy Container
+      if: (github.event_name != 'pull_request')
+      run: docker buildx build -f docker/Dockerfile.ubuntu --build-arg ARCH=arm64 --platform linux/arm64 --push -t ${{ env.container }}:ubuntu-arm ./docker
+
+  build-arm:
+    env:
+      container: ghcr.io/converged-computing/slurm
+    runs-on: ubuntu-latest
+    name: make and build arm
+    steps:
+    - name: Checkout Repository
+      uses: actions/checkout@v3
+    - uses: actions/setup-go@v3
+      with:
+        go-version: ^1.24
+    - name: GHCR Login
+      if: (github.event_name != 'pull_request')
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Add custom buildx ARM builder
+      if: (github.event_name != 'pull_request')
+      run: |
+       docker buildx create --name armbuilder
+       docker buildx use armbuilder
+       docker buildx inspect --bootstrap
+
+    - name: Build and Deploy Container
+      if: (github.event_name != 'pull_request')
+      run: docker buildx build -f docker/Dockerfile --build-arg ARCH=arm64 --platform linux/arm64 --push -t ${{ env.container }}:arm ./docker
+
+
   build:
     env:
       container: ghcr.io/converged-computing/slurm
@@ -27,6 +88,11 @@ jobs:
     - name: Build Container
       run: docker build -f docker/Dockerfile -t ${{ env.container }} ./docker
 
+    - name: Build Ubuntu Container
+      run: docker build -f docker/Dockerfile.ubuntu -t ${{ env.container }}:ubuntu ./docker
+
     - name: Deploy Container
       if: (github.event_name != 'pull_request')
-      run: docker push ${{ env.container }}
+      run: |
+        docker push ${{ env.container }}
+        docker push ${{ env.container }}:ubuntu

Dockerfile

@@ -1,5 +1,5 @@
 # Build the manager binary
-FROM golang:1.23 as builder
+FROM golang:1.24 AS builder
 ARG TARGETOS
 ARG TARGETARCH
 

Makefile

@@ -48,6 +48,7 @@ endif
 
 # Image URL to use all building/pushing image targets
 IMG ?= ghcr.io/converged-computing/slurm-operator:latest
+ARMIMG ?= ghcr.io/converged-computing/slurm-operator:arm
 
 # Testing image (for development mostly)
 DEVIMG ?= ghcr.io/converged-computing/slurm-operator:test
@@ -126,6 +127,17 @@ run: manifests generate fmt vet ## Run a controller from your host.
 docker-build: test ## Build docker image with the manager.
 	docker build -t ${IMG} .
 
+.PHONY: arm-build
+arm-build: test ## Build docker image with the manager.
+	docker buildx build ARCH=arm64 --platform linux/arm64 -t ${ARMIMG} .
+
+.PHONY: arm-deploy
+arm-deploy: manifests kustomize
+	docker buildx build --platform linux/arm64 --build-arg ARCH=arm64 --push -t ${ARMIMG} .
+	cd config/manager && $(KUSTOMIZE) edit set image controller=${ARMIMG}
+	$(KUSTOMIZE) build config/default > examples/dist/slurm-operator-arm.yaml
+
+
 .PHONY: docker-push
 docker-push: ## Push docker image with the manager.
 	docker push ${IMG}
@@ -206,6 +218,12 @@ test-deploy: manifests kustomize
 	$(KUSTOMIZE) build config/default > examples/dist/slurm-operator-dev.yaml
 	sed -i 's/        imagePullPolicy: IfNotPresent/        imagePullPolicy: Always/' examples/dist/slurm-operator-dev.yaml
 
+
+.PHONY: build-config-arm
+build-config-arm: manifests kustomize ## Deploy controller to the K8s cluster specified in ~/.kube/config.
+	cd config/manager && $(KUSTOMIZE) edit set image controller=${ARMIMG}
+	$(KUSTOMIZE) build config/default > examples/dist/slurm-operator-arm.yaml
+
 .PHONY: test-deploy-recreate
 test-deploy-recreate: test-deploy
 	kubectl delete -f ./examples/dist/slurm-operator-dev.yaml || echo "Already deleted"
@@ -217,7 +235,7 @@ list:
 
 ## Tool Versions
 KUSTOMIZE_VERSION ?= v3.8.7
-CONTROLLER_TOOLS_VERSION ?= v0.14.0
+CONTROLLER_TOOLS_VERSION ?= v0.19.0
 
 KUSTOMIZE_INSTALL_SCRIPT ?= "https://raw.githubusercontent.com/kubernetes-sigs/kustomize/master/hack/install_kustomize.sh"
 .PHONY: kustomize

api/v1alpha1/slurm_types.go

@@ -63,7 +63,7 @@ type SlurmSpec struct {
 	// +optional
 	SlurmVersion string `json:"slurmVersion,omitempty"`
 
-	// Size of the slurm (1 server + (N-1) nodes)
+	// Size is number of worker nodes
 	Size int32 `json:"size"`
 
 	// Interactive mode keeps the cluster running
@@ -168,6 +168,11 @@ type Node struct {
 	// +optional
 	WorkingDir string `json:"workingDir,omitempty"`
 
+	// Node specification. Leave empty for testing cluster
+	// This does not include hostlist (generated automatically)
+	// +optional
+	Nodespec string `json:"nodespec,omitempty"`
+
 	// PullAlways will always pull the container
 	// +optional
 	PullAlways bool `json:"pullAlways"`
@@ -225,8 +230,8 @@ func (s *Slurm) SelectorName() string {
 
 // Validate the slurm
 func (s *Slurm) Validate() bool {
-	if s.WorkerNodes() < 1 {
-		fmt.Printf("😥️ Slurm cluster must have at least one worker node, Size >= 2.\n")
+	if s.Spec.Size < 1 {
+		fmt.Printf("😥️ Slurm cluster must have 1 or more worker nodes.\n")
 		return false
 	}
 	// Ensure we have the default image set
@@ -238,6 +243,10 @@ func (s *Slurm) Validate() bool {
 		s.Spec.ClusterName = "linux"
 	}
 
+	// Default node spec
+	if s.Spec.Node.Nodespec == "" {
+		s.Spec.Node.Nodespec = "RealMemory=1000 CPUs=1 State=UNKNOWN"
+	}
 	// Along with a username and password
 	if s.Spec.Database.DatabaseName == "" {
 		s.Spec.Database.DatabaseName = "slurm_acct_db"
@@ -249,12 +258,6 @@ func (s *Slurm) Validate() bool {
 	return true
 }
 
-// WorkerNodes returns the number of worker nodes
-// At this point we've already validated size is >= 1
-func (s *Slurm) WorkerNodes() int32 {
-	return s.Spec.Size - 1
-}
-
 // WorkerNode returns the worker node (if defined) or falls back to the server
 func (s *Slurm) WorkerNode() Node {
 

config/crd/bases/flux-framework.org_slurms.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.14.0
+    controller-gen.kubebuilder.io/version: v0.19.0
   name: slurms.flux-framework.org
 spec:
   group: flux-framework.org
@@ -65,6 +65,11 @@ spec:
                     default: ghcr.io/converged-computing/slurm
                     description: Image to use for slurm
                     type: string
+                  nodespec:
+                    description: |-
+                      Node specification. Leave empty for testing cluster
+                      This does not include hostlist (generated automatically)
+                    type: string
                   ports:
                     description: |-
                       Ports to be exposed to other containers in the cluster
@@ -188,6 +193,11 @@ spec:
                     default: ghcr.io/converged-computing/slurm
                     description: Image to use for slurm
                     type: string
+                  nodespec:
+                    description: |-
+                      Node specification. Leave empty for testing cluster
+                      This does not include hostlist (generated automatically)
+                    type: string
                   ports:
                     description: |-
                       Ports to be exposed to other containers in the cluster
@@ -234,7 +244,7 @@ spec:
                 description: Resources include limits and requests
                 type: object
               size:
-                description: Size of the slurm (1 server + (N-1) nodes)
+                description: Size is number of worker nodes
                 format: int32
                 type: integer
               slurmVersion:
@@ -266,6 +276,11 @@ spec:
                     default: ghcr.io/converged-computing/slurm
                     description: Image to use for slurm
                     type: string
+                  nodespec:
+                    description: |-
+                      Node specification. Leave empty for testing cluster
+                      This does not include hostlist (generated automatically)
+                    type: string
                   ports:
                     description: |-
                       Ports to be exposed to other containers in the cluster

config/default/kustomization.yaml

@@ -12,7 +12,7 @@ namePrefix: slurm-operator-
 #commonLabels:
 #  someName: someValue
 
-bases:
+resources:
 - ../crd
 - ../rbac
 - ../manager
@@ -28,9 +28,8 @@ patchesStrategicMerge:
 # Protect the /metrics endpoint by putting it behind auth.
 # If you want your controller-manager to expose the /metrics
 # endpoint w/o any authn/z, please comment the following line.
-- manager_auth_proxy_patch.yaml
-
-
+# we have removed this because the image is deprecated 3/2026
+# - manager_auth_proxy_patch.yaml
 
 # [WEBHOOK] To enable webhook, uncomment all the sections with [WEBHOOK] prefix including the one in
 # crd/kustomization.yaml