[OCTRL-1088] rename author and properly handling TaskController as a daemon set

Author: justonedev1

control-operator/Makefile

@@ -97,7 +97,7 @@ help: ## Display this help.
 ##@ Development
 
 .PHONY: manifests
-manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and CustomResourceDefinition objects.
+manifests: controller-gen generate-proto ## Generate WebhookConfiguration, ClusterRole and CustomResourceDefinition objects.
 	# Note that the option maxDescLen=0 was added in the default scaffold in order to sort out the issue
 	# Too long: must have at most 262144 bytes. By using kubectl apply to create / update resources an annotation
 	# is created by K8s API to store the latest version of the resource ( kubectl.kubernetes.io/last-applied-configuration).
@@ -220,8 +220,15 @@ deploy-environment: manifests kustomize ## Deploy environment controller to the
 	$(KUSTOMIZE) build config/environment | $(KUBECTL) apply -f - --server-side
 
 .PHONY: undeploy
-undeploy: ## Undeploy both controllers from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
-	$(KUSTOMIZE) build config/default | $(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -f -
+undeploy: undeploy-task undeploy-environment ## Undeploy both controllers from the K8s cluster specified in ~/.kube/config.
+
+.PHONY: undeploy-task
+undeploy-task: kustomize ## Undeploy task controller from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
+	$(KUSTOMIZE) build config/task | $(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -f -
+
+.PHONY: undeploy-environment
+undeploy-environment: kustomize ## Undeploy environment controller from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
+	$(KUSTOMIZE) build config/environment | $(KUBECTL) delete --ignore-not-found=$(ignore-not-found) -f -
 
 ##@ Build Dependencies
 

control-operator/README.md

@@ -8,6 +8,14 @@ In order to deploy Task and Environment workflows to the k8s cluster you need co
 controlling custom CRDs defining ALICE custom workload. This Folder defines and implements all moving parts together with Makefile
 to build, deploy, install CRDs and operators.
 
+## Architecture
+
+The operator is split into two separate binaries with different deployment strategies:
+
+**task-manager** runs as a DaemonSet — one pod per node. Each pod is responsible only for `Task` resources assigned to its node (matched via `spec.nodeName`). This is necessary because the task-manager communicates with OCC gRPC processes running locally on the same node via `hostNetwork`.
+
+**environment-manager** runs as a Deployment with a single replica per cluster. It is responsible for `Environment` resources which are cluster-scoped and not tied to a specific node.
+
 ## Getting Started
 
 You’ll need a Kubernetes cluster to run against. You can use [KIND](https://sigs.k8s.io/kind) to get a local cluster for testing, or run against a remote cluster. Author had the most success with K3s [see](/docs/kubernetes_ecs.md).
@@ -23,16 +31,16 @@ Following commands show basic use of Makefile. However this isn't exhaustive lis
 kubectl apply -f config/samples/
 ```
 
-1. Build and push your image to the location specified by `IMG`:
+1. Build and push your images. Default image tags are defined in the Makefile via `TASK_IMG` and `ENVIRONMENT_IMG`. Override them only if you want to use a different registry or tag:
 
 ```sh
-make docker-build docker-push IMG=<some-registry>/operator:tag
+make docker-build docker-push TASK_IMG=<some-registry>/task-manager:tag ENVIRONMENT_IMG=<some-registry>/environment-manager:tag
 ```
 
-1. Deploy the controller to the cluster with the image specified by `IMG`:
+1. Deploy the controllers to the cluster. Uses the same `TASK_IMG` and `ENVIRONMENT_IMG` defaults, override them if needed:
 
 ```sh
-make deploy IMG=<some-registry>/operator:tag
+make deploy TASK_IMG=<some-registry>/task-manager:tag ENVIRONMENT_IMG=<some-registry>/environment-manager:tag
 ```
 
 ### Uninstall CRDs
@@ -70,13 +78,19 @@ which provide a reconcile function responsible for synchronizing resources until
 make install
 ```
 
-1. Run your controller (this will run in the foreground, so switch to a new terminal if you want to leave it running):
+1. Run a controller (this will run in the foreground, so switch to a new terminal if you want to leave it running):
+
+```sh
+make run-environment
+```
+
+The task-manager requires a `NODE_NAME` environment variable to know which node it is responsible for. In-cluster this is injected automatically via the downward API. When running locally you must set it manually:
 
 ```sh
-make run
+NODE_NAME=<your-node-name> make run-task
 ```
 
-**NOTE:** You can also run this in one step by running: `make install run`
+**NOTE:** You can also install CRDs and run in one step: `make install run-environment` or `make install run-task`
 
 ### Modifying the API definitions
 

control-operator/api/v1alpha1/environment_types.go

@@ -1,8 +1,8 @@
 /*
  * === This file is part of ALICE O² ===
  *
- * Copyright 2024 CERN and copyright holders of ALICE O².
- * Author: Teo Mrnjavac <teo.mrnjavac@cern.ch>
+ * Copyright 2026 CERN and copyright holders of ALICE O².
+ * Author: Michal Tichak <michal.tichak@cern.ch>
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -66,6 +66,8 @@ type EnvironmentStatus struct {
 	// - "Progressing": the resource is being created or updated
 	// - "Degraded": the resource failed to reach or maintain its desired state
 	//
+	// TODO: use conditions properly during deployment
+	//
 	// The status of each condition is one of True, False, or Unknown.
 	// +listType=map
 	// +listMapKey=type

control-operator/api/v1alpha1/tasktemplate_types.go

@@ -1,8 +1,8 @@
 /*
  * === This file is part of ALICE O² ===
  *
- * Copyright 2024 CERN and copyright holders of ALICE O².
- * Author: Teo Mrnjavac <teo.mrnjavac@cern.ch>
+ * Copyright 2026 CERN and copyright holders of ALICE O².
+ * Author: Michal Tichak <michal.tichak@cern.ch>
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

control-operator/cmd/environment-manager/main.go

@@ -1,8 +1,8 @@
 /*
  * === This file is part of ALICE O² ===
  *
- * Copyright 2024 CERN and copyright holders of ALICE O².
- * Author: Teo Mrnjavac <teo.mrnjavac@cern.ch>
+ * Copyright 2026 CERN and copyright holders of ALICE O².
+ * Author: Michal Tichak <michal.tichak@cern.ch>
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

control-operator/cmd/main.go

@@ -1,8 +1,8 @@
 /*
  * === This file is part of ALICE O² ===
  *
- * Copyright 2024 CERN and copyright holders of ALICE O².
- * Author: Teo Mrnjavac <teo.mrnjavac@cern.ch>
+ * Copyright 2026 CERN and copyright holders of ALICE O².
+ * Author: Michal Tichak <michal.tichak@cern.ch>
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -26,6 +26,7 @@ package main
 
 import (
 	"flag"
+	"fmt"
 	"os"
 
 	"k8s.io/apimachinery/pkg/runtime"
@@ -82,10 +83,17 @@ func main() {
 		os.Exit(1)
 	}
 
+	nodeName := os.Getenv("NODE_NAME")
+	if nodeName == "" {
+		setupLog.Error(fmt.Errorf("NODE_NAME environment variable not set"), "NODE_NAME is required")
+		os.Exit(1)
+	}
+
 	if err = (&controller.TaskReconciler{
 		Client:   mgr.GetClient(),
 		Scheme:   mgr.GetScheme(),
 		Recorder: mgr.GetEventRecorderFor("task-controller"),
+		NodeName: nodeName,
 	}).SetupWithManager(mgr); err != nil {
 		setupLog.Error(err, "unable to create controller", "controller", "Task")
 		os.Exit(1)

control-operator/cmd/task-manager/main.go

@@ -31,9 +31,13 @@ spec:
         - command:
             - /manager
           args:
-            - --leader-elect
             - --health-probe-bind-address=:9082
             - --metrics-bind-address=:9083
+          env:
+            - name: NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
           image: task-manager:latest
           name: manager
           securityContext:

control-operator/config/manager/task-manager/task-manager.yaml

@@ -1,8 +1,8 @@
 /*
  * === This file is part of ALICE O² ===
  *
- * Copyright 2024 CERN and copyright holders of ALICE O².
- * Author: Teo Mrnjavac <teo.mrnjavac@cern.ch>
+ * Copyright 2026 CERN and copyright holders of ALICE O².
+ * Author: Michal Tichak <michal.tichak@cern.ch>
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by

control-operator/internal/controller/environment_controller.go

@@ -1,8 +1,8 @@
 /*
  * === This file is part of ALICE O² ===
  *
- * Copyright 2024 CERN and copyright holders of ALICE O².
- * Author: Teo Mrnjavac <teo.mrnjavac@cern.ch>
+ * Copyright 2026 CERN and copyright holders of ALICE O².
+ * Author: Michal Tichak <michal.tichak@cern.ch>
  *
  * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by