Added monitoring endpoint

Makefile

@@ -1,6 +1,8 @@
 
 # Image URL to use all building/pushing image targets
 IMG ?= ghcr.io/telekom/das-schiff-network-operator:latest
+# Sidecar image URL to use all building/pushing image targets
+SIDECAR_IMG ?= ghcr.io/telekom/frr-exporter:latest
 # ENVTEST_K8S_VERSION refers to the version of kubebuilder assets to be downloaded by envtest binary.
 ENVTEST_K8S_VERSION = 1.25
 
@@ -69,7 +71,7 @@ test: manifests generate fmt vet envtest ## Run tests.
 build: generate fmt vet ## Build manager binary.
 	go build -o bin/manager cmd/manager/main.go
 
-.PHONY: build
+.PHONY: sidecar-build
 sidecar-build: build
 	go build -o bin/frr-exporter cmd/frr-exporter/main.go
 
@@ -81,10 +83,19 @@ 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: docker-build-sidecar
+docker-build-sidecar: test ## Build docker image with the manager.
+	docker build -t ${SIDECAR_IMG} -f frr-exporter.Dockerfile .
+
 .PHONY: docker-push
 docker-push: ## Push docker image with the manager.
 	docker push ${IMG}
 
+.PHONY: docker-push-sidecar
+docker-push-sidecar: ## Push docker image with the manager.
+	docker push ${SIDECAR_IMG}
+
+
 ##@ Release
 
 RELEASE_DIR ?= out
@@ -108,13 +119,22 @@ endif
 install: manifests kustomize ## Install CRDs into the K8s cluster specified in ~/.kube/config.
 	$(KUSTOMIZE) build config/crd | kubectl apply -f -
 
+.PHONY: install-certs
+install-certs: manifests kustomize ## Install certs
+	$(KUSTOMIZE) build config/certmanager | kubectl apply -f -
+
 .PHONY: uninstall
 uninstall: manifests kustomize ## Uninstall CRDs from the K8s cluster specified in ~/.kube/config. Call with ignore-not-found=true to ignore resource not found errors during deletion.
 	$(KUSTOMIZE) build config/crd | kubectl delete --ignore-not-found=$(ignore-not-found) -f -
 
+.PHONY: uninstall-certs
+uninstall-certs: manifests kustomize ## Uninstall certs
+	$(KUSTOMIZE) build config/certmanager | kubectl delete --ignore-not-found=$(ignore-not-found) -f -
+
 .PHONY: deploy
 deploy: manifests kustomize ## Deploy controller to the K8s cluster specified in ~/.kube/config.
 	cd config/manager && $(KUSTOMIZE) edit set image controller=${IMG}
+	cd config/manager && $(KUSTOMIZE) edit set image frr-exporter=${SIDECAR_IMG}
 	$(KUSTOMIZE) build config/default | kubectl apply -f -
 
 .PHONY: undeploy

cmd/frr-exporter/main.go

@@ -10,15 +10,21 @@ import (
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/client_golang/prometheus/collectors"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
+	"github.com/telekom/das-schiff-network-operator/pkg/frr"
 	"github.com/telekom/das-schiff-network-operator/pkg/monitoring"
 	ctrl "sigs.k8s.io/controller-runtime"
+	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/log/zap"
 )
 
 const (
 	twenty = 20
 )
 
+var (
+	setupLog = ctrl.Log.WithName("setup")
+)
+
 func main() {
 	var addr string
 	flag.StringVar(&addr, "listen-address", ":7082", "The address to listen on for HTTP requests.")
@@ -29,6 +35,42 @@ func main() {
 	flag.Parse()
 	ctrl.SetLogger(zap.New(zap.UseFlagOptions(&opts)))
 
+	// Setup a new registry.
+	reg, err := setupPrometheusRegistry()
+	if err != nil {
+		log.Fatal(fmt.Errorf("prometheus registry setup error: %w", err))
+	}
+
+	setupLog.Info("configured Prometheus registry")
+
+	endpoint, err := setupMonitoringEndpoint()
+	if err != nil {
+		log.Fatal(fmt.Errorf("error configuring monitoring endpoint: %w", err))
+	}
+
+	setupLog.Info("configured monitoring endpoint")
+
+	// Expose the registered metrics and monitoring endpoint via HTTP.
+	mux := setupMux(reg, endpoint)
+
+	server := http.Server{
+		Addr:              addr,
+		ReadHeaderTimeout: twenty * time.Second,
+		ReadTimeout:       time.Minute,
+		Handler:           mux,
+	}
+
+	setupLog.Info("created server, starting...", "Addr", server.Addr,
+		"ReadHeaderTimeout", server.ReadHeaderTimeout, "ReadTimeout", server.ReadTimeout)
+
+	// Run server
+	err = server.ListenAndServe()
+	if err != nil {
+		log.Fatal(fmt.Errorf("failed to start server: %w", err))
+	}
+}
+
+func setupPrometheusRegistry() (*prometheus.Registry, error) {
 	// Create a new registry.
 	reg := prometheus.NewRegistry()
 
@@ -42,27 +84,40 @@ func main() {
 			"bpf":     false,
 		})
 	if err != nil {
-		log.Fatal(fmt.Errorf("failed to create collector %w", err))
+		return nil, fmt.Errorf("failed to create collector %w", err)
 	}
 	reg.MustRegister(collector)
 
-	// Expose the registered metrics via HTTP.
-	http.Handle("/metrics", promhttp.HandlerFor(
+	return reg, nil
+}
+
+func setupMux(reg *prometheus.Registry, e *monitoring.Endpoint) *http.ServeMux {
+	mux := e.CreateMux()
+	mux.Handle("/metrics", promhttp.HandlerFor(
 		reg,
 		promhttp.HandlerOpts{
 			// Opt into OpenMetrics to support exemplars.
 			EnableOpenMetrics: true,
 			Timeout:           time.Minute,
 		},
 	))
-	server := http.Server{
-		Addr:              addr,
-		ReadHeaderTimeout: twenty * time.Second,
-		ReadTimeout:       time.Minute,
+	return mux
+}
+
+func setupMonitoringEndpoint() (*monitoring.Endpoint, error) {
+	clientConfig := ctrl.GetConfigOrDie()
+	c, err := client.New(clientConfig, client.Options{})
+	if err != nil {
+		return nil, fmt.Errorf("error creating controller-runtime client: %w", err)
 	}
-	err = server.ListenAndServe()
-	// Run server
+
+	setupLog.Info("loaded kubernetes config")
+
+	svcName, svcNamespace, err := monitoring.GetStatusServiceConfig()
 	if err != nil {
-		log.Fatal(fmt.Errorf("failed to start server: %w", err))
+		return nil, fmt.Errorf("error getting status service info: %w", err)
 	}
+	setupLog.Info("loaded status service config")
+
+	return monitoring.NewEndpoint(c, frr.NewCli(), svcName, svcNamespace), nil
 }

config/manager/kustomization.yaml

@@ -1,6 +1,7 @@
 resources:
 - manager.yaml
 - manager_master.yaml
+- service.yaml
 # - namespace.yaml
 
 generatorOptions:

config/manager/manager.yaml

@@ -85,6 +85,12 @@ spec:
           valueFrom:
             fieldRef:
               fieldPath: spec.nodeName
+        - name: STATUS_SVC_NAME
+          value: network-operator-status
+        - name: STATUS_SVC_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         image: frr-exporter:latest
         name: frr-exporter
         securityContext:

config/manager/manager_master.yaml

@@ -87,6 +87,12 @@ spec:
           valueFrom:
             fieldRef:
               fieldPath: spec.nodeName
+        - name: STATUS_SVC_NAME
+          value: network-operator-status
+        - name: STATUS_SVC_NAMESPACE
+          valueFrom:
+            fieldRef:
+              fieldPath: metadata.namespace
         image: frr-exporter:latest
         name: frr-exporter
         securityContext:

config/manager/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: status
+  namespace: system
+spec:
+  type: ClusterIP
+  clusterIP: None
+  selector:
+    app.kubernetes.io/component: worker
+    app.kubernetes.io/name: network-operator
+  ports:
+    - protocol: TCP
+      port: 7083
+      targetPort: 7083

config/rbac/role.yaml

@@ -13,6 +13,18 @@ rules:
   - list
   - update
   - watch
+- apiGroups:
+  - ""
+  resources:
+  - pods
+  verbs:
+  - list
+- apiGroups:
+  - ""
+  resources:
+  - services
+  verbs:
+  - get
 - apiGroups:
   - network.schiff.telekom.de
   resources:

pkg/frr/cli.go

@@ -30,7 +30,7 @@ func getVRFInfo(vrf string) (name string, isMulti bool) {
 	return vrf, false
 }
 
-func (frr *Cli) executeWithJSON(args []string) []byte {
+func (frr *Cli) ExecuteWithJSON(args []string) []byte {
 	// Ensure JSON is always appended
 	args = append(args, "json")
 	return frr.execute(args)
@@ -51,7 +51,7 @@ func (frr *Cli) execute(args []string) []byte {
 
 func (frr *Cli) ShowEVPNVNIDetail() (EVPNVniDetail, error) {
 	evpnInfo := EVPNVniDetail{}
-	data := frr.executeWithJSON([]string{
+	data := frr.ExecuteWithJSON([]string{
 		"show",
 		"evpn",
 		"vni",
@@ -66,7 +66,7 @@ func (frr *Cli) ShowEVPNVNIDetail() (EVPNVniDetail, error) {
 
 func (frr *Cli) ShowBGPSummary(vrf string) (BGPVrfSummary, error) {
 	vrfName, multiVRF := getVRFInfo(vrf)
-	data := frr.executeWithJSON([]string{
+	data := frr.ExecuteWithJSON([]string{
 		"show",
 		"bgp",
 		"vrf",
@@ -93,7 +93,7 @@ func (frr *Cli) ShowBGPSummary(vrf string) (BGPVrfSummary, error) {
 
 func (frr *Cli) showVRFVnis() (VrfVni, error) {
 	vrfInfo := VrfVni{}
-	vrfVniData := frr.executeWithJSON([]string{
+	vrfVniData := frr.ExecuteWithJSON([]string{
 		"show",
 		"vrf",
 		"vni",
@@ -204,15 +204,15 @@ func (frr *Cli) ShowVRFs(vrfName string) (VrfVni, error) {
 }
 
 func (frr *Cli) getDualStackRouteSummaries(vrf string) (routeSummariesV4, routeSummariesV6 RouteSummaries, err error) {
-	dataV4 := frr.executeWithJSON([]string{
+	dataV4 := frr.ExecuteWithJSON([]string{
 		"show",
 		"ip",
 		"route",
 		"vrf",
 		vrf,
 		"summary",
 	})
-	dataV6 := frr.executeWithJSON([]string{
+	dataV6 := frr.ExecuteWithJSON([]string{
 		"show",
 		"ipv6",
 		"route",