terdut-operator/cmd/main.go

package main

import (
	"crypto/tls"
	"flag"
	"os"

	// Import all Kubernetes client auth plugins (e.g. Azure, GCP, OIDC, etc.)
	// to ensure that exec-entrypoint and run can make use of them.
	_ "k8s.io/client-go/plugin/pkg/client/auth"

	"k8s.io/apimachinery/pkg/runtime"
	utilruntime "k8s.io/apimachinery/pkg/util/runtime"
	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
	ctrl "sigs.k8s.io/controller-runtime"
	"sigs.k8s.io/controller-runtime/pkg/healthz"
	"sigs.k8s.io/controller-runtime/pkg/log/zap"
	"sigs.k8s.io/controller-runtime/pkg/metrics/filters"
	metricsserver "sigs.k8s.io/controller-runtime/pkg/metrics/server"
	"sigs.k8s.io/controller-runtime/pkg/webhook"

	terdutv1alpha1 "git.ryuvia.com/niklas/terdut-operator/api/v1alpha1"
	"git.ryuvia.com/niklas/terdut-operator/internal/controller"
	// +kubebuilder:scaffold:imports
)

var (
	scheme   = runtime.NewScheme()
	setupLog = ctrl.Log.WithName("setup")
)

func init() {
	utilruntime.Must(clientgoscheme.AddToScheme(scheme))

	utilruntime.Must(terdutv1alpha1.AddToScheme(scheme))
	// +kubebuilder:scaffold:scheme
}

// nolint:gocyclo
func main() {
	var metricsAddr string
	var metricsCertPath, metricsCertName, metricsCertKey string
	var webhookCertPath, webhookCertName, webhookCertKey string
	var webhookPort int
	var enableLeaderElection bool
	var probeAddr string
	var secureMetrics bool
	var enableHTTP2 bool
	var tlsOpts []func(*tls.Config)
	flag.StringVar(&metricsAddr, "metrics-bind-address", "0", "The address the metrics endpoint binds to. "+
		"Use :8443 for HTTPS or :8080 for HTTP, or leave as 0 to disable the metrics service.")
	flag.StringVar(&probeAddr, "health-probe-bind-address", ":8081", "The address the probe endpoint binds to.")
	flag.BoolVar(&enableLeaderElection, "leader-elect", false,
		"Enable leader election for controller manager. "+
			"Enabling this will ensure there is only one active controller manager.")
	flag.BoolVar(&secureMetrics, "metrics-secure", true,
		"If set, the metrics endpoint is served securely via HTTPS. Use --metrics-secure=false to use HTTP instead.")
	flag.StringVar(&webhookCertPath, "webhook-cert-path", "", "The directory that contains the webhook certificate.")
	flag.StringVar(&webhookCertName, "webhook-cert-name", "tls.crt", "The name of the webhook certificate file.")
	flag.StringVar(&webhookCertKey, "webhook-cert-key", "tls.key", "The name of the webhook key file.")
	flag.IntVar(&webhookPort, "webhook-port", 9443, "Port the webhook server listens on. "+
		"Defaults to 9443. Set -1 to disable the webhook server.")
	flag.StringVar(&metricsCertPath, "metrics-cert-path", "",
		"The directory that contains the metrics server certificate.")
	flag.StringVar(&metricsCertName, "metrics-cert-name", "tls.crt", "The name of the metrics server certificate file.")
	flag.StringVar(&metricsCertKey, "metrics-cert-key", "tls.key", "The name of the metrics server key file.")
	flag.BoolVar(&enableHTTP2, "enable-http2", false,
		"If set, HTTP/2 will be enabled for the metrics and webhook servers")
	opts := zap.Options{
		Development: true,
	}
	opts.BindFlags(flag.CommandLine)
	flag.Parse()

	ctrl.SetLogger(zap.New(zap.UseFlagOptions(&opts)))

	// if the enable-http2 flag is false (the default), http/2 should be disabled
	// due to its vulnerabilities. More specifically, disabling http/2 will
	// prevent from being vulnerable to the HTTP/2 Stream Cancellation and
	// Rapid Reset CVEs. For more information see:
	// - https://github.com/advisories/GHSA-qppj-fm5r-hxr3
	// - https://github.com/advisories/GHSA-4374-p667-p6c8
	disableHTTP2 := func(c *tls.Config) {
		setupLog.Info("Disabling HTTP/2")
		c.NextProtos = []string{"http/1.1"}
	}

	if !enableHTTP2 {
		tlsOpts = append(tlsOpts, disableHTTP2)
	}

	// Initial webhook TLS options
	webhookTLSOpts := tlsOpts
	webhookServerOptions := webhook.Options{
		TLSOpts: webhookTLSOpts,
		Port:    webhookPort,
	}

	if len(webhookCertPath) > 0 {
		setupLog.Info("Initializing webhook certificate watcher using provided certificates",
			"webhook-cert-path", webhookCertPath, "webhook-cert-name", webhookCertName, "webhook-cert-key", webhookCertKey)

		webhookServerOptions.CertDir = webhookCertPath
		webhookServerOptions.CertName = webhookCertName
		webhookServerOptions.KeyName = webhookCertKey
	}

	webhookServer := webhook.NewServer(webhookServerOptions)

	// Metrics endpoint is enabled in 'config/default/kustomization.yaml'. The Metrics options configure the server.
	// More info:
	// - https://pkg.go.dev/sigs.k8s.io/controller-runtime@v0.25.0/pkg/metrics/server
	// - https://book.kubebuilder.io/reference/metrics.html
	metricsServerOptions := metricsserver.Options{
		BindAddress:   metricsAddr,
		SecureServing: secureMetrics,
		TLSOpts:       tlsOpts,
	}

	if secureMetrics {
		// FilterProvider is used to protect the metrics endpoint with authn/authz.
		// These configurations ensure that only authorized users and service accounts
		// can access the metrics endpoint. The RBAC are configured in 'config/rbac/kustomization.yaml'. More info:
		// https://pkg.go.dev/sigs.k8s.io/controller-runtime@v0.25.0/pkg/metrics/filters#WithAuthenticationAndAuthorization
		metricsServerOptions.FilterProvider = filters.WithAuthenticationAndAuthorization
	}

	// If the certificate is not specified, controller-runtime will automatically
	// generate self-signed certificates for the metrics server. While convenient for development and testing,
	// this setup is not recommended for production.
	//
	// TODO(user): If you enable certManager, uncomment the following lines:
	// - [METRICS-WITH-CERTS] at config/default/kustomization.yaml to generate and use certificates
	// managed by cert-manager for the metrics server.
	// - [PROMETHEUS-WITH-CERTS] at config/prometheus/kustomization.yaml for TLS certification.
	if len(metricsCertPath) > 0 {
		setupLog.Info("Initializing metrics certificate watcher using provided certificates",
			"metrics-cert-path", metricsCertPath, "metrics-cert-name", metricsCertName, "metrics-cert-key", metricsCertKey)

		metricsServerOptions.CertDir = metricsCertPath
		metricsServerOptions.CertName = metricsCertName
		metricsServerOptions.KeyName = metricsCertKey
	}

	mgr, err := ctrl.NewManager(ctrl.GetConfigOrDie(), ctrl.Options{
		Scheme:                 scheme,
		Metrics:                metricsServerOptions,
		WebhookServer:          webhookServer,
		HealthProbeBindAddress: probeAddr,
		LeaderElection:         enableLeaderElection,
		LeaderElectionID:       "455c08e3.ryuvia.com",
		// LeaderElectionReleaseOnCancel defines if the leader should step down voluntarily
		// when the Manager ends. This requires the binary to immediately end when the
		// Manager is stopped, otherwise, this setting is unsafe. Setting this significantly
		// speeds up voluntary leader transitions as the new leader don't have to wait
		// LeaseDuration time first.
		//
		// In the default scaffold provided, the program ends immediately after
		// the manager stops, so would be fine to enable this option. However,
		// if you are doing or is intended to do any operation such as perform cleanups
		// after the manager stops then its usage might be unsafe.
		// LeaderElectionReleaseOnCancel: true,
	})
	if err != nil {
		setupLog.Error(err, "Failed to start manager")
		os.Exit(1)
	}

	// POD_NAMESPACE is the operator's own namespace, via the Deployment's
	// downward API (config/manager/manager.yaml) — every credentials Secret
	// TerdutServerReconciler reads or writes lives here, never in a
	// TerdutServer's own namespace (DESIGN.md §6). Falling back to "default"
	// keeps `go run` usable for local development against a real cluster;
	// production always sets it.
	operatorNamespace := os.Getenv("POD_NAMESPACE")
	if operatorNamespace == "" {
		operatorNamespace = "default"
	}

	if err := (&controller.TerdutServerReconciler{
		Client:            mgr.GetClient(),
		Scheme:            mgr.GetScheme(),
		OperatorNamespace: operatorNamespace,
	}).SetupWithManager(mgr); err != nil {
		setupLog.Error(err, "Failed to create controller", "controller", "terdutserver")
		os.Exit(1)
	}
	if err := (&controller.TerdutTeamReconciler{
		Client:            mgr.GetClient(),
		Scheme:            mgr.GetScheme(),
		OperatorNamespace: operatorNamespace,
	}).SetupWithManager(mgr); err != nil {
		setupLog.Error(err, "Failed to create controller", "controller", "terdutteam")
		os.Exit(1)
	}
	if err := (&controller.TerdutEscalationRuleReconciler{
		Client:            mgr.GetClient(),
		Scheme:            mgr.GetScheme(),
		OperatorNamespace: operatorNamespace,
	}).SetupWithManager(mgr); err != nil {
		setupLog.Error(err, "Failed to create controller", "controller", "terdutescalationrule")
		os.Exit(1)
	}
	if err := (&controller.TerdutDeadmanSwitchReconciler{
		Client:            mgr.GetClient(),
		Scheme:            mgr.GetScheme(),
		OperatorNamespace: operatorNamespace,
	}).SetupWithManager(mgr); err != nil {
		setupLog.Error(err, "Failed to create controller", "controller", "terdutdeadmanswitch")
		os.Exit(1)
	}
	if err := (&controller.TerdutAlertSourceReconciler{
		Client:            mgr.GetClient(),
		Scheme:            mgr.GetScheme(),
		OperatorNamespace: operatorNamespace,
	}).SetupWithManager(mgr); err != nil {
		setupLog.Error(err, "Failed to create controller", "controller", "terdutalertsource")
		os.Exit(1)
	}
	// +kubebuilder:scaffold:builder

	if err := mgr.AddHealthzCheck("healthz", healthz.Ping); err != nil {
		setupLog.Error(err, "Failed to set up health check")
		os.Exit(1)
	}
	if err := mgr.AddReadyzCheck("readyz", healthz.Ping); err != nil {
		setupLog.Error(err, "Failed to set up ready check")
		os.Exit(1)
	}

	setupLog.Info("Starting manager")
	if err := mgr.Start(ctrl.SetupSignalHandler()); err != nil {
		setupLog.Error(err, "Failed to run manager")
		os.Exit(1)
	}
}