main.go

/*
Copyright 2023 Lawrence Livermore National Security, LLC
 (c.f. AUTHORS, NOTICE.LLNS, COPYING)

This is part of the Flux resource manager framework.
For details, see https://github.com/flux-framework.

SPDX-License-Identifier: Apache-2.0
*/

package main

import (
	"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/client-go/rest"

	"k8s.io/apimachinery/pkg/runtime"
	"k8s.io/apimachinery/pkg/runtime/schema"
	"k8s.io/apimachinery/pkg/runtime/serializer"
	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/client/apiutil"
	"sigs.k8s.io/controller-runtime/pkg/healthz"
	"sigs.k8s.io/controller-runtime/pkg/log/zap"

	api "github.com/converged-computing/slurm-operator/api/v1alpha1"
	controllers "github.com/converged-computing/slurm-operator/controllers/slurm"
	jobset "sigs.k8s.io/jobset/api/jobset/v1alpha2"
	//+kubebuilder:scaffold:imports
)

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

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

	utilruntime.Must(api.AddToScheme(scheme))
	utilruntime.Must(jobset.AddToScheme(scheme))

	//+kubebuilder:scaffold:scheme
}

func main() {
	var metricsAddr string
	var enableLeaderElection bool
	var probeAddr string
	flag.StringVar(&metricsAddr, "metrics-bind-address", ":8080", "The address the metric endpoint binds to.")
	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.")
	opts := zap.Options{
		Development: true,
	}
	opts.BindFlags(flag.CommandLine)
	flag.Parse()

	ctrl.SetLogger(zap.New(zap.UseFlagOptions(&opts)))
	mgr, err := ctrl.NewManager(ctrl.GetConfigOrDie(), ctrl.Options{
		Scheme:                 scheme,
		HealthProbeBindAddress: probeAddr,
		LeaderElection:         enableLeaderElection,
		LeaderElectionID:       "e113ebf9.flux-framework.org",
		// 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, "unable to start manager")
		os.Exit(1)
	}

	c, err := rest.HTTPClientFor(mgr.GetConfig())
	if err != nil {
		setupLog.Error(err, "unable to create REST HTTP client", "controller", c)
	}

	// Create a RESTful client for the MiniCluster controller. We need this to actually
	// interact with pods in the cluster!
	gvk := schema.GroupVersionKind{
		Group:   "",
		Version: "v1",
		Kind:    "Pod",
	}
	restClient, err := apiutil.RESTClientForGVK(gvk, false, mgr.GetConfig(), serializer.NewCodecFactory(mgr.GetScheme()), c)
	if err != nil {
		setupLog.Error(err, "unable to create REST client", "controller", restClient)
	}

	// Create the new reconciler
	if err = (&controllers.SlurmReconciler{
		Log:        ctrl.Log.WithName("slurm-reconciler"),
		Client:     mgr.GetClient(),
		Scheme:     mgr.GetScheme(),
		RESTConfig: mgr.GetConfig(),
		RESTClient: restClient,
	}).SetupWithManager(mgr); err != nil {
		setupLog.Error(err, "unable to create controller", "controller", "slurm")
		os.Exit(1)
	}
	//+kubebuilder:scaffold:builder

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

	setupLog.Info("starting manager")
	if err := mgr.Start(ctrl.SetupSignalHandler()); err != nil {
		setupLog.Error(err, "problem running manager")
		os.Exit(1)
	}
}