mirror of
https://github.com/hanzo-ml/kuberay.git
synced 2026-10-30 19:48:47 +00:00
* [Feature] Add NetworkIsolation support to RayClusters Co-authored-by: Pat O'Connor <[email protected]> Co-authored-by: Bryan Keane <[email protected]> * add feature gate reg to integration tests + removed redundant if err Signed-off-by: Pat O'Connor <[email protected]> * separate function for head and base ingress rules Signed-off-by: Pat O'Connor <[email protected]> * logger updates as per review Signed-off-by: Pat O'Connor <[email protected]> * adjust DNS egress rule to allow all port 53 egress Signed-off-by: Pat O'Connor <[email protected]> * resolve helm chart CI failure Signed-off-by: Pat O'Connor <[email protected]> * restrict KubeRay rule via NamespaceSelector Signed-off-by: Pat O'Connor <[email protected]> * check if update is necessary on NP via DeepEqual Signed-off-by: Pat O'Connor <[email protected]> * prevent same-name NP mod + add namespace fallback to default Signed-off-by: Pat O'Connor <[email protected]> * add missing rayStartParams ports to custom ports example Signed-off-by: Pat O'Connor <[email protected]> * emit warning when existing NP conflicts with new one via name + fix test Signed-off-by: Pat O'Connor <[email protected]> * remove redundant samples + add new samples Signed-off-by: Pat O'Connor <[email protected]> * remove permissive pod selector rule + test updates Signed-off-by: Pat O'Connor <[email protected]> * prop labels to jobsubmitter for networkpolicy rule Signed-off-by: Pat O'Connor <[email protected]> * Add opt-in ALLOW_ALL_RAYJOB_SUBMITTERS env var for broad submitter ingress on standalone RayClusters Signed-off-by: Pat O'Connor <[email protected]> * updated API and config to fix CI failures Signed-off-by: Pat O'Connor <[email protected]> * Moved label prop to getSummitterTemplate + review changes Signed-off-by: Pat O'Connor <[email protected]> * Review feedback: failed deletion event + reconcile on dupe + nits Signed-off-by: Pat O'Connor <[email protected]> * use rayStartParams for ports + review nits Signed-off-by: Pat O'Connor <[email protected]> * test fix + convert constants to CamelCase Signed-off-by: Pat O'Connor <[email protected]> * helm updates + check if RayCluster is externally managed Signed-off-by: Pat O'Connor <[email protected]> * API updates per review + autoscaling egress rule Signed-off-by: Pat O'Connor <[email protected]> * Use standard lib for CIDR + use logConstructor consistently Signed-off-by: Pat O'Connor <[email protected]> * Use EndpointSlice IPs for API server egress rule Signed-off-by: Pat O'Connor <[email protected]> * Deduplicates ports + peers across EndpointSlices in egress rules Signed-off-by: Pat O'Connor <[email protected]> * Remove operator namespace fallback and prop error if namespace not found Signed-off-by: Pat O'Connor <[email protected]> * Remove patch verb for networkpolicies Signed-off-by: Pat O'Connor <[email protected]> * Remove client port rule for operator Signed-off-by: Pat O'Connor <[email protected]> * Add reconcileConcurrency and GenerationChangedPredicate to NetworkPolicy controller setup Signed-off-by: Pat O'Connor <[email protected]> * solve 3 points, close to merge Signed-off-by: Future-Outlier <[email protected]> * helper Signed-off-by: Future-Outlier <[email protected]> * update Signed-off-by: Future-Outlier <[email protected]> * CI failure fixes after DNS logic removal Signed-off-by: Pat O'Connor <[email protected]> * Revert "helper" This reverts commit 26c4053ae5775517f60a01cc4fb9457265d832c4. * Skip networkpolicy integration test when missing namespace Signed-off-by: Pat O'Connor <[email protected]> * Normalize defaulted NetworkPolicy ports before comparing Signed-off-by: Pat O'Connor <[email protected]> * Drop network policy integration tests pending followup e2e Signed-off-by: Pat O'Connor <[email protected]> * Remove operator namespace ingress rule Signed-off-by: Pat O'Connor <[email protected]> * networkpolicy: separate head/worker custom rules in API Replace the flat ingressRules/egressRules on NetworkIsolationConfig with per-role head/worker sub-structs.Since the API has not shipped yet, this avoids locking in a shared-only design that would require a backward-compatible migration later. Head and workers have fundamentally different security profiles — head needs external access (dashboard, submitter, Prometheus) while workers typically need outbound access (S3, model registries). A shared-only API forces users to over-permit workers just to allow access to the head. New API shape: networkIsolation: mode: DenyAll head: ingressRules: [...] egressRules: [...] worker: ingressRules: [...] egressRules: [...] Co-authored-by: Cursor <[email protected]> * NetworkIsolation API change cleanup Signed-off-by: Pat O'Connor <[email protected]> * Unit tests to ensure custom policies don't leak between head and worker Signed-off-by: Pat O'Connor <[email protected]> * Sample comment indendation and removal of operator rule from API docs Signed-off-by: Pat O'Connor <[email protected]> * Indent update to pass linter Signed-off-by: Pat O'Connor <[email protected]> * Additional review nits - comments etc Signed-off-by: Pat O'Connor <[email protected]> * Remove redundant comments in controller code Signed-off-by: Pat O'Connor <[email protected]> --------- Signed-off-by: Pat O'Connor <[email protected]> Signed-off-by: Future-Outlier <[email protected]> Co-authored-by: Laura Fitzgerald <[email protected]> Co-authored-by: Bryan Keane <[email protected]> Co-authored-by: Future-Outlier <[email protected]> Co-authored-by: Cursor <[email protected]>
385 lines
16 KiB
Go
385 lines
16 KiB
Go
package main
|
|
|
|
import (
|
|
"flag"
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
|
|
"github.com/go-logr/zapr"
|
|
routev1 "github.com/openshift/api/route/v1"
|
|
"go.uber.org/zap"
|
|
"go.uber.org/zap/zapcore"
|
|
"gopkg.in/natefinch/lumberjack.v2"
|
|
batchv1 "k8s.io/api/batch/v1"
|
|
"k8s.io/apimachinery/pkg/runtime"
|
|
"k8s.io/apimachinery/pkg/runtime/serializer"
|
|
utilruntime "k8s.io/apimachinery/pkg/util/runtime"
|
|
utilfeature "k8s.io/apiserver/pkg/util/feature"
|
|
clientgoscheme "k8s.io/client-go/kubernetes/scheme"
|
|
"k8s.io/klog/v2"
|
|
ctrl "sigs.k8s.io/controller-runtime"
|
|
"sigs.k8s.io/controller-runtime/pkg/cache"
|
|
"sigs.k8s.io/controller-runtime/pkg/healthz"
|
|
k8szap "sigs.k8s.io/controller-runtime/pkg/log/zap"
|
|
ctrlmetrics "sigs.k8s.io/controller-runtime/pkg/metrics"
|
|
metricsserver "sigs.k8s.io/controller-runtime/pkg/metrics/server"
|
|
gwv1 "sigs.k8s.io/gateway-api/apis/v1"
|
|
|
|
configapi "github.com/ray-project/kuberay/ray-operator/apis/config/v1alpha1"
|
|
rayv1 "github.com/ray-project/kuberay/ray-operator/apis/ray/v1"
|
|
"github.com/ray-project/kuberay/ray-operator/controllers/ray"
|
|
"github.com/ray-project/kuberay/ray-operator/controllers/ray/batchscheduler"
|
|
"github.com/ray-project/kuberay/ray-operator/controllers/ray/metrics"
|
|
"github.com/ray-project/kuberay/ray-operator/controllers/ray/utils"
|
|
"github.com/ray-project/kuberay/ray-operator/internal/managercache"
|
|
"github.com/ray-project/kuberay/ray-operator/pkg/features"
|
|
webhooks "github.com/ray-project/kuberay/ray-operator/pkg/webhooks/v1"
|
|
)
|
|
|
|
var (
|
|
scheme = runtime.NewScheme()
|
|
setupLog = ctrl.Log.WithName("setup")
|
|
userAgent = fmt.Sprintf("kuberay-operator/%s", utils.KUBERAY_VERSION)
|
|
)
|
|
|
|
func init() {
|
|
utilruntime.Must(clientgoscheme.AddToScheme(scheme))
|
|
utilruntime.Must(rayv1.AddToScheme(scheme))
|
|
utilruntime.Must(routev1.Install(scheme))
|
|
utilruntime.Must(batchv1.AddToScheme(scheme))
|
|
utilruntime.Must(configapi.AddToScheme(scheme))
|
|
// +kubebuilder:scaffold:scheme
|
|
}
|
|
|
|
func main() {
|
|
var metricsAddr string
|
|
var enableLeaderElection bool
|
|
var leaderElectionNamespace string
|
|
var probeAddr string
|
|
var reconcileConcurrency int
|
|
var watchNamespace string
|
|
var forcedClusterUpgrade bool
|
|
var logFile string
|
|
var logFileEncoder string
|
|
var logStdoutEncoder string
|
|
var useKubernetesProxy bool
|
|
var configFile string
|
|
var featureGates string
|
|
var enableBatchScheduler bool
|
|
var batchScheduler string
|
|
var enableMetrics bool
|
|
var qps float64
|
|
var burst int
|
|
|
|
// TODO: remove flag-based config once Configuration API graduates to v1.
|
|
flag.StringVar(&metricsAddr, "metrics-addr", configapi.DefaultMetricsAddr, "The address the metric endpoint binds to.")
|
|
flag.StringVar(&probeAddr, "health-probe-bind-address", configapi.DefaultProbeAddr, "The address the probe endpoint binds to.")
|
|
flag.BoolVar(&enableLeaderElection, "enable-leader-election", configapi.DefaultEnableLeaderElection,
|
|
"Enable leader election for controller manager. Enabling this will ensure there is only one active controller manager.")
|
|
flag.StringVar(&leaderElectionNamespace, "leader-election-namespace", "",
|
|
"Namespace where the leader election resource lives. Defaults to the pod namespace if not set.")
|
|
flag.IntVar(&reconcileConcurrency, "reconcile-concurrency", configapi.DefaultReconcileConcurrency, "max concurrency for reconciling")
|
|
flag.StringVar(
|
|
&watchNamespace,
|
|
"watch-namespace",
|
|
"",
|
|
"Specify a list of namespaces to watch for custom resources, separated by commas. If left empty, all namespaces will be watched.")
|
|
flag.BoolVar(&forcedClusterUpgrade, "forced-cluster-upgrade", false,
|
|
"(Deprecated) Forced cluster upgrade flag")
|
|
flag.StringVar(&logFile, "log-file-path", "",
|
|
"Synchronize logs to local file")
|
|
flag.StringVar(&logFileEncoder, "log-file-encoder", "json",
|
|
"Encoder to use for log file. Valid values are 'json' and 'console'. Defaults to 'json'")
|
|
flag.StringVar(&logStdoutEncoder, "log-stdout-encoder", "json",
|
|
"Encoder to use for logging stdout. Valid values are 'json' and 'console'. Defaults to 'json'")
|
|
flag.BoolVar(&enableBatchScheduler, "enable-batch-scheduler", false,
|
|
"(Deprecated) Enable batch scheduler. Currently is volcano, which supports gang scheduler policy. Please use --batch-scheduler instead.")
|
|
flag.StringVar(&batchScheduler, "batch-scheduler", "",
|
|
"Batch scheduler name, supported values are volcano, yunikorn, kai-scheduler.")
|
|
flag.StringVar(&configFile, "config", "", "Path to structured config file. Flags are ignored if config file is set.")
|
|
flag.BoolVar(&useKubernetesProxy, "use-kubernetes-proxy", false,
|
|
"Use Kubernetes proxy subresource when connecting to the Ray Head node.")
|
|
flag.StringVar(&featureGates, "feature-gates", "", "A set of key=value pairs that describe feature gates. E.g. FeatureOne=true,FeatureTwo=false,...")
|
|
flag.BoolVar(&enableMetrics, "enable-metrics", false, "Enable the emission of control plane metrics.")
|
|
flag.Float64Var(&qps, "qps", float64(configapi.DefaultQPS), "The QPS value for the client communicating with the Kubernetes API server.")
|
|
flag.IntVar(&burst, "burst", configapi.DefaultBurst, "The maximum burst for throttling requests from this client to the Kubernetes API server.")
|
|
|
|
opts := k8szap.Options{
|
|
TimeEncoder: zapcore.ISO8601TimeEncoder,
|
|
}
|
|
opts.BindFlags(flag.CommandLine)
|
|
flag.Parse()
|
|
|
|
var config configapi.Configuration
|
|
if configFile != "" {
|
|
var err error
|
|
configData, err := os.ReadFile(configFile)
|
|
exitOnError(err, "failed to read config file")
|
|
|
|
config, err = decodeConfig(configData, scheme)
|
|
exitOnError(err, "failed to decode config file")
|
|
} else {
|
|
config.MetricsAddr = metricsAddr
|
|
config.ProbeAddr = probeAddr
|
|
config.EnableLeaderElection = &enableLeaderElection
|
|
config.LeaderElectionNamespace = leaderElectionNamespace
|
|
config.ReconcileConcurrency = reconcileConcurrency
|
|
config.WatchNamespace = watchNamespace
|
|
config.LogFile = logFile
|
|
config.LogFileEncoder = logFileEncoder
|
|
config.LogStdoutEncoder = logStdoutEncoder
|
|
config.EnableBatchScheduler = enableBatchScheduler
|
|
config.BatchScheduler = batchScheduler
|
|
config.UseKubernetesProxy = useKubernetesProxy
|
|
config.DeleteRayJobAfterJobFinishes = os.Getenv(utils.DELETE_RAYJOB_CR_AFTER_JOB_FINISHES) == "true"
|
|
config.EnableMetrics = enableMetrics
|
|
config.QPS = &qps
|
|
config.Burst = &burst
|
|
}
|
|
|
|
stdoutEncoder, err := newLogEncoder(logStdoutEncoder)
|
|
exitOnError(err, "failed to create log encoder for stdout")
|
|
opts.Encoder = stdoutEncoder
|
|
|
|
if config.LogFile != "" {
|
|
fileWriter := &lumberjack.Logger{
|
|
Filename: config.LogFile,
|
|
MaxSize: 500, // megabytes
|
|
MaxBackups: 10, // files
|
|
MaxAge: 30, // days
|
|
}
|
|
|
|
fileEncoder, err := newLogEncoder(logFileEncoder)
|
|
exitOnError(err, "failed to create log encoder for file")
|
|
|
|
k8sLogger := k8szap.NewRaw(k8szap.UseFlagOptions(&opts))
|
|
zapOpts := append(opts.ZapOpts, zap.AddCallerSkip(1))
|
|
combineLogger := zap.New(zapcore.NewTee(
|
|
k8sLogger.Core(),
|
|
zapcore.NewCore(fileEncoder, zapcore.AddSync(fileWriter), zap.InfoLevel),
|
|
)).WithOptions(zapOpts...)
|
|
combineLoggerR := zapr.NewLogger(combineLogger)
|
|
|
|
ctrl.SetLogger(combineLoggerR)
|
|
|
|
// By default, the log from kubernetes/client-go is not json format.
|
|
// This will apply the logger to kubernetes/client-go and change it to json format.
|
|
klog.SetLogger(combineLoggerR)
|
|
} else {
|
|
k8sLogger := k8szap.New(k8szap.UseFlagOptions(&opts))
|
|
ctrl.SetLogger(k8sLogger)
|
|
|
|
// By default, the log from kubernetes/client-go is not json format.
|
|
// This will apply the logger to kubernetes/client-go and change it to json format.
|
|
klog.SetLogger(k8sLogger)
|
|
}
|
|
|
|
if forcedClusterUpgrade {
|
|
setupLog.Info("Deprecated feature flag forced-cluster-upgrade is enabled, which has no effect.")
|
|
}
|
|
|
|
// validate the batch scheduler configs,
|
|
// exit with error if the configs is invalid.
|
|
if err := configapi.ValidateBatchSchedulerConfig(setupLog, config); err != nil {
|
|
exitOnError(err, "batch scheduler configs validation failed")
|
|
}
|
|
|
|
if err := utilfeature.DefaultMutableFeatureGate.Set(featureGates); err != nil {
|
|
exitOnError(err, "Unable to set flag gates for known features")
|
|
}
|
|
features.LogFeatureGates(setupLog)
|
|
|
|
if features.Enabled(features.RayServiceIncrementalUpgrade) {
|
|
utilruntime.Must(gwv1.Install(scheme))
|
|
}
|
|
|
|
// Although ContainerRestartPolicy is introduced in Kubernetes v1.34 as an alpha feature, which requires
|
|
// manually enabling the ContainerRestartRules feature gate, it becomes beta in v1.35.
|
|
// We require v1.35+ to avoid asking users to opt in to a separate K8s feature gate.
|
|
// NOTE: this checks the API server version only. Please make sure worker nodes are also v1.35+,
|
|
// as kubelets are allowed to be up to 3 minor versions older per the Kubernetes version skew policy.
|
|
// If ContainerRestartRules is not enabled on a kubelet, the per-container restart policy on the
|
|
// submitter container will be ignored. In this scenario, if the submitter container exit on failure,
|
|
// a 30-second timeout will be applied by the operator and could incorrectly mark the RayJob as Failed
|
|
// even if the Ray job is still running.
|
|
if features.Enabled(features.SidecarSubmitterRestart) {
|
|
serverVersion, err := utils.GetKubernetesVersion()
|
|
if err != nil {
|
|
exitOnError(err, "SidecarSubmitterRestart feature gate enabled but unable to detect K8s version. Feature requires K8s 1.35+.")
|
|
}
|
|
isAtLeast, err := utils.IsK8sVersionAtLeast(serverVersion, 1, 35, 0)
|
|
if err != nil {
|
|
exitOnError(err, "Failed to compare K8s version.")
|
|
}
|
|
if !isAtLeast {
|
|
exitOnError(fmt.Errorf("current version %s is below 1.35", serverVersion.GitVersion),
|
|
"SidecarSubmitterRestart feature gate requires K8s 1.35+")
|
|
}
|
|
}
|
|
|
|
// Manager options
|
|
options := ctrl.Options{
|
|
Cache: cache.Options{
|
|
DefaultNamespaces: map[string]cache.Config{},
|
|
},
|
|
Scheme: scheme,
|
|
Metrics: metricsserver.Options{
|
|
BindAddress: config.MetricsAddr,
|
|
},
|
|
HealthProbeBindAddress: config.ProbeAddr,
|
|
LeaderElection: *config.EnableLeaderElection,
|
|
LeaderElectionID: "ray-operator-leader",
|
|
LeaderElectionNamespace: config.LeaderElectionNamespace,
|
|
}
|
|
|
|
// Manager Cache
|
|
// Set the informers label selectors to narrow the scope of the resources being watched and cached.
|
|
// This improves the scalability of the system, both for KubeRay itself by reducing the size of the
|
|
// informers cache, and for the API server / etcd, by reducing the number of watch events.
|
|
// For example, KubeRay is only interested in:
|
|
// - the batch Jobs it creates when reconciling RayJobs (app.kubernetes.io/created-by=kuberay-operator), and
|
|
// - Ray-managed Pods (ray.io/node-type in head|worker|redis-cleanup).
|
|
// These labels are provided to the manager cache as selectors for Job and Pod resources.
|
|
selectorsByObject, err := managercache.K8sControllerRuntimeCacheSelectors()
|
|
exitOnError(err, "unable to build manager cache ByObject")
|
|
options.Cache.ByObject = selectorsByObject
|
|
|
|
if watchNamespaces := strings.Split(config.WatchNamespace, ","); len(watchNamespaces) == 1 { // It is not possible for len(watchNamespaces) == 0 to be true. The length of `strings.Split("", ",")` is still 1.
|
|
if watchNamespaces[0] == "" {
|
|
setupLog.Info("Flag watchNamespace is not set. Watch custom resources in all namespaces.")
|
|
} else {
|
|
setupLog.Info("Only watch custom resources in the namespace.", "namespace", watchNamespaces[0])
|
|
options.Cache.DefaultNamespaces[watchNamespaces[0]] = cache.Config{}
|
|
}
|
|
} else {
|
|
setupLog.Info("Only watch custom resources in multiple namespaces.", "namespaces", watchNamespaces)
|
|
for _, namespace := range watchNamespaces {
|
|
options.Cache.DefaultNamespaces[namespace] = cache.Config{}
|
|
}
|
|
}
|
|
|
|
setupLog.Info("Setup manager")
|
|
restConfig := ctrl.GetConfigOrDie()
|
|
restConfig.UserAgent = userAgent
|
|
restConfig.QPS = float32(*config.QPS)
|
|
restConfig.Burst = *config.Burst
|
|
mgr, err := ctrl.NewManager(restConfig, options)
|
|
exitOnError(err, "unable to start manager")
|
|
|
|
ctx := ctrl.SetupSignalHandler()
|
|
|
|
var rayClusterMetricsManager *metrics.RayClusterMetricsManager
|
|
var rayJobMetricsManager *metrics.RayJobMetricsManager
|
|
var rayServiceMetricsManager *metrics.RayServiceMetricsManager
|
|
var batchSchedulerManager *batchscheduler.SchedulerManager
|
|
if config.EnableMetrics {
|
|
mgrClient := mgr.GetClient()
|
|
rayClusterMetricsManager = metrics.NewRayClusterMetricsManager(ctx, mgrClient)
|
|
rayJobMetricsManager = metrics.NewRayJobMetricsManager(ctx, mgrClient)
|
|
rayServiceMetricsManager = metrics.NewRayServiceMetricsManager(ctx, mgrClient)
|
|
ctrlmetrics.Registry.MustRegister(
|
|
rayClusterMetricsManager,
|
|
rayJobMetricsManager,
|
|
rayServiceMetricsManager,
|
|
)
|
|
}
|
|
|
|
batchSchedulerManager, err = batchscheduler.NewSchedulerManager(ctx, config, restConfig, mgr.GetClient())
|
|
exitOnError(err, "unable to create batch scheduler manager")
|
|
batchSchedulerManager.AddToScheme(mgr.GetScheme())
|
|
|
|
// TODO: Remove isOpenShift and related reconciler options once Gateway API support is mature
|
|
// and Route-based dashboard access is no longer needed.
|
|
// See: https://github.com/ray-project/kuberay/pull/4365#issuecomment-4143407845
|
|
isOpenShift, err := utils.IsOpenShiftCluster(restConfig)
|
|
exitOnError(err, "unable to detect cluster type (OpenShift vs Kubernetes)")
|
|
|
|
rayClusterOptions := ray.RayClusterReconcilerOptions{
|
|
HeadSidecarContainers: config.HeadSidecarContainers,
|
|
WorkerSidecarContainers: config.WorkerSidecarContainers,
|
|
IsOpenShift: isOpenShift,
|
|
UseIngressOnOpenShift: utils.ShouldUseIngressOnOpenShift(),
|
|
RayClusterMetricsManager: rayClusterMetricsManager,
|
|
BatchSchedulerManager: batchSchedulerManager,
|
|
DefaultContainerEnvs: config.DefaultContainerEnvs,
|
|
}
|
|
exitOnError(ray.NewReconciler(mgr, rayClusterOptions).SetupWithManager(mgr, config.ReconcileConcurrency),
|
|
"unable to create controller", "controller", "RayCluster")
|
|
|
|
exitOnError(ray.NewRayServiceReconciler(ctx, mgr, config).SetupWithManager(mgr, config.ReconcileConcurrency),
|
|
"unable to create controller", "controller", "RayService")
|
|
|
|
rayJobOptions := ray.RayJobReconcilerOptions{
|
|
RayJobMetricsManager: rayJobMetricsManager,
|
|
BatchSchedulerManager: batchSchedulerManager,
|
|
}
|
|
exitOnError(ray.NewRayJobReconciler(ctx, mgr, rayJobOptions, config).SetupWithManager(mgr, config.ReconcileConcurrency),
|
|
"unable to create controller", "controller", "RayJob")
|
|
|
|
if os.Getenv("ENABLE_WEBHOOKS") == "true" {
|
|
exitOnError(webhooks.SetupRayClusterWebhookWithManager(mgr),
|
|
"unable to create webhook", "webhook", "RayCluster")
|
|
}
|
|
|
|
if features.Enabled(features.RayCronJob) {
|
|
setupLog.Info("RayCronJob feature gate is enabled, starting RayCronJob controller")
|
|
exitOnError(ray.NewRayCronJobReconciler(mgr).SetupWithManager(mgr, config.ReconcileConcurrency),
|
|
"unable to create controller", "controller", "RayCronJob")
|
|
} else {
|
|
setupLog.Info("RayCronJob feature gate is disabled, skipping RayCronJob controller setup")
|
|
}
|
|
|
|
if features.Enabled(features.RayClusterNetworkIsolation) {
|
|
setupLog.Info("RayClusterNetworkIsolation feature gate is enabled, starting NetworkPolicy controller")
|
|
networkPolicyController, err := ray.NewNetworkPolicyController(mgr)
|
|
exitOnError(err, "unable to create controller", "controller", "NetworkPolicy")
|
|
exitOnError(networkPolicyController.SetupWithManager(mgr, config.ReconcileConcurrency),
|
|
"unable to setup controller", "controller", "NetworkPolicy")
|
|
} else {
|
|
setupLog.Info("RayClusterNetworkIsolation feature gate is disabled, skipping NetworkPolicy controller setup")
|
|
}
|
|
// +kubebuilder:scaffold:builder
|
|
|
|
exitOnError(mgr.AddHealthzCheck("healthz", healthz.Ping), "unable to set up health check")
|
|
exitOnError(mgr.AddReadyzCheck("readyz", healthz.Ping), "unable to set up ready check")
|
|
|
|
setupLog.Info("starting manager")
|
|
exitOnError(mgr.Start(ctx), "problem running manager")
|
|
}
|
|
|
|
func exitOnError(err error, msg string, keysAndValues ...any) {
|
|
if err != nil {
|
|
setupLog.Error(err, msg, keysAndValues...)
|
|
os.Exit(1)
|
|
}
|
|
}
|
|
|
|
// decodeConfig decodes raw config data and returns the Configuration type.
|
|
func decodeConfig(configData []byte, scheme *runtime.Scheme) (configapi.Configuration, error) {
|
|
cfg := configapi.Configuration{}
|
|
codecs := serializer.NewCodecFactory(scheme)
|
|
|
|
if err := runtime.DecodeInto(codecs.UniversalDecoder(), configData, &cfg); err != nil {
|
|
return cfg, err
|
|
}
|
|
|
|
scheme.Default(&cfg)
|
|
return cfg, nil
|
|
}
|
|
|
|
// newLogEncoder returns a zapcore.Encoder based on the encoder type ('json' or 'console')
|
|
func newLogEncoder(encoderType string) (zapcore.Encoder, error) {
|
|
pe := zap.NewProductionEncoderConfig()
|
|
pe.EncodeTime = zapcore.ISO8601TimeEncoder
|
|
|
|
if encoderType == "json" || encoderType == "" {
|
|
return zapcore.NewJSONEncoder(pe), nil
|
|
}
|
|
if encoderType == "console" {
|
|
return zapcore.NewConsoleEncoder(pe), nil
|
|
}
|
|
|
|
return nil, fmt.Errorf("invalid encoder %q (must be 'json' or 'console')", encoderType)
|
|
}
|