Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type CollectionPolicyReconciler ¶
type CollectionPolicyReconciler struct {
client.Client
Scheme *runtime.Scheme
Log logr.Logger
KEDAClient *kedaclient.Clientset
K8sClient *kubernetes.Clientset
DynamicClient *dynamic.DynamicClient
MetadataClient metadata.Interface
DiscoveryClient *discovery.DiscoveryClient
DakrClient transport.DakrClient
ApiExtensions *apiextensionsclientset.Clientset
CollectionManager *collector.CollectionManager
MpaServer *server.MpaServer
Sender transport.DirectSender
TelemetrySender *transport.TelemetrySender
TelemetryMetrics *collector.TelemetryMetrics
TelemetryLogger telemetry_logger.Logger
ZapLogger *zap.Logger
IsRunning bool
CurrentPolicyHash string
CurrentConfig *PolicyConfig
RestartInProgress bool
MpaServerPort int
HealthManager *health.HealthManager
// contains filtered or unexported fields
}
CollectionPolicyReconciler reconciles a CollectionPolicy object
func (*CollectionPolicyReconciler) Reconcile ¶
func (r *CollectionPolicyReconciler) Reconcile( ctx context.Context, req ctrl.Request, ) (ctrl.Result, error)
Reconcile is part of the main kubernetes reconciliation loop which aims to move the current state of the cluster closer to the desired state.
func (*CollectionPolicyReconciler) SetupWithManager ¶
func (r *CollectionPolicyReconciler) SetupWithManager(mgr ctrl.Manager) error
SetupWithManager sets up the controller with the Manager.
type EnvBasedController ¶
type EnvBasedController struct {
client.Client
Scheme *runtime.Scheme
Log logr.Logger
K8sClient kubernetes.Interface
DynamicClient *dynamic.DynamicClient
DiscoveryClient *discovery.DiscoveryClient
ApiExtensions *apiextensionsclientset.Clientset
Reconciler *CollectionPolicyReconciler
// contains filtered or unexported fields
}
EnvBasedController is a controller that uses environment variables instead of CRDs
func NewEnvBasedController ¶
func NewEnvBasedController( mgr ctrl.Manager, healthManager *health.HealthManager, reconcileInterval time.Duration, mpaServerPort int, ) (*EnvBasedController, error)
NewEnvBasedController creates a new environment-based controller
func (*EnvBasedController) NeedLeaderElection ¶
func (c *EnvBasedController) NeedLeaderElection() bool
NeedLeaderElection implements the LeaderElectionRunnable interface
type GPURuntimeResolver ¶ added in v0.1.0
type GPURuntimeResolver struct {
// contains filtered or unexported fields
}
GPURuntimeResolver keeps the managed GPU DaemonSet's RuntimeClass in sync with the RuntimeClass API when the DaemonSet opts into auto mode.
func NewGPURuntimeResolver ¶ added in v0.1.0
func NewGPURuntimeResolver( c client.Client, apiReader client.Reader, namespace string, interval time.Duration, healthManager *health.HealthManager, ) *GPURuntimeResolver
NewGPURuntimeResolver builds the resolver. apiReader must be an uncached reader (mgr.GetAPIReader()): the RuntimeClass read is served by a direct GET, which the narrow get-on-resourceName RBAC allows. The manager's cached client would instead back the read with a cluster-wide LIST+WATCH informer, which the resolver's RBAC intentionally forbids, so a cached read blocks forever on a cache that can never sync. client is used for the DaemonSet patch (and its already-permitted cached read).
func (*GPURuntimeResolver) NeedLeaderElection ¶ added in v0.1.0
func (r *GPURuntimeResolver) NeedLeaderElection() bool
NeedLeaderElection makes the resolver run only on the elected manager.
func (*GPURuntimeResolver) ReconcileOnce ¶ added in v0.1.0
func (r *GPURuntimeResolver) ReconcileOnce(ctx context.Context) error
ReconcileOnce resolves and, when necessary, merge-patches the managed GPU DaemonSet. Conflicts retry the entire transaction so every attempt computes desired state from a fresh DaemonSet read.
type PolicyConfig ¶
type PolicyConfig struct {
TargetNamespaces []string
ExcludedNamespaces []string
ExcludedPods []collector.ExcludedPod
ExcludedDeployments []collector.ExcludedDeployment
ExcludedStatefulSets []collector.ExcludedStatefulSet
ExcludedDaemonSets []collector.ExcludedDaemonSet
ExcludedServices []collector.ExcludedService
ExcludedPVCs []collector.ExcludedPVC
ExcludedEvents []collector.ExcludedEvent
ExcludedJobs []collector.ExcludedJob
ExcludedCronJobs []collector.ExcludedCronJob
ExcludedReplicationControllers []collector.ExcludedReplicationController
ExcludedIngresses []collector.ExcludedIngress
ExcludedNetworkPolicies []collector.ExcludedNetworkPolicy
ExcludedEndpoints []collector.ExcludedEndpoint
ExcludedServiceAccounts []collector.ExcludedServiceAccount
ExcludedLimitRanges []collector.ExcludedLimitRange
ExcludedResourceQuotas []collector.ExcludedResourceQuota
ExcludedHPAs []collector.ExcludedHPA
ExcludedVPAs []collector.ExcludedVPA
ExcludedRoles []collector.ExcludedRole
ExcludedRoleBindings []collector.ExcludedRoleBinding
ExcludedClusterRoles []string
ExcludedClusterRoleBindings []string
ExcludedPDBs []collector.ExcludedPDB
ExcludedPSPs []string
ExcludedCRDs []string
ExcludedReplicaSet []collector.ExcludedReplicaSet
ExcludedStorageClasses []string
ExcludedPVs []string
ExcludedIngressClasses []string
ExcludedNodes []string
ExcludedCRDGroups []string
WatchedCRDs []string
ExcludedCSINodes []string
ExcludedDatadogReplicaSets []collector.ExcludedDatadogExtendedDaemonSetReplicaSet
ExcludedArgoRollouts []collector.ExcludedArgoRollout
ExcludedKedaScaledJobs []collector.ExcludedScaledJob
ExcludedKedaScaledObjects []collector.ExcludedScaledObject
ExcludedCSIDrivers []string
ExcludedCSIStorageCapacities []collector.ExcludedCSIStorageCapacity
ExcludedVolumeAttachments []string
ExcludedKubeflowNotebooks []collector.ExcludedKubeflowNotebook
ExcludedVolcanoJobs []collector.ExcludedVolcanoJob
ExcludedSparkApplications []collector.ExcludedSparkApplication
ExcludedScheduledSparkApplications []collector.ExcludedScheduledSparkApplication
ExcludedCNPGClusters []collector.ExcludedCNPGCluster
DisabledCollectors []string
// MigPartedConfigMapName/Namespace locate the NVIDIA mig-parted ConfigMap;
// empty values fall back to the GPU operator defaults.
MigPartedConfigMapName string
MigPartedConfigMapNamespace string
KubeContextName string
DakrURL string
ClusterToken string
DisableGPUMetrics bool
UpdateInterval time.Duration
NodeMetricsInterval time.Duration
ClusterSnapshotInterval time.Duration
BufferSize int
MaskSecretData bool
NumResourceProcessors int
NodeMetricsConcurrency int
NodemonRequestTimeout time.Duration
KubeletFallbackTimeout time.Duration
}
PolicyConfig holds the current configuration
Source Files