v1alpha1

Documentation

Index

• Constants
• func IsJobFinished(launcher *batchv1.Job) bool
• type MPIJobController
  • func NewMPIJobController(kubeClient kubernetes.Interface, kubeflowClient clientset.Interface, ...) *MPIJobController
  • func (c *MPIJobController) Run(threadiness int, stopCh <-chan struct{}) error

Constants

const (
	// SuccessSynced is used as part of the Event 'reason' when an MPIJob is
	// synced.
	SuccessSynced = "Synced"
	// ErrResourceExists is used as part of the Event 'reason' when an MPIJob
	// fails to sync due to dependent resources of the same name already
	// existing.
	ErrResourceExists = "ErrResourceExists"

	// MessageResourceExists is the message used for Events when a resource
	// fails to sync due to dependent resources already existing.
	MessageResourceExists = "Resource %q of Kind %q already exists and is not managed by MPIJob"
	// MessageResourceSynced is the message used for an Event fired when an
	// MPIJob is synced successfully.
	MessageResourceSynced = "MPIJob synced successfully"

	// LabelNodeRoleMaster specifies that a node is a master
	LabelNodeRoleMaster = "node-role.kubernetes.io/master"
)

Functions

func IsJobFinished

func IsJobFinished(launcher *batchv1.Job) bool

Types

type MPIJobController

type MPIJobController struct {
	// contains filtered or unexported fields
}

MPIJobController is the controller implementation for MPIJob resources.

func NewMPIJobController

func NewMPIJobController(
	kubeClient kubernetes.Interface,
	kubeflowClient clientset.Interface,
	configMapInformer coreinformers.ConfigMapInformer,
	serviceAccountInformer coreinformers.ServiceAccountInformer,
	roleInformer rbacinformers.RoleInformer,
	roleBindingInformer rbacinformers.RoleBindingInformer,
	statefulSetInformer appsinformers.StatefulSetInformer,
	jobInformer batchinformers.JobInformer,
	pdbInformer policyinformers.PodDisruptionBudgetInformer,
	mpiJobInformer informers.MPIJobInformer,
	gpusPerNode int,
	processingUnitsPerNode int,
	processingResourceType string,
	kubectlDeliveryImage string,
	enableGangScheduling bool) *MPIJobController

NewMPIJobController returns a new MPIJob controller.

func (*MPIJobController) Run

func (c *MPIJobController) Run(threadiness int, stopCh <-chan struct{}) error

Run will set up the event handlers for types we are interested in, as well as syncing informer caches and starting workers. It will block until stopCh is closed, at which point it will shutdown the work queue and wait for workers to finish processing their current work items.