kubernetesrm

package
v0.38.0-rc8 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Nov 4, 2024 License: Apache-2.0 Imports: 77 Imported by: 0

Documentation

Index

Constants

View Source 
const (

	// ReleaseNamespaceEnvVar is the name of the environment variable within a pod running the
	// master service containing the namespace in which determined was deployed.
	ReleaseNamespaceEnvVar = "DET_RELEASE_NAMESPACE"
	// ResourceTypeNvidia describes the GPU resource type.
	ResourceTypeNvidia = "nvidia.com/gpu"
)

Variables

This section is empty.

Functions

This section is empty.

Types

type ResourceManager 

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

ResourceManager is a resource manager that manages k8s resources.

func New 

func New(
	db *db.PgDB,
	rmConfigs *config.ResourceManagerWithPoolsConfig,
	taskContainerDefaults *model.TaskContainerDefaultsConfig,
	opts *aproto.MasterSetAgentOptions,
	cert *tls.Certificate,
) (*ResourceManager, error)

New returns a new ResourceManager, which communicates with and submits work to a Kubernetes apiserver.

func (*ResourceManager) Allocate 

func (k *ResourceManager) Allocate(msg sproto.AllocateRequest) (*sproto.ResourcesSubscription, error)

Allocate implements rm.ResourceManager.

func (*ResourceManager) CreateNamespace 

func (k *ResourceManager) CreateNamespace(namespaceName string, clusterName string,
	fanout bool,
) error

CreateNamespace implements rm.ResourceManager.

func (*ResourceManager) DefaultNamespace 

func (k *ResourceManager) DefaultNamespace(clusterName string) (*string, error)

DefaultNamespace implements rm.ResourceManager.

func (ResourceManager) DeleteJob 

func (ResourceManager) DeleteJob(sproto.DeleteJob) (sproto.DeleteJobResponse, error)

DeleteJob implements rm.ResourceManager.

func (*ResourceManager) DeleteNamespace 

func (k *ResourceManager) DeleteNamespace(namespace string) error

DeleteNamespace implements rm.ResourceManager.

func (*ResourceManager) DisableAgent 

func (k *ResourceManager) DisableAgent(
	req *apiv1.DisableAgentRequest,
) (resp *apiv1.DisableAgentResponse, err error)

DisableAgent prevents scheduling on a node and has the option to kill running jobs.

func (ResourceManager) DisableSlot 

func (k ResourceManager) DisableSlot(
	req *apiv1.DisableSlotRequest,
) (resp *apiv1.DisableSlotResponse, err error)

DisableSlot implements 'det slot disable...' functionality.

func (*ResourceManager) EnableAgent 

func (k *ResourceManager) EnableAgent(
	req *apiv1.EnableAgentRequest,
) (resp *apiv1.EnableAgentResponse, err error)

EnableAgent allows scheduling on a node that has been disabled.

func (ResourceManager) EnableSlot 

func (k ResourceManager) EnableSlot(
	req *apiv1.EnableSlotRequest,
) (resp *apiv1.EnableSlotResponse, err error)

EnableSlot implements 'det slot enable...' functionality.

func (*ResourceManager) GetAgent 

func (k *ResourceManager) GetAgent(msg *apiv1.GetAgentRequest) (*apiv1.GetAgentResponse, error)

GetAgent implements rm.ResourceManager.

func (*ResourceManager) GetAgents 

func (k *ResourceManager) GetAgents() (*apiv1.GetAgentsResponse, error)

GetAgents implements rm.ResourceManager.

func (*ResourceManager) GetAllocationSummaries 

func (k *ResourceManager) GetAllocationSummaries() (map[model.AllocationID]sproto.AllocationSummary, error)

GetAllocationSummaries implements rm.ResourceManager.

func (*ResourceManager) GetDefaultAuxResourcePool 

func (k *ResourceManager) GetDefaultAuxResourcePool() (rm.ResourcePoolName, error)

GetDefaultAuxResourcePool implements rm.ResourceManager.

func (*ResourceManager) GetDefaultComputeResourcePool 

func (k *ResourceManager) GetDefaultComputeResourcePool() (rm.ResourcePoolName, error)

GetDefaultComputeResourcePool implements rm.ResourceManager.

func (ResourceManager) GetExternalJobs 

func (ResourceManager) GetExternalJobs(rm.ResourcePoolName) ([]*jobv1.Job, error)

GetExternalJobs implements rm.ResourceManager.

func (*ResourceManager) GetJobQ 

func (k *ResourceManager) GetJobQ(rpName rm.ResourcePoolName) (map[model.JobID]*sproto.RMJobInfo, error)

GetJobQ implements rm.ResourceManager.

func (*ResourceManager) GetJobQueueStatsRequest 

func (k *ResourceManager) GetJobQueueStatsRequest(
	msg *apiv1.GetJobQueueStatsRequest,
) (*apiv1.GetJobQueueStatsResponse, error)

GetJobQueueStatsRequest implements rm.ResourceManager.

func (*ResourceManager) GetNamespaceResourceQuota 

func (k *ResourceManager) GetNamespaceResourceQuota(namespaceName string, clusterName string) (*float64, error)

GetNamespaceResourceQuota gets the resource quota for the specified namespace.

func (*ResourceManager) GetResourcePools 

func (k *ResourceManager) GetResourcePools() (*apiv1.GetResourcePoolsResponse, error)

GetResourcePools implements rm.ResourceManager.

func (*ResourceManager) GetSlot 

func (k *ResourceManager) GetSlot(msg *apiv1.GetSlotRequest) (*apiv1.GetSlotResponse, error)

GetSlot implements rm.ResourceManager.

func (*ResourceManager) GetSlots 

func (k *ResourceManager) GetSlots(msg *apiv1.GetSlotsRequest) (*apiv1.GetSlotsResponse, error)

GetSlots implements rm.ResourceManager.

func (*ResourceManager) HealthCheck 

func (k *ResourceManager) HealthCheck() []model.ResourceManagerHealth

HealthCheck tries to call the KubeAPI.

func (ResourceManager) IsReattachableOnlyAfterStarted 

func (k ResourceManager) IsReattachableOnlyAfterStarted() bool

IsReattachableOnlyAfterStarted always returns false for the k8s resource manager.

func (ResourceManager) NotifyContainerRunning 

func (k ResourceManager) NotifyContainerRunning(
	msg sproto.NotifyContainerRunning,
) error

NotifyContainerRunning receives a notification from the container to let the master know that the container is running.

func (*ResourceManager) RecoverJobPosition 

func (k *ResourceManager) RecoverJobPosition(msg sproto.RecoverJobPosition)

RecoverJobPosition implements rm.ResourceManager.

func (*ResourceManager) Release 

func (k *ResourceManager) Release(msg sproto.ResourcesReleased)

Release implements rm.ResourceManager.

func (*ResourceManager) RemoveEmptyNamespace 

func (k *ResourceManager) RemoveEmptyNamespace(namespaceName string,
	clusterName string,
) error

RemoveEmptyNamespace removes a namespace from our interfaces in cluster if it is no longer used by any workspace.

func (ResourceManager) ResolveResourcePool 

func (k ResourceManager) ResolveResourcePool(
	name rm.ResourcePoolName,
	workspaceID int,
	slots int,
) (rm.ResourcePoolName, error)

ResolveResourcePool resolves the resource pool completely.

func (*ResourceManager) SetGroupMaxSlots 

func (k *ResourceManager) SetGroupMaxSlots(msg sproto.SetGroupMaxSlots)

SetGroupMaxSlots implements rm.ResourceManager.

func (*ResourceManager) SetGroupPriority 

func (k *ResourceManager) SetGroupPriority(msg sproto.SetGroupPriority) error

SetGroupPriority implements rm.ResourceManager.

func (*ResourceManager) SetGroupWeight 

func (k *ResourceManager) SetGroupWeight(msg sproto.SetGroupWeight) error

SetGroupWeight implements rm.ResourceManager.

func (*ResourceManager) SetResourceQuota 

func (k *ResourceManager) SetResourceQuota(quota int, namespace, clusterName string) error

SetResourceQuota implements rm.ResourceManager.

func (*ResourceManager) SmallerValueIsHigherPriority 

func (k *ResourceManager) SmallerValueIsHigherPriority() (bool, error)

SmallerValueIsHigherPriority returns true if smaller priority values indicate a higher priority level.

func (ResourceManager) TaskContainerDefaults 

func (k ResourceManager) TaskContainerDefaults(
	resourcePoolName rm.ResourcePoolName,
	defaultConfig model.TaskContainerDefaultsConfig,
) (model.TaskContainerDefaultsConfig, error)

TaskContainerDefaults returns TaskContainerDefaults for the specified pool.

func (ResourceManager) ValidateResourcePool 

func (k ResourceManager) ValidateResourcePool(name rm.ResourcePoolName) error

ValidateResourcePool validates that the named resource pool exists.

func (*ResourceManager) ValidateResources 

func (k *ResourceManager) ValidateResources(
	msg sproto.ValidateResourcesRequest,
) ([]command.LaunchWarning, error)

ValidateResources implements rm.ResourceManager.

func (*ResourceManager) VerifyNamespaceExists 

func (k *ResourceManager) VerifyNamespaceExists(namespaceName string, clusterName string) error

VerifyNamespaceExists implements rm.ResourceManager.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.