metrics

Documentation

Index

• Constants
• Variables
• func AdmissionAttempt(result AdmissionResult, duration time.Duration)
• func AdmittedWorkload(cqName kueue.ClusterQueueReference, waitTime time.Duration)
• func ClearCacheMetrics(cqName string)
• func ClearQueueSystemMetrics(cqName string)
• func Register()
• func ReportClusterQueueStatus(cqName string, cqStatus ClusterQueueStatus)
• func ReportPendingWorkloads(cqName string, active, inadmissible int)
• type AdmissionResult
• type ClusterQueueStatus

Constants

const (
	AdmissionResultSuccess      AdmissionResult = "success"
	AdmissionResultInadmissible AdmissionResult = "inadmissible"

	PendingStatusActive       = "active"
	PendingStatusInadmissible = "inadmissible"

	// CQStatusPending means the ClusterQueue is accepted but not yet active,
	// this can be because of a missing ResourceFlavor referenced by the ClusterQueue.
	// In this state, the ClusterQueue can't admit new workloads and its quota can't be borrowed
	// by other active ClusterQueues in the cohort.
	CQStatusPending ClusterQueueStatus = "pending"
	// CQStatusActive means the ClusterQueue can admit new workloads and its quota
	// can be borrowed by other ClusterQueues in the cohort.
	CQStatusActive ClusterQueueStatus = "active"
	// CQStatusTerminating means the clusterQueue is in pending deletion.
	CQStatusTerminating ClusterQueueStatus = "terminating"
)

Variables

var (
	CQStatuses = []ClusterQueueStatus{CQStatusPending, CQStatusActive, CQStatusTerminating}

	PendingWorkloads = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: constants.KueueName,
			Name:      "pending_workloads",
			Help: `The number of pending workloads, per 'cluster_queue' and 'status'.
'status' can have the following values:
- "active" means that the workloads are in the admission queue.
- "inadmissible" means there was a failed admission attempt for these workloads and they won't be retried until cluster conditions, which could make this workload admissible, change`,
		}, []string{"cluster_queue", "status"},
	)

	AdmittedWorkloadsTotal = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: constants.KueueName,
			Name:      "admitted_workloads_total",
			Help:      "The total number of admitted workloads per 'cluster_queue'",
		}, []string{"cluster_queue"},
	)

	AdmittedActiveWorkloads = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: constants.KueueName,
			Name:      "admitted_active_workloads",
			Help:      "The number of admitted Workloads that are active (unsuspended and not finished), per 'cluster_queue'",
		}, []string{"cluster_queue"},
	)

	ClusterQueueByStatus = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: constants.KueueName,
			Name:      "cluster_queue_status",
			Help: `Reports 'cluster_queue' with its 'status' (with possible values 'pending', 'active' or 'terminated').
For a ClusterQueue, the metric only reports a value of 1 for one of the statuses.`,
		}, []string{"cluster_queue", "status"},
	)
)

Functions

func AdmissionAttempt

func AdmissionAttempt(result AdmissionResult, duration time.Duration)

func AdmittedWorkload

func AdmittedWorkload(cqName kueue.ClusterQueueReference, waitTime time.Duration)

func ClearCacheMetrics

func ClearCacheMetrics(cqName string)

func ClearQueueSystemMetrics

func ClearQueueSystemMetrics(cqName string)

func Register

func Register()

func ReportClusterQueueStatus

func ReportClusterQueueStatus(cqName string, cqStatus ClusterQueueStatus)

func ReportPendingWorkloads

func ReportPendingWorkloads(cqName string, active, inadmissible int)

Types

type AdmissionResult

type AdmissionResult string

type ClusterQueueStatus

type ClusterQueueStatus string