metrics

Documentation

Index

• Constants
• Variables
• func Register(containerCache kubecontainer.RuntimeCache, collectors ...prometheus.Collector)
• func SetActiveConfig(source *corev1.NodeConfigSource) error
• func SetAssignedConfig(source *corev1.NodeConfigSource) error
• func SetConfigError(err bool)
• func SetLastKnownGoodConfig(source *corev1.NodeConfigSource) error
• func SinceInMicroseconds(start time.Time) float64

Constants

const (
	KubeletSubsystem             = "kubelet"
	PodWorkerLatencyKey          = "pod_worker_latency_microseconds"
	PodStartLatencyKey           = "pod_start_latency_microseconds"
	CgroupManagerOperationsKey   = "cgroup_manager_latency_microseconds"
	PodWorkerStartLatencyKey     = "pod_worker_start_latency_microseconds"
	PLEGRelistLatencyKey         = "pleg_relist_latency_microseconds"
	PLEGRelistIntervalKey        = "pleg_relist_interval_microseconds"
	EvictionStatsAgeKey          = "eviction_stats_age_microseconds"
	VolumeStatsCapacityBytesKey  = "volume_stats_capacity_bytes"
	VolumeStatsAvailableBytesKey = "volume_stats_available_bytes"
	VolumeStatsUsedBytesKey      = "volume_stats_used_bytes"
	VolumeStatsInodesKey         = "volume_stats_inodes"
	VolumeStatsInodesFreeKey     = "volume_stats_inodes_free"
	VolumeStatsInodesUsedKey     = "volume_stats_inodes_used"
	// Metrics keys of remote runtime operations
	RuntimeOperationsKey        = "runtime_operations"
	RuntimeOperationsLatencyKey = "runtime_operations_latency_microseconds"
	RuntimeOperationsErrorsKey  = "runtime_operations_errors"
	// Metrics keys of device plugin operations
	DevicePluginRegistrationCountKey = "device_plugin_registration_count"
	DevicePluginAllocationLatencyKey = "device_plugin_alloc_latency_microseconds"

	// Metric keys for node config
	AssignedConfigKey             = "node_config_assigned"
	ActiveConfigKey               = "node_config_active"
	LastKnownGoodConfigKey        = "node_config_last_known_good"
	ConfigErrorKey                = "node_config_error"
	ConfigSourceLabelKey          = "node_config_source"
	ConfigSourceLabelValueLocal   = "local"
	ConfigUIDLabelKey             = "node_config_uid"
	ConfigResourceVersionLabelKey = "node_config_resource_version"
	KubeletConfigKeyLabelKey      = "node_config_kubelet_key"
)

Variables

var (
	ContainersPerPodCount = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      "containers_per_pod_count",
			Help:      "The number of containers per pod.",
		},
	)
	PodWorkerLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      PodWorkerLatencyKey,
			Help:      "Latency in microseconds to sync a single pod. Broken down by operation type: create, update, or sync",
		},
		[]string{"operation_type"},
	)
	PodStartLatency = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      PodStartLatencyKey,
			Help:      "Latency in microseconds for a single pod to go from pending to running. Broken down by podname.",
		},
	)
	CgroupManagerLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      CgroupManagerOperationsKey,
			Help:      "Latency in microseconds for cgroup manager operations. Broken down by method.",
		},
		[]string{"operation_type"},
	)
	PodWorkerStartLatency = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      PodWorkerStartLatencyKey,
			Help:      "Latency in microseconds from seeing a pod to starting a worker.",
		},
	)
	PLEGRelistLatency = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      PLEGRelistLatencyKey,
			Help:      "Latency in microseconds for relisting pods in PLEG.",
		},
	)
	PLEGRelistInterval = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      PLEGRelistIntervalKey,
			Help:      "Interval in microseconds between relisting in PLEG.",
		},
	)
	// Metrics of remote runtime operations.
	RuntimeOperations = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      RuntimeOperationsKey,
			Help:      "Cumulative number of runtime operations by operation type.",
		},
		[]string{"operation_type"},
	)
	RuntimeOperationsLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      RuntimeOperationsLatencyKey,
			Help:      "Latency in microseconds of runtime operations. Broken down by operation type.",
		},
		[]string{"operation_type"},
	)
	RuntimeOperationsErrors = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      RuntimeOperationsErrorsKey,
			Help:      "Cumulative number of runtime operation errors by operation type.",
		},
		[]string{"operation_type"},
	)
	EvictionStatsAge = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      EvictionStatsAgeKey,
			Help:      "Time between when stats are collected, and when pod is evicted based on those stats by eviction signal",
		},
		[]string{"eviction_signal"},
	)
	DevicePluginRegistrationCount = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      DevicePluginRegistrationCountKey,
			Help:      "Cumulative number of device plugin registrations. Broken down by resource name.",
		},
		[]string{"resource_name"},
	)
	DevicePluginAllocationLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DevicePluginAllocationLatencyKey,
			Help:      "Latency in microseconds to serve a device plugin Allocation request. Broken down by resource name.",
		},
		[]string{"resource_name"},
	)

	AssignedConfig = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: KubeletSubsystem,
			Name:      AssignedConfigKey,
			Help:      "The node's understanding of intended config. The count is always 1.",
		},
		[]string{ConfigSourceLabelKey, ConfigUIDLabelKey, ConfigResourceVersionLabelKey, KubeletConfigKeyLabelKey},
	)
	ActiveConfig = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: KubeletSubsystem,
			Name:      ActiveConfigKey,
			Help:      "The config source the node is actively using. The count is always 1.",
		},
		[]string{ConfigSourceLabelKey, ConfigUIDLabelKey, ConfigResourceVersionLabelKey, KubeletConfigKeyLabelKey},
	)
	LastKnownGoodConfig = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: KubeletSubsystem,
			Name:      LastKnownGoodConfigKey,
			Help:      "The config source the node will fall back to when it encounters certain errors. The count is always 1.",
		},
		[]string{ConfigSourceLabelKey, ConfigUIDLabelKey, ConfigResourceVersionLabelKey, KubeletConfigKeyLabelKey},
	)
	ConfigError = prometheus.NewGauge(
		prometheus.GaugeOpts{
			Subsystem: KubeletSubsystem,
			Name:      ConfigErrorKey,
			Help:      "This metric is true (1) if the node is experiencing a configuration-related error, false (0) otherwise.",
		},
	)
)

Functions

func Register

func Register(containerCache kubecontainer.RuntimeCache, collectors ...prometheus.Collector)

Register all metrics.

func SetActiveConfig

func SetActiveConfig(source *corev1.NodeConfigSource) error

func SetAssignedConfig

func SetAssignedConfig(source *corev1.NodeConfigSource) error

func SetConfigError

func SetConfigError(err bool)

func SetLastKnownGoodConfig

func SetLastKnownGoodConfig(source *corev1.NodeConfigSource) error

func SinceInMicroseconds

func SinceInMicroseconds(start time.Time) float64

Gets the time since the specified start in microseconds.