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 SetNodeName(name types.NodeName)
• func SinceInMicroseconds(start time.Time) float64
• func SinceInSeconds(start time.Time) float64

Constants

const (
	KubeletSubsystem                     = "kubelet"
	NodeNameKey                          = "node_name"
	NodeLabelKey                         = "node"
	PodWorkerDurationKey                 = "pod_worker_duration_seconds"
	PodStartDurationKey                  = "pod_start_duration_seconds"
	CgroupManagerOperationsKey           = "cgroup_manager_duration_seconds"
	PodWorkerStartDurationKey            = "pod_worker_start_duration_seconds"
	PLEGRelistDurationKey                = "pleg_relist_duration_seconds"
	PLEGDiscardEventsKey                 = "pleg_discard_events"
	PLEGRelistIntervalKey                = "pleg_relist_interval_seconds"
	EvictionStatsAgeKey                  = "eviction_stats_age_seconds"
	DeprecatedPodWorkerLatencyKey        = "pod_worker_latency_microseconds"
	DeprecatedPodStartLatencyKey         = "pod_start_latency_microseconds"
	DeprecatedCgroupManagerOperationsKey = "cgroup_manager_latency_microseconds"
	DeprecatedPodWorkerStartLatencyKey   = "pod_worker_start_latency_microseconds"
	DeprecatedPLEGRelistLatencyKey       = "pleg_relist_latency_microseconds"
	DeprecatedPLEGRelistIntervalKey      = "pleg_relist_interval_microseconds"
	DeprecatedEvictionStatsAgeKey        = "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_total"
	RuntimeOperationsDurationKey          = "runtime_operations_duration_seconds"
	RuntimeOperationsErrorsKey            = "runtime_operations_errors_total"
	DeprecatedRuntimeOperationsKey        = "runtime_operations"
	DeprecatedRuntimeOperationsLatencyKey = "runtime_operations_latency_microseconds"
	DeprecatedRuntimeOperationsErrorsKey  = "runtime_operations_errors"
	// Metrics keys of device plugin operations
	DevicePluginRegistrationCountKey           = "device_plugin_registration_total"
	DevicePluginAllocationDurationKey          = "device_plugin_alloc_duration_seconds"
	DeprecatedDevicePluginRegistrationCountKey = "device_plugin_registration_count"
	DeprecatedDevicePluginAllocationLatencyKey = "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"

	// Metrics keys for RuntimeClass
	RunPodSandboxDurationKey = "run_podsandbox_duration_seconds"
	RunPodSandboxErrorsKey   = "run_podsandbox_errors_total"
)

Variables

var (
	NodeName = prometheus.NewGaugeVec(
		prometheus.GaugeOpts{
			Subsystem: KubeletSubsystem,
			Name:      NodeNameKey,
			Help:      "The node's name. The count is always 1.",
		},
		[]string{NodeLabelKey},
	)
	ContainersPerPodCount = prometheus.NewHistogram(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      "containers_per_pod_count",
			Help:      "The number of containers per pod.",
			Buckets:   prometheus.DefBuckets,
		},
	)
	PodWorkerDuration = prometheus.NewHistogramVec(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      PodWorkerDurationKey,
			Help:      "Duration in seconds to sync a single pod. Broken down by operation type: create, update, or sync",
			Buckets:   prometheus.DefBuckets,
		},
		[]string{"operation_type"},
	)
	PodStartDuration = prometheus.NewHistogram(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      PodStartDurationKey,
			Help:      "Duration in seconds for a single pod to go from pending to running.",
			Buckets:   prometheus.DefBuckets,
		},
	)
	CgroupManagerDuration = prometheus.NewHistogramVec(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      CgroupManagerOperationsKey,
			Help:      "Duration in seconds for cgroup manager operations. Broken down by method.",
			Buckets:   prometheus.DefBuckets,
		},
		[]string{"operation_type"},
	)
	PodWorkerStartDuration = prometheus.NewHistogram(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      PodWorkerStartDurationKey,
			Help:      "Duration in seconds from seeing a pod to starting a worker.",
			Buckets:   prometheus.DefBuckets,
		},
	)
	PLEGRelistDuration = prometheus.NewHistogram(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      PLEGRelistDurationKey,
			Help:      "Duration in seconds for relisting pods in PLEG.",
			Buckets:   prometheus.DefBuckets,
		},
	)
	PLEGDiscardEvents = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      PLEGDiscardEventsKey,
			Help:      "The number of discard events in PLEG.",
		},
		[]string{},
	)
	PLEGRelistInterval = prometheus.NewHistogram(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      PLEGRelistIntervalKey,
			Help:      "Interval in seconds between relisting in PLEG.",
			Buckets:   prometheus.DefBuckets,
		},
	)
	// 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"},
	)
	RuntimeOperationsDuration = prometheus.NewHistogramVec(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      RuntimeOperationsDurationKey,
			Help:      "Duration in seconds of runtime operations. Broken down by operation type.",
			Buckets:   prometheus.DefBuckets,
		},
		[]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.NewHistogramVec(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      EvictionStatsAgeKey,
			Help:      "Time between when stats are collected, and when pod is evicted based on those stats by eviction signal",
			Buckets:   prometheus.DefBuckets,
		},
		[]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"},
	)
	DevicePluginAllocationDuration = prometheus.NewHistogramVec(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      DevicePluginAllocationDurationKey,
			Help:      "Duration in seconds to serve a device plugin Allocation request. Broken down by resource name.",
			Buckets:   prometheus.DefBuckets,
		},
		[]string{"resource_name"},
	)

	DeprecatedPodWorkerLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedPodWorkerLatencyKey,
			Help:      "(Deprecated) Latency in microseconds to sync a single pod. Broken down by operation type: create, update, or sync",
		},
		[]string{"operation_type"},
	)
	DeprecatedPodStartLatency = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedPodStartLatencyKey,
			Help:      "(Deprecated) Latency in microseconds for a single pod to go from pending to running.",
		},
	)
	DeprecatedCgroupManagerLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedCgroupManagerOperationsKey,
			Help:      "(Deprecated) Latency in microseconds for cgroup manager operations. Broken down by method.",
		},
		[]string{"operation_type"},
	)
	DeprecatedPodWorkerStartLatency = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedPodWorkerStartLatencyKey,
			Help:      "(Deprecated) Latency in microseconds from seeing a pod to starting a worker.",
		},
	)
	DeprecatedPLEGRelistLatency = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedPLEGRelistLatencyKey,
			Help:      "(Deprecated) Latency in microseconds for relisting pods in PLEG.",
		},
	)
	DeprecatedPLEGRelistInterval = prometheus.NewSummary(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedPLEGRelistIntervalKey,
			Help:      "(Deprecated) Interval in microseconds between relisting in PLEG.",
		},
	)
	DeprecatedRuntimeOperations = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedRuntimeOperationsKey,
			Help:      "(Deprecated) Cumulative number of runtime operations by operation type.",
		},
		[]string{"operation_type"},
	)
	DeprecatedRuntimeOperationsLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedRuntimeOperationsLatencyKey,
			Help:      "(Deprecated) Latency in microseconds of runtime operations. Broken down by operation type.",
		},
		[]string{"operation_type"},
	)
	DeprecatedRuntimeOperationsErrors = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedRuntimeOperationsErrorsKey,
			Help:      "(Deprecated) Cumulative number of runtime operation errors by operation type.",
		},
		[]string{"operation_type"},
	)
	DeprecatedEvictionStatsAge = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedEvictionStatsAgeKey,
			Help:      "(Deprecated) Time between when stats are collected, and when pod is evicted based on those stats by eviction signal",
		},
		[]string{"eviction_signal"},
	)
	DeprecatedDevicePluginRegistrationCount = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedDevicePluginRegistrationCountKey,
			Help:      "(Deprecated) Cumulative number of device plugin registrations. Broken down by resource name.",
		},
		[]string{"resource_name"},
	)
	DeprecatedDevicePluginAllocationLatency = prometheus.NewSummaryVec(
		prometheus.SummaryOpts{
			Subsystem: KubeletSubsystem,
			Name:      DeprecatedDevicePluginAllocationLatencyKey,
			Help:      "(Deprecated) 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.",
		},
	)
	RunPodSandboxDuration = prometheus.NewHistogramVec(
		prometheus.HistogramOpts{
			Subsystem: KubeletSubsystem,
			Name:      RunPodSandboxDurationKey,
			Help:      "Duration in seconds of the run_podsandbox operations. Broken down by RuntimeClass.",

			Buckets: prometheus.DefBuckets,
		},
		[]string{"runtime_handler"},
	)
	RunPodSandboxErrors = prometheus.NewCounterVec(
		prometheus.CounterOpts{
			Subsystem: KubeletSubsystem,
			Name:      RunPodSandboxErrorsKey,
			Help:      "Cumulative number of the run_podsandbox operation errors by RuntimeClass.",
		},
		[]string{"runtime_handler"},
	)
)

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 SetNodeName

func SetNodeName(name types.NodeName)

func SinceInMicroseconds

func SinceInMicroseconds(start time.Time) float64

Gets the time since the specified start in microseconds.

func SinceInSeconds

func SinceInSeconds(start time.Time) float64

SinceInSeconds gets the time since the specified start in seconds.