metrics

package
v1.10.20 Latest Latest
Warning

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

 Go to latest Published: Feb 13, 2023 License: Apache-2.0 Imports: 22 Imported by: 103

Documentation

Overview

Package metrics holds prometheus metrics objects and related utility functions. It does not abstract away the prometheus client but the caller rarely needs to refer to prometheus directly.

Index

Constants

View Source 
const (
	// ErrorTimeout is the value used to notify timeout errors.
	ErrorTimeout = "timeout"

	// ErrorProxy is the value used to notify errors on Proxy.
	ErrorProxy = "proxy"

	//L7DNS is the value used to report DNS label on metrics
	L7DNS = "dns"

	// SubsystemBPF is the subsystem to scope metrics related to the bpf syscalls.
	SubsystemBPF = "bpf"

	// SubsystemDatapath is the subsystem to scope metrics related to management of
	// the datapath. It is prepended to metric names and separated with a '_'.
	SubsystemDatapath = "datapath"

	// SubsystemAgent is the subsystem to scope metrics related to the cilium agent itself.
	SubsystemAgent = "agent"

	// SubsystemFQDN is the subsystem to scope metrics related to the FQDN proxy.
	SubsystemIPCache = "ipcache"

	// SubsystemK8s is the subsystem to scope metrics related to Kubernetes
	SubsystemK8s = "k8s"

	// SubsystemK8sClient is the subsystem to scope metrics related to the kubernetes client.
	SubsystemK8sClient = "k8s_client"

	// SubsystemKVStore is the subsystem to scope metrics related to the kvstore.
	SubsystemKVStore = "kvstore"

	// SubsystemFQDN is the subsystem to scope metrics related to the FQDN proxy.
	SubsystemFQDN = "fqdn"

	// SubsystemNodes is the subsystem to scope metrics related to the node manager.
	SubsystemNodes = "nodes"

	// SubsystemTriggers is the subsystem to scope metrics related to the trigger package.
	SubsystemTriggers = "triggers"

	// SubsystemAPILimiter is the subsystem to scope metrics related to the API limiter package.
	SubsystemAPILimiter = "api_limiter"

	// SubsystemNodeNeigh is the subsystem to scope metrics related to management of node neighbor.
	SubsystemNodeNeigh = "node_neigh"

	// Namespace is used to scope metrics from cilium. It is prepended to metric
	// names and separated with a '_'
	Namespace = "cilium"

	// LabelError indicates the type of error (string)
	LabelError = "error"

	// LabelOutcome indicates whether the outcome of the operation was successful or not
	LabelOutcome = "outcome"

	// LabelAttempts is the number of attempts it took to complete the operation
	LabelAttempts = "attempts"

	// LabelValueOutcomeSuccess is used as a successful outcome of an operation
	LabelValueOutcomeSuccess = "success"

	// LabelValueOutcomeFail is used as an unsuccessful outcome of an operation
	LabelValueOutcomeFail = "fail"

	// LabelEventSourceAPI marks event-related metrics that come from the API
	LabelEventSourceAPI = "api"

	// LabelEventSourceK8s marks event-related metrics that come from k8s
	LabelEventSourceK8s = "k8s"

	// LabelEventSourceFQDN marks event-related metrics that come from pkg/fqdn
	LabelEventSourceFQDN = "fqdn"

	// LabelEventSourceContainerd marks event-related metrics that come from docker
	LabelEventSourceContainerd = "docker"

	// LabelDatapathArea marks which area the metrics are related to (eg, which BPF map)
	LabelDatapathArea = "area"

	// LabelDatapathName marks a unique identifier for this metric.
	// The name should be defined once for a given type of error.
	LabelDatapathName = "name"

	// LabelDatapathFamily marks which protocol family (IPv4, IPV6) the metric is related to.
	LabelDatapathFamily = "family"

	// LabelProtocol marks the L4 protocol (TCP, ANY) for the metric.
	LabelProtocol = "protocol"

	// LabelSignalType marks the signal name
	LabelSignalType = "signal"

	// LabelSignalData marks the signal data
	LabelSignalData = "data"

	// LabelStatus the label from completed task
	LabelStatus = "status"

	// LabelPolicyEnforcement is the label used to see the enforcement status
	LabelPolicyEnforcement = "enforcement"

	// LabelPolicySource is the label used to see the enforcement status
	LabelPolicySource = "source"

	// LabelScope is the label used to defined multiples scopes in the same
	// metric. For example, one counter may measure a metric over the scope of
	// the entire event (scope=global), or just part of an event
	// (scope=slow_path)
	LabelScope = "scope"

	// LabelProtocolL7 is the label used when working with layer 7 protocols.
	LabelProtocolL7 = "protocol_l7"

	// LabelBuildState is the state a build queue entry is in
	LabelBuildState = "state"

	// LabelBuildQueueName is the name of the build queue
	LabelBuildQueueName = "name"

	// LabelAction is the label used to defined what kind of action was performed in a metric
	LabelAction = "action"

	// LabelSubsystem is the label used to refer to any of the child process
	// started by cilium (Envoy, monitor, etc..)
	LabelSubsystem = "subsystem"

	// LabelKind is the kind a label
	LabelKind = "kind"

	// LabelPath is the label for the API path
	LabelPath = "path"
	// LabelMethod is the label for the HTTP method
	LabelMethod = "method"

	// LabelAPIReturnCode is the HTTP code returned for that API path
	LabelAPIReturnCode = "return_code"

	// LabelOperation is the label for BPF maps operations
	LabelOperation = "operation"

	// LabelMapName is the label for the BPF map name
	LabelMapName = "map_name"

	// LabelVersion is the label for the version number
	LabelVersion = "version"

	// LabelDirection is the label for traffic direction
	LabelDirection = "direction"

	LabelPeerEndpoint = "endpoint"

	// LabelType is the label for type in general (e.g. endpoint, node)
	LabelType = "type"
)

Variables

View Source 
var (
	NoOpMetric    prometheus.Metric    = &metric{}
	NoOpCollector prometheus.Collector = &collector{}

	NoOpCounter     prometheus.Counter     = &counter{NoOpMetric, NoOpCollector}
	NoOpCounterVec  CounterVec             = &counterVec{NoOpCollector}
	NoOpObserver    prometheus.Observer    = &observer{}
	NoOpObserverVec prometheus.ObserverVec = &observerVec{NoOpCollector}
	NoOpGauge       prometheus.Gauge       = &gauge{NoOpMetric, NoOpCollector}
	NoOpGaugeVec    GaugeVec               = &gaugeVec{NoOpCollector}
)
View Source 
var (

	// APIInteractions is the total time taken to process an API call made
	// to the cilium-agent
	APIInteractions = NoOpObserverVec

	// Endpoint is a function used to collect this metric.
	// It must be thread-safe.
	Endpoint prometheus.GaugeFunc

	// EndpointRegenerationTotal is a count of the number of times any endpoint
	// has been regenerated and success/fail outcome
	EndpointRegenerationTotal = NoOpCounterVec

	// EndpointStateCount is the total count of the endpoints in various states.
	EndpointStateCount = NoOpGaugeVec

	// EndpointRegenerationTimeStats is the total time taken to regenerate
	// endpoints, labeled by span name and status ("success" or "failure")
	EndpointRegenerationTimeStats = NoOpObserverVec

	// Policy
	// Policy is the number of policies loaded into the agent
	Policy = NoOpGauge

	// PolicyRegenerationCount is the total number of successful policy
	// regenerations.
	PolicyRegenerationCount = NoOpCounter

	// PolicyRegenerationTimeStats is the total time taken to generate policies
	PolicyRegenerationTimeStats = NoOpObserverVec

	// PolicyRevision is the current policy revision number for this agent
	PolicyRevision = NoOpGauge

	// PolicyImportErrorsTotal is a count of failed policy imports
	PolicyImportErrorsTotal = NoOpCounter

	// PolicyEndpointStatus is the number of endpoints with policy labeled by enforcement type
	PolicyEndpointStatus = NoOpGaugeVec

	// PolicyImplementationDelay is a distribution of times taken from adding a
	// policy (and incrementing the policy revision) to seeing it in the datapath
	// per Endpoint. This reflects the actual delay perceived by traffic flowing
	// through the datapath. The longest times will roughly correlate with the
	// time taken to fully deploy an endpoint.
	PolicyImplementationDelay = NoOpObserverVec

	// Identity is the number of identities currently in use on the node by type
	Identity = NoOpGaugeVec

	// EventTSK8s is the timestamp of k8s events
	EventTSK8s = NoOpGauge

	// EventLagK8s is the lag calculation for k8s Pod events.
	EventLagK8s = NoOpGauge

	// EventTSContainerd is the timestamp of docker events
	EventTSContainerd = NoOpGauge

	// EventTSAPI is the timestamp of docker events
	EventTSAPI = NoOpGauge

	// ProxyRedirects is the number of redirects labeled by protocol
	ProxyRedirects = NoOpGaugeVec

	// ProxyPolicyL7Total is a count of all l7 requests handled by proxy
	ProxyPolicyL7Total = NoOpCounterVec

	// ProxyParseErrors is a count of failed parse errors on proxy
	// Deprecated: in favor of ProxyPolicyL7Total
	ProxyParseErrors = NoOpCounter

	// ProxyForwarded is a count of all forwarded requests by proxy
	// Deprecated: in favor of ProxyPolicyL7Total
	ProxyForwarded = NoOpCounter

	// ProxyDenied is a count of all denied requests by policy by the proxy
	// Deprecated: in favor of ProxyPolicyL7Total
	ProxyDenied = NoOpCounter

	// ProxyReceived is a count of all received requests by the proxy
	// Deprecated: in favor of ProxyPolicyL7Total
	ProxyReceived = NoOpCounter

	// ProxyUpstreamTime is how long the upstream server took to reply labeled
	// by error, protocol and span time
	ProxyUpstreamTime = NoOpObserverVec

	// ProxyDatapathUpdateTimeout is a count of all the timeouts encountered while
	// updating the datapath due to an FQDN IP update
	ProxyDatapathUpdateTimeout = NoOpCounter

	// DropCount is the total drop requests,
	// tagged by drop reason and direction(ingress/egress)
	DropCount = NoOpCounterVec

	// DropBytes is the total dropped bytes,
	// tagged by drop reason and direction(ingress/egress)
	DropBytes = NoOpCounterVec

	// ForwardCount is the total forwarded packets,
	// tagged by ingress/egress direction
	ForwardCount = NoOpCounterVec

	// ForwardBytes is the total forwarded bytes,
	// tagged by ingress/egress direction
	ForwardBytes = NoOpCounterVec

	// ConntrackGCRuns is the number of times that the conntrack GC
	// process was run.
	ConntrackGCRuns = NoOpCounterVec

	// ConntrackGCKeyFallbacks number of times that the conntrack key fallback was invalid.
	ConntrackGCKeyFallbacks = NoOpCounterVec

	// ConntrackGCSize the number of entries in the conntrack table
	ConntrackGCSize = NoOpGaugeVec

	// NatGCSize the number of entries in the nat table
	NatGCSize = NoOpGaugeVec

	// ConntrackGCDuration the duration of the conntrack GC process in milliseconds.
	ConntrackGCDuration = NoOpObserverVec

	// ConntrackDumpReset marks the count for conntrack dump resets
	ConntrackDumpResets = NoOpCounterVec

	// SignalsHandled is the number of signals received.
	SignalsHandled = NoOpCounterVec

	// ServicesCount number of services
	ServicesCount = NoOpCounterVec

	// ErrorsWarnings is the number of errors and warnings in cilium-agent instances
	ErrorsWarnings = NoOpCounterVec

	// ControllerRuns is the number of times that a controller process runs.
	ControllerRuns = NoOpCounterVec

	// ControllerRunsDuration the duration of the controller process in seconds
	ControllerRunsDuration = NoOpObserverVec

	// subprocess, labeled by Subsystem
	SubprocessStart = NoOpCounterVec

	// KubernetesEventProcessed is the number of Kubernetes events
	// processed labeled by scope, action and execution result
	KubernetesEventProcessed = NoOpCounterVec

	// KubernetesEventReceived is the number of Kubernetes events received
	// labeled by scope, action, valid data and equalness.
	KubernetesEventReceived = NoOpCounterVec

	// KubernetesAPIInteractions is the total time taken to process an API call made
	// to the kube-apiserver
	KubernetesAPIInteractions = NoOpObserverVec

	// KubernetesAPICallsTotal is the counter for all API calls made to
	// kube-apiserver.
	KubernetesAPICallsTotal = NoOpCounterVec

	// KubernetesCNPStatusCompletion is the number of seconds it takes to
	// complete a CNP status update
	KubernetesCNPStatusCompletion = NoOpObserverVec

	// IpamEvent is the number of IPAM events received labeled by action and
	// datapath family type
	IpamEvent = NoOpCounterVec

	// KVStoreOperationsDuration records the duration of kvstore operations
	KVStoreOperationsDuration = NoOpObserverVec

	// KVStoreEventsQueueDuration records the duration in seconds of time
	// received event was blocked before it could be queued
	KVStoreEventsQueueDuration = NoOpObserverVec

	// KVStoreQuorumErrors records the number of kvstore quorum errors
	KVStoreQuorumErrors = NoOpCounterVec

	// FQDNGarbageCollectorCleanedTotal is the number of domains cleaned by the
	// GC job.
	FQDNGarbageCollectorCleanedTotal = NoOpCounter

	// FQDNActiveNames is the number of domains inside the DNS cache that have
	// not expired (by TTL), per endpoint.
	FQDNActiveNames = NoOpGaugeVec

	// FQDNActiveIPs is the number of IPs inside the DNS cache associated with
	// a domain that has not expired (by TTL) and are currently active, per
	// endpoint.
	FQDNActiveIPs = NoOpGaugeVec

	// FQDNAliveZombieConnections is the number IPs associated with domains
	// that have expired (by TTL) yet still associated with an active
	// connection (aka zombie), per endpoint.
	FQDNAliveZombieConnections = NoOpGaugeVec

	// FQDNSemaphoreRejectedTotal is the total number of DNS requests rejected
	// by the DNS proxy because too many requests were in flight, as enforced by
	// the admission semaphore.
	FQDNSemaphoreRejectedTotal = NoOpCounter

	// IPCacheErrorsTotal is the total number of IPCache events handled in
	// the IPCache subsystem that resulted in errors.
	IPCacheErrorsTotal = NoOpCounterVec

	// IPCacheEventsTotal is the total number of IPCache events handled in
	// the IPCache subsystem.
	IPCacheEventsTotal = NoOpCounterVec

	// BPFSyscallDuration is the metric for bpf syscalls duration.
	BPFSyscallDuration = NoOpObserverVec

	// BPFMapOps is the metric to measure the number of operations done to a
	// bpf map.
	BPFMapOps = NoOpCounterVec

	// TriggerPolicyUpdateTotal is the metric to count total number of
	// policy update triggers
	TriggerPolicyUpdateTotal = NoOpCounterVec

	// TriggerPolicyUpdateFolds is the current level folding that is
	// happening when running policy update triggers
	TriggerPolicyUpdateFolds = NoOpGauge

	// TriggerPolicyUpdateCallDuration measures the latency and call
	// duration of policy update triggers
	TriggerPolicyUpdateCallDuration = NoOpObserverVec

	// VersionMetric labelled by Cilium version
	VersionMetric = NoOpGaugeVec

	// APILimiterWaitHistoryDuration is a histogram that measures the
	// individual wait durations of API limiters
	APILimiterWaitHistoryDuration = NoOpObserverVec

	// APILimiterWaitDuration is the gauge of the current mean, min, and
	// max wait duration
	APILimiterWaitDuration = NoOpGaugeVec

	// APILimiterProcessingDuration is the gauge of the mean and estimated
	// processing duration
	APILimiterProcessingDuration = NoOpGaugeVec

	// APILimiterRequestsInFlight is the gauge of the current and max
	// requests in flight
	APILimiterRequestsInFlight = NoOpGaugeVec

	// APILimiterRateLimit is the gauge of the current rate limiting
	// configuration including limit and burst
	APILimiterRateLimit = NoOpGaugeVec

	// APILimiterAdjustmentFactor is the gauge representing the latest
	// adjustment factor that was applied
	APILimiterAdjustmentFactor = NoOpGaugeVec

	// APILimiterProcessedRequests is the counter of the number of
	// processed (successful and failed) requests
	APILimiterProcessedRequests = NoOpCounterVec

	// ArpingRequestsTotal is the counter of the number of sent
	// (successful and failed) arping requests
	ArpingRequestsTotal = NoOpCounterVec
)

Functions

func DefaultMetrics added in v1.5.1 

func DefaultMetrics() map[string]struct{}

func DumpMetrics 

func DumpMetrics() ([]*models.Metric, error)

DumpMetrics gets the current Cilium metrics and dumps all into a models.Metrics structure.If metrics cannot be retrieved, returns an error

func Enable added in v1.5.0 

func Enable(addr string) <-chan error

Enable begins serving prometheus metrics on the address passed in. Addresses of the form ":8080" will bind the port on all interfaces.

func Errno2Outcome 

func Errno2Outcome(errno unix.Errno) string

Errno2Outcome converts a unix.Errno to LabelOutcome

func Error2Outcome 

func Error2Outcome(err error) string

Error2Outcome converts an error to LabelOutcome

func GetCounterValue 

func GetCounterValue(m prometheus.Counter) float64

GetCounterValue returns the current value stored for the counter

func GetGaugeValue 

func GetGaugeValue(m prometheus.Gauge) float64

GetGaugeValue returns the current value stored for the gauge. This function is useful in tests.

func MustRegister added in v1.5.0 

func MustRegister(c ...prometheus.Collector)

MustRegister adds the collector to the registry, exposing this metric to prometheus scrapes. It will panic on error.

func Register 

func Register(c prometheus.Collector) error

Register registers a collector

func RegisterList 

func RegisterList(list []prometheus.Collector) error

RegisterList registers a list of collectors. If registration of one collector fails, no collector is registered.

func Unregister 

func Unregister(c prometheus.Collector) bool

Unregister unregisters a collector

Types

type APIEventTSHelper 

type APIEventTSHelper struct {
	Next      http.Handler
	TSGauge   prometheus.Gauge
	Histogram prometheus.ObserverVec
}

APIEventTSHelper is intended to be a global middleware to track metrics around API calls. It records the timestamp of an API call in the provided gauge.

func (*APIEventTSHelper) ServeHTTP 

func (m *APIEventTSHelper) ServeHTTP(r http.ResponseWriter, req *http.Request)

ServeHTTP implements the http.Handler interface. It records the timestamp this API call began at, then chains to the next handler.

type Configuration added in v1.5.1 

type Configuration struct {
	APIInteractionsEnabled                  bool
	EndpointRegenerationCountEnabled        bool
	EndpointStateCountEnabled               bool
	EndpointRegenerationTimeStatsEnabled    bool
	PolicyCountEnabled                      bool
	PolicyRegenerationCountEnabled          bool
	PolicyRegenerationTimeStatsEnabled      bool
	PolicyRevisionEnabled                   bool
	PolicyImportErrorsEnabled               bool
	PolicyEndpointStatusEnabled             bool
	PolicyImplementationDelayEnabled        bool
	IdentityCountEnabled                    bool
	EventTSK8sEnabled                       bool
	EventLagK8sEnabled                      bool
	EventTSContainerdEnabled                bool
	EventTSAPIEnabled                       bool
	ProxyRedirectsEnabled                   bool
	ProxyPolicyL7Enabled                    bool
	ProxyParseErrorsEnabled                 bool
	ProxyForwardedEnabled                   bool
	ProxyDeniedEnabled                      bool
	ProxyReceivedEnabled                    bool
	ProxyDatapathUpdateTimeoutEnabled       bool
	NoOpObserverVecEnabled                  bool
	DropCountEnabled                        bool
	DropBytesEnabled                        bool
	NoOpCounterVecEnabled                   bool
	ForwardBytesEnabled                     bool
	ConntrackGCRunsEnabled                  bool
	ConntrackGCKeyFallbacksEnabled          bool
	ConntrackGCSizeEnabled                  bool
	ConntrackGCDurationEnabled              bool
	ConntrackDumpResetsEnabled              bool
	SignalsHandledEnabled                   bool
	ServicesCountEnabled                    bool
	ErrorsWarningsEnabled                   bool
	ControllerRunsEnabled                   bool
	ControllerRunsDurationEnabled           bool
	SubprocessStartEnabled                  bool
	KubernetesEventProcessedEnabled         bool
	KubernetesEventReceivedEnabled          bool
	KubernetesAPIInteractionsEnabled        bool
	KubernetesAPICallsEnabled               bool
	KubernetesCNPStatusCompletionEnabled    bool
	IpamEventEnabled                        bool
	IPCacheErrorsTotalEnabled               bool
	IPCacheEventsTotalEnabled               bool
	KVStoreOperationsDurationEnabled        bool
	KVStoreEventsQueueDurationEnabled       bool
	KVStoreQuorumErrorsEnabled              bool
	FQDNGarbageCollectorCleanedTotalEnabled bool
	FQDNActiveNames                         bool
	FQDNActiveIPs                           bool
	FQDNActiveZombiesConnections            bool
	FQDNSemaphoreRejectedTotal              bool
	BPFSyscallDurationEnabled               bool
	BPFMapOps                               bool
	BPFMapPressure                          bool
	TriggerPolicyUpdateTotal                bool
	TriggerPolicyUpdateFolds                bool
	TriggerPolicyUpdateCallDuration         bool
	VersionMetric                           bool
	APILimiterWaitHistoryDuration           bool
	APILimiterWaitDuration                  bool
	APILimiterProcessingDuration            bool
	APILimiterRequestsInFlight              bool
	APILimiterRateLimit                     bool
	APILimiterAdjustmentFactor              bool
	APILimiterProcessedRequests             bool
	ArpingRequestsTotalEnabled              bool
}

func CreateConfiguration added in v1.5.1 

func CreateConfiguration(metricsEnabled []string) (Configuration, []prometheus.Collector)

CreateConfiguration returns a Configuration with all metrics that are considered enabled from the given slice of metricsEnabled as well as a slice of prometheus.Collectors that must be registered in the prometheus default register.

type CounterVec added in v1.5.1 

type CounterVec interface {
	WithLabelValues(lvls ...string) prometheus.Counter
	GetMetricWithLabelValues(lvs ...string) (prometheus.Counter, error)
	With(labels prometheus.Labels) prometheus.Counter
	prometheus.Collector
}

type GaugeVec added in v1.5.1 

type GaugeVec interface {
	WithLabelValues(lvls ...string) prometheus.Gauge
	prometheus.Collector
}

type GaugeWithThreshold 

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

GaugeWithThreshold is a prometheus gauge that registers itself with prometheus if over a threshold value and unregisters when under.

func NewBPFMapPressureGauge 

func NewBPFMapPressureGauge(mapname string, threshold float64) *GaugeWithThreshold

NewBPFMapPressureGauge creates a new GaugeWithThreshold for the cilium_bpf_map_pressure metric with the map name as constant label.

func NewGaugeWithThreshold 

func NewGaugeWithThreshold(name string, subsystem string, desc string, labels map[string]string, threshold float64) *GaugeWithThreshold

NewGaugeWithThreshold creates a new GaugeWithThreshold.

func (*GaugeWithThreshold) Set 

func (gwt *GaugeWithThreshold) Set(value float64)

Set the value of the GaugeWithThreshold.

type LoggingHook 

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

LoggingHook is a hook for logrus which counts error and warning messages as a Prometheus metric.

func NewLoggingHook 

func NewLoggingHook(component string) *LoggingHook

NewLoggingHook returns a new instance of LoggingHook for the given Cilium component.

func (*LoggingHook) Fire 

func (h *LoggingHook) Fire(entry *logrus.Entry) error

Fire is the main method which is called every time when logger has an error or warning message.

func (*LoggingHook) Levels 

func (h *LoggingHook) Levels() []logrus.Level

Levels returns the list of logging levels on which the hook is triggered.

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.