mirror of
https://github.com/k3s-io/kubernetes.git
synced 2025-07-24 12:15:52 +00:00
Merge pull request #81534 from logicalhan/kubelet-migration
migrate kubelet's metrics/probes & metrics endpoint to metrics stability framework
This commit is contained in:
Kubernetes Prow Robot
GitHub
commit
ca5babc1da
@ -26,7 +26,8 @@ go_library(
|
||||
"//staging/src/k8s.io/client-go/rest:go_default_library",
|
||||
"//staging/src/k8s.io/client-go/util/certificate:go_default_library",
|
||||
"//staging/src/k8s.io/client-go/util/connrotation:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/k8s.io/klog:go_default_library",
|
||||
],
|
||||
)
|
||||
|
||||
@ -24,14 +24,14 @@ import (
|
||||
"net"
|
||||
"sort"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
|
||||
certificates "k8s.io/api/certificates/v1beta1"
|
||||
"k8s.io/api/core/v1"
|
||||
"k8s.io/apimachinery/pkg/types"
|
||||
clientset "k8s.io/client-go/kubernetes"
|
||||
certificatesclient "k8s.io/client-go/kubernetes/typed/certificates/v1beta1"
|
||||
"k8s.io/client-go/util/certificate"
|
||||
compbasemetrics "k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
kubeletconfig "k8s.io/kubernetes/pkg/kubelet/apis/config"
|
||||
"k8s.io/kubernetes/pkg/kubelet/metrics"
|
||||
)
|
||||
@ -52,15 +52,16 @@ func NewKubeletServerCertificateManager(kubeClient clientset.Interface, kubeCfg
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to initialize server certificate store: %v", err)
|
||||
}
|
||||
var certificateExpiration = prometheus.NewGauge(
|
||||
prometheus.GaugeOpts{
|
||||
Namespace: metrics.KubeletSubsystem,
|
||||
Subsystem: "certificate_manager",
|
||||
Name: "server_expiration_seconds",
|
||||
Help: "Gauge of the lifetime of a certificate. The value is the date the certificate will expire in seconds since January 1, 1970 UTC.",
|
||||
var certificateExpiration = compbasemetrics.NewGauge(
|
||||
&compbasemetrics.GaugeOpts{
|
||||
Namespace: metrics.KubeletSubsystem,
|
||||
Subsystem: "certificate_manager",
|
||||
Name: "server_expiration_seconds",
|
||||
Help: "Gauge of the lifetime of a certificate. The value is the date the certificate will expire in seconds since January 1, 1970 UTC.",
|
||||
StabilityLevel: compbasemetrics.ALPHA,
|
||||
},
|
||||
)
|
||||
prometheus.MustRegister(certificateExpiration)
|
||||
legacyregistry.MustRegister(certificateExpiration)
|
||||
|
||||
getTemplate := func() *x509.CertificateRequest {
|
||||
hostnames, ips := addressesToHostnamesAndIPs(getAddresses())
|
||||
@ -166,15 +167,16 @@ func NewKubeletClientCertificateManager(
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to initialize client certificate store: %v", err)
|
||||
}
|
||||
var certificateExpiration = prometheus.NewGauge(
|
||||
prometheus.GaugeOpts{
|
||||
Namespace: metrics.KubeletSubsystem,
|
||||
Subsystem: "certificate_manager",
|
||||
Name: "client_expiration_seconds",
|
||||
Help: "Gauge of the lifetime of a certificate. The value is the date the certificate will expire in seconds since January 1, 1970 UTC.",
|
||||
var certificateExpiration = compbasemetrics.NewGauge(
|
||||
&compbasemetrics.GaugeOpts{
|
||||
Namespace: metrics.KubeletSubsystem,
|
||||
Subsystem: "certificate_manager",
|
||||
Name: "client_expiration_seconds",
|
||||
Help: "Gauge of the lifetime of a certificate. The value is the date the certificate will expire in seconds since January 1, 1970 UTC.",
|
||||
StabilityLevel: compbasemetrics.ALPHA,
|
||||
},
|
||||
)
|
||||
prometheus.Register(certificateExpiration)
|
||||
legacyregistry.Register(certificateExpiration)
|
||||
|
||||
m, err := certificate.NewManager(&certificate.Config{
|
||||
ClientFn: clientFn,
|
||||
|
||||
@ -5,7 +5,11 @@ go_library(
|
||||
srcs = ["metrics.go"],
|
||||
importpath = "k8s.io/kubernetes/pkg/kubelet/dockershim/metrics",
|
||||
visibility = ["//visibility:public"],
|
||||
deps = ["//vendor/github.com/prometheus/client_golang/prometheus:go_default_library"],
|
||||
deps = [
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
],
|
||||
)
|
||||
|
||||
filegroup(
|
||||
|
||||
@ -21,6 +21,9 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
|
||||
"k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
)
|
||||
|
||||
const (
|
||||
@ -49,79 +52,87 @@ const (
|
||||
var (
|
||||
// DockerOperationsLatency collects operation latency numbers by operation
|
||||
// type.
|
||||
DockerOperationsLatency = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsLatencyKey,
|
||||
Help: "Latency in seconds of Docker operations. Broken down by operation type.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
DockerOperationsLatency = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsLatencyKey,
|
||||
Help: "Latency in seconds of Docker operations. Broken down by operation type.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DockerOperations collects operation counts by operation type.
|
||||
DockerOperations = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsKey,
|
||||
Help: "Cumulative number of Docker operations by operation type.",
|
||||
DockerOperations = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsKey,
|
||||
Help: "Cumulative number of Docker operations by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DockerOperationsErrors collects operation errors by operation
|
||||
// type.
|
||||
DockerOperationsErrors = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsErrorsKey,
|
||||
Help: "Cumulative number of Docker operation errors by operation type.",
|
||||
DockerOperationsErrors = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsErrorsKey,
|
||||
Help: "Cumulative number of Docker operation errors by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DockerOperationsTimeout collects operation timeouts by operation type.
|
||||
DockerOperationsTimeout = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsTimeoutKey,
|
||||
Help: "Cumulative number of Docker operation timeout by operation type.",
|
||||
DockerOperationsTimeout = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DockerOperationsTimeoutKey,
|
||||
Help: "Cumulative number of Docker operation timeout by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
|
||||
// DeprecatedDockerOperationsLatency collects operation latency numbers by operation
|
||||
// type.
|
||||
DeprecatedDockerOperationsLatency = prometheus.NewSummaryVec(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds of Docker operations. Broken down by operation type.",
|
||||
DeprecatedDockerOperationsLatency = metrics.NewSummaryVec(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds of Docker operations. Broken down by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedDockerOperations collects operation counts by operation type.
|
||||
DeprecatedDockerOperations = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsKey,
|
||||
Help: "(Deprecated) Cumulative number of Docker operations by operation type.",
|
||||
DeprecatedDockerOperations = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsKey,
|
||||
Help: "(Deprecated) Cumulative number of Docker operations by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedDockerOperationsErrors collects operation errors by operation
|
||||
// type.
|
||||
DeprecatedDockerOperationsErrors = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsErrorsKey,
|
||||
Help: "(Deprecated) Cumulative number of Docker operation errors by operation type.",
|
||||
DeprecatedDockerOperationsErrors = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsErrorsKey,
|
||||
Help: "(Deprecated) Cumulative number of Docker operation errors by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedDockerOperationsTimeout collects operation timeouts by operation type.
|
||||
DeprecatedDockerOperationsTimeout = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsTimeoutKey,
|
||||
Help: "(Deprecated) Cumulative number of Docker operation timeout by operation type.",
|
||||
DeprecatedDockerOperationsTimeout = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedDockerOperationsTimeoutKey,
|
||||
Help: "(Deprecated) Cumulative number of Docker operation timeout by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
@ -132,14 +143,14 @@ var registerMetrics sync.Once
|
||||
// Register all metrics.
|
||||
func Register() {
|
||||
registerMetrics.Do(func() {
|
||||
prometheus.MustRegister(DockerOperationsLatency)
|
||||
prometheus.MustRegister(DockerOperations)
|
||||
prometheus.MustRegister(DockerOperationsErrors)
|
||||
prometheus.MustRegister(DockerOperationsTimeout)
|
||||
prometheus.MustRegister(DeprecatedDockerOperationsLatency)
|
||||
prometheus.MustRegister(DeprecatedDockerOperations)
|
||||
prometheus.MustRegister(DeprecatedDockerOperationsErrors)
|
||||
prometheus.MustRegister(DeprecatedDockerOperationsTimeout)
|
||||
legacyregistry.MustRegister(DockerOperationsLatency)
|
||||
legacyregistry.MustRegister(DockerOperations)
|
||||
legacyregistry.MustRegister(DockerOperationsErrors)
|
||||
legacyregistry.MustRegister(DockerOperationsTimeout)
|
||||
legacyregistry.MustRegister(DeprecatedDockerOperationsLatency)
|
||||
legacyregistry.MustRegister(DeprecatedDockerOperations)
|
||||
legacyregistry.MustRegister(DeprecatedDockerOperationsErrors)
|
||||
legacyregistry.MustRegister(DeprecatedDockerOperationsTimeout)
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@ -5,7 +5,11 @@ go_library(
|
||||
srcs = ["metrics.go"],
|
||||
importpath = "k8s.io/kubernetes/pkg/kubelet/dockershim/network/metrics",
|
||||
visibility = ["//visibility:public"],
|
||||
deps = ["//vendor/github.com/prometheus/client_golang/prometheus:go_default_library"],
|
||||
deps = [
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
],
|
||||
)
|
||||
|
||||
filegroup(
|
||||
|
||||
@ -21,6 +21,9 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
|
||||
"k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
)
|
||||
|
||||
const (
|
||||
@ -38,23 +41,25 @@ const (
|
||||
var (
|
||||
// NetworkPluginOperationsLatency collects operation latency numbers by operation
|
||||
// type.
|
||||
NetworkPluginOperationsLatency = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: NetworkPluginOperationsLatencyKey,
|
||||
Help: "Latency in seconds of network plugin operations. Broken down by operation type.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
NetworkPluginOperationsLatency = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: NetworkPluginOperationsLatencyKey,
|
||||
Help: "Latency in seconds of network plugin operations. Broken down by operation type.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
|
||||
// DeprecatedNetworkPluginOperationsLatency collects operation latency numbers by operation
|
||||
// type.
|
||||
DeprecatedNetworkPluginOperationsLatency = prometheus.NewSummaryVec(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedNetworkPluginOperationsLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds of network plugin operations. Broken down by operation type.",
|
||||
DeprecatedNetworkPluginOperationsLatency = metrics.NewSummaryVec(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: DeprecatedNetworkPluginOperationsLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds of network plugin operations. Broken down by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
@ -65,8 +70,8 @@ var registerMetrics sync.Once
|
||||
// Register all metrics.
|
||||
func Register() {
|
||||
registerMetrics.Do(func() {
|
||||
prometheus.MustRegister(NetworkPluginOperationsLatency)
|
||||
prometheus.MustRegister(DeprecatedNetworkPluginOperationsLatency)
|
||||
legacyregistry.MustRegister(NetworkPluginOperationsLatency)
|
||||
legacyregistry.MustRegister(DeprecatedNetworkPluginOperationsLatency)
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@ -117,12 +117,11 @@ go_test(
|
||||
"//staging/src/k8s.io/apiserver/pkg/util/feature:go_default_library",
|
||||
"//staging/src/k8s.io/client-go/util/flowcontrol:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/featuregate/testing:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//staging/src/k8s.io/cri-api/pkg/apis/runtime/v1alpha2:go_default_library",
|
||||
"//staging/src/k8s.io/cri-api/pkg/apis/testing:go_default_library",
|
||||
"//vendor/github.com/golang/mock/gomock:go_default_library",
|
||||
"//vendor/github.com/google/cadvisor/info/v1:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus/promhttp:go_default_library",
|
||||
"//vendor/github.com/stretchr/testify/assert:go_default_library",
|
||||
"//vendor/github.com/stretchr/testify/require:go_default_library",
|
||||
"//vendor/k8s.io/utils/pointer:go_default_library",
|
||||
|
||||
@ -22,17 +22,17 @@ import (
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/client_golang/prometheus/promhttp"
|
||||
"github.com/stretchr/testify/assert"
|
||||
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
runtimeapi "k8s.io/cri-api/pkg/apis/runtime/v1alpha2"
|
||||
"k8s.io/kubernetes/pkg/kubelet/metrics"
|
||||
)
|
||||
|
||||
func TestRecordOperation(t *testing.T) {
|
||||
prometheus.MustRegister(metrics.RuntimeOperations)
|
||||
prometheus.MustRegister(metrics.RuntimeOperationsDuration)
|
||||
prometheus.MustRegister(metrics.RuntimeOperationsErrors)
|
||||
legacyregistry.MustRegister(metrics.RuntimeOperations)
|
||||
legacyregistry.MustRegister(metrics.RuntimeOperationsDuration)
|
||||
legacyregistry.MustRegister(metrics.RuntimeOperationsErrors)
|
||||
|
||||
temporalServer := "127.0.0.1:1234"
|
||||
l, err := net.Listen("tcp", temporalServer)
|
||||
@ -41,7 +41,8 @@ func TestRecordOperation(t *testing.T) {
|
||||
|
||||
prometheusURL := "http://" + temporalServer + "/metrics"
|
||||
mux := http.NewServeMux()
|
||||
mux.Handle("/metrics", promhttp.Handler())
|
||||
//lint:ignore SA1019 ignore deprecated warning until we move off of global registries
|
||||
mux.Handle("/metrics", legacyregistry.Handler())
|
||||
server := &http.Server{
|
||||
Addr: temporalServer,
|
||||
Handler: mux,
|
||||
|
||||
@ -15,6 +15,8 @@ go_library(
|
||||
"//staging/src/k8s.io/api/core/v1:go_default_library",
|
||||
"//staging/src/k8s.io/apimachinery/pkg/types:go_default_library",
|
||||
"//staging/src/k8s.io/apiserver/pkg/util/feature:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//vendor/k8s.io/klog:go_default_library",
|
||||
],
|
||||
|
||||
@ -18,6 +18,8 @@ package metrics
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
@ -88,279 +90,307 @@ const (
|
||||
|
||||
var (
|
||||
// NodeName is a Gauge that tracks the ode's name. The count is always 1.
|
||||
NodeName = prometheus.NewGaugeVec(
|
||||
prometheus.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: NodeNameKey,
|
||||
Help: "The node's name. The count is always 1.",
|
||||
NodeName = metrics.NewGaugeVec(
|
||||
&metrics.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: NodeNameKey,
|
||||
Help: "The node's name. The count is always 1.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{NodeLabelKey},
|
||||
)
|
||||
// ContainersPerPodCount is a Counter that tracks the number of containers per pod.
|
||||
ContainersPerPodCount = prometheus.NewHistogram(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: "containers_per_pod_count",
|
||||
Help: "The number of containers per pod.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
ContainersPerPodCount = metrics.NewHistogram(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: "containers_per_pod_count",
|
||||
Help: "The number of containers per pod.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// PodWorkerDuration is a Histogram that tracks the duration (in seconds) in takes to sync a single pod.
|
||||
// Broken down by the operation type.
|
||||
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,
|
||||
PodWorkerDuration = metrics.NewHistogramVec(
|
||||
&metrics.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,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// PodStartDuration is a Histogram that tracks the duration (in seconds) it takes for a single pod to go from pending to running.
|
||||
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,
|
||||
PodStartDuration = metrics.NewHistogram(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PodStartDurationKey,
|
||||
Help: "Duration in seconds for a single pod to go from pending to running.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// CgroupManagerDuration is a Histogram that tracks the duration (in seconds) it takes for cgroup manager operations to complete.
|
||||
// Broken down by method.
|
||||
CgroupManagerDuration = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: CgroupManagerOperationsKey,
|
||||
Help: "Duration in seconds for cgroup manager operations. Broken down by method.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
CgroupManagerDuration = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: CgroupManagerOperationsKey,
|
||||
Help: "Duration in seconds for cgroup manager operations. Broken down by method.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// PodWorkerStartDuration is a Histogram that tracks the duration (in seconds) it takes from seeing a pod to starting a worker.
|
||||
PodWorkerStartDuration = prometheus.NewHistogram(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PodWorkerStartDurationKey,
|
||||
Help: "Duration in seconds from seeing a pod to starting a worker.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
PodWorkerStartDuration = metrics.NewHistogram(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PodWorkerStartDurationKey,
|
||||
Help: "Duration in seconds from seeing a pod to starting a worker.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// PLEGRelistDuration is a Histogram that tracks the duration (in seconds) it takes for relisting pods in the Kubelet's
|
||||
// Pod Lifecycle Event Generator (PLEG).
|
||||
PLEGRelistDuration = prometheus.NewHistogram(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PLEGRelistDurationKey,
|
||||
Help: "Duration in seconds for relisting pods in PLEG.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
PLEGRelistDuration = metrics.NewHistogram(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PLEGRelistDurationKey,
|
||||
Help: "Duration in seconds for relisting pods in PLEG.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// PLEGDiscardEvents is a Histogram that tracks the duration (in seconds) it takes for discarding events in the Kubelet's
|
||||
// Pod Lifecycle Event Generator (PLEG).
|
||||
PLEGDiscardEvents = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PLEGDiscardEventsKey,
|
||||
Help: "The number of discard events in PLEG.",
|
||||
PLEGDiscardEvents = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PLEGDiscardEventsKey,
|
||||
Help: "The number of discard events in PLEG.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{},
|
||||
)
|
||||
// PLEGRelistInterval is a Histogram that tracks the intervals (in seconds) between relisting in the Kubelet's
|
||||
// Pod Lifecycle Event Generator (PLEG).
|
||||
PLEGRelistInterval = prometheus.NewHistogram(
|
||||
prometheus.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PLEGRelistIntervalKey,
|
||||
Help: "Interval in seconds between relisting in PLEG.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
PLEGRelistInterval = metrics.NewHistogram(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: PLEGRelistIntervalKey,
|
||||
Help: "Interval in seconds between relisting in PLEG.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// RuntimeOperations is a Counter that tracks the cumulative number of remote runtime operations.
|
||||
// Broken down by operation type.
|
||||
RuntimeOperations = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RuntimeOperationsKey,
|
||||
Help: "Cumulative number of runtime operations by operation type.",
|
||||
RuntimeOperations = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RuntimeOperationsKey,
|
||||
Help: "Cumulative number of runtime operations by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// RuntimeOperationsDuration is a Histogram that tracks the duration (in seconds) for remote runtime operations to complete.
|
||||
// Broken down by 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,
|
||||
RuntimeOperationsDuration = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RuntimeOperationsDurationKey,
|
||||
Help: "Duration in seconds of runtime operations. Broken down by operation type.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// RuntimeOperationsErrors is a Counter that tracks the cumulative number of remote runtime operations errors.
|
||||
// Broken down by operation type.
|
||||
RuntimeOperationsErrors = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RuntimeOperationsErrorsKey,
|
||||
Help: "Cumulative number of runtime operation errors by operation type.",
|
||||
RuntimeOperationsErrors = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RuntimeOperationsErrorsKey,
|
||||
Help: "Cumulative number of runtime operation errors by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// Evictions is a Counter that tracks the cumulative number of pod evictions initiated by the kubelet.
|
||||
// Broken down by eviction signal.
|
||||
Evictions = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: EvictionsKey,
|
||||
Help: "Cumulative number of pod evictions by eviction signal",
|
||||
Evictions = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: EvictionsKey,
|
||||
Help: "Cumulative number of pod evictions by eviction signal",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"eviction_signal"},
|
||||
)
|
||||
// EvictionStatsAge is a Histogram that tracks the time (in seconds) between when stats are collected and when a pod is evicted
|
||||
// based on those stats. Broken down by eviction signal.
|
||||
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,
|
||||
EvictionStatsAge = metrics.NewHistogramVec(
|
||||
&metrics.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,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"eviction_signal"},
|
||||
)
|
||||
// DevicePluginRegistrationCount is a Counter that tracks the cumulative number of device plugin registrations.
|
||||
// Broken down by resource name.
|
||||
DevicePluginRegistrationCount = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DevicePluginRegistrationCountKey,
|
||||
Help: "Cumulative number of device plugin registrations. Broken down by resource name.",
|
||||
DevicePluginRegistrationCount = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DevicePluginRegistrationCountKey,
|
||||
Help: "Cumulative number of device plugin registrations. Broken down by resource name.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"resource_name"},
|
||||
)
|
||||
// DevicePluginAllocationDuration is a Histogram that tracks the duration (in seconds) to serve a device plugin allocation request.
|
||||
// Broken down by 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,
|
||||
DevicePluginAllocationDuration = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DevicePluginAllocationDurationKey,
|
||||
Help: "Duration in seconds to serve a device plugin Allocation request. Broken down by resource name.",
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"resource_name"},
|
||||
)
|
||||
// DeprecatedPodWorkerLatency is a Summary that tracks the latency (in microseconds) to sync a single pod.
|
||||
// Broken down by operation type. This metric is deprecated.
|
||||
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",
|
||||
DeprecatedPodWorkerLatency = metrics.NewSummaryVec(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPodWorkerLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds to sync a single pod. Broken down by operation type: create, update, or sync",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedPodStartLatency is a Summary that tracks the latency (in microseconds) for a single pod to go from pending to running.
|
||||
// This metric is deprecated.
|
||||
DeprecatedPodStartLatency = prometheus.NewSummary(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPodStartLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds for a single pod to go from pending to running.",
|
||||
DeprecatedPodStartLatency = metrics.NewSummary(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPodStartLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds for a single pod to go from pending to running.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// DeprecatedCgroupManagerLatency is a Summary that tracks the latency (in microseconds) for cgroup manager operations to complete.
|
||||
// Broken down by operation type. This metric is deprecated.
|
||||
DeprecatedCgroupManagerLatency = prometheus.NewSummaryVec(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedCgroupManagerOperationsKey,
|
||||
Help: "(Deprecated) Latency in microseconds for cgroup manager operations. Broken down by method.",
|
||||
DeprecatedCgroupManagerLatency = metrics.NewSummaryVec(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedCgroupManagerOperationsKey,
|
||||
Help: "(Deprecated) Latency in microseconds for cgroup manager operations. Broken down by method.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedPodWorkerStartLatency is a Summary that tracks the latency (in microseconds) from seeing a pod to starting a worker.
|
||||
// This metric is deprecated.
|
||||
DeprecatedPodWorkerStartLatency = prometheus.NewSummary(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPodWorkerStartLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds from seeing a pod to starting a worker.",
|
||||
DeprecatedPodWorkerStartLatency = metrics.NewSummary(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPodWorkerStartLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds from seeing a pod to starting a worker.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// DeprecatedPLEGRelistLatency is a Summary that tracks the latency (in microseconds) for relisting pods in PLEG.
|
||||
// This metric is deprecated.
|
||||
DeprecatedPLEGRelistLatency = prometheus.NewSummary(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPLEGRelistLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds for relisting pods in PLEG.",
|
||||
DeprecatedPLEGRelistLatency = metrics.NewSummary(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPLEGRelistLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds for relisting pods in PLEG.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// DeprecatedPLEGRelistInterval is a Summary that tracks the interval (in microseconds) between relistings in PLEG.
|
||||
// This metric is deprecated.
|
||||
DeprecatedPLEGRelistInterval = prometheus.NewSummary(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPLEGRelistIntervalKey,
|
||||
Help: "(Deprecated) Interval in microseconds between relisting in PLEG.",
|
||||
DeprecatedPLEGRelistInterval = metrics.NewSummary(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedPLEGRelistIntervalKey,
|
||||
Help: "(Deprecated) Interval in microseconds between relisting in PLEG.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// DeprecatedRuntimeOperations is a Counter that tracks the cumulative number of remote runtime operations.
|
||||
// Broken down by operation type. This metric is deprecated.
|
||||
DeprecatedRuntimeOperations = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedRuntimeOperationsKey,
|
||||
Help: "(Deprecated) Cumulative number of runtime operations by operation type.",
|
||||
DeprecatedRuntimeOperations = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedRuntimeOperationsKey,
|
||||
Help: "(Deprecated) Cumulative number of runtime operations by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedRuntimeOperationsLatency is a Summary that tracks the latency (in microseconds) of remote runtime operations
|
||||
// to complete. Broken down by operation type. This metric is deprecated.
|
||||
DeprecatedRuntimeOperationsLatency = prometheus.NewSummaryVec(
|
||||
prometheus.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedRuntimeOperationsLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds of runtime operations. Broken down by operation type.",
|
||||
DeprecatedRuntimeOperationsLatency = metrics.NewSummaryVec(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedRuntimeOperationsLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds of runtime operations. Broken down by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedRuntimeOperationsErrors is a Counter that tracks the cumulative number of remote runtime operation errors.
|
||||
// Broken down by operation type. This metric is deprecated.
|
||||
DeprecatedRuntimeOperationsErrors = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedRuntimeOperationsErrorsKey,
|
||||
Help: "(Deprecated) Cumulative number of runtime operation errors by operation type.",
|
||||
DeprecatedRuntimeOperationsErrors = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedRuntimeOperationsErrorsKey,
|
||||
Help: "(Deprecated) Cumulative number of runtime operation errors by operation type.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"operation_type"},
|
||||
)
|
||||
// DeprecatedEvictionStatsAge is a Summary that tracks the time (in microseconds) between when stats are collected and when a pod
|
||||
// is evicted based on those stats. Broken down by eviction signal. This metric is deprecated.
|
||||
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",
|
||||
DeprecatedEvictionStatsAge = metrics.NewSummaryVec(
|
||||
&metrics.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",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"eviction_signal"},
|
||||
)
|
||||
// DeprecatedDevicePluginRegistrationCount is a Counter that tracks the cumulative number of device plugin registrations.
|
||||
// Broken down by resource name. This metric is deprecated.
|
||||
DeprecatedDevicePluginRegistrationCount = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedDevicePluginRegistrationCountKey,
|
||||
Help: "(Deprecated) Cumulative number of device plugin registrations. Broken down by resource name.",
|
||||
DeprecatedDevicePluginRegistrationCount = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedDevicePluginRegistrationCountKey,
|
||||
Help: "(Deprecated) Cumulative number of device plugin registrations. Broken down by resource name.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"resource_name"},
|
||||
)
|
||||
// DeprecatedDevicePluginAllocationLatency is a Summary that tracks the latncy (in microseconds) for serving device plugin allocation requests.
|
||||
// Broken down by resource name. This metric is deprecated.
|
||||
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.",
|
||||
DeprecatedDevicePluginAllocationLatency = metrics.NewSummaryVec(
|
||||
&metrics.SummaryOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: DeprecatedDevicePluginAllocationLatencyKey,
|
||||
Help: "(Deprecated) Latency in microseconds to serve a device plugin Allocation request. Broken down by resource name.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"resource_name"},
|
||||
)
|
||||
@ -368,60 +398,66 @@ var (
|
||||
// Metrics for node config
|
||||
|
||||
// AssignedConfig is a Gauge that is set 1 if the Kubelet has a NodeConfig assigned.
|
||||
AssignedConfig = prometheus.NewGaugeVec(
|
||||
prometheus.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: AssignedConfigKey,
|
||||
Help: "The node's understanding of intended config. The count is always 1.",
|
||||
AssignedConfig = metrics.NewGaugeVec(
|
||||
&metrics.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: AssignedConfigKey,
|
||||
Help: "The node's understanding of intended config. The count is always 1.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{ConfigSourceLabelKey, ConfigUIDLabelKey, ConfigResourceVersionLabelKey, KubeletConfigKeyLabelKey},
|
||||
)
|
||||
// ActiveConfig is a Gauge that is set to 1 if the Kubelet has an active NodeConfig.
|
||||
ActiveConfig = prometheus.NewGaugeVec(
|
||||
prometheus.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: ActiveConfigKey,
|
||||
Help: "The config source the node is actively using. The count is always 1.",
|
||||
ActiveConfig = metrics.NewGaugeVec(
|
||||
&metrics.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: ActiveConfigKey,
|
||||
Help: "The config source the node is actively using. The count is always 1.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{ConfigSourceLabelKey, ConfigUIDLabelKey, ConfigResourceVersionLabelKey, KubeletConfigKeyLabelKey},
|
||||
)
|
||||
// LastKnownGoodConfig is a Gauge that is set to 1 if the Kubelet has a NodeConfig it can fall back to if there
|
||||
// are certain errors.
|
||||
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.",
|
||||
LastKnownGoodConfig = metrics.NewGaugeVec(
|
||||
&metrics.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.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{ConfigSourceLabelKey, ConfigUIDLabelKey, ConfigResourceVersionLabelKey, KubeletConfigKeyLabelKey},
|
||||
)
|
||||
// ConfigError is a Gauge that is set to 1 if the node is experiencing a configuration-related error.
|
||||
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.",
|
||||
ConfigError = metrics.NewGauge(
|
||||
&metrics.GaugeOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: ConfigErrorKey,
|
||||
Help: "This metric is true (1) if the node is experiencing a configuration-related error, false (0) otherwise.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
)
|
||||
// RunPodSandboxDuration is a Histogram that tracks the duration (in seconds) it takes to run Pod Sandbox operations.
|
||||
// Broken down by RuntimeClass.
|
||||
RunPodSandboxDuration = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
RunPodSandboxDuration = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RunPodSandboxDurationKey,
|
||||
Help: "Duration in seconds of the run_podsandbox operations. Broken down by RuntimeClass.",
|
||||
// Use DefBuckets for now, will customize the buckets if necessary.
|
||||
Buckets: prometheus.DefBuckets,
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"runtime_handler"},
|
||||
)
|
||||
// RunPodSandboxErrors is a Counter that tracks the cumulative number of Pod Sandbox operations errors.
|
||||
// Broken down by RuntimeClass.
|
||||
RunPodSandboxErrors = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RunPodSandboxErrorsKey,
|
||||
Help: "Cumulative number of the run_podsandbox operation errors by RuntimeClass.",
|
||||
RunPodSandboxErrors = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: KubeletSubsystem,
|
||||
Name: RunPodSandboxErrorsKey,
|
||||
Help: "Cumulative number of the run_podsandbox operation errors by RuntimeClass.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"runtime_handler"},
|
||||
)
|
||||
@ -433,43 +469,43 @@ var registerMetrics sync.Once
|
||||
func Register(containerCache kubecontainer.RuntimeCache, collectors ...prometheus.Collector) {
|
||||
// Register the metrics.
|
||||
registerMetrics.Do(func() {
|
||||
prometheus.MustRegister(NodeName)
|
||||
prometheus.MustRegister(PodWorkerDuration)
|
||||
prometheus.MustRegister(PodStartDuration)
|
||||
prometheus.MustRegister(CgroupManagerDuration)
|
||||
prometheus.MustRegister(PodWorkerStartDuration)
|
||||
prometheus.MustRegister(ContainersPerPodCount)
|
||||
prometheus.MustRegister(newPodAndContainerCollector(containerCache))
|
||||
prometheus.MustRegister(PLEGRelistDuration)
|
||||
prometheus.MustRegister(PLEGDiscardEvents)
|
||||
prometheus.MustRegister(PLEGRelistInterval)
|
||||
prometheus.MustRegister(RuntimeOperations)
|
||||
prometheus.MustRegister(RuntimeOperationsDuration)
|
||||
prometheus.MustRegister(RuntimeOperationsErrors)
|
||||
prometheus.MustRegister(Evictions)
|
||||
prometheus.MustRegister(EvictionStatsAge)
|
||||
prometheus.MustRegister(DevicePluginRegistrationCount)
|
||||
prometheus.MustRegister(DevicePluginAllocationDuration)
|
||||
prometheus.MustRegister(DeprecatedPodWorkerLatency)
|
||||
prometheus.MustRegister(DeprecatedPodStartLatency)
|
||||
prometheus.MustRegister(DeprecatedCgroupManagerLatency)
|
||||
prometheus.MustRegister(DeprecatedPodWorkerStartLatency)
|
||||
prometheus.MustRegister(DeprecatedPLEGRelistLatency)
|
||||
prometheus.MustRegister(DeprecatedPLEGRelistInterval)
|
||||
prometheus.MustRegister(DeprecatedRuntimeOperations)
|
||||
prometheus.MustRegister(DeprecatedRuntimeOperationsLatency)
|
||||
prometheus.MustRegister(DeprecatedRuntimeOperationsErrors)
|
||||
prometheus.MustRegister(DeprecatedEvictionStatsAge)
|
||||
prometheus.MustRegister(DeprecatedDevicePluginRegistrationCount)
|
||||
prometheus.MustRegister(DeprecatedDevicePluginAllocationLatency)
|
||||
legacyregistry.MustRegister(NodeName)
|
||||
legacyregistry.MustRegister(PodWorkerDuration)
|
||||
legacyregistry.MustRegister(PodStartDuration)
|
||||
legacyregistry.MustRegister(CgroupManagerDuration)
|
||||
legacyregistry.MustRegister(PodWorkerStartDuration)
|
||||
legacyregistry.MustRegister(ContainersPerPodCount)
|
||||
legacyregistry.RawMustRegister(newPodAndContainerCollector(containerCache))
|
||||
legacyregistry.MustRegister(PLEGRelistDuration)
|
||||
legacyregistry.MustRegister(PLEGDiscardEvents)
|
||||
legacyregistry.MustRegister(PLEGRelistInterval)
|
||||
legacyregistry.MustRegister(RuntimeOperations)
|
||||
legacyregistry.MustRegister(RuntimeOperationsDuration)
|
||||
legacyregistry.MustRegister(RuntimeOperationsErrors)
|
||||
legacyregistry.MustRegister(Evictions)
|
||||
legacyregistry.MustRegister(EvictionStatsAge)
|
||||
legacyregistry.MustRegister(DevicePluginRegistrationCount)
|
||||
legacyregistry.MustRegister(DevicePluginAllocationDuration)
|
||||
legacyregistry.MustRegister(DeprecatedPodWorkerLatency)
|
||||
legacyregistry.MustRegister(DeprecatedPodStartLatency)
|
||||
legacyregistry.MustRegister(DeprecatedCgroupManagerLatency)
|
||||
legacyregistry.MustRegister(DeprecatedPodWorkerStartLatency)
|
||||
legacyregistry.MustRegister(DeprecatedPLEGRelistLatency)
|
||||
legacyregistry.MustRegister(DeprecatedPLEGRelistInterval)
|
||||
legacyregistry.MustRegister(DeprecatedRuntimeOperations)
|
||||
legacyregistry.MustRegister(DeprecatedRuntimeOperationsLatency)
|
||||
legacyregistry.MustRegister(DeprecatedRuntimeOperationsErrors)
|
||||
legacyregistry.MustRegister(DeprecatedEvictionStatsAge)
|
||||
legacyregistry.MustRegister(DeprecatedDevicePluginRegistrationCount)
|
||||
legacyregistry.MustRegister(DeprecatedDevicePluginAllocationLatency)
|
||||
if utilfeature.DefaultFeatureGate.Enabled(features.DynamicKubeletConfig) {
|
||||
prometheus.MustRegister(AssignedConfig)
|
||||
prometheus.MustRegister(ActiveConfig)
|
||||
prometheus.MustRegister(LastKnownGoodConfig)
|
||||
prometheus.MustRegister(ConfigError)
|
||||
legacyregistry.MustRegister(AssignedConfig)
|
||||
legacyregistry.MustRegister(ActiveConfig)
|
||||
legacyregistry.MustRegister(LastKnownGoodConfig)
|
||||
legacyregistry.MustRegister(ConfigError)
|
||||
}
|
||||
for _, collector := range collectors {
|
||||
prometheus.MustRegister(collector)
|
||||
legacyregistry.RawMustRegister(collector)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
@ -32,6 +32,7 @@ go_library(
|
||||
"//staging/src/k8s.io/apimachinery/pkg/util/sets:go_default_library",
|
||||
"//staging/src/k8s.io/apimachinery/pkg/util/wait:go_default_library",
|
||||
"//staging/src/k8s.io/client-go/tools/record:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//vendor/k8s.io/klog:go_default_library",
|
||||
"//vendor/k8s.io/utils/exec:go_default_library",
|
||||
|
||||
@ -19,12 +19,12 @@ package prober
|
||||
import (
|
||||
"sync"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
v1 "k8s.io/api/core/v1"
|
||||
"k8s.io/apimachinery/pkg/types"
|
||||
"k8s.io/apimachinery/pkg/util/sets"
|
||||
"k8s.io/apimachinery/pkg/util/wait"
|
||||
"k8s.io/client-go/tools/record"
|
||||
"k8s.io/component-base/metrics"
|
||||
"k8s.io/klog"
|
||||
kubecontainer "k8s.io/kubernetes/pkg/kubelet/container"
|
||||
"k8s.io/kubernetes/pkg/kubelet/prober/results"
|
||||
@ -33,11 +33,12 @@ import (
|
||||
)
|
||||
|
||||
// ProberResults stores the cumulative number of a probe by result as prometheus metrics.
|
||||
var ProberResults = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: "prober",
|
||||
Name: "probe_total",
|
||||
Help: "Cumulative number of a liveness or readiness probe for a container by result.",
|
||||
var ProberResults = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: "prober",
|
||||
Name: "probe_total",
|
||||
Help: "Cumulative number of a liveness or readiness probe for a container by result.",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"probe_type",
|
||||
"result",
|
||||
|
||||
@ -47,6 +47,7 @@ go_library(
|
||||
"//staging/src/k8s.io/apiserver/pkg/util/flushwriter:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/logs:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/github.com/emicklei/go-restful:go_default_library",
|
||||
"//vendor/github.com/google/cadvisor/container:go_default_library",
|
||||
"//vendor/github.com/google/cadvisor/info/v1:go_default_library",
|
||||
|
||||
@ -10,6 +10,8 @@ go_library(
|
||||
srcs = ["metrics.go"],
|
||||
importpath = "k8s.io/kubernetes/pkg/kubelet/server/metrics",
|
||||
deps = [
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
],
|
||||
)
|
||||
|
||||
@ -21,6 +21,9 @@ import (
|
||||
"time"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
|
||||
"k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
)
|
||||
|
||||
const (
|
||||
@ -29,11 +32,12 @@ const (
|
||||
|
||||
var (
|
||||
// HTTPRequests tracks the number of the http requests received since the server started.
|
||||
HTTPRequests = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: "http_requests_total",
|
||||
Help: "Number of the http requests received since the server started",
|
||||
HTTPRequests = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: "http_requests_total",
|
||||
Help: "Number of the http requests received since the server started",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
// server_type aims to differentiate the readonly server and the readwrite server.
|
||||
// long_running marks whether the request is long-running or not.
|
||||
@ -41,22 +45,24 @@ var (
|
||||
[]string{"method", "path", "server_type", "long_running"},
|
||||
)
|
||||
// HTTPRequestsDuration tracks the duration in seconds to serve http requests.
|
||||
HTTPRequestsDuration = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
HTTPRequestsDuration = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: "http_requests_duration_seconds",
|
||||
Help: "Duration in seconds to serve http requests",
|
||||
// Use DefBuckets for now, will customize the buckets if necessary.
|
||||
Buckets: prometheus.DefBuckets,
|
||||
Buckets: prometheus.DefBuckets,
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"method", "path", "server_type", "long_running"},
|
||||
)
|
||||
// HTTPInflightRequests tracks the number of the inflight http requests.
|
||||
HTTPInflightRequests = prometheus.NewGaugeVec(
|
||||
prometheus.GaugeOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: "http_inflight_requests",
|
||||
Help: "Number of the inflight http requests",
|
||||
HTTPInflightRequests = metrics.NewGaugeVec(
|
||||
&metrics.GaugeOpts{
|
||||
Subsystem: kubeletSubsystem,
|
||||
Name: "http_inflight_requests",
|
||||
Help: "Number of the inflight http requests",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"method", "path", "server_type", "long_running"},
|
||||
)
|
||||
@ -67,9 +73,9 @@ var registerMetrics sync.Once
|
||||
// Register all metrics.
|
||||
func Register() {
|
||||
registerMetrics.Do(func() {
|
||||
prometheus.MustRegister(HTTPRequests)
|
||||
prometheus.MustRegister(HTTPRequestsDuration)
|
||||
prometheus.MustRegister(HTTPInflightRequests)
|
||||
legacyregistry.MustRegister(HTTPRequests)
|
||||
legacyregistry.MustRegister(HTTPRequestsDuration)
|
||||
legacyregistry.MustRegister(HTTPInflightRequests)
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@ -32,7 +32,7 @@ import (
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
restful "github.com/emicklei/go-restful"
|
||||
"github.com/emicklei/go-restful"
|
||||
cadvisormetrics "github.com/google/cadvisor/container"
|
||||
cadvisorapi "github.com/google/cadvisor/info/v1"
|
||||
"github.com/google/cadvisor/metrics"
|
||||
@ -56,6 +56,7 @@ import (
|
||||
"k8s.io/apiserver/pkg/util/flushwriter"
|
||||
"k8s.io/component-base/logs"
|
||||
compbasemetrics "k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
"k8s.io/kubernetes/pkg/api/legacyscheme"
|
||||
api "k8s.io/kubernetes/pkg/apis/core"
|
||||
"k8s.io/kubernetes/pkg/apis/core/v1/validation"
|
||||
@ -297,7 +298,7 @@ func (s *Server) InstallDefaultHandlers(enableCAdvisorJSONEndpoints bool) {
|
||||
|
||||
s.restfulCont.Add(stats.CreateHandlers(statsPath, s.host, s.resourceAnalyzer, enableCAdvisorJSONEndpoints))
|
||||
//lint:ignore SA1019 https://github.com/kubernetes/enhancements/issues/1206
|
||||
s.restfulCont.Handle(metricsPath, prometheus.Handler())
|
||||
s.restfulCont.Handle(metricsPath, legacyregistry.Handler())
|
||||
|
||||
// cAdvisor metrics are exposed under the secured handler as well
|
||||
r := prometheus.NewRegistry()
|
||||
@ -325,8 +326,9 @@ func (s *Server) InstallDefaultHandlers(enableCAdvisorJSONEndpoints bool) {
|
||||
)
|
||||
|
||||
// prober metrics are exposed under a different endpoint
|
||||
p := prometheus.NewRegistry()
|
||||
compbasemetrics.RegisterProcessStartTime(p)
|
||||
|
||||
p := compbasemetrics.NewKubeRegistry()
|
||||
compbasemetrics.RegisterProcessStartTime(p.RawRegister)
|
||||
p.MustRegister(prober.ProberResults)
|
||||
s.restfulCont.Handle(proberMetricsPath,
|
||||
promhttp.HandlerFor(p, promhttp.HandlerOpts{ErrorHandling: promhttp.ContinueOnError}),
|
||||
|
||||
@ -9,6 +9,7 @@ go_library(
|
||||
"//pkg/kubelet/volumemanager/cache:go_default_library",
|
||||
"//pkg/volume:go_default_library",
|
||||
"//pkg/volume/util:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//vendor/k8s.io/klog:go_default_library",
|
||||
],
|
||||
|
||||
@ -17,6 +17,7 @@ limitations under the License.
|
||||
package metrics
|
||||
|
||||
import (
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
"sync"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
@ -59,7 +60,7 @@ func (v volumeCount) add(state, plugin string) {
|
||||
// Register registers Volume Manager metrics.
|
||||
func Register(asw cache.ActualStateOfWorld, dsw cache.DesiredStateOfWorld, pluginMgr *volume.VolumePluginMgr) {
|
||||
registerMetrics.Do(func() {
|
||||
prometheus.MustRegister(&totalVolumesCollector{asw, dsw, pluginMgr})
|
||||
legacyregistry.RawMustRegister(&totalVolumesCollector{asw, dsw, pluginMgr})
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@ -41,7 +41,8 @@ go_library(
|
||||
"//staging/src/k8s.io/apimachinery/pkg/util/strategicpatch:go_default_library",
|
||||
"//staging/src/k8s.io/apiserver/pkg/util/feature:go_default_library",
|
||||
"//staging/src/k8s.io/client-go/kubernetes:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//vendor/k8s.io/klog:go_default_library",
|
||||
"//vendor/k8s.io/utils/strings:go_default_library",
|
||||
],
|
||||
|
||||
@ -20,7 +20,8 @@ import (
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"k8s.io/component-base/metrics"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
"k8s.io/kubernetes/pkg/volume"
|
||||
)
|
||||
|
||||
@ -29,36 +30,48 @@ const (
|
||||
statusFailUnknown = "fail-unknown"
|
||||
)
|
||||
|
||||
var storageOperationMetric = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
Name: "storage_operation_duration_seconds",
|
||||
Help: "Storage operation duration",
|
||||
Buckets: []float64{.1, .25, .5, 1, 2.5, 5, 10, 15, 25, 50, 120, 300, 600},
|
||||
/*
|
||||
* By default, all the following metrics are defined as falling under
|
||||
* ALPHA stability level https://github.com/kubernetes/enhancements/blob/master/keps/sig-instrumentation/20190404-kubernetes-control-plane-metrics-stability.md#stability-classes)
|
||||
*
|
||||
* Promoting the stability level of the metric is a responsibility of the component owner, since it
|
||||
* involves explicitly acknowledging support for the metric across multiple releases, in accordance with
|
||||
* the metric stability policy.
|
||||
*/
|
||||
var storageOperationMetric = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Name: "storage_operation_duration_seconds",
|
||||
Help: "Storage operation duration",
|
||||
Buckets: []float64{.1, .25, .5, 1, 2.5, 5, 10, 15, 25, 50, 120, 300, 600},
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"volume_plugin", "operation_name"},
|
||||
)
|
||||
|
||||
var storageOperationErrorMetric = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Name: "storage_operation_errors_total",
|
||||
Help: "Storage operation errors",
|
||||
var storageOperationErrorMetric = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Name: "storage_operation_errors_total",
|
||||
Help: "Storage operation errors",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"volume_plugin", "operation_name"},
|
||||
)
|
||||
|
||||
var storageOperationStatusMetric = prometheus.NewCounterVec(
|
||||
prometheus.CounterOpts{
|
||||
Name: "storage_operation_status_count",
|
||||
Help: "Storage operation return statuses count",
|
||||
var storageOperationStatusMetric = metrics.NewCounterVec(
|
||||
&metrics.CounterOpts{
|
||||
Name: "storage_operation_status_count",
|
||||
Help: "Storage operation return statuses count",
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"volume_plugin", "operation_name", "status"},
|
||||
)
|
||||
|
||||
var storageOperationEndToEndLatencyMetric = prometheus.NewHistogramVec(
|
||||
prometheus.HistogramOpts{
|
||||
Name: "volume_operation_total_seconds",
|
||||
Help: "Storage operation end to end duration in seconds",
|
||||
Buckets: []float64{.1, .25, .5, 1, 2.5, 5, 10, 15, 25, 50, 120, 300, 600},
|
||||
var storageOperationEndToEndLatencyMetric = metrics.NewHistogramVec(
|
||||
&metrics.HistogramOpts{
|
||||
Name: "volume_operation_total_seconds",
|
||||
Help: "Storage operation end to end duration in seconds",
|
||||
Buckets: []float64{.1, .25, .5, 1, 2.5, 5, 10, 15, 25, 50, 120, 300, 600},
|
||||
StabilityLevel: metrics.ALPHA,
|
||||
},
|
||||
[]string{"plugin_name", "operation_name"},
|
||||
)
|
||||
@ -68,10 +81,12 @@ func init() {
|
||||
}
|
||||
|
||||
func registerMetrics() {
|
||||
prometheus.MustRegister(storageOperationMetric)
|
||||
prometheus.MustRegister(storageOperationErrorMetric)
|
||||
prometheus.MustRegister(storageOperationStatusMetric)
|
||||
prometheus.MustRegister(storageOperationEndToEndLatencyMetric)
|
||||
// legacyregistry is the internal k8s wrapper around the prometheus
|
||||
// global registry, used specifically for metric stability enforcement
|
||||
legacyregistry.MustRegister(storageOperationMetric)
|
||||
legacyregistry.MustRegister(storageOperationErrorMetric)
|
||||
legacyregistry.MustRegister(storageOperationStatusMetric)
|
||||
legacyregistry.MustRegister(storageOperationEndToEndLatencyMetric)
|
||||
}
|
||||
|
||||
// OperationCompleteHook returns a hook to call when an operation is completed
|
||||
|
||||
@ -65,8 +65,8 @@ go_test(
|
||||
"//staging/src/k8s.io/client-go/tools/record:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/featuregate:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/featuregate/testing:go_default_library",
|
||||
"//staging/src/k8s.io/component-base/metrics/legacyregistry:go_default_library",
|
||||
"//staging/src/k8s.io/csi-translation-lib/plugins:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_golang/prometheus:go_default_library",
|
||||
"//vendor/github.com/prometheus/client_model/go:go_default_library",
|
||||
"//vendor/github.com/stretchr/testify/assert:go_default_library",
|
||||
],
|
||||
|
||||
@ -18,7 +18,6 @@ package operationexecutor
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"github.com/prometheus/client_golang/prometheus"
|
||||
"github.com/prometheus/client_model/go"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"k8s.io/api/core/v1"
|
||||
@ -30,6 +29,7 @@ import (
|
||||
"k8s.io/client-go/tools/record"
|
||||
"k8s.io/component-base/featuregate"
|
||||
featuregatetesting "k8s.io/component-base/featuregate/testing"
|
||||
"k8s.io/component-base/metrics/legacyregistry"
|
||||
"k8s.io/csi-translation-lib/plugins"
|
||||
"k8s.io/kubernetes/pkg/features"
|
||||
"k8s.io/kubernetes/pkg/volume"
|
||||
@ -229,7 +229,7 @@ func getTestVolumeToUnmount(pod *v1.Pod, pvSpec v1.PersistentVolumeSpec, pluginN
|
||||
}
|
||||
|
||||
func getMetricFamily(metricFamilyName string) *io_prometheus_client.MetricFamily {
|
||||
metricFamilies, _ := prometheus.DefaultGatherer.Gather()
|
||||
metricFamilies, _ := legacyregistry.DefaultGatherer.Gather()
|
||||
for _, mf := range metricFamilies {
|
||||
if *mf.Name == metricFamilyName {
|
||||
return mf
|
||||
|
||||
@ -32,17 +32,22 @@ var processStartTime = prometheus.NewGaugeVec(
|
||||
[]string{},
|
||||
)
|
||||
|
||||
// Registerer is an interface expected by RegisterProcessStartTime in order to register the metric
|
||||
type Registerer interface {
|
||||
Register(prometheus.Collector) error
|
||||
}
|
||||
|
||||
// RegisterProcessStartTime registers the process_start_time_seconds to
|
||||
// a prometheus registry. This metric needs to be included to ensure counter
|
||||
// data fidelity.
|
||||
func RegisterProcessStartTime(registerer prometheus.Registerer) error {
|
||||
func RegisterProcessStartTime(registrationFunc func(prometheus.Collector) error) error {
|
||||
start, err := getProcessStart()
|
||||
if err != nil {
|
||||
klog.Errorf("Could not get process start time, %v", err)
|
||||
start = float64(time.Now().Unix())
|
||||
}
|
||||
processStartTime.WithLabelValues().Set(start)
|
||||
return registerer.Register(processStartTime)
|
||||
return registrationFunc(processStartTime)
|
||||
}
|
||||
|
||||
func getProcessStart() (float64, error) {
|
||||
|
||||
@ -32,6 +32,6 @@ var (
|
||||
// RegisterBuildInfo registers the build and version info in a metadata metric in prometheus
|
||||
func RegisterBuildInfo(r KubeRegistry) {
|
||||
info := version.Get()
|
||||
buildInfo.WithLabelValues(info.Major, info.Minor, info.GitVersion, info.GitCommit, info.GitTreeState, info.BuildDate, info.GoVersion, info.Compiler, info.Platform).Set(1)
|
||||
r.MustRegister(buildInfo)
|
||||
buildInfo.WithLabelValues(info.Major, info.Minor, info.GitVersion, info.GitCommit, info.GitTreeState, info.BuildDate, info.GoVersion, info.Compiler, info.Platform).Set(1)
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user