diff --git a/test/instrumentation/documentation/main.go b/test/instrumentation/documentation/main.go index d52a3d4e0b7..e423ded75b6 100755 --- a/test/instrumentation/documentation/main.go +++ b/test/instrumentation/documentation/main.go @@ -53,9 +53,9 @@ description: >- This page details the metrics that different Kubernetes components export. You can query the metrics endpoint for these components using an HTTP scrape, and fetch the current metrics data in Prometheus format. -### List of Kubernetes Metrics +### List of Stable Kubernetes Metrics - +
@@ -67,7 +67,31 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu -{{range $index, $metric := .Metrics}} +{{range $index, $metric := .StableMetrics}} + + + + +{{if not $metric.Labels }}{{else }}{{end}} +{{if not $metric.ConstLabels }}{{else }}{{end}}{{end}} + +
Name
{{with $metric}}{{.BuildFQName}}{{end}}{{$metric.StabilityLevel}}{{$metric.Type}}{{$metric.Help}}None{{range $label := $metric.Labels}}
{{$label}}
{{end}}		None{{$metric.ConstLabels}}
+ +### List of Alpha Kubernetes Metrics + + + + + + + + + + + + + +{{range $index, $metric := .AlphaMetrics}} @@ -80,32 +104,35 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu ) type templateData struct { - Metrics []metric + AlphaMetrics []metric + StableMetrics []metric GeneratedDate time.Time } func main() { dat, err := os.ReadFile("test/instrumentation/testdata/documentation-list.yaml") if err == nil { - metrics := []metric{} - err = yaml.Unmarshal(dat, &metrics) + var parsedMetrics []metric + err = yaml.Unmarshal(dat, &parsedMetrics) if err != nil { println("err", err) } - sort.Sort(byFQName(metrics)) + sort.Sort(byFQName(parsedMetrics)) t := template.New("t").Funcs(funcMap) t, err := t.Parse(templ) if err != nil { println("err", err) } var tpl bytes.Buffer - for i, m := range metrics { + for i, m := range parsedMetrics { m.Help = strings.Join(strings.Split(m.Help, "\n"), ", ") _ = m.BuildFQName() // ignore golint error - metrics[i] = m + parsedMetrics[i] = m } + sortedMetrics := byStabilityLevel(parsedMetrics) data := templateData{ - Metrics: metrics, + AlphaMetrics: sortedMetrics["ALPHA"], + StableMetrics: sortedMetrics["STABLE"], GeneratedDate: time.Now(), } err = t.Execute(&tpl, data) @@ -154,3 +181,14 @@ func (ms byFQName) Less(i, j int) bool { func (ms byFQName) Swap(i, j int) { ms[i], ms[j] = ms[j], ms[i] } + +func byStabilityLevel(ms []metric) map[string][]metric { + res := map[string][]metric{} + for _, m := range ms { + if _, ok := res[m.StabilityLevel]; !ok { + res[m.StabilityLevel] = []metric{} + } + res[m.StabilityLevel] = append(res[m.StabilityLevel], m) + } + return res +} diff --git a/test/instrumentation/testdata/documentation.md b/test/instrumentation/testdata/documentation.md index c7085b7c24b..6a75ad66c48 100644 --- a/test/instrumentation/testdata/documentation.md +++ b/test/instrumentation/testdata/documentation.md @@ -6,14 +6,152 @@ description: >- --- -## Metrics (auto-generated 2022 Oct 25) +## Metrics (auto-generated 2022 Oct 27) This page details the metrics that different Kubernetes components export. You can query the metrics endpoint for these -components using an HTTP scrape, and fetch the current metrics data in Prometheus format. +components using an HTTP scrape, and fetch the metrics in Prometheus format. -### List of Kubernetes Metrics +### List of Stable Kubernetes Metrics -
NameStability LevelTypeHelpLabelsConst Labels
{{with $metric}}{{.BuildFQName}}{{end}} {{$metric.StabilityLevel}} {{$metric.Type}}
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
NameStability LevelTypeHelpLabelsConst Labels
apiserver_admission_controller_admission_duration_secondsSTABLEHistogramAdmission controller latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).
name
operation
rejected
type
None
apiserver_admission_step_admission_duration_secondsSTABLEHistogramAdmission sub-step latency histogram in seconds, broken out for each operation and API resource and step type (validate or admit).
operation
rejected
type
None
apiserver_admission_webhook_admission_duration_secondsSTABLEHistogramAdmission webhook latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).
name
operation
rejected
type
None
apiserver_current_inflight_requestsSTABLEGaugeMaximal number of currently used inflight request limit of this apiserver per request kind in last second.
request_kind
None
apiserver_longrunning_requestsSTABLEGaugeGauge of all active long-running apiserver requests broken out by verb, group, version, resource, scope and component. Not all requests are tracked this way.
component
group
resource
scope
subresource
verb
version
None
apiserver_request_duration_secondsSTABLEHistogramResponse latency distribution in seconds for each verb, dry run value, group, version, resource, subresource, scope and component.
component
dry_run
group
resource
scope
subresource
verb
version
None
apiserver_request_totalSTABLECounterCounter of apiserver requests broken out for each verb, dry run value, group, version, resource, scope, component, and HTTP response code.
code
component
dry_run
group
resource
scope
subresource
verb
version
None
apiserver_requested_deprecated_apisSTABLEGaugeGauge of deprecated APIs that have been requested, broken out by API group, version, resource, subresource, and removed_release.
group
removed_release
resource
subresource
version
None
apiserver_response_sizesSTABLEHistogramResponse size distribution in bytes for each group, version, verb, resource, subresource, scope and component.
component
group
resource
scope
subresource
verb
version
None
apiserver_storage_objectsSTABLEGaugeNumber of stored objects at the time of last check split by kind.
resource
None
node_collector_evictions_totalSTABLECounterNumber of Node evictions that happened since current instance of NodeController started.
zone
None
scheduler_framework_extension_point_duration_secondsSTABLEHistogramLatency for running all plugins of a specific extension point.
extension_point
profile
status
None
scheduler_pending_podsSTABLEGaugeNumber of pending pods, by the queue type. 'active' means number of pods in activeQ; 'backoff' means number of pods in backoffQ; 'unschedulable' means number of pods in unschedulablePods.
queue
None
scheduler_pod_scheduling_attemptsSTABLEHistogramNumber of attempts to successfully schedule a pod.NoneNone
scheduler_pod_scheduling_duration_secondsSTABLEHistogramE2e latency for a pod being scheduled which may include multiple scheduling attempts.
attempts
None
scheduler_preemption_attempts_totalSTABLECounterTotal preemption attempts in the cluster till nowNoneNone
scheduler_preemption_victimsSTABLEHistogramNumber of selected preemption victimsNoneNone
scheduler_queue_incoming_pods_totalSTABLECounterNumber of pods added to scheduling queues by event and queue type.
event
queue
None
scheduler_schedule_attempts_totalSTABLECounterNumber of attempts to schedule pods, by the result. 'unschedulable' means a pod could not be scheduled, while 'error' means an internal scheduler problem.
profile
result
None
scheduler_scheduling_attempt_duration_secondsSTABLEHistogramScheduling attempt latency in seconds (scheduling algorithm + binding)
profile
result
None
+ +### List of Alpha Kubernetes Metrics + + @@ -1682,125 +1820,5 @@ components using an HTTP scrape, and fetch the current metrics data in Prometheu - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
NameHow long in seconds processing an item from workqueue takes.
name
 None
apiserver_admission_controller_admission_duration_secondsSTABLEHistogramAdmission controller latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).
name
operation
rejected
type
None
apiserver_admission_step_admission_duration_secondsSTABLEHistogramAdmission sub-step latency histogram in seconds, broken out for each operation and API resource and step type (validate or admit).
operation
rejected
type
None
apiserver_admission_webhook_admission_duration_secondsSTABLEHistogramAdmission webhook latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).
name
operation
rejected
type
None
apiserver_current_inflight_requestsSTABLEGaugeMaximal number of currently used inflight request limit of this apiserver per request kind in last second.
request_kind
None
apiserver_longrunning_requestsSTABLEGaugeGauge of all active long-running apiserver requests broken out by verb, group, version, resource, scope and component. Not all requests are tracked this way.
component
group
resource
scope
subresource
verb
version
None
apiserver_request_duration_secondsSTABLEHistogramResponse latency distribution in seconds for each verb, dry run value, group, version, resource, subresource, scope and component.
component
dry_run
group
resource
scope
subresource
verb
version
None
apiserver_request_totalSTABLECounterCounter of apiserver requests broken out for each verb, dry run value, group, version, resource, scope, component, and HTTP response code.
code
component
dry_run
group
resource
scope
subresource
verb
version
None
apiserver_requested_deprecated_apisSTABLEGaugeGauge of deprecated APIs that have been requested, broken out by API group, version, resource, subresource, and removed_release.
group
removed_release
resource
subresource
version
None
apiserver_response_sizesSTABLEHistogramResponse size distribution in bytes for each group, version, verb, resource, subresource, scope and component.
component
group
resource
scope
subresource
verb
version
None
apiserver_storage_objectsSTABLEGaugeNumber of stored objects at the time of last check split by kind.
resource
None
node_collector_evictions_totalSTABLECounterNumber of Node evictions that happened since current instance of NodeController started.
zone
None
scheduler_framework_extension_point_duration_secondsSTABLEHistogramLatency for running all plugins of a specific extension point.
extension_point
profile
status
None
scheduler_pending_podsSTABLEGaugeNumber of pending pods, by the queue type. 'active' means number of pods in activeQ; 'backoff' means number of pods in backoffQ; 'unschedulable' means number of pods in unschedulablePods.
queue
None
scheduler_pod_scheduling_attemptsSTABLEHistogramNumber of attempts to successfully schedule a pod.NoneNone
scheduler_pod_scheduling_duration_secondsSTABLEHistogramE2e latency for a pod being scheduled which may include multiple scheduling attempts.
attempts
None
scheduler_preemption_attempts_totalSTABLECounterTotal preemption attempts in the cluster till nowNoneNone
scheduler_preemption_victimsSTABLEHistogramNumber of selected preemption victimsNoneNone
scheduler_queue_incoming_pods_totalSTABLECounterNumber of pods added to scheduling queues by event and queue type.
event
queue
None
scheduler_schedule_attempts_totalSTABLECounterNumber of attempts to schedule pods, by the result. 'unschedulable' means a pod could not be scheduled, while 'error' means an internal scheduler problem.
profile
result
None
scheduler_scheduling_attempt_duration_secondsSTABLEHistogramScheduling attempt latency in seconds (scheduling algorithm + binding)
profile
result
None