mirror of
https://github.com/k3s-io/kubernetes.git
synced 2025-07-18 17:33:39 +00:00
adjust sizes and documentation
Change-Id: Icd89c0c5bd6fbfb616255132db602b4db5ee2fe9
This commit is contained in:
Han Kang
parent
eb7253dfd5
commit
1e99f54bb6
@ -20,6 +20,7 @@ import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"os"
|
||||
"sort"
|
||||
"strings"
|
||||
"text/template"
|
||||
"time"
|
||||
@ -37,7 +38,7 @@ var (
|
||||
|
||||
const (
|
||||
templ = `---
|
||||
title: Kubernetes Metrics Across Components
|
||||
title: Kubernetes Metrics
|
||||
content_type: instrumentation
|
||||
---
|
||||
|
||||
@ -55,8 +56,8 @@ These are the metrics which are exported in Kubernetes components (i.e. kube-api
|
||||
<tr>
|
||||
<td width="20%">Name</td>
|
||||
<td width="10%">Stability Level</td>
|
||||
<td width="10%">Type</td>
|
||||
<td width="30%">Help</td>
|
||||
<td width="13%">Type</td>
|
||||
<td width="27%">Help</td>
|
||||
<td width="20%">Labels</td>
|
||||
<td width="10%">Const Labels</td>
|
||||
</tr>
|
||||
@ -82,6 +83,7 @@ func main() {
|
||||
if err != nil {
|
||||
println("err", err)
|
||||
}
|
||||
sort.Sort(byFQName(metrics))
|
||||
t := template.New("t")
|
||||
t, err := t.Parse(templ)
|
||||
if err != nil {
|
||||
@ -128,3 +130,18 @@ type metric struct {
|
||||
func (m metric) BuildFQName() string {
|
||||
return metrics.BuildFQName(m.Namespace, m.Subsystem, m.Name)
|
||||
}
|
||||
|
||||
type byFQName []metric
|
||||
|
||||
func (ms byFQName) Len() int { return len(ms) }
|
||||
func (ms byFQName) Less(i, j int) bool {
|
||||
if ms[i].StabilityLevel < ms[j].StabilityLevel {
|
||||
return true
|
||||
} else if ms[i].StabilityLevel > ms[j].StabilityLevel {
|
||||
return false
|
||||
}
|
||||
return ms[i].BuildFQName() < ms[j].BuildFQName()
|
||||
}
|
||||
func (ms byFQName) Swap(i, j int) {
|
||||
ms[i], ms[j] = ms[j], ms[i]
|
||||
}
|
||||
|
||||
@ -89,6 +89,12 @@ func main() {
|
||||
if len(stableMetrics) == 0 {
|
||||
os.Exit(0)
|
||||
}
|
||||
for i, m := range stableMetrics {
|
||||
if m.StabilityLevel == "" {
|
||||
m.StabilityLevel = "ALPHA"
|
||||
}
|
||||
stableMetrics[i] = m
|
||||
}
|
||||
sort.Sort(byFQName(stableMetrics))
|
||||
data, err := yaml.Marshal(stableMetrics)
|
||||
if err != nil {
|
||||
|
||||
@ -115,7 +115,7 @@ kube::update::documentation::list() {
|
||||
exit 1
|
||||
fi
|
||||
mv -f "$temp_file" "${KUBE_ROOT}/test/instrumentation/testdata/documentation-list.yaml"
|
||||
echo "${green}Updated golden list of stable metrics.${reset}"
|
||||
echo "${green}Updated list of metrics for documentation ${reset}"
|
||||
}
|
||||
|
||||
kube::update::documentation() {
|
||||
|
||||
@ -12,12 +12,6 @@
|
||||
certificate is invalid or unused, the value will be +INF.
|
||||
type: Gauge
|
||||
stabilityLevel: ALPHA
|
||||
- name: endpointslices_changed_per_sync
|
||||
subsystem: endpoint_slice_controller
|
||||
help: Number of EndpointSlices changed on each Service sync
|
||||
type: Histogram
|
||||
labels:
|
||||
- topology
|
||||
- name: cronjob_job_creation_skew_duration_seconds
|
||||
subsystem: cronjob_controller
|
||||
help: Time between when a cronjob is scheduled to be run, and when the corresponding
|
||||
@ -94,6 +88,13 @@
|
||||
- 8192
|
||||
- 16384
|
||||
- 32768
|
||||
- name: endpointslices_changed_per_sync
|
||||
subsystem: endpoint_slice_controller
|
||||
help: Number of EndpointSlices changed on each Service sync
|
||||
type: Histogram
|
||||
stabilityLevel: ALPHA
|
||||
labels:
|
||||
- topology
|
||||
- name: num_endpoint_slices
|
||||
subsystem: endpoint_slice_controller
|
||||
help: Number of EndpointSlices
|
||||
@ -269,22 +270,6 @@
|
||||
stabilityLevel: ALPHA
|
||||
labels:
|
||||
- code
|
||||
- name: job_pods_finished_total
|
||||
subsystem: job_controller
|
||||
help: The number of finished Pods that are fully tracked
|
||||
type: Counter
|
||||
labels:
|
||||
- completion_mode
|
||||
- result
|
||||
- name: terminated_pods_tracking_finalizer_total
|
||||
subsystem: job_controller
|
||||
help: |-
|
||||
`The number of terminated pods (phase=Failed|Succeeded)
|
||||
that have the finalizer batch.kubernetes.io/job-tracking
|
||||
The event label can be "add" or "delete".`
|
||||
type: Counter
|
||||
labels:
|
||||
- event
|
||||
- name: attachdetach_controller_forced_detaches
|
||||
help: Number of times the A/D Controller performed a forced detach
|
||||
type: Counter
|
||||
@ -297,6 +282,14 @@
|
||||
labels:
|
||||
- completion_mode
|
||||
- result
|
||||
- name: job_pods_finished_total
|
||||
subsystem: job_controller
|
||||
help: The number of finished Pods that are fully tracked
|
||||
type: Counter
|
||||
stabilityLevel: ALPHA
|
||||
labels:
|
||||
- completion_mode
|
||||
- result
|
||||
- name: job_sync_duration_seconds
|
||||
subsystem: job_controller
|
||||
help: The time it took to sync a job
|
||||
@ -331,6 +324,16 @@
|
||||
- action
|
||||
- completion_mode
|
||||
- result
|
||||
- name: terminated_pods_tracking_finalizer_total
|
||||
subsystem: job_controller
|
||||
help: |-
|
||||
`The number of terminated pods (phase=Failed|Succeeded)
|
||||
that have the finalizer batch.kubernetes.io/job-tracking
|
||||
The event label can be "add" or "delete".`
|
||||
type: Counter
|
||||
stabilityLevel: ALPHA
|
||||
labels:
|
||||
- event
|
||||
- name: evictions_number
|
||||
subsystem: node_collector
|
||||
help: Number of Node evictions that happened since current instance of NodeController
|
||||
|
||||
444
test/instrumentation/testdata/documentation.md
vendored
444
test/instrumentation/testdata/documentation.md
vendored
@ -1,5 +1,5 @@
|
||||
---
|
||||
title: Kubernetes Metrics Across Components
|
||||
title: Kubernetes Metrics
|
||||
content_type: instrumentation
|
||||
---
|
||||
|
||||
@ -17,165 +17,18 @@ These are the metrics which are exported in Kubernetes components (i.e. kube-api
|
||||
<tr>
|
||||
<td width="20%">Name</td>
|
||||
<td width="10%">Stability Level</td>
|
||||
<td width="10%">Type</td>
|
||||
<td width="30%">Help</td>
|
||||
<td width="13%">Type</td>
|
||||
<td width="27%">Help</td>
|
||||
<td width="20%">Labels</td>
|
||||
<td width="10%">Const Labels</td>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr><td>etcd_version_info</td><td>ALPHA</td><td>Gauge</td><td>Etcd server's binary version</td><td><div>binary_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_client_ttl_seconds</td><td>ALPHA</td><td>Gauge</td><td>Gauge of the TTL (time-to-live) of the Kubelet's client certificate. The value is in seconds until certificate expiry (negative if already expired). If client certificate is invalid or unused, the value will be +INF.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpointslices_changed_per_sync</td><td></td><td>Histogram</td><td>Number of EndpointSlices changed on each Service sync</td><td><div>topology</div></td><td>None</td></tr>
|
||||
<tr><td>cronjob_controller_cronjob_job_creation_skew_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Time between when a cronjob is scheduled to be run, and when the corresponding job is created</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_changes</td><td>ALPHA</td><td>Counter</td><td>Number of EndpointSlice changes</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_desired_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices that would exist with perfect endpoint allocation</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpoints_added_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints added on each Service sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpoints_desired</td><td>ALPHA</td><td>Gauge</td><td>Number of endpoints desired</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpoints_removed_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints removed on each Service sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_num_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_syncs</td><td>ALPHA</td><td>Counter</td><td>Number of EndpointSlice syncs</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_addresses_skipped_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of addresses skipped on each Endpoints sync due to being invalid or exceeding MaxEndpointsPerSubset</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_changes</td><td>ALPHA</td><td>Counter</td><td>Number of EndpointSlice changes</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_desired_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices that would exist with perfect endpoint allocation</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_added_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints added on each Endpoints sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_desired</td><td>ALPHA</td><td>Gauge</td><td>Number of endpoints desired</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_removed_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints removed on each Endpoints sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_sync_duration</td><td>ALPHA</td><td>Histogram</td><td>Duration of syncEndpoints() in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_updated_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints updated on each Endpoints sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_num_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>garbagecollector_controller_resources_sync_error_total</td><td>ALPHA</td><td>Counter</td><td>Number of garbage collector resources sync errors</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>root_ca_cert_publisher_sync_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Number of namespace syncs happened in root ca cert publisher.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>root_ca_cert_publisher_sync_total</td><td>ALPHA</td><td>Counter</td><td>Number of namespace syncs happened in root ca cert publisher.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_pods_finished_total</td><td></td><td>Counter</td><td>The number of finished Pods that are fully tracked</td><td><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_terminated_pods_tracking_finalizer_total</td><td></td><td>Counter</td><td>`The number of terminated pods (phase=Failed|Succeeded), that have the finalizer batch.kubernetes.io/job-tracking, The event label can be "add" or "delete".`</td><td><div>event</div></td><td>None</td></tr>
|
||||
<tr><td>attachdetach_controller_forced_detaches</td><td>ALPHA</td><td>Counter</td><td>Number of times the A/D Controller performed a forced detach</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_finished_total</td><td>ALPHA</td><td>Counter</td><td>The number of finished job</td><td><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_sync_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>The time it took to sync a job</td><td><div>action</div><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_sync_total</td><td>ALPHA</td><td>Counter</td><td>The number of job syncs</td><td><div>action</div><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_evictions_number</td><td>ALPHA</td><td>Counter</td><td>Number of Node evictions that happened since current instance of NodeController started, This metric is replaced by node_collector_evictions_total.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_unhealthy_nodes_in_zone</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring number of not Ready Nodes per zones.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_zone_health</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring percentage of healthy nodes per zone.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_zone_size</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring number of registered Nodes per zones.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_allocation_tries_per_request</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints added on each Service sync</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_cidrs_allocations_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR allocations.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_cidrs_releases_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR releases.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_usage_cidrs</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring percentage of allocated CIDRs.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_allocation_tries_per_request</td><td>ALPHA</td><td>Histogram</td><td>Histogram measuring CIDR allocation tries per request.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_cidrs_allocations_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR allocations.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_cidrs_releases_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR releases.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_usage_cidrs</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring percentage of allocated CIDRs.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>replicaset_controller_sorting_deletion_age_ratio</td><td>ALPHA</td><td>Histogram</td><td>The ratio of chosen deleted pod's ages to the current youngest pod's age (at the time). Should be <2.The intent of this metric is to measure the rough efficacy of the LogarithmicScaleDown feature gate's effect onthe sorting (and deletion) of pods when a replicaset scales down. This only considers Ready pods when calculating and reporting.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>ttl_after_finished_controller_job_deletion_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>The time it took to delete the job since it became eligible for deletion</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>node_collector_evictions_total</td><td>STABLE</td><td>Counter</td><td>Number of Node evictions that happened since current instance of NodeController started.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>ephemeral_volume_controller_create_failures_total</td><td>ALPHA</td><td>Counter</td><td>Number of PersistenVolumeClaims creation requests</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>ephemeral_volume_controller_create_total</td><td>ALPHA</td><td>Counter</td><td>Number of PersistenVolumeClaims creation requests</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_client_expiration_renew_errors</td><td>ALPHA</td><td>Counter</td><td>Counter of certificate renewal errors.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_server_rotation_seconds</td><td>ALPHA</td><td>Histogram</td><td>Histogram of the number of seconds the previous certificate lived before being rotated.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_server_ttl_seconds</td><td>ALPHA</td><td>Gauge</td><td>Gauge of the shortest TTL (time-to-live) of the Kubelet's serving certificate. The value is in seconds until certificate expiry (negative if already expired). If serving certificate is invalid or unused, the value will be +INF.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_kubelet_credential_provider_plugin_duration</td><td>ALPHA</td><td>Histogram</td><td>Duration of execution in seconds for credential provider plugin</td><td><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_kubelet_credential_provider_plugin_errors</td><td>ALPHA</td><td>Counter</td><td>Number of errors from credential provider plugin</td><td><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_server_expiration_renew_errors</td><td>ALPHA</td><td>Counter</td><td>Counter of certificate renewal errors.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_operation_total_errors</td><td>ALPHA</td><td>Counter</td><td>Total volume operation errors</td><td><div>operation_name</div><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_cgroup_manager_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds for cgroup manager operations. Broken down by method.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_containers_per_pod_count</td><td>ALPHA</td><td>Histogram</td><td>The number of containers per pod.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_device_plugin_alloc_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to serve a device plugin Allocation request. Broken down by resource name.</td><td><div>resource_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_device_plugin_registration_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of device plugin registrations. Broken down by resource name.</td><td><div>resource_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_eviction_stats_age_seconds</td><td>ALPHA</td><td>Histogram</td><td>Time between when stats are collected, and when pod is evicted based on those stats by eviction signal</td><td><div>eviction_signal</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_evictions</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of pod evictions by eviction signal</td><td><div>eviction_signal</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_graceful_shutdown_end_time_seconds</td><td>ALPHA</td><td>Gauge</td><td>Last graceful shutdown start time since unix epoch in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_graceful_shutdown_start_time_seconds</td><td>ALPHA</td><td>Gauge</td><td>Last graceful shutdown start time since unix epoch in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_http_inflight_requests</td><td>ALPHA</td><td>Gauge</td><td>Number of the inflight http requests</td><td><div>long_running</div><div>method</div><div>path</div><div>server_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_http_requests_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to serve http requests</td><td><div>long_running</div><div>method</div><div>path</div><div>server_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_http_requests_total</td><td>ALPHA</td><td>Counter</td><td>Number of the http requests received since the server started</td><td><div>long_running</div><div>method</div><div>path</div><div>server_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_lifecycle_handler_http_fallbacks_total</td><td>ALPHA</td><td>Counter</td><td>The number of times lifecycle handlers successfully fell back to http from https.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_managed_ephemeral_containers</td><td>ALPHA</td><td>Gauge</td><td>Current number of ephemeral containers in pods managed by this kubelet. Ephemeral containers will be ignored if disabled by the EphemeralContainers feature gate, and this number will be 0.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_node_name</td><td>ALPHA</td><td>Gauge</td><td>The node's name. The count is always 1.</td><td><div>node</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_discard_events</td><td>ALPHA</td><td>Counter</td><td>The number of discard events in PLEG.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_last_seen_seconds</td><td>ALPHA</td><td>Gauge</td><td>Timestamp in seconds when PLEG was last seen active.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_relist_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds for relisting pods in PLEG.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_relist_interval_seconds</td><td>ALPHA</td><td>Histogram</td><td>Interval in seconds between relisting in PLEG.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_errors_get_allocatable</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource GetAllocatableResources endpoint which returned error. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_errors_list</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource List endpoint which returned error. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_requests_get_allocatable</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource GetAllocatableResources endpoint. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_requests_list</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource List endpoint. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_requests_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of requests to the PodResource endpoint. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_start_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds from kubelet seeing a pod for the first time to the pod starting to run</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_status_sync_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to sync a pod status update. Measures time from detection of a change to pod status until the API is successfully updated for that pod, even if multiple intevening changes to pod status occur.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_worker_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to sync a single pod. Broken down by operation type: create, update, or sync</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_worker_start_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds from kubelet seeing a pod to starting a worker.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_preemptions</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of pod preemptions by preemption resource</td><td><div>preemption_signal</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_run_podsandbox_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds of the run_podsandbox operations. Broken down by RuntimeClass.Handler.</td><td><div>runtime_handler</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_run_podsandbox_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of the run_podsandbox operation errors by RuntimeClass.Handler.</td><td><div>runtime_handler</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_running_containers</td><td>ALPHA</td><td>Gauge</td><td>Number of containers currently running</td><td><div>container_state</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_running_pods</td><td>ALPHA</td><td>Gauge</td><td>Number of pods that have a running pod sandbox</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_runtime_operations_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds of runtime operations. Broken down by operation type.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_runtime_operations_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of runtime operation errors by operation type.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_runtime_operations_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of runtime operations by operation type.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_containers_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of errors when starting containers</td><td><div>code</div><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_containers_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of containers started</td><td><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_host_process_containers_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of errors when starting hostprocess containers. This metric will only be collected on Windows and requires WindowsHostProcessContainers feature gate to be enabled.</td><td><div>code</div><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_host_process_containers_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of hostprocess containers started. This metric will only be collected on Windows and requires WindowsHostProcessContainers feature gate to be enabled.</td><td><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_pods_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of errors when starting pods</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_pods_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of pods started</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_volume_metric_collection_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to calculate volume stats</td><td><div>metric_source</div></td><td>None</td></tr>
|
||||
<tr><td>prober_probe_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds for a probe response.</td><td><div>container</div><div>namespace</div><div>pod</div><div>probe_type</div></td><td>None</td></tr>
|
||||
<tr><td>prober_probe_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of a liveness, readiness or startup probe for a container by result.</td><td><div>container</div><div>namespace</div><div>pod</div><div>pod_uid</div><div>probe_type</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_certificates_registry_csr_honored_duration_total</td><td>ALPHA</td><td>Counter</td><td>Total number of issued CSRs with a requested duration that was honored, sliced by signer (only kubernetes.io signer names are specifically identified)</td><td><div>signerName</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_certificates_registry_csr_requested_duration_total</td><td>ALPHA</td><td>Counter</td><td>Total number of issued CSRs with a requested duration, sliced by signer (only kubernetes.io signer names are specifically identified)</td><td><div>signerName</div></td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_network_programming_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>In Cluster Network Programming Latency in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>SyncProxyRules latency in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_endpoint_changes_pending</td><td>ALPHA</td><td>Gauge</td><td>Pending proxy rules Endpoint changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_endpoint_changes_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative proxy rules Endpoint changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_iptables_restore_failures_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative proxy iptables restore failures</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_iptables_total</td><td>ALPHA</td><td>Gauge</td><td>Number of proxy iptables rules programmed</td><td><div>table</div></td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_last_queued_timestamp_seconds</td><td>ALPHA</td><td>Gauge</td><td>The last time a sync of proxy rules was queued</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_last_timestamp_seconds</td><td>ALPHA</td><td>Gauge</td><td>The last time proxy rules were successfully synced</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_no_local_endpoints_total</td><td>ALPHA</td><td>Gauge</td><td>Number of services with a Local traffic policy and no endpoints</td><td><div>traffic_policy</div></td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_service_changes_pending</td><td>ALPHA</td><td>Gauge</td><td>Pending proxy rules Service changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_service_changes_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative proxy rules Service changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_container_errors_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when kubelet cannot compute SELinux context for a container. Kubelet can't start such a Pod then and it will retry, therefore value of this metric may not represent the actual nr. of containers.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_container_warnings_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when kubelet cannot compute SELinux context for a container that are ignored. They will become real errors when SELinuxMountReadWriteOncePod feature is expanded to all volume access modes.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_pod_context_mismatch_errors_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod defines different SELinux contexts for its containers that use the same volume. Kubelet can't start such a Pod then and it will retry, therefore value of this metric may not represent the actual nr. of Pods.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_pod_context_mismatch_warnings_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod defines different SELinux contexts for its containers that use the same volume. They are not errors yet, but they will become real errors when SELinuxMountReadWriteOncePod feature is expanded to all volume access modes.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_volume_context_mismatch_errors_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod uses a volume that is already mounted with a different SELinux context than the Pod needs. Kubelet can't start such a Pod then and it will retry, therefore value of this metric may not represent the actual nr. of Pods.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_volume_context_mismatch_warnings_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod uses a volume that is already mounted with a different SELinux context than the Pod needs. They are not errors yet, but they will become real errors when SELinuxMountReadWriteOncePod feature is expanded to all volume access modes.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_volumes_admitted_total</td><td>ALPHA</td><td>Gauge</td><td>Number of volumes whose SELinux context was fine and will be mounted with mount -o context option.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_allocated_ips</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring the number of allocated IPs for Services</td><td><div>cidr</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_allocation_errors_total</td><td>ALPHA</td><td>Counter</td><td>Number of errors trying to allocate Cluster IPs</td><td><div>cidr</div><div>scope</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_allocation_total</td><td>ALPHA</td><td>Counter</td><td>Number of Cluster IPs allocations</td><td><div>cidr</div><div>scope</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_available_ips</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring the number of available IPs for Services</td><td><div>cidr</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_pod_logs_pods_logs_backend_tls_failure_total</td><td>ALPHA</td><td>Counter</td><td>Total number of requests for pods/logs that failed due to kubelet server TLS verification</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_pod_logs_pods_logs_insecure_backend_total</td><td>ALPHA</td><td>Counter</td><td>Total number of requests for pods/logs sliced by usage type: enforce_tls, skip_tls_allowed, skip_tls_denied</td><td><div>usage</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_e2e_scheduling_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>E2e scheduling latency in seconds (scheduling algorithm + binding). This metric is replaced by scheduling_attempt_duration_seconds.</td><td><div>profile</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_goroutines</td><td>ALPHA</td><td>Gauge</td><td>Number of running goroutines split by the work they do such as binding.</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_permit_wait_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration of waiting on permit.</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_plugin_execution_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration for running a plugin at a specific extension point.</td><td><div>extension_point</div><div>plugin</div><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduler_cache_size</td><td>ALPHA</td><td>Gauge</td><td>Number of nodes, pods, and assumed (bound) pods in the scheduler cache.</td><td><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduler_goroutines</td><td>ALPHA</td><td>Gauge</td><td>Number of running goroutines split by the work they do such as binding. This metric is replaced by the \"goroutines\" metric.</td><td><div>work</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduling_algorithm_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Scheduling algorithm latency in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_unschedulable_pods</td><td>ALPHA</td><td>Gauge</td><td>The number of unschedulable pods broken down by plugin name. A pod will increment the gauge for all plugins that caused it to not schedule and so this metric have meaning only when broken down by plugin.</td><td><div>plugin</div><div>profile</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_volume_binder_cache_requests_total</td><td>ALPHA</td><td>Counter</td><td>Total number for request volume binding cache</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_volume_scheduling_stage_error_total</td><td>ALPHA</td><td>Counter</td><td>Volume scheduling stage error count</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>serviceaccount_legacy_tokens_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative legacy service account tokens used</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>serviceaccount_stale_tokens_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative stale projected service account tokens used</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>serviceaccount_valid_tokens_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative valid projected service account tokens used</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_framework_extension_point_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Latency for running all plugins of a specific extension point.</td><td><div>extension_point</div><div>profile</div><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_pending_pods</td><td>STABLE</td><td>Gauge</td><td>Number 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.</td><td><div>queue</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_pod_scheduling_attempts</td><td>STABLE</td><td>Histogram</td><td>Number of attempts to successfully schedule a pod.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_pod_scheduling_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>E2e latency for a pod being scheduled which may include multiple scheduling attempts.</td><td><div>attempts</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_preemption_attempts_total</td><td>STABLE</td><td>Counter</td><td>Total preemption attempts in the cluster till now</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_preemption_victims</td><td>STABLE</td><td>Histogram</td><td>Number of selected preemption victims</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_queue_incoming_pods_total</td><td>STABLE</td><td>Counter</td><td>Number of pods added to scheduling queues by event and queue type.</td><td><div>event</div><div>queue</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_schedule_attempts_total</td><td>STABLE</td><td>Counter</td><td>Number of attempts to schedule pods, by the result. 'unschedulable' means a pod could not be scheduled, while 'error' means an internal scheduler problem.</td><td><div>profile</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduling_attempt_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Scheduling attempt latency in seconds (scheduling algorithm + binding)</td><td><div>profile</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>csi_operations_seconds</td><td>ALPHA</td><td>Histogram</td><td>Container Storage Interface operation duration with gRPC error code status total</td><td><div>driver_name</div><div>grpc_status_code</div><div>method_name</div><div>migrated</div></td><td>None</td></tr>
|
||||
<tr><td>storage_operation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Storage operation duration</td><td><div>migrated</div><div>operation_name</div><div>status</div><div>volume_plugin</div></td><td>None</td></tr>
|
||||
<tr><td>volume_operation_total_seconds</td><td>ALPHA</td><td>Histogram</td><td>Storage operation end to end duration in seconds</td><td><div>operation_name</div><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>node_authorizer_graph_actions_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Histogram of duration of graph actions in node authorizer.</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>aggregator_openapi_v2_regeneration_count</td><td>ALPHA</td><td>Counter</td><td>Counter of OpenAPI v2 spec regeneration count broken down by causing APIService name and reason.</td><td><div>apiservice</div><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>aggregator_openapi_v2_regeneration_duration</td><td>ALPHA</td><td>Gauge</td><td>Gauge of OpenAPI v2 spec regeneration duration in seconds.</td><td><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>aggregator_unavailable_apiservice_total</td><td>ALPHA</td><td>Counter</td><td>Counter of APIServices which are marked as unavailable broken down by APIService name and reason.</td><td><div>name</div><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>apiextensions_openapi_v2_regeneration_count</td><td>ALPHA</td><td>Counter</td><td>Counter of OpenAPI v2 spec regeneration count broken down by causing CRD name and reason.</td><td><div>crd</div><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>apiextensions_openapi_v3_regeneration_count</td><td>ALPHA</td><td>Counter</td><td>Counter of OpenAPI v3 spec regeneration count broken down by group, version, causing CRD and reason.</td><td><div>crd</div><div>group</div><div>reason</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_crd_webhook_conversion_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>CRD webhook conversion duration in seconds</td><td><div>crd_name</div><div>from_version</div><div>succeeded</div><div>to_version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_step_admission_duration_seconds_summary</td><td>ALPHA</td><td>Summary</td><td>Admission sub-step latency summary in seconds, broken out for each operation and API resource and step type (validate or admit).</td><td><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_webhook_fail_open_count</td><td>ALPHA</td><td>Counter</td><td>Admission webhook fail open count, identified by name and broken out for each admission type (validating or mutating).</td><td><div>name</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_webhook_rejection_count</td><td>ALPHA</td><td>Counter</td><td>Admission webhook rejection count, identified by name and broken out for each admission type (validating or admit) and operation. Additional labels specify an error type (calling_webhook_error or apiserver_internal_error if an error occurred; no_error otherwise) and optionally a non-zero rejection code if the webhook rejects the request with an HTTP status code (honored by the apiserver when the code is greater or equal to 400). Codes greater than 600 are truncated to 600, to keep the metrics cardinality bounded.</td><td><div>error_type</div><div>name</div><div>operation</div><div>rejection_code</div><div>type</div></td><td>None</td></tr>
|
||||
@ -184,47 +37,22 @@ These are the metrics which are exported in Kubernetes components (i.e. kube-api
|
||||
<tr><td>apiserver_audit_event_total</td><td>ALPHA</td><td>Counter</td><td>Counter of audit events generated and sent to the audit backend.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_audit_level_total</td><td>ALPHA</td><td>Counter</td><td>Counter of policy levels for audit events (1 per request).</td><td><div>level</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_audit_requests_rejected_total</td><td>ALPHA</td><td>Counter</td><td>Counter of apiserver requests rejected due to an error in audit logging backend.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_delegated_authn_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request latency in seconds. Broken down by status code.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_delegated_authn_request_total</td><td>ALPHA</td><td>Counter</td><td>Number of HTTP requests partitioned by status code.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_controller_admission_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Admission controller latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).</td><td><div>name</div><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_step_admission_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Admission sub-step latency histogram in seconds, broken out for each operation and API resource and step type (validate or admit).</td><td><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_webhook_admission_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Admission webhook latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).</td><td><div>name</div><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cache_list_fetched_objects_total</td><td>ALPHA</td><td>Counter</td><td>Number of objects read from watch cache in the course of serving a LIST request</td><td><div>index</div><div>resource_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cache_list_returned_objects_total</td><td>ALPHA</td><td>Counter</td><td>Number of objects returned for a LIST request from watch cache</td><td><div>resource_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cache_list_total</td><td>ALPHA</td><td>Counter</td><td>Number of LIST requests served from watch cache</td><td><div>index</div><div>resource_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cel_compilation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td></td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_cel_evaluation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td></td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_certificates_registry_csr_honored_duration_total</td><td>ALPHA</td><td>Counter</td><td>Total number of issued CSRs with a requested duration that was honored, sliced by signer (only kubernetes.io signer names are specifically identified)</td><td><div>signerName</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_certificates_registry_csr_requested_duration_total</td><td>ALPHA</td><td>Counter</td><td>Total number of issued CSRs with a requested duration, sliced by signer (only kubernetes.io signer names are specifically identified)</td><td><div>signerName</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_client_certificate_expiration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Distribution of the remaining lifetime on the certificate used to authenticate a request.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_crd_webhook_conversion_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>CRD webhook conversion duration in seconds</td><td><div>crd_name</div><div>from_version</div><div>succeeded</div><div>to_version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_current_inqueue_requests</td><td>ALPHA</td><td>Gauge</td><td>Maximal number of queued requests in this apiserver per request kind in last second.</td><td><div>request_kind</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_delegated_authn_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request latency in seconds. Broken down by status code.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_delegated_authn_request_total</td><td>ALPHA</td><td>Counter</td><td>Number of HTTP requests partitioned by status code.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_delegated_authz_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request latency in seconds. Broken down by status code.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_delegated_authz_request_total</td><td>ALPHA</td><td>Counter</td><td>Number of HTTP requests partitioned by status code.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_egress_dialer_dial_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Dial latency histogram in seconds, labeled by the protocol (http-connect or grpc), transport (tcp or uds)</td><td><div>protocol</div><div>transport</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_egress_dialer_dial_failure_count</td><td>ALPHA</td><td>Counter</td><td>Dial failure count, labeled by the protocol (http-connect or grpc), transport (tcp or uds), and stage (connect or proxy). The stage indicates at which stage the dial failed</td><td><div>protocol</div><div>stage</div><div>transport</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_aborts_total</td><td>ALPHA</td><td>Counter</td><td>Number of requests which apiserver aborted possibly due to a timeout, for each group, version, verb, resource, subresource and scope</td><td><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_body_sizes</td><td>ALPHA</td><td>Histogram</td><td>Apiserver request body sizes broken out by size.</td><td><div>resource</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_filter_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request filter latency distribution in seconds, for each filter type</td><td><div>filter</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_post_timeout_total</td><td>ALPHA</td><td>Counter</td><td>Tracks the activity of the request handlers after the associated requests have been timed out by the apiserver</td><td><div>source</div><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_slo_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Response latency distribution (not counting webhook duration) in seconds for each verb, group, version, resource, subresource, scope and component.</td><td><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_terminations_total</td><td>ALPHA</td><td>Counter</td><td>Number of requests which apiserver terminated in self-defense.</td><td><div>code</div><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_timestamp_comparison_time</td><td>ALPHA</td><td>Histogram</td><td>Time taken for comparison of old vs new objects in UPDATE or PATCH requests</td><td><div>code_path</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_selfrequest_total</td><td>ALPHA</td><td>Counter</td><td>Counter of apiserver self-requests broken out for each verb, API resource and subresource.</td><td><div>resource</div><div>subresource</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_tls_handshake_errors_total</td><td>ALPHA</td><td>Counter</td><td>Number of requests dropped with 'TLS handshake error from' error</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_watch_events_sizes</td><td>ALPHA</td><td>Histogram</td><td>Watch event size distribution in bytes</td><td><div>group</div><div>kind</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_watch_events_total</td><td>ALPHA</td><td>Counter</td><td>Number of events sent in watch clients</td><td><div>group</div><div>kind</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>authenticated_user_requests</td><td>ALPHA</td><td>Counter</td><td>Counter of authenticated requests broken out by username.</td><td><div>username</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_attempts</td><td>ALPHA</td><td>Counter</td><td>Counter of authenticated attempts.</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Authentication duration in seconds broken out by result.</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_active_fetch_count</td><td>ALPHA</td><td>Gauge</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_fetch_total</td><td>ALPHA</td><td>Counter</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_request_total</td><td>ALPHA</td><td>Counter</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>field_validation_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Response latency distribution in seconds for each field validation value and whether field validation is enabled or not</td><td><div>enabled</div><div>field_validation</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_current_inflight_requests</td><td>STABLE</td><td>Gauge</td><td>Maximal number of currently used inflight request limit of this apiserver per request kind in last second.</td><td><div>request_kind</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_longrunning_requests</td><td>STABLE</td><td>Gauge</td><td>Gauge of all active long-running apiserver requests broken out by verb, group, version, resource, scope and component. Not all requests are tracked this way.</td><td><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Response latency distribution in seconds for each verb, dry run value, group, version, resource, subresource, scope and component.</td><td><div>component</div><div>dry_run</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_total</td><td>STABLE</td><td>Counter</td><td>Counter of apiserver requests broken out for each verb, dry run value, group, version, resource, scope, component, and HTTP response code.</td><td><div>code</div><div>component</div><div>dry_run</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_requested_deprecated_apis</td><td>STABLE</td><td>Gauge</td><td>Gauge of deprecated APIs that have been requested, broken out by API group, version, resource, subresource, and removed_release.</td><td><div>group</div><div>removed_release</div><div>resource</div><div>subresource</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_response_sizes</td><td>STABLE</td><td>Histogram</td><td>Response size distribution in bytes for each group, version, verb, resource, subresource, scope and component.</td><td><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cache_list_fetched_objects_total</td><td>ALPHA</td><td>Counter</td><td>Number of objects read from watch cache in the course of serving a LIST request</td><td><div>index</div><div>resource_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cache_list_returned_objects_total</td><td>ALPHA</td><td>Counter</td><td>Number of objects returned for a LIST request from watch cache</td><td><div>resource_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_cache_list_total</td><td>ALPHA</td><td>Counter</td><td>Number of LIST requests served from watch cache</td><td><div>index</div><div>resource_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_envelope_encryption_dek_cache_fill_percent</td><td>ALPHA</td><td>Gauge</td><td>Percent of the cache slots currently occupied by cached DEKs.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_envelope_encryption_dek_cache_inter_arrival_time_seconds</td><td>ALPHA</td><td>Histogram</td><td>Time (in seconds) of inter arrival of transformation requests.</td><td><div>transformation_type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_flowcontrol_current_executing_requests</td><td>ALPHA</td><td>Gauge</td><td>Number of requests in initial (for a WATCH) or any (for a non-WATCH) execution stage in the API Priority and Fairness subsystem</td><td><div>flow_schema</div><div>priority_level</div></td><td>None</td></tr>
|
||||
@ -249,6 +77,16 @@ These are the metrics which are exported in Kubernetes components (i.e. kube-api
|
||||
<tr><td>apiserver_flowcontrol_watch_count_samples</td><td>ALPHA</td><td>Histogram</td><td>count of watchers for mutating requests in API Priority and Fairness</td><td><div>flow_schema</div><div>priority_level</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_flowcontrol_work_estimated_seats</td><td>ALPHA</td><td>Histogram</td><td>Number of estimated seats (maximum of initial and final seats) associated with requests in API Priority and Fairness</td><td><div>flow_schema</div><div>priority_level</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_init_events_total</td><td>ALPHA</td><td>Counter</td><td>Counter of init events processed in watch cache broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_kube_aggregator_x509_insecure_sha1_total</td><td>ALPHA</td><td>Counter</td><td>Counts the number of requests to servers with insecure SHA1 signatures in their serving certificate OR the number of connection failures due to the insecure SHA1 signatures (either/or, based on the runtime environment)</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_kube_aggregator_x509_missing_san_total</td><td>ALPHA</td><td>Counter</td><td>Counts the number of requests to servers missing SAN extension in their serving certificate OR the number of connection failures due to the lack of x509 certificate SAN extension missing (either/or, based on the runtime environment)</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_aborts_total</td><td>ALPHA</td><td>Counter</td><td>Number of requests which apiserver aborted possibly due to a timeout, for each group, version, verb, resource, subresource and scope</td><td><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_body_sizes</td><td>ALPHA</td><td>Histogram</td><td>Apiserver request body sizes broken out by size.</td><td><div>resource</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_filter_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request filter latency distribution in seconds, for each filter type</td><td><div>filter</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_post_timeout_total</td><td>ALPHA</td><td>Counter</td><td>Tracks the activity of the request handlers after the associated requests have been timed out by the apiserver</td><td><div>source</div><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_slo_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Response latency distribution (not counting webhook duration) in seconds for each verb, group, version, resource, subresource, scope and component.</td><td><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_terminations_total</td><td>ALPHA</td><td>Counter</td><td>Number of requests which apiserver terminated in self-defense.</td><td><div>code</div><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_timestamp_comparison_time</td><td>ALPHA</td><td>Histogram</td><td>Time taken for comparison of old vs new objects in UPDATE or PATCH requests</td><td><div>code_path</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_selfrequest_total</td><td>ALPHA</td><td>Counter</td><td>Counter of apiserver self-requests broken out for each verb, API resource and subresource.</td><td><div>resource</div><div>subresource</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_storage_data_key_generation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Latencies in seconds of data encryption key(DEK) generation operations.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_storage_data_key_generation_failures_total</td><td>ALPHA</td><td>Counter</td><td>Total number of failed data encryption key(DEK) generation operations.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_storage_envelope_transformation_cache_misses_total</td><td>ALPHA</td><td>Counter</td><td>Total number of cache misses while accessing key decryption key(KEK).</td><td>None</td><td>None</td></tr>
|
||||
@ -259,46 +97,21 @@ These are the metrics which are exported in Kubernetes components (i.e. kube-api
|
||||
<tr><td>apiserver_storage_transformation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Latencies in seconds of value transformation operations.</td><td><div>transformation_type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_storage_transformation_operations_total</td><td>ALPHA</td><td>Counter</td><td>Total number of transformations.</td><td><div>status</div><div>transformation_type</div><div>transformer_prefix</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_terminated_watchers_total</td><td>ALPHA</td><td>Counter</td><td>Counter of watchers closed due to unresponsiveness broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_tls_handshake_errors_total</td><td>ALPHA</td><td>Counter</td><td>Number of requests dropped with 'TLS handshake error from' error</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_watch_cache_events_dispatched_total</td><td>ALPHA</td><td>Counter</td><td>Counter of events dispatched in watch cache broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_watch_cache_initializations_total</td><td>ALPHA</td><td>Counter</td><td>Counter of watch cache initializations broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_watch_events_sizes</td><td>ALPHA</td><td>Histogram</td><td>Watch event size distribution in bytes</td><td><div>group</div><div>kind</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_watch_events_total</td><td>ALPHA</td><td>Counter</td><td>Number of events sent in watch clients</td><td><div>group</div><div>kind</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_webhooks_x509_insecure_sha1_total</td><td>ALPHA</td><td>Counter</td><td>Counts the number of requests to servers with insecure SHA1 signatures in their serving certificate OR the number of connection failures due to the insecure SHA1 signatures (either/or, based on the runtime environment)</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_webhooks_x509_missing_san_total</td><td>ALPHA</td><td>Counter</td><td>Counts the number of requests to servers missing SAN extension in their serving certificate OR the number of connection failures due to the lack of x509 certificate SAN extension missing (either/or, based on the runtime environment)</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>etcd_bookmark_counts</td><td>ALPHA</td><td>Gauge</td><td>Number of etcd bookmarks (progress notify events) split by kind.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>etcd_db_total_size_in_bytes</td><td>ALPHA</td><td>Gauge</td><td>Total size of the etcd database file physically allocated in bytes.</td><td><div>endpoint</div></td><td>None</td></tr>
|
||||
<tr><td>etcd_lease_object_counts</td><td>ALPHA</td><td>Histogram</td><td>Number of objects attached to a single etcd lease.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>etcd_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Etcd request latency in seconds for each operation and object type.</td><td><div>operation</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>watch_cache_capacity</td><td>ALPHA</td><td>Gauge</td><td>Total capacity of watch cache broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>watch_cache_capacity_decrease_total</td><td>ALPHA</td><td>Counter</td><td>Total number of watch cache capacity decrease events broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>watch_cache_capacity_increase_total</td><td>ALPHA</td><td>Counter</td><td>Total number of watch cache capacity increase events broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_storage_objects</td><td>STABLE</td><td>Gauge</td><td>Number of stored objects at the time of last check split by kind.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>service_controller_nodesync_latency_seconds</td><td>ALPHA</td><td>Histogram</td><td>A metric measuring the latency for nodesync which updates loadbalancer hosts on cluster node updates.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>service_controller_update_loadbalancer_host_latency_seconds</td><td>ALPHA</td><td>Histogram</td><td>A metric measuring the latency for updating each load balancer hosts.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubernetes_build_info</td><td>ALPHA</td><td>Gauge</td><td>A metric with a constant '1' value labeled by major, minor, git version, git commit, git tree state, build date, Go version, and compiler from which Kubernetes was built, and platform on which it is running.</td><td><div>build_date</div><div>compiler</div><div>git_commit</div><div>git_tree_state</div><div>git_version</div><div>go_version</div><div>major</div><div>minor</div><div>platform</div></td><td>None</td></tr>
|
||||
<tr><td>kubernetes_feature_enabled</td><td>ALPHA</td><td>Gauge</td><td>This metric records the data about the stage and enablement of a k8s feature.</td><td><div>name</div><div>stage</div></td><td>None</td></tr>
|
||||
<tr><td>kubernetes_healthcheck</td><td>ALPHA</td><td>Gauge</td><td>This metric records the result of a single healthcheck.</td><td><div>name</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>kubernetes_healthchecks_total</td><td>ALPHA</td><td>Counter</td><td>This metric records the results of all healthcheck.</td><td><div>name</div><div>status</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>leader_election_master_status</td><td>ALPHA</td><td>Gauge</td><td>Gauge of if the reporting system is master of the relevant lease, 0 indicates backup, 1 indicates master. 'name' is the string used to identify the lease. Please make sure to group by name.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_exec_plugin_call_total</td><td>ALPHA</td><td>Counter</td><td>Number of calls to an exec plugin, partitioned by the type of event encountered (no_error, plugin_execution_error, plugin_not_found_error, client_internal_error) and an optional exit code. The exit code will be set to 0 if and only if the plugin call was successful.</td><td><div>call_status</div><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_exec_plugin_certificate_rotation_age</td><td>ALPHA</td><td>Histogram</td><td>Histogram of the number of seconds the last auth exec plugin client certificate lived before being rotated. If auth exec plugin client certificates are unused, histogram will contain no data.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>rest_client_exec_plugin_ttl_seconds</td><td>ALPHA</td><td>Gauge</td><td>Gauge of the shortest TTL (time-to-live) of the client certificate(s) managed by the auth exec plugin. The value is in seconds until certificate expiry (negative if already expired). If auth exec plugins are unused or manage no TLS certificates, the value will be +INF.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>rest_client_rate_limiter_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Client side rate limiter latency in seconds. Broken down by verb, and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request latency in seconds. Broken down by verb, and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_request_size_bytes</td><td>ALPHA</td><td>Histogram</td><td>Request size in bytes. Broken down by verb and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_requests_total</td><td>ALPHA</td><td>Counter</td><td>Number of HTTP requests, partitioned by status code, method, and host.</td><td><div>code</div><div>host</div><div>method</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_response_size_bytes</td><td>ALPHA</td><td>Histogram</td><td>Response size in bytes. Broken down by verb and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>running_managed_controllers</td><td>ALPHA</td><td>Gauge</td><td>Indicates where instances of a controller are currently running</td><td><div>manager</div><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_adds_total</td><td>ALPHA</td><td>Counter</td><td>Total number of adds handled by workqueue</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_depth</td><td>ALPHA</td><td>Gauge</td><td>Current depth of workqueue</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_longest_running_processor_seconds</td><td>ALPHA</td><td>Gauge</td><td>How many seconds has the longest running processor for workqueue been running.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_queue_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>How long in seconds an item stays in workqueue before being requested.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_retries_total</td><td>ALPHA</td><td>Counter</td><td>Total number of retries handled by workqueue</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_unfinished_work_seconds</td><td>ALPHA</td><td>Gauge</td><td>How many seconds of work has done that is in progress and hasn't been observed by work_duration. Large values indicate stuck threads. One can deduce the number of stuck threads by observing the rate at which this increases.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_work_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>How long in seconds processing an item from workqueue takes.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_kube_aggregator_x509_insecure_sha1_total</td><td>ALPHA</td><td>Counter</td><td>Counts the number of requests to servers with insecure SHA1 signatures in their serving certificate OR the number of connection failures due to the insecure SHA1 signatures (either/or, based on the runtime environment)</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>apiserver_kube_aggregator_x509_missing_san_total</td><td>ALPHA</td><td>Counter</td><td>Counts the number of requests to servers missing SAN extension in their serving certificate OR the number of connection failures due to the lack of x509 certificate SAN extension missing (either/or, based on the runtime environment)</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>aggregator_openapi_v2_regeneration_count</td><td>ALPHA</td><td>Counter</td><td>Counter of OpenAPI v2 spec regeneration count broken down by causing APIService name and reason.</td><td><div>apiservice</div><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>aggregator_openapi_v2_regeneration_duration</td><td>ALPHA</td><td>Gauge</td><td>Gauge of OpenAPI v2 spec regeneration duration in seconds.</td><td><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>aggregator_unavailable_apiservice_total</td><td>ALPHA</td><td>Counter</td><td>Counter of APIServices which are marked as unavailable broken down by APIService name and reason.</td><td><div>name</div><div>reason</div></td><td>None</td></tr>
|
||||
<tr><td>attachdetach_controller_forced_detaches</td><td>ALPHA</td><td>Counter</td><td>Number of times the A/D Controller performed a forced detach</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>authenticated_user_requests</td><td>ALPHA</td><td>Counter</td><td>Counter of authenticated requests broken out by username.</td><td><div>username</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_attempts</td><td>ALPHA</td><td>Counter</td><td>Counter of authenticated attempts.</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Authentication duration in seconds broken out by result.</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_active_fetch_count</td><td>ALPHA</td><td>Gauge</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_fetch_total</td><td>ALPHA</td><td>Counter</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>authentication_token_cache_request_total</td><td>ALPHA</td><td>Counter</td><td></td><td><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>cloudprovider_aws_api_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Latency of AWS API calls</td><td><div>request</div></td><td>None</td></tr>
|
||||
<tr><td>cloudprovider_aws_api_request_errors</td><td>ALPHA</td><td>Counter</td><td>AWS API errors</td><td><div>request</div></td><td>None</td></tr>
|
||||
<tr><td>cloudprovider_aws_api_throttled_requests_total</td><td>ALPHA</td><td>Counter</td><td>AWS API throttled requests</td><td><div>operation_name</div></td><td>None</td></tr>
|
||||
@ -314,12 +127,199 @@ These are the metrics which are exported in Kubernetes components (i.e. kube-api
|
||||
<tr><td>cloudprovider_vsphere_api_request_errors</td><td>ALPHA</td><td>Counter</td><td>vsphere Api errors</td><td><div>request</div></td><td>None</td></tr>
|
||||
<tr><td>cloudprovider_vsphere_operation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Latency of vsphere operation call</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>cloudprovider_vsphere_operation_errors</td><td>ALPHA</td><td>Counter</td><td>vsphere operation errors</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>cronjob_controller_cronjob_job_creation_skew_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Time between when a cronjob is scheduled to be run, and when the corresponding job is created</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>csi_operations_seconds</td><td>ALPHA</td><td>Histogram</td><td>Container Storage Interface operation duration with gRPC error code status total</td><td><div>driver_name</div><div>grpc_status_code</div><div>method_name</div><div>migrated</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_changes</td><td>ALPHA</td><td>Counter</td><td>Number of EndpointSlice changes</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_desired_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices that would exist with perfect endpoint allocation</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpoints_added_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints added on each Service sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpoints_desired</td><td>ALPHA</td><td>Gauge</td><td>Number of endpoints desired</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpoints_removed_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints removed on each Service sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_endpointslices_changed_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of EndpointSlices changed on each Service sync</td><td><div>topology</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_num_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_controller_syncs</td><td>ALPHA</td><td>Counter</td><td>Number of EndpointSlice syncs</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_addresses_skipped_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of addresses skipped on each Endpoints sync due to being invalid or exceeding MaxEndpointsPerSubset</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_changes</td><td>ALPHA</td><td>Counter</td><td>Number of EndpointSlice changes</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_desired_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices that would exist with perfect endpoint allocation</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_added_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints added on each Endpoints sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_desired</td><td>ALPHA</td><td>Gauge</td><td>Number of endpoints desired</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_removed_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints removed on each Endpoints sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_sync_duration</td><td>ALPHA</td><td>Histogram</td><td>Duration of syncEndpoints() in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_endpoints_updated_per_sync</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints updated on each Endpoints sync</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>endpoint_slice_mirroring_controller_num_endpoint_slices</td><td>ALPHA</td><td>Gauge</td><td>Number of EndpointSlices</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>ephemeral_volume_controller_create_failures_total</td><td>ALPHA</td><td>Counter</td><td>Number of PersistenVolumeClaims creation requests</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>ephemeral_volume_controller_create_total</td><td>ALPHA</td><td>Counter</td><td>Number of PersistenVolumeClaims creation requests</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>etcd_bookmark_counts</td><td>ALPHA</td><td>Gauge</td><td>Number of etcd bookmarks (progress notify events) split by kind.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>etcd_db_total_size_in_bytes</td><td>ALPHA</td><td>Gauge</td><td>Total size of the etcd database file physically allocated in bytes.</td><td><div>endpoint</div></td><td>None</td></tr>
|
||||
<tr><td>etcd_lease_object_counts</td><td>ALPHA</td><td>Histogram</td><td>Number of objects attached to a single etcd lease.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>etcd_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Etcd request latency in seconds for each operation and object type.</td><td><div>operation</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>etcd_version_info</td><td>ALPHA</td><td>Gauge</td><td>Etcd server's binary version</td><td><div>binary_version</div></td><td>None</td></tr>
|
||||
<tr><td>field_validation_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Response latency distribution in seconds for each field validation value and whether field validation is enabled or not</td><td><div>enabled</div><div>field_validation</div></td><td>None</td></tr>
|
||||
<tr><td>garbagecollector_controller_resources_sync_error_total</td><td>ALPHA</td><td>Counter</td><td>Number of garbage collector resources sync errors</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>get_token_count</td><td>ALPHA</td><td>Counter</td><td>Counter of total Token() requests to the alternate token source</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>get_token_fail_count</td><td>ALPHA</td><td>Counter</td><td>Counter of failed Token() requests to the alternate token source</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_finished_total</td><td>ALPHA</td><td>Counter</td><td>The number of finished job</td><td><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_pods_finished_total</td><td>ALPHA</td><td>Counter</td><td>The number of finished Pods that are fully tracked</td><td><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_sync_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>The time it took to sync a job</td><td><div>action</div><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_job_sync_total</td><td>ALPHA</td><td>Counter</td><td>The number of job syncs</td><td><div>action</div><div>completion_mode</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>job_controller_terminated_pods_tracking_finalizer_total</td><td>ALPHA</td><td>Counter</td><td>`The number of terminated pods (phase=Failed|Succeeded), that have the finalizer batch.kubernetes.io/job-tracking, The event label can be "add" or "delete".`</td><td><div>event</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_allocated_ips</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring the number of allocated IPs for Services</td><td><div>cidr</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_allocation_errors_total</td><td>ALPHA</td><td>Counter</td><td>Number of errors trying to allocate Cluster IPs</td><td><div>cidr</div><div>scope</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_allocation_total</td><td>ALPHA</td><td>Counter</td><td>Number of Cluster IPs allocations</td><td><div>cidr</div><div>scope</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_clusterip_allocator_available_ips</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring the number of available IPs for Services</td><td><div>cidr</div></td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_pod_logs_pods_logs_backend_tls_failure_total</td><td>ALPHA</td><td>Counter</td><td>Total number of requests for pods/logs that failed due to kubelet server TLS verification</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kube_apiserver_pod_logs_pods_logs_insecure_backend_total</td><td>ALPHA</td><td>Counter</td><td>Total number of requests for pods/logs sliced by usage type: enforce_tls, skip_tls_allowed, skip_tls_denied</td><td><div>usage</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_client_expiration_renew_errors</td><td>ALPHA</td><td>Counter</td><td>Counter of certificate renewal errors.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_client_ttl_seconds</td><td>ALPHA</td><td>Gauge</td><td>Gauge of the TTL (time-to-live) of the Kubelet's client certificate. The value is in seconds until certificate expiry (negative if already expired). If client certificate is invalid or unused, the value will be +INF.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_server_rotation_seconds</td><td>ALPHA</td><td>Histogram</td><td>Histogram of the number of seconds the previous certificate lived before being rotated.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_certificate_manager_server_ttl_seconds</td><td>ALPHA</td><td>Gauge</td><td>Gauge of the shortest TTL (time-to-live) of the Kubelet's serving certificate. The value is in seconds until certificate expiry (negative if already expired). If serving certificate is invalid or unused, the value will be +INF.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_cgroup_manager_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds for cgroup manager operations. Broken down by method.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_containers_per_pod_count</td><td>ALPHA</td><td>Histogram</td><td>The number of containers per pod.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_device_plugin_alloc_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to serve a device plugin Allocation request. Broken down by resource name.</td><td><div>resource_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_device_plugin_registration_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of device plugin registrations. Broken down by resource name.</td><td><div>resource_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_eviction_stats_age_seconds</td><td>ALPHA</td><td>Histogram</td><td>Time between when stats are collected, and when pod is evicted based on those stats by eviction signal</td><td><div>eviction_signal</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_evictions</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of pod evictions by eviction signal</td><td><div>eviction_signal</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_graceful_shutdown_end_time_seconds</td><td>ALPHA</td><td>Gauge</td><td>Last graceful shutdown start time since unix epoch in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_graceful_shutdown_start_time_seconds</td><td>ALPHA</td><td>Gauge</td><td>Last graceful shutdown start time since unix epoch in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_http_inflight_requests</td><td>ALPHA</td><td>Gauge</td><td>Number of the inflight http requests</td><td><div>long_running</div><div>method</div><div>path</div><div>server_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_http_requests_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to serve http requests</td><td><div>long_running</div><div>method</div><div>path</div><div>server_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_http_requests_total</td><td>ALPHA</td><td>Counter</td><td>Number of the http requests received since the server started</td><td><div>long_running</div><div>method</div><div>path</div><div>server_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_kubelet_credential_provider_plugin_duration</td><td>ALPHA</td><td>Histogram</td><td>Duration of execution in seconds for credential provider plugin</td><td><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_kubelet_credential_provider_plugin_errors</td><td>ALPHA</td><td>Counter</td><td>Number of errors from credential provider plugin</td><td><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_lifecycle_handler_http_fallbacks_total</td><td>ALPHA</td><td>Counter</td><td>The number of times lifecycle handlers successfully fell back to http from https.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_managed_ephemeral_containers</td><td>ALPHA</td><td>Gauge</td><td>Current number of ephemeral containers in pods managed by this kubelet. Ephemeral containers will be ignored if disabled by the EphemeralContainers feature gate, and this number will be 0.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_node_name</td><td>ALPHA</td><td>Gauge</td><td>The node's name. The count is always 1.</td><td><div>node</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_discard_events</td><td>ALPHA</td><td>Counter</td><td>The number of discard events in PLEG.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_last_seen_seconds</td><td>ALPHA</td><td>Gauge</td><td>Timestamp in seconds when PLEG was last seen active.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_relist_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds for relisting pods in PLEG.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pleg_relist_interval_seconds</td><td>ALPHA</td><td>Histogram</td><td>Interval in seconds between relisting in PLEG.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_errors_get_allocatable</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource GetAllocatableResources endpoint which returned error. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_errors_list</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource List endpoint which returned error. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_requests_get_allocatable</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource GetAllocatableResources endpoint. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_requests_list</td><td>ALPHA</td><td>Counter</td><td>Number of requests to the PodResource List endpoint. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_resources_endpoint_requests_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of requests to the PodResource endpoint. Broken down by server api version.</td><td><div>server_api_version</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_start_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds from kubelet seeing a pod for the first time to the pod starting to run</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_status_sync_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to sync a pod status update. Measures time from detection of a change to pod status until the API is successfully updated for that pod, even if multiple intevening changes to pod status occur.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_worker_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to sync a single pod. Broken down by operation type: create, update, or sync</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_pod_worker_start_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds from kubelet seeing a pod to starting a worker.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_preemptions</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of pod preemptions by preemption resource</td><td><div>preemption_signal</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_run_podsandbox_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds of the run_podsandbox operations. Broken down by RuntimeClass.Handler.</td><td><div>runtime_handler</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_run_podsandbox_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of the run_podsandbox operation errors by RuntimeClass.Handler.</td><td><div>runtime_handler</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_running_containers</td><td>ALPHA</td><td>Gauge</td><td>Number of containers currently running</td><td><div>container_state</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_running_pods</td><td>ALPHA</td><td>Gauge</td><td>Number of pods that have a running pod sandbox</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_runtime_operations_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds of runtime operations. Broken down by operation type.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_runtime_operations_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of runtime operation errors by operation type.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_runtime_operations_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of runtime operations by operation type.</td><td><div>operation_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_server_expiration_renew_errors</td><td>ALPHA</td><td>Counter</td><td>Counter of certificate renewal errors.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_containers_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of errors when starting containers</td><td><div>code</div><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_containers_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of containers started</td><td><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_host_process_containers_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of errors when starting hostprocess containers. This metric will only be collected on Windows and requires WindowsHostProcessContainers feature gate to be enabled.</td><td><div>code</div><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_host_process_containers_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of hostprocess containers started. This metric will only be collected on Windows and requires WindowsHostProcessContainers feature gate to be enabled.</td><td><div>container_type</div></td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_pods_errors_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of errors when starting pods</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_started_pods_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of pods started</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubelet_volume_metric_collection_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds to calculate volume stats</td><td><div>metric_source</div></td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_network_programming_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>In Cluster Network Programming Latency in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>SyncProxyRules latency in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_endpoint_changes_pending</td><td>ALPHA</td><td>Gauge</td><td>Pending proxy rules Endpoint changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_endpoint_changes_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative proxy rules Endpoint changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_iptables_restore_failures_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative proxy iptables restore failures</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_iptables_total</td><td>ALPHA</td><td>Gauge</td><td>Number of proxy iptables rules programmed</td><td><div>table</div></td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_last_queued_timestamp_seconds</td><td>ALPHA</td><td>Gauge</td><td>The last time a sync of proxy rules was queued</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_last_timestamp_seconds</td><td>ALPHA</td><td>Gauge</td><td>The last time proxy rules were successfully synced</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_no_local_endpoints_total</td><td>ALPHA</td><td>Gauge</td><td>Number of services with a Local traffic policy and no endpoints</td><td><div>traffic_policy</div></td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_service_changes_pending</td><td>ALPHA</td><td>Gauge</td><td>Pending proxy rules Service changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubeproxy_sync_proxy_rules_service_changes_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative proxy rules Service changes</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>kubernetes_build_info</td><td>ALPHA</td><td>Gauge</td><td>A metric with a constant '1' value labeled by major, minor, git version, git commit, git tree state, build date, Go version, and compiler from which Kubernetes was built, and platform on which it is running.</td><td><div>build_date</div><div>compiler</div><div>git_commit</div><div>git_tree_state</div><div>git_version</div><div>go_version</div><div>major</div><div>minor</div><div>platform</div></td><td>None</td></tr>
|
||||
<tr><td>kubernetes_feature_enabled</td><td>ALPHA</td><td>Gauge</td><td>This metric records the data about the stage and enablement of a k8s feature.</td><td><div>name</div><div>stage</div></td><td>None</td></tr>
|
||||
<tr><td>kubernetes_healthcheck</td><td>ALPHA</td><td>Gauge</td><td>This metric records the result of a single healthcheck.</td><td><div>name</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>kubernetes_healthchecks_total</td><td>ALPHA</td><td>Counter</td><td>This metric records the results of all healthcheck.</td><td><div>name</div><div>status</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>leader_election_master_status</td><td>ALPHA</td><td>Gauge</td><td>Gauge of if the reporting system is master of the relevant lease, 0 indicates backup, 1 indicates master. 'name' is the string used to identify the lease. Please make sure to group by name.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>node_authorizer_graph_actions_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Histogram of duration of graph actions in node authorizer.</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_evictions_number</td><td>ALPHA</td><td>Counter</td><td>Number of Node evictions that happened since current instance of NodeController started, This metric is replaced by node_collector_evictions_total.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_unhealthy_nodes_in_zone</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring number of not Ready Nodes per zones.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_zone_health</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring percentage of healthy nodes per zone.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_zone_size</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring number of registered Nodes per zones.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_allocation_tries_per_request</td><td>ALPHA</td><td>Histogram</td><td>Number of endpoints added on each Service sync</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_cidrs_allocations_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR allocations.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_cidrs_releases_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR releases.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_cidrset_usage_cidrs</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring percentage of allocated CIDRs.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_allocation_tries_per_request</td><td>ALPHA</td><td>Histogram</td><td>Histogram measuring CIDR allocation tries per request.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_cidrs_allocations_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR allocations.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_cidrs_releases_total</td><td>ALPHA</td><td>Counter</td><td>Counter measuring total number of CIDR releases.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>node_ipam_controller_multicidrset_usage_cidrs</td><td>ALPHA</td><td>Gauge</td><td>Gauge measuring percentage of allocated CIDRs.</td><td><div>clusterCIDR</div></td><td>None</td></tr>
|
||||
<tr><td>number_of_l4_ilbs</td><td>ALPHA</td><td>Gauge</td><td>Number of L4 ILBs</td><td><div>feature</div></td><td>None</td></tr>
|
||||
<tr><td>pod_security_errors_total</td><td>ALPHA</td><td>Counter</td><td>Number of errors preventing normal evaluation. Non-fatal errors may result in the latest restricted profile being used for evaluation.</td><td><div>fatal</div><div>request_operation</div><div>resource</div><div>subresource</div></td><td>None</td></tr>
|
||||
<tr><td>pod_security_evaluations_total</td><td>ALPHA</td><td>Counter</td><td>Number of policy evaluations that occurred, not counting ignored or exempt requests.</td><td><div>decision</div><div>mode</div><div>policy_level</div><div>policy_version</div><div>request_operation</div><div>resource</div><div>subresource</div></td><td>None</td></tr>
|
||||
<tr><td>pod_security_exemptions_total</td><td>ALPHA</td><td>Counter</td><td>Number of exempt requests, not counting ignored or out of scope requests.</td><td><div>request_operation</div><div>resource</div><div>subresource</div></td><td>None</td></tr>
|
||||
<tr><td>prober_probe_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration in seconds for a probe response.</td><td><div>container</div><div>namespace</div><div>pod</div><div>probe_type</div></td><td>None</td></tr>
|
||||
<tr><td>prober_probe_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative number of a liveness, readiness or startup probe for a container by result.</td><td><div>container</div><div>namespace</div><div>pod</div><div>pod_uid</div><div>probe_type</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>replicaset_controller_sorting_deletion_age_ratio</td><td>ALPHA</td><td>Histogram</td><td>The ratio of chosen deleted pod's ages to the current youngest pod's age (at the time). Should be <2.The intent of this metric is to measure the rough efficacy of the LogarithmicScaleDown feature gate's effect onthe sorting (and deletion) of pods when a replicaset scales down. This only considers Ready pods when calculating and reporting.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>rest_client_exec_plugin_call_total</td><td>ALPHA</td><td>Counter</td><td>Number of calls to an exec plugin, partitioned by the type of event encountered (no_error, plugin_execution_error, plugin_not_found_error, client_internal_error) and an optional exit code. The exit code will be set to 0 if and only if the plugin call was successful.</td><td><div>call_status</div><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_exec_plugin_certificate_rotation_age</td><td>ALPHA</td><td>Histogram</td><td>Histogram of the number of seconds the last auth exec plugin client certificate lived before being rotated. If auth exec plugin client certificates are unused, histogram will contain no data.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>rest_client_exec_plugin_ttl_seconds</td><td>ALPHA</td><td>Gauge</td><td>Gauge of the shortest TTL (time-to-live) of the client certificate(s) managed by the auth exec plugin. The value is in seconds until certificate expiry (negative if already expired). If auth exec plugins are unused or manage no TLS certificates, the value will be +INF.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>rest_client_rate_limiter_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Client side rate limiter latency in seconds. Broken down by verb, and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_request_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Request latency in seconds. Broken down by verb, and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_request_size_bytes</td><td>ALPHA</td><td>Histogram</td><td>Request size in bytes. Broken down by verb and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_requests_total</td><td>ALPHA</td><td>Counter</td><td>Number of HTTP requests, partitioned by status code, method, and host.</td><td><div>code</div><div>host</div><div>method</div></td><td>None</td></tr>
|
||||
<tr><td>rest_client_response_size_bytes</td><td>ALPHA</td><td>Histogram</td><td>Response size in bytes. Broken down by verb and host.</td><td><div>host</div><div>verb</div></td><td>None</td></tr>
|
||||
<tr><td>root_ca_cert_publisher_sync_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Number of namespace syncs happened in root ca cert publisher.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>root_ca_cert_publisher_sync_total</td><td>ALPHA</td><td>Counter</td><td>Number of namespace syncs happened in root ca cert publisher.</td><td><div>code</div></td><td>None</td></tr>
|
||||
<tr><td>running_managed_controllers</td><td>ALPHA</td><td>Gauge</td><td>Indicates where instances of a controller are currently running</td><td><div>manager</div><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_e2e_scheduling_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>E2e scheduling latency in seconds (scheduling algorithm + binding). This metric is replaced by scheduling_attempt_duration_seconds.</td><td><div>profile</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_goroutines</td><td>ALPHA</td><td>Gauge</td><td>Number of running goroutines split by the work they do such as binding.</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_permit_wait_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration of waiting on permit.</td><td><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_plugin_execution_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Duration for running a plugin at a specific extension point.</td><td><div>extension_point</div><div>plugin</div><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduler_cache_size</td><td>ALPHA</td><td>Gauge</td><td>Number of nodes, pods, and assumed (bound) pods in the scheduler cache.</td><td><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduler_goroutines</td><td>ALPHA</td><td>Gauge</td><td>Number of running goroutines split by the work they do such as binding. This metric is replaced by the \"goroutines\" metric.</td><td><div>work</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduling_algorithm_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Scheduling algorithm latency in seconds</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_unschedulable_pods</td><td>ALPHA</td><td>Gauge</td><td>The number of unschedulable pods broken down by plugin name. A pod will increment the gauge for all plugins that caused it to not schedule and so this metric have meaning only when broken down by plugin.</td><td><div>plugin</div><div>profile</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_volume_binder_cache_requests_total</td><td>ALPHA</td><td>Counter</td><td>Total number for request volume binding cache</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_volume_scheduling_stage_error_total</td><td>ALPHA</td><td>Counter</td><td>Volume scheduling stage error count</td><td><div>operation</div></td><td>None</td></tr>
|
||||
<tr><td>service_controller_nodesync_latency_seconds</td><td>ALPHA</td><td>Histogram</td><td>A metric measuring the latency for nodesync which updates loadbalancer hosts on cluster node updates.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>service_controller_update_loadbalancer_host_latency_seconds</td><td>ALPHA</td><td>Histogram</td><td>A metric measuring the latency for updating each load balancer hosts.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>serviceaccount_legacy_tokens_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative legacy service account tokens used</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>serviceaccount_stale_tokens_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative stale projected service account tokens used</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>serviceaccount_valid_tokens_total</td><td>ALPHA</td><td>Counter</td><td>Cumulative valid projected service account tokens used</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>storage_operation_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>Storage operation duration</td><td><div>migrated</div><div>operation_name</div><div>status</div><div>volume_plugin</div></td><td>None</td></tr>
|
||||
<tr><td>ttl_after_finished_controller_job_deletion_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>The time it took to delete the job since it became eligible for deletion</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_container_errors_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when kubelet cannot compute SELinux context for a container. Kubelet can't start such a Pod then and it will retry, therefore value of this metric may not represent the actual nr. of containers.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_container_warnings_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when kubelet cannot compute SELinux context for a container that are ignored. They will become real errors when SELinuxMountReadWriteOncePod feature is expanded to all volume access modes.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_pod_context_mismatch_errors_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod defines different SELinux contexts for its containers that use the same volume. Kubelet can't start such a Pod then and it will retry, therefore value of this metric may not represent the actual nr. of Pods.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_pod_context_mismatch_warnings_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod defines different SELinux contexts for its containers that use the same volume. They are not errors yet, but they will become real errors when SELinuxMountReadWriteOncePod feature is expanded to all volume access modes.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_volume_context_mismatch_errors_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod uses a volume that is already mounted with a different SELinux context than the Pod needs. Kubelet can't start such a Pod then and it will retry, therefore value of this metric may not represent the actual nr. of Pods.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_volume_context_mismatch_warnings_total</td><td>ALPHA</td><td>Gauge</td><td>Number of errors when a Pod uses a volume that is already mounted with a different SELinux context than the Pod needs. They are not errors yet, but they will become real errors when SELinuxMountReadWriteOncePod feature is expanded to all volume access modes.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_manager_selinux_volumes_admitted_total</td><td>ALPHA</td><td>Gauge</td><td>Number of volumes whose SELinux context was fine and will be mounted with mount -o context option.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>volume_operation_total_errors</td><td>ALPHA</td><td>Counter</td><td>Total volume operation errors</td><td><div>operation_name</div><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>volume_operation_total_seconds</td><td>ALPHA</td><td>Histogram</td><td>Storage operation end to end duration in seconds</td><td><div>operation_name</div><div>plugin_name</div></td><td>None</td></tr>
|
||||
<tr><td>watch_cache_capacity</td><td>ALPHA</td><td>Gauge</td><td>Total capacity of watch cache broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>watch_cache_capacity_decrease_total</td><td>ALPHA</td><td>Counter</td><td>Total number of watch cache capacity decrease events broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>watch_cache_capacity_increase_total</td><td>ALPHA</td><td>Counter</td><td>Total number of watch cache capacity increase events broken by resource type.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_adds_total</td><td>ALPHA</td><td>Counter</td><td>Total number of adds handled by workqueue</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_depth</td><td>ALPHA</td><td>Gauge</td><td>Current depth of workqueue</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_longest_running_processor_seconds</td><td>ALPHA</td><td>Gauge</td><td>How many seconds has the longest running processor for workqueue been running.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_queue_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>How long in seconds an item stays in workqueue before being requested.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_retries_total</td><td>ALPHA</td><td>Counter</td><td>Total number of retries handled by workqueue</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_unfinished_work_seconds</td><td>ALPHA</td><td>Gauge</td><td>How many seconds of work has done that is in progress and hasn't been observed by work_duration. Large values indicate stuck threads. One can deduce the number of stuck threads by observing the rate at which this increases.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>workqueue_work_duration_seconds</td><td>ALPHA</td><td>Histogram</td><td>How long in seconds processing an item from workqueue takes.</td><td><div>name</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_controller_admission_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Admission controller latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).</td><td><div>name</div><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_step_admission_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Admission sub-step latency histogram in seconds, broken out for each operation and API resource and step type (validate or admit).</td><td><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_admission_webhook_admission_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Admission webhook latency histogram in seconds, identified by name and broken out for each operation and API resource and type (validate or admit).</td><td><div>name</div><div>operation</div><div>rejected</div><div>type</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_current_inflight_requests</td><td>STABLE</td><td>Gauge</td><td>Maximal number of currently used inflight request limit of this apiserver per request kind in last second.</td><td><div>request_kind</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_longrunning_requests</td><td>STABLE</td><td>Gauge</td><td>Gauge of all active long-running apiserver requests broken out by verb, group, version, resource, scope and component. Not all requests are tracked this way.</td><td><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Response latency distribution in seconds for each verb, dry run value, group, version, resource, subresource, scope and component.</td><td><div>component</div><div>dry_run</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_request_total</td><td>STABLE</td><td>Counter</td><td>Counter of apiserver requests broken out for each verb, dry run value, group, version, resource, scope, component, and HTTP response code.</td><td><div>code</div><div>component</div><div>dry_run</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_requested_deprecated_apis</td><td>STABLE</td><td>Gauge</td><td>Gauge of deprecated APIs that have been requested, broken out by API group, version, resource, subresource, and removed_release.</td><td><div>group</div><div>removed_release</div><div>resource</div><div>subresource</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_response_sizes</td><td>STABLE</td><td>Histogram</td><td>Response size distribution in bytes for each group, version, verb, resource, subresource, scope and component.</td><td><div>component</div><div>group</div><div>resource</div><div>scope</div><div>subresource</div><div>verb</div><div>version</div></td><td>None</td></tr>
|
||||
<tr><td>apiserver_storage_objects</td><td>STABLE</td><td>Gauge</td><td>Number of stored objects at the time of last check split by kind.</td><td><div>resource</div></td><td>None</td></tr>
|
||||
<tr><td>node_collector_evictions_total</td><td>STABLE</td><td>Counter</td><td>Number of Node evictions that happened since current instance of NodeController started.</td><td><div>zone</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_framework_extension_point_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Latency for running all plugins of a specific extension point.</td><td><div>extension_point</div><div>profile</div><div>status</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_pending_pods</td><td>STABLE</td><td>Gauge</td><td>Number 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.</td><td><div>queue</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_pod_scheduling_attempts</td><td>STABLE</td><td>Histogram</td><td>Number of attempts to successfully schedule a pod.</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_pod_scheduling_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>E2e latency for a pod being scheduled which may include multiple scheduling attempts.</td><td><div>attempts</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_preemption_attempts_total</td><td>STABLE</td><td>Counter</td><td>Total preemption attempts in the cluster till now</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_preemption_victims</td><td>STABLE</td><td>Histogram</td><td>Number of selected preemption victims</td><td>None</td><td>None</td></tr>
|
||||
<tr><td>scheduler_queue_incoming_pods_total</td><td>STABLE</td><td>Counter</td><td>Number of pods added to scheduling queues by event and queue type.</td><td><div>event</div><div>queue</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_schedule_attempts_total</td><td>STABLE</td><td>Counter</td><td>Number of attempts to schedule pods, by the result. 'unschedulable' means a pod could not be scheduled, while 'error' means an internal scheduler problem.</td><td><div>profile</div><div>result</div></td><td>None</td></tr>
|
||||
<tr><td>scheduler_scheduling_attempt_duration_seconds</td><td>STABLE</td><td>Histogram</td><td>Scheduling attempt latency in seconds (scheduling algorithm + binding)</td><td><div>profile</div><div>result</div></td><td>None</td></tr>
|
||||
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
Loading…
Reference in New Issue
Block a user