mirrors/node-feature-discovery
1
0
Fork 0
mirror of https://github.com/kubernetes-sigs/node-feature-discovery.git synced 2024-12-14 11:57:51 +00:00
Code Activity

chore: add metrics system prefix

Browse source
This commit is contained in:
googs1025 2024-11-17 11:55:25 +08:00
parent 835832729f
commit e631a52374
6 changed files with 117 additions and 79 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
docs/deployment/metrics.md
View file

@ -14,20 +14,21 @@ By default NFD Master and Worker expose metrics on port 8081.
The exposed metrics are
| Metric | Type | Description |
| ------------------------------------------------- | --------- | ------------------------------------------------------- |
| -------------------------------------------------------- | --------- | -------------------------------------------------------------------------- |
| `nfd_master_build_info` | Gauge | Version from which nfd-master was built |
| `nfd_worker_build_info` | Gauge | Version from which nfd-worker was built |
| `nfd_gc_build_info` | Gauge | Version from which nfd-gc was built |
| `nfd_topology_updater_build_info` | Gauge | Version from which nfd-topology-updater was built |
| `nfd_node_update_requests_total` | Counter | Number of node update requests received by the master over gRPC |
| `nfd_node_updates_total` | Counter | Number of nodes updated |
| `nfd_node_update_failures_total` | Counter | Number of nodes update failures |
| `nfd_node_labels_rejected_total` | Counter | Number of nodes labels rejected by nfd-master |
| `nfd_node_extendedresources_rejected_total` | Counter | Number of nodes extended resources rejected by nfd-master |
| `nfd_node_taints_rejected_total` | Counter | Number of nodes taints rejected by nfd-master |
| `nfd_nodefeaturerule_processing_duration_seconds` | Histogram | Time taken to process NodeFeatureRule objects |
| `nfd_nodefeaturerule_processing_errors_total` | Counter | Number or errors encountered while processing NodeFeatureRule objects |
| `nfd_feature_discovery_duration_seconds` | Histogram | Time taken to discover features on a node |
| `nfd_master_node_update_requests_total` | Counter | Number of node update requests received by the master over gRPC |
| `nfd_master_node_updates_total` | Counter | Number of nodes updated |
| `nfd_master_node_feature_group_update_requests_total` | Counter | Number of cluster feature update requests processed by the master |
| `nfd_master_node_update_failures_total` | Counter | Number of nodes update failures |
| `nfd_master_node_labels_rejected_total` | Counter | Number of nodes labels rejected by nfd-master |
| `nfd_master_node_extendedresources_rejected_total` | Counter | Number of nodes extended resources rejected by nfd-master |
| `nfd_master_node_taints_rejected_total` | Counter | Number of nodes taints rejected by nfd-master |
| `nfd_master_nodefeaturerule_processing_duration_seconds` | Histogram | Time taken to process NodeFeatureRule objects |
| `nfd_master_nodefeaturerule_processing_errors_total` | Counter | Number or errors encountered while processing NodeFeatureRule objects |
| `nfd_worker_feature_discovery_duration_seconds` | Histogram | Time taken to discover features on a node |
| `nfd_topology_updater_scan_errors_total` | Counter | Number of errors in scanning resource allocation of pods. |
| `nfd_gc_objects_deleted_total` | Counter | Number of NodeFeature and NodeResourceTopology objects garbage collected. |
| `nfd_gc_object_delete_failures_total` | Counter | Number of errors in deleting NodeFeature and NodeResourceTopology objects. |

16
examples/grafana-dashboard.json
View file

@ -391,7 +391,7 @@
},
"disableTextWrap": false,
"editorMode": "builder",
"expr": "nfd_node_updates_total",
"expr": "nfd_master_node_updates_total",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
@ -586,7 +586,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "nfd_node_update_failures_total",
"expr": "nfd_master_node_update_failures_total",
"legendFormat": "total",
"range": true,
"refId": "A"
@ -679,7 +679,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "nfd_nodefeaturerule_processing_errors_total",
"expr": "nfd_master_nodefeaturerule_processing_errors_total",
"hide": false,
"legendFormat": "total",
"range": true,
@ -940,7 +940,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "sum by(le) (nfd_feature_discovery_duration_seconds_bucket)",
"expr": "sum by(le) (nfd_worker_feature_discovery_duration_seconds_bucket)",
"format": "heatmap",
"legendFormat": "__auto",
"range": true,
@ -1007,7 +1007,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "sum by(le) (nfd_nodefeaturerule_processing_duration_seconds_bucket)",
"expr": "sum by(le) (nfd_master_nodefeaturerule_processing_duration_seconds_bucket)",
"format": "heatmap",
"legendFormat": "__auto",
"range": true,
@ -1101,7 +1101,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "nfd_node_labels_rejected_total",
"expr": "nfd_master_node_labels_rejected_total",
"legendFormat": "total",
"range": true,
"refId": "A"
@ -1194,7 +1194,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "nfd_node_extendedresources_rejected_total",
"expr": "nfd_master_node_extendedresources_rejected_total",
"hide": false,
"legendFormat": "total",
"range": true,
@ -1288,7 +1288,7 @@
"uid": "prometheus"
},
"editorMode": "builder",
"expr": "nfd_node_taints_rejected_total",
"expr": "nfd_master_node_taints_rejected_total",
"hide": false,
"legendFormat": "total",
"range": true,

14
pkg/nfd-gc/metrics.go
View file

@ -23,13 +23,19 @@ import (
// When adding metric names, see https://prometheus.io/docs/practices/naming/#metric-names
const (
buildInfoQuery = "nfd_gc_build_info"
objectsDeletedQuery = "nfd_gc_objects_deleted_total"
objectDeleteErrorsQuery = "nfd_gc_object_delete_failures_total"
buildInfoQuery = "build_info"
objectsDeletedQuery = "objects_deleted_total"
objectDeleteErrorsQuery = "object_delete_failures_total"
)
const (
// nfdGCPrefix - subsystem name used by nfd gc.
nfdGCPrefix = "nfd_gc"
)
var (
buildInfo = prometheus.NewGauge(prometheus.GaugeOpts{
Subsystem: nfdGCPrefix,
Name: buildInfoQuery,
Help: "Version from which Node Feature Discovery was built.",
ConstLabels: map[string]string{
@ -37,11 +43,13 @@ var (
},
})
objectsDeleted = prometheus.NewCounterVec(prometheus.CounterOpts{
Subsystem: nfdGCPrefix,
Name: objectsDeletedQuery,
Help: "Number of NodeFeature and NodeResourceTopology objects garbage collected."},
[]string{"kind"},
)
objectDeleteErrors = prometheus.NewCounterVec(prometheus.CounterOpts{
Subsystem: nfdGCPrefix,
Name: objectDeleteErrorsQuery,
Help: "Number of errors in deleting NodeFeature and NodeResourceTopology objects."},
[]string{"kind"},

35
pkg/nfd-master/metrics.go
View file

@ -23,20 +23,26 @@ import (
// When adding metric names, see https://prometheus.io/docs/practices/naming/#metric-names
const (
buildInfoQuery = "nfd_master_build_info"
nodeUpdateRequestsQuery = "nfd_node_update_requests_total"
nodeUpdatesQuery = "nfd_node_updates_total"
nodeFeatureGroupUpdateRequestsQuery = "nfd_node_feature_group_update_requests_total"
nodeUpdateFailuresQuery = "nfd_node_update_failures_total"
nodeLabelsRejectedQuery = "nfd_node_labels_rejected_total"
nodeERsRejectedQuery = "nfd_node_extendedresources_rejected_total"
nodeTaintsRejectedQuery = "nfd_node_taints_rejected_total"
nfrProcessingTimeQuery = "nfd_nodefeaturerule_processing_duration_seconds"
nfrProcessingErrorsQuery = "nfd_nodefeaturerule_processing_errors_total"
buildInfoQuery = "build_info"
nodeUpdateRequestsQuery = "node_update_requests_total"
nodeUpdatesQuery = "node_updates_total"
nodeFeatureGroupUpdateRequestsQuery = "node_feature_group_update_requests_total"
nodeUpdateFailuresQuery = "node_update_failures_total"
nodeLabelsRejectedQuery = "node_labels_rejected_total"
nodeERsRejectedQuery = "node_extendedresources_rejected_total"
nodeTaintsRejectedQuery = "node_taints_rejected_total"
nfrProcessingTimeQuery = "nodefeaturerule_processing_duration_seconds"
nfrProcessingErrorsQuery = "nodefeaturerule_processing_errors_total"
)
const (
// nfdMasterPrefix - subsystem name used by nfd master.
nfdMasterPrefix = "nfd_master"
)
var (
buildInfo = prometheus.NewGauge(prometheus.GaugeOpts{
Subsystem: nfdMasterPrefix,
Name: buildInfoQuery,
Help: "Version from which Node Feature Discovery was built.",
ConstLabels: map[string]string{
@ -44,35 +50,43 @@ var (
},
})
nodeUpdateRequests = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeUpdateRequestsQuery,
Help: "Number of node update requests processed by the master.",
})
nodeFeatureGroupUpdateRequests = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeFeatureGroupUpdateRequestsQuery,
Help: "Number of cluster feature update requests processed by the master.",
})
nodeUpdates = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeUpdatesQuery,
Help: "Number of nodes updated by the master.",
})
nodeUpdateFailures = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeUpdateFailuresQuery,
Help: "Number of node update failures.",
})
nodeLabelsRejected = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeLabelsRejectedQuery,
Help: "Number of node labels that were rejected by nfd-master.",
})
nodeERsRejected = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeERsRejectedQuery,
Help: "Number of node extended resources that were rejected by nfd-master.",
})
nodeTaintsRejected = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nodeTaintsRejectedQuery,
Help: "Number of node taints that were rejected by nfd-master.",
})
nfrProcessingTime = prometheus.NewHistogramVec(
prometheus.HistogramOpts{
Subsystem: nfdMasterPrefix,
Name: nfrProcessingTimeQuery,
Help: "Time processing time of NodeFeatureRule objects.",
Buckets: []float64{0.0001, 0.00025, 0.0005, 0.001, 0.0025, 0.005, 0.01},
@ -83,6 +97,7 @@ var (
},
)
nfrProcessingErrors = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdMasterPrefix,
Name: nfrProcessingErrorsQuery,
Help: "Number of errors encountered while processing NodeFeatureRule objects.",
})

11
pkg/nfd-topology-updater/metrics.go
View file

@ -23,12 +23,18 @@ import (
// When adding metric names, see https://prometheus.io/docs/practices/naming/#metric-names
const (
buildInfoQuery = "nfd_topology_updater_build_info"
scanErrorsQuery = "nfd_topology_updater_scan_errors_total"
buildInfoQuery = "build_info"
scanErrorsQuery = "scan_errors_total"
)
const (
// nfdTopologyUpdaterPrefix - subsystem name used by nfd topology updater.
nfdTopologyUpdaterPrefix = "nfd_topology_updater"
)
var (
buildInfo = prometheus.NewGauge(prometheus.GaugeOpts{
Subsystem: nfdTopologyUpdaterPrefix,
Name: buildInfoQuery,
Help: "Version from which Node Feature Discovery was built.",
ConstLabels: map[string]string{
@ -36,6 +42,7 @@ var (
},
})
scanErrors = prometheus.NewCounter(prometheus.CounterOpts{
Subsystem: nfdTopologyUpdaterPrefix,
Name: scanErrorsQuery,
Help: "Number of errors in scanning resource allocation of pods.",
})

11
pkg/nfd-worker/metrics.go
View file

@ -23,13 +23,19 @@ import (
// When adding metric names, see https://prometheus.io/docs/practices/naming/#metric-names
const (
buildInfoQuery = "nfd_worker_build_info"
featureDiscoveryDurationQuery = "nfd_feature_discovery_duration_seconds"
buildInfoQuery = "build_info"
featureDiscoveryDurationQuery = "feature_discovery_duration_seconds"
)
const (
// nfdWorkerPrefix - subsystem name used by nfd worker.
nfdWorkerPrefix = "nfd_worker"
)
var (
featureDiscoveryDuration = prometheus.NewHistogramVec(
prometheus.HistogramOpts{
Subsystem: nfdWorkerPrefix,
Name: featureDiscoveryDurationQuery,
Help: "Time taken to discover features",
Buckets: []float64{0.01, 0.025, 0.05, 0.1, 0.25, 0.5, 1},
@ -37,6 +43,7 @@ var (
[]string{"node"},
)
buildInfo = prometheus.NewGauge(prometheus.GaugeOpts{
Subsystem: nfdWorkerPrefix,
Name: buildInfoQuery,
Help: "Version from which Node Feature Discovery was built.",
ConstLabels: map[string]string{