Update metric help to be more descriptive. (#12764)

Signed-off-by: Brad Davidson <[email protected]>
Co-authored-by: Brad Davidson <[email protected]>

Author: dereknola

pkg/agent/loadbalancer/metrics.go

@@ -9,17 +9,18 @@ import (
 var (
 	loadbalancerConnections = prometheus.NewGaugeVec(prometheus.GaugeOpts{
 		Name: version.Program + "_loadbalancer_server_connections",
-		Help: "Count of current connections to loadbalancer server",
+		Help: "Count of current connections to loadbalancer server, labeled by loadbalancer name and server address.",
 	}, []string{"name", "server"})
 
 	loadbalancerState = prometheus.NewGaugeVec(prometheus.GaugeOpts{
 		Name: version.Program + "_loadbalancer_server_health",
-		Help: "Current health value of loadbalancer server",
+		Help: "Current health state of loadbalancer backend servers, labeled by loadbalancer name and server address. " +
+			"State is enum of 0=INVALID, 1=FAILED, 2=STANDBY, 3=UNCHECKED, 4=RECOVERING, 5=HEALTHY, 6=PREFERRED, 7=ACTIVE.",
 	}, []string{"name", "server"})
 
 	loadbalancerDials = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_loadbalancer_dial_duration_seconds",
-		Help:    "Time taken to dial a connection to a backend server",
+		Help:    "Time in seconds taken to dial a connection to a backend server, labeled by loadbalancer name and success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.001, 2, 15),
 	}, []string{"name", "status"})
 )

pkg/certmonitor/certmonitor.go

@@ -36,7 +36,7 @@ var (
 
 	certificateExpirationSeconds = prometheus.NewGaugeVec(prometheus.GaugeOpts{
 		Name: version.Program + "_certificate_expiration_seconds",
-		Help: "Remaining lifetime on the certificate.",
+		Help: "Remaining lifetime in seconds of the certificate, labeled by certificate subject and usages.",
 	}, []string{"subject", "usages"})
 )
 

pkg/etcd/snapshot_metrics.go

@@ -9,37 +9,37 @@ import (
 var (
 	snapshotSaveCount = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_etcd_snapshot_save_duration_seconds",
-		Help:    "Total time taken to complete the etcd snapshot process",
+		Help:    "Total time in seconds taken to complete the etcd snapshot process, labeled by success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.008, 2, 15),
 	}, []string{"status"})
 
 	snapshotSaveLocalCount = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_etcd_snapshot_save_local_duration_seconds",
-		Help:    "Total time taken to save a local snapshot file",
+		Help:    "Total time in seconds taken to save a local snapshot file, labeled by success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.008, 2, 15),
 	}, []string{"status"})
 
 	snapshotSaveS3Count = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_etcd_snapshot_save_s3_duration_seconds",
-		Help:    "Total time taken to upload a snapshot file to S3",
+		Help:    "Total time in seconds taken to upload a snapshot file to S3, labeled by success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.008, 2, 15),
 	}, []string{"status"})
 
 	snapshotReconcileCount = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_etcd_snapshot_reconcile_duration_seconds",
-		Help:    "Total time taken to sync the list of etcd snapshots",
+		Help:    "Total time in seconds taken to sync the list of etcd snapshots, labeled by success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.008, 2, 15),
 	}, []string{"status"})
 
 	snapshotReconcileLocalCount = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_etcd_snapshot_reconcile_local_duration_seconds",
-		Help:    "Total time taken to list local snapshot files",
+		Help:    "Total time in seconds taken to list local snapshot files, labeled by success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.008, 2, 15),
 	}, []string{"status"})
 
 	snapshotReconcileS3Count = prometheus.NewHistogramVec(prometheus.HistogramOpts{
 		Name:    version.Program + "_etcd_snapshot_reconcile_s3_duration_seconds",
-		Help:    "Total time taken to list S3 snapshot files",
+		Help:    "Total time in seconds taken to list S3 snapshot files, labeled by success/failure status.",
 		Buckets: metrics.ExponentialBuckets(0.008, 2, 15),
 	}, []string{"status"})
 )