finish adding static server metrics

agent/cache/cache.go

@@ -24,6 +24,7 @@ import (
 	"time"
 
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"golang.org/x/time/rate"
 
 	"github.com/hashicorp/consul/lib"
@@ -32,6 +33,34 @@ import (
 
 //go:generate mockery -all -inpkg
 
+// TODO(kit): remove the namespace from these once the metrics themselves change
+var Gauges = []prometheus.GaugeDefinition{
+	{
+		Name: []string{"consul", "cache", "entries_count"},
+		Help: "",
+	},
+}
+
+// TODO(kit): remove the namespace from these once the metrics themselves change
+var Counters = []prometheus.CounterDefinition{
+	{
+		Name: []string{"consul", "cache", "bypass"},
+		Help: "",
+	},
+	{
+		Name: []string{"consul", "cache", "fetch_success"},
+		Help: "",
+	},
+	{
+		Name: []string{"consul", "cache", "fetch_error"},
+		Help: "",
+	},
+	{
+		Name: []string{"consul", "cache", "evict_expired"},
+		Help: "",
+	},
+}
+
 // Constants related to refresh backoff. We probably don't ever need to
 // make these configurable knobs since they primarily exist to lower load.
 const (
@@ -629,6 +658,7 @@ func (c *Cache) fetch(key string, r getOptions, allowNew bool, attempt uint, ign
 		// Error handling
 		if err == nil {
 			labels := []metrics.Label{{Name: "result_not_modified", Value: strconv.FormatBool(result.NotModified)}}
+			// TODO(kit): move tEntry.Name to a label on the first write here and deprecate the second write
 			metrics.IncrCounterWithLabels([]string{"consul", "cache", "fetch_success"}, 1, labels)
 			metrics.IncrCounterWithLabels([]string{"consul", "cache", tEntry.Name, "fetch_success"}, 1, labels)
 
@@ -658,6 +688,7 @@ func (c *Cache) fetch(key string, r getOptions, allowNew bool, attempt uint, ign
 				newEntry.RefreshLostContact = time.Time{}
 			}
 		} else {
+			// TODO(kit): Add tEntry.Name to label on fetch_error and deprecate second write
 			metrics.IncrCounter([]string{"consul", "cache", "fetch_error"}, 1)
 			metrics.IncrCounter([]string{"consul", "cache", tEntry.Name, "fetch_error"}, 1)
 

agent/catalog_endpoint.go

@@ -11,7 +11,6 @@ import (
 	"github.com/hashicorp/consul/agent/structs"
 )
 
-// TODO(kit): Add help strings for each
 var CatalogCounters = []prometheus.CounterDefinition{
 	{
 		Name: []string{"client", "api", "catalog_register"},
@@ -19,71 +18,71 @@ var CatalogCounters = []prometheus.CounterDefinition{
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_register"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a catalog register request.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_register"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a catalog register request.",
 	},
 	{
 		Name: []string{"client", "api", "catalog_deregister"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives a catalog deregister request.",
 	},
 	{
 		Name: []string{"client", "api", "catalog_datacenters"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives a request to list datacenters in the catalog.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_deregister"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a catalog deregister request.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_nodes"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list nodes.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_nodes"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a request to list nodes.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_deregister"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a catalog deregister request.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_datacenters"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a request to list datacenters.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_datacenters"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list datacenters.",
 	},
 	{
 		Name: []string{"client", "api", "catalog_nodes"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives a request to list nodes from the catalog.",
 	},
 	{
 		Name: []string{"client", "api", "catalog_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives a request to list services from the catalog.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a request to list services.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list services.",
 	},
 	{
 		Name: []string{"client", "api", "catalog_service_nodes"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives a request to list nodes offering a service.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_service_nodes"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a request to list nodes offering a service.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_service_nodes"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list nodes offering a service.",
 	},
 	{
 		Name: []string{"client", "api", "error", "catalog_service_nodes"},
@@ -91,15 +90,15 @@ var CatalogCounters = []prometheus.CounterDefinition{
 	},
 	{
 		Name: []string{"client", "api", "catalog_node_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list nodes offering a service.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_node_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list services in a node.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_node_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a request to list services in a node.",
 	},
 	{
 		Name: []string{"client", "api", "catalog_node_service_list"},
@@ -115,15 +114,15 @@ var CatalogCounters = []prometheus.CounterDefinition{
 	},
 	{
 		Name: []string{"client", "api", "catalog_gateway_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives a request to list services associated with a gateway.",
 	},
 	{
 		Name: []string{"client", "rpc", "error", "catalog_gateway_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent receives an RPC error for a request to list services associated with a gateway.",
 	},
 	{
 		Name: []string{"client", "api", "success", "catalog_gateway_services"},
-		Help: "",
+		Help: "This increments whenever a Consul agent successfully responds to a request to list services associated with a gateway.",
 	},
 }
 

agent/consul/acl_endpoint_legacy.go

@@ -5,6 +5,7 @@ import (
 	"time"
 
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/acl"
 	"github.com/hashicorp/consul/agent/consul/state"
 	"github.com/hashicorp/consul/agent/structs"
@@ -12,6 +13,13 @@ import (
 	"github.com/hashicorp/go-memdb"
 )
 
+var ACLEndpointLegacySummaries = []prometheus.SummaryDefinition{
+	{
+		Name: []string{"acl", "apply"},
+		Help: "This measures the time it takes to complete an update to the ACL store.",
+	},
+}
+
 // Bootstrap is used to perform a one-time ACL bootstrap operation on
 // a cluster to get the first management token.
 func (a *ACL) Bootstrap(args *structs.DCSpecificRequest, reply *structs.ACL) error {

agent/consul/autopilot.go

@@ -16,7 +16,7 @@ import (
 var AutopilotGauges = []prometheus.GaugeDefinition{
 	{
 		Name: []string{"autopilot", "failure_tolerance"},
-		Help: "",
+		Help: "This tracks the number of voting servers that the cluster can lose while continuing to function.",
 	},
 	{
 		Name: []string{"autopilot", "healthy"},

agent/consul/catalog_endpoint.go

@@ -21,7 +21,7 @@ import (
 var CatalogCounters = []prometheus.CounterDefinition{
 	{
 		Name: []string{"catalog", "service", "query"},
-		Help: "",
+		Help: "This increments for each catalog query for the given service.",
 	},
 	{
 		Name: []string{"catalog", "connect", "query"},
@@ -29,7 +29,7 @@ var CatalogCounters = []prometheus.CounterDefinition{
 	},
 	{
 		Name: []string{"catalog", "service", "query-tag"},
-		Help: "",
+		Help: "This increments for each catalog query for the given service with the given tag.",
 	},
 	{
 		Name: []string{"catalog", "connect", "query-tag"},
@@ -37,7 +37,7 @@ var CatalogCounters = []prometheus.CounterDefinition{
 	},
 	{
 		Name: []string{"catalog", "service", "query-tags"},
-		Help: "",
+		Help: "This increments for each catalog query for the given service with the given tags.",
 	},
 	{
 		Name: []string{"catalog", "connect", "query-tags"},
@@ -45,7 +45,7 @@ var CatalogCounters = []prometheus.CounterDefinition{
 	},
 	{
 		Name: []string{"catalog", "service", "not-found"},
-		Help: "",
+		Help: "This increments for each catalog query where the given service could not be found.",
 	},
 	{
 		Name: []string{"catalog", "connect", "not-found"},
@@ -56,11 +56,11 @@ var CatalogCounters = []prometheus.CounterDefinition{
 var CatalogSummaries = []prometheus.SummaryDefinition{
 	{
 		Name: []string{"catalog", "deregister"},
-		Help: "",
+		Help: "This measures the time it takes to complete a catalog deregister operation.",
 	},
 	{
 		Name: []string{"catalog", "register"},
-		Help: "",
+		Help: "This measures the time it takes to complete a catalog register operation.",
 	},
 }
 

agent/consul/fsm/commands_oss.go

@@ -4,11 +4,102 @@ import (
 	"fmt"
 	"time"
 
-	metrics "github.com/armon/go-metrics"
+	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/agent/structs"
 	"github.com/hashicorp/consul/api"
 )
 
+var CommandsSummaries = []prometheus.SummaryDefinition{
+	{
+		Name: []string{"fsm", "register"},
+		Help: "This measures the time it takes to apply a catalog register operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "deregister"},
+		Help: "This measures the time it takes to apply a catalog deregister operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "kvs"},
+		Help: "This measures the time it takes to apply the given KV operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "session"},
+		Help: "This measures the time it takes to apply the given session operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "acl"},
+		Help: "This measures the time it takes to apply the given ACL operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "tombstone"},
+		Help: "This measures the time it takes to apply the given tombstone operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "coordinate", "batch-update"},
+		Help: "This measures the time it takes to apply the given batch coordinate update to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "prepared-query"},
+		Help: "This measures the time it takes to apply the given prepared query update operation to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "txn"},
+		Help: "This measures the time it takes to apply the given transaction update to the FSM.",
+	},
+	{
+		Name: []string{"fsm", "autopilot"},
+		Help: "This measures the time it takes to apply the given autopilot update to the FSM.",
+	},
+	{
+		Name: []string{"consul", "fsm", "intention"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "intention"},
+		Help: "",
+	},
+	{
+		Name: []string{"consul", "fsm", "ca"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "ca", "leaf"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "acl", "token"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "ca", "leaf"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "acl", "policy"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "acl", "bindingrule"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "acl", "authmethod"},
+		Help: "",
+	},
+	{
+		Name: []string{"fsm", "system_metadata"},
+		Help: "",
+	},
+	// TODO(kit): We generate the config-entry fsm summaries by reading off of the request. It is
+	//  possible to statically declare these when we know all of the names, but I didn't get to it
+	//  in this patch. Config-entries are known though and we should add these in the future.
+	// {
+	// 	Name:        []string{"fsm", "config_entry", req.Entry.GetKind()},
+	// 	Help:        "",
+	// },
+}
+
 func init() {
 	registerCommand(structs.RegisterRequestType, (*FSM).applyRegister)
 	registerCommand(structs.DeregisterRequestType, (*FSM).applyDeregister)

agent/consul/fsm/snapshot.go

@@ -5,6 +5,7 @@ import (
 	"time"
 
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/agent/consul/state"
 	"github.com/hashicorp/consul/agent/structs"
 	"github.com/hashicorp/go-msgpack/codec"
@@ -12,6 +13,13 @@ import (
 	"github.com/hashicorp/raft"
 )
 
+var SnapshotSummaries = []prometheus.SummaryDefinition{
+	{
+		Name: []string{"fsm", "persist"},
+		Help: "This measures the time it takes to persist the FSM to a raft snapshot.",
+	},
+}
+
 // snapshot is used to provide a snapshot of the current
 // state in a way that can be accessed concurrently with operations
 // that may modify the live state.

agent/consul/leader.go

@@ -11,6 +11,7 @@ import (
 	"time"
 
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/acl"
 	"github.com/hashicorp/consul/agent/metadata"
 	"github.com/hashicorp/consul/agent/structs"
@@ -27,6 +28,21 @@ import (
 	"golang.org/x/time/rate"
 )
 
+var LeaderSummaries = []prometheus.SummaryDefinition{
+	{
+		Name: []string{"leader", "barrier"},
+		Help: "This measures the time spent waiting for the raft barrier upon gaining leadership.",
+	},
+	{
+		Name: []string{"leader", "reconcileMember"},
+		Help: "This measures the time spent updating the raft store for a single serf member's information.",
+	},
+	{
+		Name: []string{"leader", "reapTombstones"},
+		Help: "This measures the time spent clearing tombstones.",
+	},
+}
+
 const (
 	newLeaderEvent      = "consul:new-leader"
 	barrierWriteTimeout = 2 * time.Minute

agent/consul/prepared_query_endpoint.go

@@ -19,19 +19,19 @@ import (
 var PreparedQuerySummaries = []prometheus.SummaryDefinition{
 	{
 		Name: []string{"prepared-query", "apply"},
-		Help: "",
+		Help: "This measures the time it takes to apply a prepared query update.",
 	},
 	{
 		Name: []string{"prepared-query", "explain"},
-		Help: "",
+		Help: "This measures the time it takes to process a prepared query explain request.",
 	},
 	{
 		Name: []string{"prepared-query", "execute"},
-		Help: "",
+		Help: "This measures the time it takes to process a prepared query execute request.",
 	},
 	{
 		Name: []string{"prepared-query", "execute_remote"},
-		Help: "",
+		Help: "This measures the time it takes to process a prepared query execute request that was forwarded to another datacenter.",
 	},
 }
 

agent/consul/rpc.go

@@ -35,41 +35,41 @@ import (
 var RPCCounters = []prometheus.CounterDefinition{
 	{
 		Name: []string{"rpc", "accept_conn"},
-		Help: "",
+		Help: "This increments when a server accepts an RPC connection.",
 	},
 	{
 		Name: []string{"rpc", "raft_handoff"},
-		Help: "",
+		Help: "This increments when a server accepts a Raft-related RPC connection.",
 	},
 	{
 		Name: []string{"rpc", "request_error"},
-		Help: "",
+		Help: "This increments when a server returns an error from an RPC request.",
 	},
 	{
 		Name: []string{"rpc", "request"},
-		Help: "",
+		Help: "This increments when a server receives a Consul-related RPC request.",
 	},
 	{
 		Name: []string{"rpc", "cross-dc"},
-		Help: "",
+		Help: "This increments when a server sends a (potentially blocking) cross datacenter RPC query.",
 	},
 	{
 		Name: []string{"rpc", "query"},
-		Help: "",
+		Help: "This increments when a server receives a new blocking RPC request, indicating the rate of new blocking query calls.",
 	},
 }
 
 var RPCGauges = []prometheus.GaugeDefinition{
 	{
 		Name: []string{"rpc", "queries_blocking"},
-		Help: "",
+		Help: "This shows the current number of in-flight blocking queries the server is handling.",
 	},
 }
 
 var RPCSummaries = []prometheus.SummaryDefinition{
 	{
 		Name: []string{"rpc", "consistentRead"},
-		Help: "",
+		Help: "This measures the time spent confirming that a consistent read can be performed.",
 	},
 }
 

agent/consul/segment_oss.go

@@ -7,10 +7,18 @@ import (
 	"time"
 
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/agent/structs"
 	"github.com/hashicorp/serf/serf"
 )
 
+var SegmentOSSSummaries = []prometheus.SummaryDefinition{
+	{
+		Name: []string{"leader", "reconcile"},
+		Help: "This measures the time spent updating the raft store from the serf member information.",
+	},
+}
+
 // LANMembersAllSegments returns members from all segments.
 func (s *Server) LANMembersAllSegments() ([]serf.Member, error) {
 	return s.LANMembers(), nil

agent/consul/session_endpoint.go

@@ -5,6 +5,7 @@ import (
 	"time"
 
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/acl"
 	"github.com/hashicorp/consul/agent/consul/state"
 	"github.com/hashicorp/consul/agent/structs"
@@ -13,6 +14,17 @@ import (
 	"github.com/hashicorp/go-uuid"
 )
 
+var SessionEndpointSummaries = []prometheus.SummaryDefinition{
+	{
+		Name: []string{"session", "apply"},
+		Help: "This measures the time spent applying a session update.",
+	},
+	{
+		Name: []string{"session", "renew"},
+		Help: "This measures the time spent renewing a session.",
+	},
+}
+
 // Session endpoint is used to manipulate sessions for KV
 type Session struct {
 	srv    *Server

agent/consul/session_ttl.go

@@ -4,16 +4,15 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/armon/go-metrics/prometheus"
-
 	"github.com/armon/go-metrics"
+	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/agent/structs"
 )
 
 var SessionGauges = []prometheus.GaugeDefinition{
 	{
 		Name: []string{"session_ttl", "active"},
-		Help: "",
+		Help: "This tracks the active number of sessions being tracked.",
 	},
 	{
 		Name: []string{"raft", "applied_index"},
@@ -28,7 +27,7 @@ var SessionGauges = []prometheus.GaugeDefinition{
 var SessionSummaries = []prometheus.SummaryDefinition{
 	{
 		Name: []string{"session_ttl", "invalidate"},
-		Help: "",
+		Help: "This measures the time spent invalidating an expired session.",
 	},
 }
 

agent/consul/txn_endpoint.go

@@ -19,7 +19,7 @@ var TxnSummaries = []prometheus.SummaryDefinition{
 	},
 	{
 		Name: []string{"txn", "read"},
-		Help: "",
+		Help: "This measures the time spent returning a read transaction.",
 	},
 }
 

agent/consul/usagemetrics/usagemetrics.go

@@ -15,16 +15,16 @@ import (
 
 var Gauges = []prometheus.GaugeDefinition{
 	{
-		Name: []string{"state", "nodes"},
+		Name: []string{"consul", "state", "nodes"},
-		Help: "",
+		Help: "This measures the current number of nodes registered with Consul. It is only emitted by Consul servers. Added in v1.9.0.",
 	},
 	{
-		Name: []string{"state", "services"},
+		Name: []string{"consul", "state", "services"},
-		Help: "",
+		Help: "This measures the current number of unique services registered with Consul, based on service name. It is only emitted by Consul servers. Added in v1.9.0.",
 	},
 	{
-		Name: []string{"state", "service_instances"},
+		Name: []string{"consul", "state", "service_instances"},
-		Help: "",
+		Help: "This measures the current number of unique services registered with Consul, based on service name. It is only emitted by Consul servers. Added in v1.9.0.",
 	},
 }
 

agent/dns.go

@@ -31,18 +31,18 @@ import (
 var DNSCounters = []prometheus.CounterDefinition{
 	{
 		Name: []string{"dns", "stale_queries"},
-		Help: "",
+		Help: "This increments when an agent serves a query within the allowed stale threshold.",
 	},
 }
 
 var DNSSummaries = []prometheus.SummaryDefinition{
 	{
 		Name: []string{"dns", "ptr_query"},
-		Help: "",
+		Help: "This measures the time spent handling a reverse DNS query for the given node.",
 	},
 	{
 		Name: []string{"dns", "domain_query"},
-		Help: "",
+		Help: "This measures the time spent handling a domain query for the given node.",
 	},
 }
 

agent/grpc/stats.go

@@ -14,37 +14,37 @@ var defaultMetrics = metrics.Default()
 var StatsGauges = []prometheus.GaugeDefinition{
 	{
 		Name: []string{"grpc", "server", "connections"},
-		Help: "",
+		Help: "This metric measures the number of active gRPC connections open on the server.",
 	},
 	{
 		Name: []string{"grpc", "client", "connections"},
-		Help: "",
+		Help: "This metric measures the number of active gRPC connections open from the client agent to any Consul servers.",
 	},
 	{
 		Name: []string{"grpc", "server", "streams"},
-		Help: "",
+		Help: "This metric measures the number of active gRPC streams handled by the server.",
 	},
 }
 var StatsCounters = []prometheus.CounterDefinition{
 	{
 		Name: []string{"grpc", "client", "request", "count"},
-		Help: "",
+		Help: "This metric counts the number of gRPC requests made by the client agent to a Consul server.",
 	},
 	{
 		Name: []string{"grpc", "server", "request", "count"},
-		Help: "",
+		Help: "This metric counts the number of gRPC requests received by the server.",
 	},
 	{
 		Name: []string{"grpc", "client", "connection", "count"},
-		Help: "",
+		Help: "This metric counts the number of new gRPC connections opened by the client agent to a Consul server.",
 	},
 	{
 		Name: []string{"grpc", "server", "connection", "count"},
-		Help: "",
+		Help: "This metric counts the number of new gRPC connections received by the server.",
 	},
 	{
 		Name: []string{"grpc", "server", "stream", "count"},
-		Help: "",
+		Help: "This metric counts the number of new gRPC streams received by the server.",
 	},
 }
 

agent/http.go

@@ -35,7 +35,7 @@ import (
 var HTTPSummaries = []prometheus.SummaryDefinition{
 	{
 		Name: []string{"api", "http"},
-		Help: "",
+		Help: "Samples how long it takes to service the given HTTP request for the given verb and path.",
 	},
 }
 

agent/local/state.go

@@ -21,25 +21,29 @@ import (
 )
 
 var StateCounters = []prometheus.CounterDefinition{
-	{
-		Name: []string{"acl", "blocked", "service", "deregistration"},
-		Help: "",
-	},
-	{
-		Name: []string{"acl", "blocked", "check", "deregistration"},
-		Help: "",
-	},
 	{
 		Name: []string{"acl", "blocked", "service", "registration"},
-		Help: "",
+		Help: "This increments whenever a registration fails for a service (blocked by an ACL)",
+	},
+	{
+		Name: []string{"acl", "blocked", "service", "deregistration"},
+		Help: "This increments whenever a deregistration fails for a service (blocked by an ACL)",
 	},
 	{
 		Name: []string{"acl", "blocked", "check", "registration"},
-		Help: "",
+		Help: "This increments whenever a registration fails for a check (blocked by an ACL)",
+	},
+	{
+		Name: []string{"acl", "blocked", "check", "deregistration"},
+		Help: "This increments whenever a deregistration fails for a check (blocked by an ACL)",
 	},
 	{
 		Name: []string{"acl", "blocked", "node", "registration"},
-		Help: "",
+		Help: "This increments whenever a registration fails for a node (blocked by an ACL)",
+	},
+	{
+		Name: []string{"acl", "blocked", "node", "deregistration"},
+		Help: "This increments whenever a deregistration fails for a node (blocked by an ACL)",
 	},
 }
 

agent/setup.go

@@ -8,6 +8,8 @@ import (
 	"sync"
 	"time"
 
+	"github.com/hashicorp/consul/agent/consul/fsm"
+
 	"github.com/armon/go-metrics/prometheus"
 	"github.com/hashicorp/consul/agent/consul/usagemetrics"
 	"github.com/hashicorp/consul/agent/local"
@@ -187,6 +189,7 @@ func registerWithGRPC(b grpcresolver.Builder) {
 func getPrometheusDefs() lib.PrometheusDefs {
 	serviceName := []string{"consul"}
 	var gauges = [][]prometheus.GaugeDefinition{
+		cache.Gauges,
 		consul.AutopilotGauges,
 		consul.RPCGauges,
 		consul.SessionGauges,
@@ -205,9 +208,8 @@ func getPrometheusDefs() lib.PrometheusDefs {
 	}
 
 	raftCounters := []prometheus.CounterDefinition{
-		// TODO(kit): "consul.raft..." metrics come from the raft lib and we should migrate these to a telemetry
+		// TODO(kit): "raft..." metrics come from the raft lib and we should migrate these to a telemetry
-		//  package within. In the mean time, we're going to define them here because it's important that they're always
+		//  package within. In the mean time, we're going to define a few here because they're key to monitoring Consul.
-		//  present for Consul users setting up dashboards.
 		{
 			Name: []string{"raft", "apply"},
 			Help: "This counts the number of Raft transactions occurring over the interval.",
@@ -224,6 +226,7 @@ func getPrometheusDefs() lib.PrometheusDefs {
 
 	var counters = [][]prometheus.CounterDefinition{
 		CatalogCounters,
+		cache.Counters,
 		consul.ACLCounters,
 		consul.CatalogCounters,
 		consul.ClientCounters,
@@ -244,9 +247,8 @@ func getPrometheusDefs() lib.PrometheusDefs {
 	}
 
 	raftSummaries := []prometheus.SummaryDefinition{
-		// TODO(kit): "consul.raft..." metrics come from the raft lib and we should migrate these to a telemetry
+		// TODO(kit): "raft..." metrics come from the raft lib and we should migrate these to a telemetry
-		//  package within. In the mean time, we're going to define them here because it's important that they're always
+		//  package within. In the mean time, we're going to define a few here because they're key to monitoring Consul.
-		//  present for Consul users setting up dashboards.
 		{
 			Name: []string{"raft", "commitTime"},
 			Help: "This measures the time it takes to commit a new entry to the Raft log on the leader.",
@@ -261,14 +263,20 @@ func getPrometheusDefs() lib.PrometheusDefs {
 		HTTPSummaries,
 		consul.ACLSummaries,
 		consul.ACLEndpointSummaries,
+		consul.ACLEndpointLegacySummaries,
 		consul.CatalogSummaries,
 		consul.FederationStateSummaries,
 		consul.IntentionSummaries,
 		consul.KVSummaries,
+		consul.LeaderSummaries,
 		consul.PreparedQuerySummaries,
 		consul.RPCSummaries,
+		consul.SegmentOSSSummaries,
 		consul.SessionSummaries,
+		consul.SessionEndpointSummaries,
 		consul.TxnSummaries,
+		fsm.CommandsSummaries,
+		fsm.SnapshotSummaries,
 		raftSummaries,
 	}
 	var summaryDefs []prometheus.SummaryDefinition