status-im
/
consul
mirror of https://github.com/status-im/consul.git
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #9245 from hashicorp/telemetry/fix-missing-and-stale-docs 

Telemetry/fix missing and stale docs
This commit is contained in:
Kit Patella 2020-11-20 12:54:29 -08:00 committed by hashicorp-ci
parent 3ffd1fdc8b
commit fe6ef7e414
3 changed files with 61 additions and 64 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
agent/catalog_endpoint.go
View File

@ -86,7 +86,7 @@ var CatalogCounters = []prometheus.CounterDefinition{
}, },
{ {
Name: []string{"client", "api", "error", "catalog_service_nodes"}, Name: []string{"client", "api", "error", "catalog_service_nodes"},
Help: "", Help: "Increments whenever a Consul agent receives an RPC error for request to list nodes offering a service.",
}, },
{ {
Name: []string{"client", "api", "catalog_node_services"}, Name: []string{"client", "api", "catalog_node_services"},
@ -102,15 +102,15 @@ var CatalogCounters = []prometheus.CounterDefinition{
}, },
{ {
Name: []string{"client", "api", "catalog_node_service_list"}, Name: []string{"client", "api", "catalog_node_service_list"},
Help: "", Help: "Increments whenever a Consul agent receives a request to list a node's registered services.",
}, },
{ {
Name: []string{"client", "rpc", "error", "catalog_node_service_list"}, Name: []string{"client", "rpc", "error", "catalog_node_service_list"},
Help: "", Help: "Increments whenever a Consul agent receives an RPC error for request to list a node's registered services.",
}, },
{ {
Name: []string{"client", "api", "success", "catalog_node_service_list"}, Name: []string{"client", "api", "success", "catalog_node_service_list"},
Help: "", Help: "Increments whenever a Consul agent successfully responds to a request to list a node's registered services.",
}, },
{ {
Name: []string{"client", "api", "catalog_gateway_services"}, Name: []string{"client", "api", "catalog_gateway_services"},

10
agent/consul/acl.go
View File

@ -19,26 +19,26 @@ import (
var ACLCounters = []prometheus.CounterDefinition{ var ACLCounters = []prometheus.CounterDefinition{
{ {
Name: []string{"acl", "token", "cache_hit"}, Name: []string{"acl", "token", "cache_hit"},
Help: "", Help: "Increments if Consul is able to resolve a token's identity, or a legacy token, from the cache.",
}, },
{ {
Name: []string{"acl", "token", "cache_miss"}, Name: []string{"acl", "token", "cache_miss"},
Help: "", Help: "Increments if Consul cannot resolve a token's identity, or a legacy token, from the cache.",
}, },
} }
var ACLSummaries = []prometheus.SummaryDefinition{ var ACLSummaries = []prometheus.SummaryDefinition{
{ {
Name: []string{"acl", "resolveTokenLegacy"}, Name: []string{"acl", "resolveTokenLegacy"},
Help: "", Help: "This measures the time it takes to resolve an ACL token using the legacy ACL system.",
}, },
{ {
Name: []string{"acl", "ResolveToken"}, Name: []string{"acl", "ResolveToken"},
Help: "", Help: "This measures the time it takes to resolve an ACL token.",
}, },
{ {
Name: []string{"acl", "ResolveTokenToIdentity"}, Name: []string{"acl", "ResolveTokenToIdentity"},
Help: "", Help: "This measures the time it takes to resolve an ACL token to an Identity.",
}, },
} }

29
website/pages/docs/agent/telemetry.mdx
View File

@ -138,9 +138,9 @@ when retrieving metrics from the built-in store using the above described signal
This is a full list of metrics emitted by Consul. This is a full list of metrics emitted by Consul.
| Metric | Description | Unit | Type | | Metric | Description | Unit | Type |
| ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- | ------- | | -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------- | ------- |
| `consul.acl.blocked.service.registration` | This increments whenever a deregistration fails for a service (blocked by an ACL) | requests | counter | | `consul.acl.blocked.{check,node,service}.deregistration` | This increments whenever a deregistration fails for an entity (check, node or service) is blocked by an ACL. | requests | counter |
| `consul.acl.blocked..registration` | This increments whenever a registration fails for an entity (check, node or service) is blocked by an ACL | requests | counter | | `consul.acl.blocked.{check,node,service}.registration` | This increments whenever a registration fails for an entity (check, node or service) is blocked by an ACL. | requests | counter |
| `consul.api.http` | Migrated from consul.http.. this samples how long it takes to service the given HTTP request for the given verb and path. Includes labels for `path` and `method`. `path` does not include details like service or key names, for these an underscore will be present as a placeholder (eg. path=`v1.kv._`) | ms | timer | | `consul.api.http` | Migrated from consul.http.. this samples how long it takes to service the given HTTP request for the given verb and path. Includes labels for `path` and `method`. `path` does not include details like service or key names, for these an underscore will be present as a placeholder (eg. path=`v1.kv._`) | ms | timer |
| `consul.client.rpc` | This increments whenever a Consul agent in client mode makes an RPC request to a Consul server. This gives a measure of how much a given agent is loading the Consul servers. Currently, this is only generated by agents in client mode, not Consul servers. | requests | counter | | `consul.client.rpc` | This increments whenever a Consul agent in client mode makes an RPC request to a Consul server. This gives a measure of how much a given agent is loading the Consul servers. Currently, this is only generated by agents in client mode, not Consul servers. | requests | counter |
| `consul.client.rpc.exceeded` | This increments whenever a Consul agent in client mode makes an RPC request to a Consul server gets rate limited by that agent's [`limits`](/docs/agent/options#limits) configuration. This gives an indication that there's an abusive application making too many requests on the agent, or that the rate limit needs to be increased. Currently, this only applies to agents in client mode, not Consul servers. | rejected requests | counter | | `consul.client.rpc.exceeded` | This increments whenever a Consul agent in client mode makes an RPC request to a Consul server gets rate limited by that agent's [`limits`](/docs/agent/options#limits) configuration. This gives an indication that there's an abusive application making too many requests on the agent, or that the rate limit needs to be increased. Currently, this only applies to agents in client mode, not Consul servers. | rejected requests | counter |
@ -162,10 +162,14 @@ This is a full list of metrics emitted by Consul.
| `consul.client.rpc.error.catalog_services.` | This increments whenever a Consul agent receives an RPC error for a request to list services. | errors | counter | | `consul.client.rpc.error.catalog_services.` | This increments whenever a Consul agent receives an RPC error for a request to list services. | errors | counter |
| `consul.client.api.catalog_service_nodes.` | This increments whenever a Consul agent receives a request to list nodes offering a service. | requests | counter | | `consul.client.api.catalog_service_nodes.` | This increments whenever a Consul agent receives a request to list nodes offering a service. | requests | counter |
| `consul.client.api.success.catalog_service_nodes.` | This increments whenever a Consul agent successfully responds to a request to list nodes offering a service. | requests | counter | | `consul.client.api.success.catalog_service_nodes.` | This increments whenever a Consul agent successfully responds to a request to list nodes offering a service. | requests | counter |
| `consul.client.api.error.catalog_service_nodes.` | Increments whenever a Consul agent receives an RPC error for request to list nodes offering a service. | requests | counter |
| `consul.client.rpc.error.catalog_service_nodes.` | This increments whenever a Consul agent receives an RPC error for a request to list nodes offering a service. | errors | counter | | `consul.client.rpc.error.catalog_service_nodes.` | This increments whenever a Consul agent receives an RPC error for a request to list nodes offering a service. | errors | counter |
| `consul.client.api.catalog_node_services.` | This increments whenever a Consul agent receives a request to list services registered in a node. | requests | counter | | `consul.client.api.catalog_node_services.` | This increments whenever a Consul agent receives a request to list services registered in a node. | requests | counter |
| `consul.client.api.success.catalog_node_services.` | This increments whenever a Consul agent successfully responds to a request to list services in a node. | requests | counter | | `consul.client.api.success.catalog_node_services.` | This increments whenever a Consul agent successfully responds to a request to list services in a node. | requests | counter |
| `consul.client.rpc.error.catalog_node_services.` | This increments whenever a Consul agent receives an RPC error for a request to list services in a node. | errors | counter | | `consul.client.rpc.error.catalog_node_services.` | This increments whenever a Consul agent receives an RPC error for a request to list services in a node. | errors | counter |
| `consul.client.api.catalog_node_service_list` | Increments whenever a Consul agent receives a request to list a node's registered services. | requests | counter |
| `consul.client.rpc.error.catalog_node_service_list` | Increments whenever a Consul agent receives an RPC error for request to list a node's registered services. | errors | counter |
| `consul.client.api.success.catalog_node_service_list` | Increments whenever a Consul agent successfully responds to a request to list a node's registered services. | requests | counter |
| `consul.client.api.catalog_gateway_services.` | This increments whenever a Consul agent receives a request to list services associated with a gateway. | requests | counter | | `consul.client.api.catalog_gateway_services.` | This increments whenever a Consul agent receives a request to list services associated with a gateway. | requests | counter |
| `consul.client.api.success.catalog_gateway_services.` | This increments whenever a Consul agent successfully responds to a request to list services associated with a gateway. | requests | counter | | `consul.client.api.success.catalog_gateway_services.` | This increments whenever a Consul agent successfully responds to a request to list services associated with a gateway. | requests | counter |
| `consul.client.rpc.error.catalog_gateway_services.` | This increments whenever a Consul agent receives an RPC error for a request to list services associated with a gateway. | errors | counter | | `consul.client.rpc.error.catalog_gateway_services.` | This increments whenever a Consul agent receives an RPC error for a request to list services associated with a gateway. | errors | counter |
@ -175,9 +179,6 @@ This is a full list of metrics emitted by Consul.
| `consul.state.nodes` | This measures the current number of nodes registered with Consul. It is only emitted by Consul servers. Added in v1.9.0. | number of objects | gauge | | `consul.state.nodes` | This measures the current number of nodes registered with Consul. It is only emitted by Consul servers. Added in v1.9.0. | number of objects | gauge |
| `consul.state.services` | 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. | number of objects | gauge | | `consul.state.services` | 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. | number of objects | gauge |
| `consul.state.service_instances` | This measures the current number of unique service instances registered with Consul. It is only emitted by Consul servers. Added in v1.9.0. | number of objects | gauge | | `consul.state.service_instances` | This measures the current number of unique service instances registered with Consul. It is only emitted by Consul servers. Added in v1.9.0. | number of objects | gauge |
| `consul.acl.cache_hit` | The number of ACL cache hits. | hits | counter |
| `consul.acl.cache_miss` | The number of ACL cache misses. | misses | counter |
| `consul.acl.replication_hit` | The number of ACL replication cache hits (when not running in the ACL datacenter). | hits | counter |
| `consul.dns.stale_queries` | This increments when an agent serves a query within the allowed stale threshold. | queries | counter | | `consul.dns.stale_queries` | This increments when an agent serves a query within the allowed stale threshold. | queries | counter |
| `consul.dns.ptr_query.` | This measures the time spent handling a reverse DNS query for the given node. | ms | timer | | `consul.dns.ptr_query.` | This measures the time spent handling a reverse DNS query for the given node. | ms | timer |
| `consul.dns.domain_query.` | This measures the time spent handling a domain query for the given node. | ms | timer | | `consul.dns.domain_query.` | This measures the time spent handling a domain query for the given node. | ms | timer |
@ -189,6 +190,12 @@ These metrics are used to monitor the health of the Consul servers.
| Metric | Description | Unit | Type | | Metric | Description | Unit | Type |
| ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------- | ------- | | ----------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------- | ------- |
| `consul.acl.apply` | This measures the time it takes to complete an update to the ACL store. | ms | timer |
| `consul.acl.resolveTokenLegacy` | This measures the time it takes to resolve an ACL token using the legacy ACL system. | ms | timer |
| `consul.acl.ResolveToken` | This measures the time it takes to resolve an ACL token. | ms | timer |
| `consul.acl.ResolveTokenToIdentity` | This measures the time it takes to resolve an ACL token to an Identity. | ms | timer |
| `consul.acl.token.cache_hit` | Increments if Consul is able to resolve a token's identity, or a legacy token, from the cache. | cache read op | counter |
| `consul.acl.token.cache_miss` | Increments if Consul cannot resolve a token's identity, or a legacy token, from the cache. | cache read op | counter |
| `consul.raft.fsm.snapshot` | This metric measures the time taken by the FSM to record the current state for the snapshot. | ms | timer | | `consul.raft.fsm.snapshot` | This metric measures the time taken by the FSM to record the current state for the snapshot. | ms | timer |
| `consul.raft.fsm.apply` | This metric gives the number of logs committed since the last interval. | commit logs / interval | counter | | `consul.raft.fsm.apply` | This metric gives the number of logs committed since the last interval. | commit logs / interval | counter |
| `consul.raft.commitNumLogs` | This metric measures the count of logs processed for application to the FSM in a single batch. | logs | gauge | | `consul.raft.commitNumLogs` | This metric measures the count of logs processed for application to the FSM in a single batch. | logs | gauge |
@ -222,12 +229,6 @@ These metrics are used to monitor the health of the Consul servers.
| `consul.raft.replication.appendEntries.rpc` | This metric measures the time taken by the append entries RFC, to replicate the log entries of a leader agent onto its follower agent(s) | ms | timer | | `consul.raft.replication.appendEntries.rpc` | This metric measures the time taken by the append entries RFC, to replicate the log entries of a leader agent onto its follower agent(s) | ms | timer |
| `consul.raft.replication.appendEntries.logs` | This metric measures the number of logs replicated to an agent, to bring it up to speed with the leader's logs. | logs appended/ interval | counter | | `consul.raft.replication.appendEntries.logs` | This metric measures the number of logs replicated to an agent, to bring it up to speed with the leader's logs. | logs appended/ interval | counter |
| `consul.raft.leader.lastContact` | This will only be emitted by the Raft leader and measures the time since the leader was last able to contact the follower nodes when checking its leader lease. It can be used as a measure for how stable the Raft timing is and how close the leader is to timing out its lease.The lease timeout is 500 ms times the [`raft_multiplier` configuration](/docs/agent/options#raft_multiplier), so this telemetry value should not be getting close to that configured value, otherwise the Raft timing is marginal and might need to be tuned, or more powerful servers might be needed. See the [Server Performance](/docs/install/performance) guide for more details. | ms | timer | | `consul.raft.leader.lastContact` | This will only be emitted by the Raft leader and measures the time since the leader was last able to contact the follower nodes when checking its leader lease. It can be used as a measure for how stable the Raft timing is and how close the leader is to timing out its lease.The lease timeout is 500 ms times the [`raft_multiplier` configuration](/docs/agent/options#raft_multiplier), so this telemetry value should not be getting close to that configured value, otherwise the Raft timing is marginal and might need to be tuned, or more powerful servers might be needed. See the [Server Performance](/docs/install/performance) guide for more details. | ms | timer |
| `consul.acl.apply` | This measures the time it takes to complete an update to the ACL store. | ms | timer |
| `consul.acl.fault` | This measures the time it takes to fault in the rules for an ACL during a cache miss. | ms | timer |
| `consul.acl.fetchRemoteACLs` | This measures the time it takes to fetch remote ACLs during replication. | ms | timer |
| `consul.acl.updateLocalACLs` | This measures the time it takes to apply replication changes to the local ACL store. | ms | timer |
| `consul.acl.replicateACLs` | This measures the time it takes to do one pass of the ACL replication algorithm. | ms | timer |
| `consul.acl.resolveToken` | This measures the time it takes to resolve an ACL token. | ms | timer |
| `consul.rpc.accept_conn` | This increments when a server accepts an RPC connection. | connections | counter | | `consul.rpc.accept_conn` | This increments when a server accepts an RPC connection. | connections | counter |
| `consul.catalog.register` | This measures the time it takes to complete a catalog register operation. | ms | timer | | `consul.catalog.register` | This measures the time it takes to complete a catalog register operation. | ms | timer |
| `consul.catalog.deregister` | This measures the time it takes to complete a catalog deregister operation. | ms | timer | | `consul.catalog.deregister` | This measures the time it takes to complete a catalog deregister operation. | ms | timer |
@ -305,10 +306,6 @@ These metrics give insight into the health of the cluster as a whole.
| `consul.catalog.service.query-tag..` | This increments for each catalog query for the given service with the given tag. | queries | counter | | `consul.catalog.service.query-tag..` | This increments for each catalog query for the given service with the given tag. | queries | counter |
| `consul.catalog.service.query-tags..` | This increments for each catalog query for the given service with the given tags. | queries | counter | | `consul.catalog.service.query-tags..` | This increments for each catalog query for the given service with the given tags. | queries | counter |
| `consul.catalog.service.not-found.` | This increments for each catalog query where the given service could not be found. | queries | counter | | `consul.catalog.service.not-found.` | This increments for each catalog query where the given service could not be found. | queries | counter |
| `consul.health.service.query.` | This increments for each health query for the given service. | queries | counter |
| `consul.health.service.query-tag..` | This increments for each health query for the given service with the given tag. | queries | counter |
| `consul.health.service.query-tags..` | This increments for each health query for the given service with the given tags. | queries | counter |
| `consul.health.service.not-found.` | This increments for each health query where the given service could not be found. | queries | counter |
## Connect Built-in Proxy Metrics ## Connect Built-in Proxy Metrics