diff options
Diffstat (limited to '')
| -rw-r--r-- | src/go/collectors/go.d.plugin/modules/consul/metadata.yaml | 599 |
1 files changed, 599 insertions, 0 deletions
diff --git a/src/go/collectors/go.d.plugin/modules/consul/metadata.yaml b/src/go/collectors/go.d.plugin/modules/consul/metadata.yaml new file mode 100644 index 000000000..470959139 --- /dev/null +++ b/src/go/collectors/go.d.plugin/modules/consul/metadata.yaml @@ -0,0 +1,599 @@ +plugin_name: go.d.plugin +modules: + - meta: + id: collector-go.d.plugin-consul + plugin_name: go.d.plugin + module_name: consul + monitored_instance: + name: Consul + link: https://www.consul.io/ + categories: + - data-collection.service-discovery-registry + icon_filename: consul.svg + alternative_monitored_instances: [] + related_resources: + integrations: + list: [] + info_provided_to_referring_integrations: + description: "" + keywords: + - service networking platform + - hashicorp + most_popular: true + overview: + data_collection: + metrics_description: | + This collector monitors [key metrics](https://developer.hashicorp.com/consul/docs/agent/telemetry#key-metrics) of Consul Agents: transaction timings, leadership changes, memory usage and more. + method_description: | + It periodically sends HTTP requests to [Consul REST API](https://developer.hashicorp.com/consul/api-docs). + + Used endpoints: + + - [/operator/autopilot/health](https://developer.hashicorp.com/consul/api-docs/operator/autopilot#read-health) + - [/agent/checks](https://developer.hashicorp.com/consul/api-docs/agent/check#list-checks) + - [/agent/self](https://developer.hashicorp.com/consul/api-docs/agent#read-configuration) + - [/agent/metrics](https://developer.hashicorp.com/consul/api-docs/agent#view-metrics) + - [/coordinate/nodes](https://developer.hashicorp.com/consul/api-docs/coordinate#read-lan-coordinates-for-all-nodes) + supported_platforms: + include: [] + exclude: [] + multi_instance: true + additional_permissions: + description: "" + default_behavior: + auto_detection: + description: | + This collector discovers instances running on the local host, that provide metrics on port 8500. + + On startup, it tries to collect metrics from: + + - http://localhost:8500 + - http://127.0.0.1:8500 + limits: + description: "" + performance_impact: + description: "" + setup: + prerequisites: + list: + - title: Enable Prometheus telemetry + description: | + [Enable](https://developer.hashicorp.com/consul/docs/agent/config/config-files#telemetry-prometheus_retention_time) telemetry on your Consul agent, by increasing the value of `prometheus_retention_time` from `0`. + - title: Add required ACLs to Token + description: | + Required **only if authentication is enabled**. + + | ACL | Endpoint | + |:---------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| + | `operator:read` | [autopilot health status](https://developer.hashicorp.com/consul/api-docs/operator/autopilot#read-health) | + | `node:read` | [checks](https://developer.hashicorp.com/consul/api-docs/agent/check#list-checks) | + | `agent:read` | [configuration](https://developer.hashicorp.com/consul/api-docs/agent#read-configuration), [metrics](https://developer.hashicorp.com/consul/api-docs/agent#view-metrics), and [lan coordinates](https://developer.hashicorp.com/consul/api-docs/coordinate#read-lan-coordinates-for-all-nodes) | + configuration: + file: + name: go.d/consul.conf + options: + description: | + The following options can be defined globally: update_every, autodetection_retry. + folding: + title: All options + enabled: true + list: + - name: update_every + description: Data collection frequency. + default_value: 1 + required: false + - name: autodetection_retry + description: Recheck interval in seconds. Zero means no recheck will be scheduled. + default_value: 0 + required: false + - name: url + description: Server URL. + default_value: http://localhost:8500 + required: true + - name: acl_token + description: ACL token used in every request. + default_value: "" + required: false + - name: max_checks + description: Checks processing/charting limit. + default_value: "" + required: false + - name: max_filter + description: Checks processing/charting filter. Uses [simple patterns](https://github.com/netdata/netdata/blob/master/src/libnetdata/simple_pattern/README.md). + default_value: "" + required: false + - name: username + description: Username for basic HTTP authentication. + default_value: "" + required: false + - name: password + description: Password for basic HTTP authentication. + default_value: "" + required: false + - name: proxy_url + description: Proxy URL. + default_value: "" + required: false + - name: proxy_username + description: Username for proxy basic HTTP authentication. + default_value: "" + required: false + - name: proxy_password + description: Password for proxy basic HTTP authentication. + default_value: "" + required: false + - name: timeout + description: HTTP request timeout. + default_value: 1 + required: false + - name: method + description: HTTP request method. + default_value: GET + required: false + - name: body + description: HTTP request body. + default_value: "" + required: false + - name: headers + description: HTTP request headers. + default_value: "" + required: false + - name: not_follow_redirects + description: Redirect handling policy. Controls whether the client follows redirects. + default_value: false + required: false + - name: tls_skip_verify + description: Server certificate chain and hostname validation policy. Controls whether the client performs this check. + default_value: false + required: false + - name: tls_ca + description: Certification authority that the client uses when verifying the server's certificates. + default_value: "" + required: false + - name: tls_cert + description: Client tls certificate. + default_value: "" + required: false + - name: tls_key + description: Client tls key. + default_value: "" + required: false + examples: + folding: + title: Config + enabled: true + list: + - name: Basic + description: An example configuration. + folding: + enabled: false + config: | + jobs: + - name: local + url: http://127.0.0.1:8500 + acl_token: "ec15675e-2999-d789-832e-8c4794daa8d7" + - name: Basic HTTP auth + description: Local server with basic HTTP authentication. + config: | + jobs: + - name: local + url: http://127.0.0.1:8500 + acl_token: "ec15675e-2999-d789-832e-8c4794daa8d7" + username: foo + password: bar + - name: Multi-instance + description: | + > **Note**: When you define multiple jobs, their names must be unique. + + Collecting metrics from local and remote instances. + config: | + jobs: + - name: local + url: http://127.0.0.1:8500 + acl_token: "ec15675e-2999-d789-832e-8c4794daa8d7" + + - name: remote + url: http://203.0.113.10:8500 + acl_token: "ada7f751-f654-8872-7f93-498e799158b6" + troubleshooting: + problems: + list: [] + alerts: + - name: consul_node_health_check_status + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.node_health_check_status + info: node health check ${label:check_name} has failed on server ${label:node_name} datacenter ${label:datacenter} + - name: consul_service_health_check_status + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.service_health_check_status + info: service health check ${label:check_name} for service ${label:service_name} has failed on server ${label:node_name} datacenter ${label:datacenter} + - name: consul_client_rpc_requests_exceeded + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.client_rpc_requests_exceeded_rate + info: number of rate-limited RPC requests made by server ${label:node_name} datacenter ${label:datacenter} + - name: consul_client_rpc_requests_failed + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.client_rpc_requests_failed_rate + info: number of failed RPC requests made by server ${label:node_name} datacenter ${label:datacenter} + - name: consul_gc_pause_time + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.gc_pause_time + info: time spent in stop-the-world garbage collection pauses on server ${label:node_name} datacenter ${label:datacenter} + - name: consul_autopilot_health_status + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.autopilot_health_status + info: datacenter ${label:datacenter} cluster is unhealthy as reported by server ${label:node_name} + - name: consul_autopilot_server_health_status + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.autopilot_server_health_status + info: server ${label:node_name} from datacenter ${label:datacenter} is unhealthy + - name: consul_raft_leader_last_contact_time + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.raft_leader_last_contact_time + info: median time elapsed since leader server ${label:node_name} datacenter ${label:datacenter} was last able to contact the follower nodes + - name: consul_raft_leadership_transitions + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.raft_leadership_transitions_rate + info: there has been a leadership change and server ${label:node_name} datacenter ${label:datacenter} has become the leader + - name: consul_raft_thread_main_saturation + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.raft_thread_main_saturation_perc + info: average saturation of the main Raft goroutine on server ${label:node_name} datacenter ${label:datacenter} + - name: consul_raft_thread_fsm_saturation + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.raft_thread_fsm_saturation_perc + info: average saturation of the FSM Raft goroutine on server ${label:node_name} datacenter ${label:datacenter} + - name: consul_license_expiration_time + link: https://github.com/netdata/netdata/blob/master/src/health/health.d/consul.conf + metric: consul.license_expiration_time + info: Consul Enterprise licence expiration time on node ${label:node_name} datacenter ${label:datacenter} + metrics: + folding: + title: Metrics + enabled: false + description: | + The set of metrics depends on the [Consul Agent mode](https://developer.hashicorp.com/consul/docs/install/glossary#agent). + availability: + - Leader + - Follower + - Client + scopes: + - name: global + description: These metrics refer to the entire monitored application. + labels: [] + metrics: + - name: consul.client_rpc_requests_rate + description: Client RPC requests + unit: requests/s + chart_type: line + dimensions: + - name: rpc + - name: consul.client_rpc_requests_exceeded_rate + description: Client rate-limited RPC requests + unit: requests/s + chart_type: line + dimensions: + - name: exceeded + - name: consul.client_rpc_requests_failed_rate + description: Client failed RPC requests + unit: requests/s + chart_type: line + dimensions: + - name: failed + - name: consul.memory_allocated + description: Memory allocated by the Consul process + unit: bytes + chart_type: line + dimensions: + - name: allocated + - name: consul.memory_sys + description: Memory obtained from the OS + unit: bytes + chart_type: line + dimensions: + - name: sys + - name: consul.gc_pause_time + description: Garbage collection stop-the-world pause time + unit: seconds + chart_type: line + dimensions: + - name: gc_pause + - name: consul.kvs_apply_time + description: KVS apply time + unit: ms + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.kvs_apply_operations_rate + description: KVS apply operations + unit: ops/s + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: kvs_apply + - name: consul.txn_apply_time + description: Transaction apply time + unit: ms + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.txn_apply_operations_rate + description: Transaction apply operations + unit: ops/s + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: txn_apply + - name: consul.autopilot_health_status + description: Autopilot cluster health status + unit: status + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: healthy + - name: unhealthy + - name: consul.autopilot_failure_tolerance + description: Autopilot cluster failure tolerance + unit: servers + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: failure_tolerance + - name: consul.autopilot_server_health_status + description: Autopilot server health status + unit: status + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: healthy + - name: unhealthy + - name: consul.autopilot_server_stable_time + description: Autopilot server stable time + unit: seconds + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: stable + - name: consul.autopilot_server_serf_status + description: Autopilot server Serf status + unit: status + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: active + - name: failed + - name: left + - name: none + - name: consul.autopilot_server_voter_status + description: Autopilot server Raft voting membership + unit: status + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: voter + - name: not_voter + - name: consul.network_lan_rtt + description: Network lan RTT + unit: ms + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: min + - name: max + - name: avg + - name: consul.raft_commit_time + description: Raft commit time + unit: ms + chart_type: line + availability: + - Leader + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.raft_commits_rate + description: Raft commits rate + unit: commits/s + chart_type: line + availability: + - Leader + dimensions: + - name: commits + - name: consul.raft_leader_last_contact_time + description: Raft leader last contact time + unit: ms + chart_type: line + availability: + - Leader + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.raft_leader_oldest_log_age + description: Raft leader oldest log age + unit: seconds + chart_type: line + availability: + - Leader + dimensions: + - name: oldest_log_age + - name: consul.raft_follower_last_contact_leader_time + description: Raft follower last contact with the leader time + unit: ms + chart_type: line + availability: + - Follower + dimensions: + - name: leader_last_contact + - name: consul.raft_rpc_install_snapshot_time + description: Raft RPC install snapshot time + unit: ms + chart_type: line + availability: + - Follower + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.raft_leader_elections_rate + description: Raft leader elections rate + unit: elections/s + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: leader + - name: consul.raft_leadership_transitions_rate + description: Raft leadership transitions rate + unit: transitions/s + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: leadership + - name: consul.server_leadership_status + description: Server leadership status + unit: status + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: leader + - name: not_leader + - name: consul.raft_thread_main_saturation_perc + description: Raft main thread saturation + unit: percentage + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.raft_thread_fsm_saturation_perc + description: Raft FSM thread saturation + unit: percentage + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.raft_fsm_last_restore_duration + description: Raft last restore duration + unit: ms + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: last_restore_duration + - name: consul.raft_boltdb_freelist_bytes + description: Raft BoltDB freelist + unit: bytes + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: freelist + - name: consul.raft_boltdb_logs_per_batch_rate + description: Raft BoltDB logs written per batch + unit: logs/s + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: written + - name: consul.raft_boltdb_store_logs_time + description: Raft BoltDB store logs time + unit: ms + chart_type: line + availability: + - Leader + - Follower + dimensions: + - name: quantile_0.5 + - name: quantile_0.9 + - name: quantile_0.99 + - name: consul.license_expiration_time + description: License expiration time + unit: seconds + chart_type: line + dimensions: + - name: license_expiration + - name: node check + description: Metrics about checks on Node level. + labels: + - name: datacenter + description: Datacenter Identifier + - name: node_name + description: The node's name + - name: check_name + description: The check's name + metrics: + - name: consul.node_health_check_status + description: Node health check status + unit: status + chart_type: line + dimensions: + - name: passing + - name: maintenance + - name: warning + - name: critical + - name: service check + description: Metrics about checks at a Service level. + labels: + - name: datacenter + description: Datacenter Identifier + - name: node_name + description: The node's name + - name: check_name + description: The check's name + - name: service_name + description: The service's name + metrics: + - name: consul.service_health_check_status + description: Service health check status + unit: status + chart_type: line + dimensions: + - name: passing + - name: maintenance + - name: warning + - name: critical |