From f55f8c59fc4083b67bc12db18363739e6a11db24 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 3 Jul 2026 19:40:59 +0100 Subject: [PATCH] feat(telemetry): stamp service.name and network on native metrics The native OTel metrics path hard-coded service.name="xrpld" and stamped no network attribute, while traces stamped a configurable service.name and xrpl.network.type. Metrics therefore could not be filtered by service or network. Align the two paths: - OTelCollector::New / OTelCollectorImp gain serviceName + networkType params. service.name uses the configured value (default "xrpld" when unset, preserving today's behavior); xrpl.network.type is stamped when provided. The key is a string literal because beast/insight sits below the telemetry module and cannot include its SpanNames const. - CollectorManager reads service_name from [insight], falling back to the [telemetry] value, and receives the network type from the caller. - Application derives the network type once via the shared telemetry::networkTypeFromId, now declared in Telemetry.h and moved out of an anonymous namespace so the trace and metric paths reuse a single 0/1/2 -> mainnet/testnet/devnet mapping (no duplication). Dashboards (5 system-* files): add $service_name, $deployment_environment, $xrpl_network_type template variables and wire them into every panel query that filters by $node. Co-Authored-By: Claude Opus 4.8 --- .../dashboards/system-ledger-data-sync.json | 138 +++++++++++----- .../dashboards/system-network-traffic.json | 112 ++++++++++--- .../dashboards/system-node-health.json | 152 ++++++++++++------ .../system-overlay-traffic-detail.json | 132 ++++++++++----- .../dashboards/system-rpc-pathfinding.json | 104 +++++++++--- include/xrpl/beast/insight/OTelCollector.h | 10 ++ include/xrpl/telemetry/Telemetry.h | 11 ++ src/libxrpl/beast/insight/OTelCollector.cpp | 35 +++- src/libxrpl/telemetry/TelemetryConfig.cpp | 10 +- src/xrpld/app/main/Application.cpp | 6 + src/xrpld/app/main/CollectorManager.cpp | 26 ++- src/xrpld/app/main/CollectorManager.h | 18 ++- 12 files changed, 568 insertions(+), 186 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/system-ledger-data-sync.json b/docker/telemetry/grafana/dashboards/system-ledger-data-sync.json index 02e6083dea..28610ecc40 100644 --- a/docker/telemetry/grafana/dashboards/system-ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/system-ledger-data-sync.json @@ -30,56 +30,56 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Data Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Data Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_Transaction_Set_candidate_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_Transaction_Set_candidate_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Set Candidate Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_Transaction_Set_candidate_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_Transaction_Set_candidate_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Set Candidate Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_Transaction_Node_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_Transaction_Node_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_Transaction_Node_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_Transaction_Node_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_Account_State_Node_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_Account_State_Node_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Node Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_data_Account_State_Node_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_data_Account_State_Node_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Node Share [{{exported_instance}}]" } ], @@ -118,56 +118,56 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Share In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Get In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_Transaction_Set_candidate_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_Transaction_Set_candidate_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Set Candidate Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_Transaction_Set_candidate_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_Transaction_Set_candidate_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Set Candidate Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_Transaction_node_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_Transaction_node_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_Transaction_node_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_Transaction_node_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_Account_State_node_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_Account_State_node_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_ledger_Account_State_node_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_ledger_Account_State_node_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Get [{{exported_instance}}]" } ], @@ -206,56 +206,56 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Ledger_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Ledger_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Ledger_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Ledger_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transaction_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transaction_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Transaction Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transaction_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transaction_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Transaction Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transaction_node_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transaction_node_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transaction_node_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transaction_node_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Account_State_node_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Account_State_node_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Account_State_node_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Account_State_node_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Share [{{exported_instance}}]" } ], @@ -294,49 +294,49 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_CAS_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_CAS_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "CAS Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_CAS_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_CAS_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "CAS Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Fetch_Pack_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Fetch_Pack_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Fetch Pack Share [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Fetch_Pack_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Fetch_Pack_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Fetch Pack Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transactions_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transactions_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Transactions Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Aggregate Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Aggregate Share [{{exported_instance}}]" } ], @@ -375,49 +375,49 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Ledger_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Ledger_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ledger Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transaction_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transaction_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Transaction Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transaction_node_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transaction_node_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Node Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Account_State_node_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Account_State_node_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Account State Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_CAS_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_CAS_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "CAS Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Fetch_Pack_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Fetch_Pack_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Fetch Pack Get [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_getobject_Transactions_get_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_getobject_Transactions_get_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Transactions Get [{{exported_instance}}]" } ], @@ -463,7 +463,7 @@ "datasource": { "type": "prometheus" }, - "expr": "topk(20, {exported_instance=~\"$node\", __name__=~\"xrpld_.*_Bytes_In\", __name__!~\"xrpld_total_.*\"})", + "expr": "topk(20, {exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", __name__=~\"xrpld_.*_Bytes_In\", __name__!~\"xrpld_total_.*\"})", "legendFormat": "{{__name__}} [{{exported_instance}}]" } ], @@ -496,6 +496,66 @@ "tags": ["rippled", "statsd", "ledger", "sync", "telemetry"], "templating": { "list": [ + { + "name": "service_name", + "label": "Service", + "description": "Filter by service.name (e.g. xrpld, pratik-xrpld)", + "type": "query", + "query": "label_values(service_name)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "deployment_environment", + "label": "Environment", + "description": "Filter by deployment tier (local/ci/test/prod)", + "type": "query", + "query": "label_values(deployment_environment)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "xrpl_network_type", + "label": "Network", + "description": "Filter by XRPL network (mainnet/testnet/devnet)", + "type": "query", + "query": "label_values(xrpl_network_type)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, { "name": "node", "label": "Node", diff --git a/docker/telemetry/grafana/dashboards/system-network-traffic.json b/docker/telemetry/grafana/dashboards/system-network-traffic.json index d915e766e6..b63901ed7f 100644 --- a/docker/telemetry/grafana/dashboards/system-network-traffic.json +++ b/docker/telemetry/grafana/dashboards/system-network-traffic.json @@ -30,14 +30,14 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_Peer_Finder_Active_Inbound_Peers{exported_instance=~\"$node\"}", + "expr": "xrpld_Peer_Finder_Active_Inbound_Peers{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Inbound Peers [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_Peer_Finder_Active_Outbound_Peers{exported_instance=~\"$node\"}", + "expr": "xrpld_Peer_Finder_Active_Outbound_Peers{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Outbound Peers [{{exported_instance}}]" } ], @@ -76,7 +76,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_Overlay_Peer_Disconnects{exported_instance=~\"$node\"}", + "expr": "xrpld_Overlay_Peer_Disconnects{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Disconnects [{{exported_instance}}]" } ], @@ -115,14 +115,14 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_total_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_total_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_total_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_total_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Bytes Out [{{exported_instance}}]" } ], @@ -161,14 +161,14 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_total_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_total_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Messages In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_total_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_total_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Messages Out [{{exported_instance}}]" } ], @@ -207,21 +207,21 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_transactions_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_transactions_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Messages In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_transactions_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_transactions_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Messages Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_transactions_duplicate_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_transactions_duplicate_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "TX Duplicate In [{{exported_instance}}]" } ], @@ -260,28 +260,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_proposals_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_proposals_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Proposals In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_proposals_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_proposals_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Proposals Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_proposals_untrusted_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_proposals_untrusted_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Untrusted In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_proposals_duplicate_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_proposals_duplicate_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Duplicate In [{{exported_instance}}]" } ], @@ -320,28 +320,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_validations_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_validations_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Validations In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_validations_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_validations_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Validations Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_validations_untrusted_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_validations_untrusted_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Untrusted In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_validations_duplicate_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_validations_duplicate_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Duplicate In [{{exported_instance}}]" } ], @@ -380,7 +380,7 @@ "datasource": { "type": "prometheus" }, - "expr": "topk(10, {exported_instance=~\"$node\", __name__=~\"xrpld_.*_Bytes_In\", __name__!~\"xrpld_total_.*\"})", + "expr": "topk(10, {exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", __name__=~\"xrpld_.*_Bytes_In\", __name__!~\"xrpld_total_.*\"})", "legendFormat": "{{__name__}} [{{exported_instance}}]" } ], @@ -677,42 +677,42 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_transactions_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_transactions_duplicate_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "TX Duplicate In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_transactions_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_transactions_duplicate_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "TX Duplicate Out" }, { "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_proposals_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_proposals_duplicate_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Proposals Duplicate In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_proposals_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_proposals_duplicate_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Proposals Duplicate Out" }, { "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_validations_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_validations_duplicate_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Validations Duplicate In" }, { "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_validations_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_validations_duplicate_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Validations Duplicate Out" } ], @@ -751,7 +751,7 @@ "datasource": { "type": "prometheus" }, - "expr": "topk(15, rate({__name__=~\"xrpld_.*_Bytes_In\", __name__!~\"xrpld_total_{exported_instance=~\"$node\"}.*\"}[5m]))", + "expr": "topk(15, rate({__name__=~\"xrpld_.*_Bytes_In\", __name__!~\"xrpld_total_{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}.*\"}[5m]))", "legendFormat": "{{__name__}}" } ], @@ -774,6 +774,66 @@ "tags": ["rippled", "statsd", "network", "telemetry"], "templating": { "list": [ + { + "name": "service_name", + "label": "Service", + "description": "Filter by service.name (e.g. xrpld, pratik-xrpld)", + "type": "query", + "query": "label_values(service_name)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "deployment_environment", + "label": "Environment", + "description": "Filter by deployment tier (local/ci/test/prod)", + "type": "query", + "query": "label_values(deployment_environment)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "xrpl_network_type", + "label": "Network", + "description": "Filter by XRPL network (mainnet/testnet/devnet)", + "type": "query", + "query": "label_values(xrpl_network_type)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, { "name": "node", "label": "Node", diff --git a/docker/telemetry/grafana/dashboards/system-node-health.json b/docker/telemetry/grafana/dashboards/system-node-health.json index e82643f347..1ee48df3a3 100644 --- a/docker/telemetry/grafana/dashboards/system-node-health.json +++ b/docker/telemetry/grafana/dashboards/system-node-health.json @@ -30,7 +30,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\"}", + "expr": "xrpld_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Validated Age [{{exported_instance}}]" } ], @@ -78,7 +78,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\"}", + "expr": "xrpld_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Published Age [{{exported_instance}}]" } ], @@ -126,35 +126,35 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Full_duration{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Full_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Full [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Tracking_duration{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Tracking_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Tracking [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Syncing_duration{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Syncing_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Syncing [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Connected_duration{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Connected_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Connected [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Disconnected_duration{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Disconnected_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Disconnected [{{exported_instance}}]" } ], @@ -193,35 +193,35 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Full_transitions{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Full_transitions{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Full [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Tracking_transitions{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Tracking_transitions{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Tracking [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Syncing_transitions{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Syncing_transitions{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Syncing [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Connected_transitions{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Connected_transitions{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Connected [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_State_Accounting_Disconnected_transitions{exported_instance=~\"$node\"}", + "expr": "xrpld_State_Accounting_Disconnected_transitions{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Disconnected [{{exported_instance}}]" } ], @@ -260,14 +260,14 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_ios_latency_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_ios_latency_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P95 I/O Latency [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(xrpld_ios_latency_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(xrpld_ios_latency_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P50 I/O Latency [{{exported_instance}}]" } ], @@ -306,7 +306,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_job_count{exported_instance=~\"$node\"}", + "expr": "xrpld_job_count{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Job Queue Depth [{{exported_instance}}]" } ], @@ -345,7 +345,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_ledger_fetches_total{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_ledger_fetches_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Fetches / Sec [{{exported_instance}}]" } ], @@ -377,7 +377,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_ledger_history_mismatch_total{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_ledger_history_mismatch_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Mismatches / Sec [{{exported_instance}}]" } ], @@ -433,77 +433,77 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_acceptLedger_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_acceptLedger_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Accept Ledger [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_advanceLedger_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_advanceLedger_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Advance Ledger [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_transaction_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_transaction_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Transaction [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_writeObjects_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_writeObjects_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Write Objects [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_heartbeat_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_heartbeat_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Heartbeat [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_sweep_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_sweep_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Sweep [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedValidation_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedValidation_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Trusted Validation [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedProposal_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedProposal_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Trusted Proposal [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_publishNewLedger_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_publishNewLedger_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Publish New Ledger [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_clientRPC_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_clientRPC_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Client RPC [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_ledgerData_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_ledgerData_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Ledger Data [{{quantile}}]" } ], @@ -542,77 +542,77 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_acceptLedger_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_acceptLedger_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Accept Ledger [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_advanceLedger_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_advanceLedger_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Advance Ledger [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_transaction_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_transaction_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Transaction [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_writeObjects_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_writeObjects_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Write Objects [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_heartbeat_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_heartbeat_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Heartbeat [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_sweep_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_sweep_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Sweep [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedValidation_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedValidation_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Trusted Validation [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedProposal_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedProposal_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Trusted Proposal [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_publishNewLedger_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_publishNewLedger_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Publish New Ledger [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_clientRPC_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_clientRPC_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Client RPC [{{quantile}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_ledgerData_q_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_ledgerData_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "Ledger Data [{{quantile}}]" } ], @@ -651,7 +651,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_Node_family_full_below_cache_size{exported_instance=~\"$node\"}", + "expr": "xrpld_Node_family_full_below_cache_size{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "FullBelowCache Size" } ], @@ -690,7 +690,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_Node_family_full_below_cache_hit_rate{exported_instance=~\"$node\"}", + "expr": "xrpld_Node_family_full_below_cache_hit_rate{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Hit Rate" } ], @@ -740,7 +740,7 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\"} - xrpld_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\"}", + "expr": "xrpld_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"} - xrpld_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Publish Gap" } ], @@ -788,14 +788,14 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_State_Accounting_Full_duration{exported_instance=~\"$node\"}[5m]) / 1000000", + "expr": "rate(xrpld_State_Accounting_Full_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) / 1000000", "legendFormat": "Full Mode Rate" }, { "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_State_Accounting_Tracking_duration{exported_instance=~\"$node\"}[5m]) / 1000000", + "expr": "rate(xrpld_State_Accounting_Tracking_duration{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) / 1000000", "legendFormat": "Tracking Mode Rate" } ], @@ -834,7 +834,7 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, __name__) (rate({__name__=~\"xrpld_(makeFetchPack|publishAcqLedger|untrustedValidation|manifest|localTransaction|ledgerReplayRequest|ledgerRequest|untrustedProposal|ledgerReplayTask|ledgerData|clientCommand|clientSubscribe|clientFeeChange|clientConsensus|clientAccountHistory|clientRPC|clientWebsocket|RPC|updatePaths|transaction|batch|advanceLedger|publishNewLedger|fetchTxnData|writeAhead|trustedValidation|writeObjects|acceptLedger|trustedProposal|sweep|clusterReport|heartbeat|administration|handleHaveTransactions|doTransactions)_milliseconds_bucket\", exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, __name__) (rate({__name__=~\"xrpld_(makeFetchPack|publishAcqLedger|untrustedValidation|manifest|localTransaction|ledgerReplayRequest|ledgerRequest|untrustedProposal|ledgerReplayTask|ledgerData|clientCommand|clientSubscribe|clientFeeChange|clientConsensus|clientAccountHistory|clientRPC|clientWebsocket|RPC|updatePaths|transaction|batch|advanceLedger|publishNewLedger|fetchTxnData|writeAhead|trustedValidation|writeObjects|acceptLedger|trustedProposal|sweep|clusterReport|heartbeat|administration|handleHaveTransactions|doTransactions)_milliseconds_bucket\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "{{__name__}}" } ], @@ -873,7 +873,7 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile($quantile, sum by (le, __name__) (rate({__name__=~\"xrpld_(makeFetchPack_q|publishAcqLedger_q|untrustedValidation_q|manifest_q|localTransaction_q|ledgerReplayRequest_q|ledgerRequest_q|untrustedProposal_q|ledgerReplayTask_q|ledgerData_q|clientCommand_q|clientSubscribe_q|clientFeeChange_q|clientConsensus_q|clientAccountHistory_q|clientRPC_q|clientWebsocket_q|RPC_q|updatePaths_q|transaction_q|batch_q|advanceLedger_q|publishNewLedger_q|fetchTxnData_q|writeAhead_q|trustedValidation_q|writeObjects_q|acceptLedger_q|trustedProposal_q|sweep_q|clusterReport_q|heartbeat_q|administration_q|handleHaveTransactions_q|doTransactions_q)_milliseconds_bucket\", exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile($quantile, sum by (le, __name__) (rate({__name__=~\"xrpld_(makeFetchPack_q|publishAcqLedger_q|untrustedValidation_q|manifest_q|localTransaction_q|ledgerReplayRequest_q|ledgerRequest_q|untrustedProposal_q|ledgerReplayTask_q|ledgerData_q|clientCommand_q|clientSubscribe_q|clientFeeChange_q|clientConsensus_q|clientAccountHistory_q|clientRPC_q|clientWebsocket_q|RPC_q|updatePaths_q|transaction_q|batch_q|advanceLedger_q|publishNewLedger_q|fetchTxnData_q|writeAhead_q|trustedValidation_q|writeObjects_q|acceptLedger_q|trustedProposal_q|sweep_q|clusterReport_q|heartbeat_q|administration_q|handleHaveTransactions_q|doTransactions_q)_milliseconds_bucket\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "{{__name__}}" } ], @@ -896,6 +896,66 @@ "tags": ["rippled", "statsd", "node-health", "telemetry"], "templating": { "list": [ + { + "name": "service_name", + "label": "Service", + "description": "Filter by service.name (e.g. xrpld, pratik-xrpld)", + "type": "query", + "query": "label_values(service_name)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "deployment_environment", + "label": "Environment", + "description": "Filter by deployment tier (local/ci/test/prod)", + "type": "query", + "query": "label_values(deployment_environment)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "xrpl_network_type", + "label": "Network", + "description": "Filter by XRPL network (mainnet/testnet/devnet)", + "type": "query", + "query": "label_values(xrpl_network_type)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, { "name": "node", "label": "Node", diff --git a/docker/telemetry/grafana/dashboards/system-overlay-traffic-detail.json b/docker/telemetry/grafana/dashboards/system-overlay-traffic-detail.json index 0650b4bbed..8fde032271 100644 --- a/docker/telemetry/grafana/dashboards/system-overlay-traffic-detail.json +++ b/docker/telemetry/grafana/dashboards/system-overlay-traffic-detail.json @@ -30,42 +30,42 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_squelch_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_squelch_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Squelch In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_squelch_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_squelch_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Squelch Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_squelch_suppressed_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_squelch_suppressed_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Suppressed In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_squelch_suppressed_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_squelch_suppressed_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Suppressed Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_squelch_ignored_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_squelch_ignored_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ignored In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_squelch_ignored_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_squelch_ignored_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Ignored Out [{{exported_instance}}]" } ], @@ -104,42 +104,42 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_overhead_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_overhead_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Base Overhead In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_overhead_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_overhead_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Base Overhead Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_overhead_cluster_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_overhead_cluster_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Cluster In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_overhead_cluster_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_overhead_cluster_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Cluster Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_overhead_manifest_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_overhead_manifest_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Manifest In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_overhead_manifest_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_overhead_manifest_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Manifest Out [{{exported_instance}}]" } ], @@ -178,28 +178,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_validator_lists_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_validator_lists_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_validator_lists_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_validator_lists_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Bytes Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_validator_lists_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_validator_lists_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Messages In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_validator_lists_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_validator_lists_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Messages Out [{{exported_instance}}]" } ], @@ -255,28 +255,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_set_get_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_set_get_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Set Get In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_set_get_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_set_get_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Set Get Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_set_share_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_set_share_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Set Share In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_set_share_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_set_share_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Set Share Out [{{exported_instance}}]" } ], @@ -315,28 +315,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_have_transactions_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_have_transactions_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Have TX In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_have_transactions_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_have_transactions_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Have TX Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_requested_transactions_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_requested_transactions_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Requested TX In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_requested_transactions_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_requested_transactions_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Requested TX Out [{{exported_instance}}]" } ], @@ -375,28 +375,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_unknown_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_unknown_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Unknown Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_unknown_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_unknown_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Unknown Bytes Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_unknown_Messages_In{exported_instance=~\"$node\"}", + "expr": "xrpld_unknown_Messages_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Unknown Messages In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_unknown_Messages_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_unknown_Messages_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Unknown Messages Out [{{exported_instance}}]" } ], @@ -452,28 +452,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_proof_path_request_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_proof_path_request_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Request Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_proof_path_request_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_proof_path_request_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Request Bytes Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_proof_path_response_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_proof_path_response_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Response Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_proof_path_response_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_proof_path_response_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Response Bytes Out [{{exported_instance}}]" } ], @@ -512,28 +512,28 @@ "datasource": { "type": "prometheus" }, - "expr": "xrpld_replay_delta_request_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_replay_delta_request_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Request Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_replay_delta_request_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_replay_delta_request_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Request Bytes Out [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_replay_delta_response_Bytes_In{exported_instance=~\"$node\"}", + "expr": "xrpld_replay_delta_response_Bytes_In{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Response Bytes In [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "xrpld_replay_delta_response_Bytes_Out{exported_instance=~\"$node\"}", + "expr": "xrpld_replay_delta_response_Bytes_Out{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", "legendFormat": "Response Bytes Out [{{exported_instance}}]" } ], @@ -556,6 +556,66 @@ "tags": ["rippled", "statsd", "overlay", "network", "telemetry"], "templating": { "list": [ + { + "name": "service_name", + "label": "Service", + "description": "Filter by service.name (e.g. xrpld, pratik-xrpld)", + "type": "query", + "query": "label_values(service_name)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "deployment_environment", + "label": "Environment", + "description": "Filter by deployment tier (local/ci/test/prod)", + "type": "query", + "query": "label_values(deployment_environment)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "xrpl_network_type", + "label": "Network", + "description": "Filter by XRPL network (mainnet/testnet/devnet)", + "type": "query", + "query": "label_values(xrpl_network_type)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, { "name": "node", "label": "Node", diff --git a/docker/telemetry/grafana/dashboards/system-rpc-pathfinding.json b/docker/telemetry/grafana/dashboards/system-rpc-pathfinding.json index d2e001e1cc..2786548b78 100644 --- a/docker/telemetry/grafana/dashboards/system-rpc-pathfinding.json +++ b/docker/telemetry/grafana/dashboards/system-rpc-pathfinding.json @@ -30,7 +30,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_rpc_requests_total{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_rpc_requests_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Requests / Sec [{{exported_instance}}]" } ], @@ -62,14 +62,14 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P95 Response Time [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P50 Response Time [{{exported_instance}}]" } ], @@ -108,14 +108,14 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_size_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_size_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P95 Response Size [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_rpc_size_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_rpc_size_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P50 Response Size [{{exported_instance}}]" } ], @@ -154,28 +154,28 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P50 [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.9, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.9, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P90 [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P95 [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(xrpld_rpc_time_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P99 [{{exported_instance}}]" } ], @@ -214,14 +214,14 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_pathfind_fast_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_pathfind_fast_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P95 Fast Pathfind [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_pathfind_fast_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_pathfind_fast_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P50 Fast Pathfind [{{exported_instance}}]" } ], @@ -260,14 +260,14 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_pathfind_full_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_pathfind_full_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P95 Full Pathfind [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_pathfind_full_milliseconds_bucket{exported_instance=~\"$node\"}[5m])))", + "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(xrpld_pathfind_full_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))", "legendFormat": "P50 Full Pathfind [{{exported_instance}}]" } ], @@ -306,7 +306,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_warn_total{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_warn_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Warnings / Sec [{{exported_instance}}]" } ], @@ -354,7 +354,7 @@ "datasource": { "type": "prometheus" }, - "expr": "rate(xrpld_drop_total{exported_instance=~\"$node\"}[5m])", + "expr": "rate(xrpld_drop_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])", "legendFormat": "Drops / Sec [{{exported_instance}}]" } ], @@ -402,7 +402,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (method, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m]))", + "expr": "sum by (method, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m]))", "legendFormat": "{{method}} [{{exported_instance}}]" } ], @@ -441,7 +441,7 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, method, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, method, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m])))", "legendFormat": "{{method}} [{{exported_instance}}]" } ], @@ -480,7 +480,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (grpc_status, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[5m]))", + "expr": "sum by (grpc_status, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[5m]))", "legendFormat": "{{grpc_status}} [{{exported_instance}}]" } ], @@ -519,14 +519,14 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"pathfind.compute\"}[5m])))", + "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.compute\"}[5m])))", "legendFormat": "P95 Compute [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"pathfind.compute\"}[5m])))", + "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.compute\"}[5m])))", "legendFormat": "P50 Compute [{{exported_instance}}]" } ], @@ -565,14 +565,14 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"pathfind.request\"}[5m]))", + "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.request\"}[5m]))", "legendFormat": "Requests / Sec [{{exported_instance}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"pathfind.discover\"}[5m]))", + "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.discover\"}[5m]))", "legendFormat": "Discoveries / Sec [{{exported_instance}}]" } ], @@ -595,6 +595,66 @@ "tags": ["rippled", "statsd", "rpc", "pathfinding", "telemetry"], "templating": { "list": [ + { + "name": "service_name", + "label": "Service", + "description": "Filter by service.name (e.g. xrpld, pratik-xrpld)", + "type": "query", + "query": "label_values(service_name)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "deployment_environment", + "label": "Environment", + "description": "Filter by deployment tier (local/ci/test/prod)", + "type": "query", + "query": "label_values(deployment_environment)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, + { + "name": "xrpl_network_type", + "label": "Network", + "description": "Filter by XRPL network (mainnet/testnet/devnet)", + "type": "query", + "query": "label_values(xrpl_network_type)", + "datasource": { + "type": "prometheus", + "uid": "prometheus" + }, + "includeAll": true, + "allValue": ".*", + "current": { + "text": "All", + "value": "$__all" + }, + "multi": true, + "refresh": 2, + "sort": 1 + }, { "name": "node", "label": "Node", diff --git a/include/xrpl/beast/insight/OTelCollector.h b/include/xrpl/beast/insight/OTelCollector.h index 32a7fc621c..f3387614a8 100644 --- a/include/xrpl/beast/insight/OTelCollector.h +++ b/include/xrpl/beast/insight/OTelCollector.h @@ -77,6 +77,14 @@ public: * emitted as the `service.instance.id` OTel * resource attribute. Defaults to empty string * (attribute omitted when empty). + * @param serviceName Value for the `service.name` OTel resource + * attribute. When empty, defaults to "xrpld". + * Matches the trace exporter's service.name so + * metrics and traces share one service identity. + * @param networkType Value for the `xrpl.network.type` OTel resource + * attribute (e.g. "mainnet"). When empty, the + * attribute is omitted. Supplied by the node so + * metrics carry the same network label as traces. * @param journal Journal for logging. * @return Shared pointer to the created Collector. */ @@ -85,6 +93,8 @@ public: New(std::string const& endpoint, std::string const& prefix, std::string const& instanceId, + std::string const& serviceName, + std::string const& networkType, Journal journal); }; diff --git a/include/xrpl/telemetry/Telemetry.h b/include/xrpl/telemetry/Telemetry.h index 471fe0b93e..d998450066 100644 --- a/include/xrpl/telemetry/Telemetry.h +++ b/include/xrpl/telemetry/Telemetry.h @@ -364,4 +364,15 @@ makeTelemetrySetup( std::string const& version, std::uint32_t networkId); +/** Derive a human-readable network type label from the numeric network ID. + + Shared by the trace and metric export paths so both stamp the same + `xrpl.network.type` resource attribute value. + + @param networkId The network identifier from [network_id] config. + @return "mainnet" (0), "testnet" (1), "devnet" (2), or "unknown". +*/ +std::string +networkTypeFromId(std::uint32_t networkId); + } // namespace xrpl::telemetry diff --git a/src/libxrpl/beast/insight/OTelCollector.cpp b/src/libxrpl/beast/insight/OTelCollector.cpp index b42972b54f..9893fbedef 100644 --- a/src/libxrpl/beast/insight/OTelCollector.cpp +++ b/src/libxrpl/beast/insight/OTelCollector.cpp @@ -371,7 +371,8 @@ private: * Example usage: * @code * auto collector = OTelCollector::New( - * "http://localhost:4318/v1/metrics", "xrpld", journal); + * "http://localhost:4318/v1/metrics", "xrpld", + * "node-1", "xrpld", "mainnet", journal); * auto counter = collector->makeCounter("rpc.requests"); * counter.increment(1); * // Metric "xrpld_rpc_requests" exported via OTLP every 1s. @@ -387,12 +388,18 @@ public: * @param prefix Prefix for all metric names. * @param instanceId Value for the service.instance.id resource attribute. * When empty, the attribute is omitted. + * @param serviceName Value for the service.name resource attribute. + * When empty, defaults to "xrpld". + * @param networkType Value for the xrpl.network.type resource attribute. + * When empty, the attribute is omitted. * @param journal Journal for logging. */ OTelCollectorImp( std::string const& endpoint, std::string prefix, std::string const& instanceId, + std::string const& serviceName, + std::string const& networkType, Journal journal); /** @@ -662,6 +669,8 @@ OTelCollectorImp::OTelCollectorImp( std::string const& endpoint, std::string prefix, std::string const& instanceId, + std::string const& serviceName, + std::string const& networkType, Journal journal) : journal_(journal), prefix_(std::move(prefix)) { @@ -684,15 +693,24 @@ OTelCollectorImp::OTelCollectorImp( auto reader = metrics_sdk::PeriodicExportingMetricReaderFactory::Create(std::move(exporter), readerOpts); - // Configure resource attributes matching the trace exporter. - // Include service.instance.id when provided so Prometheus - // exported_instance labels distinguish multi-node deployments. + // Configure resource attributes matching the trace exporter so metrics + // and traces share one identity. service.name defaults to "xrpld" when + // unset. service.instance.id and xrpl.network.type are added when + // provided so Prometheus labels distinguish node and network. + // "xrpl.network.type" is a string literal (not the telemetry SpanNames + // const) because beast/insight sits below the telemetry module and + // cannot include it; the value must match the trace exporter's key. resource::ResourceAttributes attrs; - attrs[opentelemetry::semconv::service::kServiceName] = "xrpld"; + attrs[opentelemetry::semconv::service::kServiceName] = + serviceName.empty() ? "xrpld" : serviceName; if (!instanceId.empty()) { attrs[opentelemetry::semconv::service::kServiceInstanceId] = instanceId; } + if (!networkType.empty()) + { + attrs["xrpl.network.type"] = networkType; + } auto resourceAttrs = resource::Resource::Create(attrs); // Create MeterProvider with resource, then attach the metric reader. @@ -859,9 +877,12 @@ OTelCollector::New( std::string const& endpoint, std::string const& prefix, std::string const& instanceId, + std::string const& serviceName, + std::string const& networkType, Journal journal) { - return std::make_shared(endpoint, prefix, instanceId, journal); + return std::make_shared( + endpoint, prefix, instanceId, serviceName, networkType, journal); } } // namespace beast::insight @@ -883,6 +904,8 @@ OTelCollector::New( std::string const& /* endpoint */, std::string const& /* prefix */, std::string const& /* instanceId */, + std::string const& /* serviceName */, + std::string const& /* networkType */, Journal /* journal */) { return NullCollector::make(); diff --git a/src/libxrpl/telemetry/TelemetryConfig.cpp b/src/libxrpl/telemetry/TelemetryConfig.cpp index 66de3933b7..00705aa4ed 100644 --- a/src/libxrpl/telemetry/TelemetryConfig.cpp +++ b/src/libxrpl/telemetry/TelemetryConfig.cpp @@ -61,10 +61,10 @@ constexpr std::uint32_t batchDelayMs = 5000u; constexpr std::uint32_t maxQueueSize = 2048u; } // namespace dflt -/** Derive a human-readable network type label from the numeric network ID. - @param networkId The network identifier from [network_id] config. - @return "mainnet", "testnet", "devnet", or "unknown" for other values. -*/ +} // namespace + +// Declared in Telemetry.h; shared by the trace and metric export paths so +// both stamp the same xrpl.network.type resource attribute value. std::string networkTypeFromId(std::uint32_t networkId) { @@ -81,8 +81,6 @@ networkTypeFromId(std::uint32_t networkId) } } -} // namespace - Telemetry::Setup makeTelemetrySetup( Section const& section, diff --git a/src/xrpld/app/main/Application.cpp b/src/xrpld/app/main/Application.cpp index e02a433824..39c2027b90 100644 --- a/src/xrpld/app/main/Application.cpp +++ b/src/xrpld/app/main/Application.cpp @@ -340,6 +340,12 @@ public: , txMaster_(*this) , collectorManager_(makeCollectorManager( config_->section(Sections::kInsight), + // Fall back to [telemetry] service_name so metrics inherit the + // same service.name as traces when [insight] omits it. Network + // type is derived from [network_id] via the shared telemetry + // helper, keeping metrics and traces on one network label. + config_->section("telemetry").valueOr("service_name", ""), + telemetry::networkTypeFromId(config_->networkId), logs_->journal("Collector"))) , jobQueue_( std::make_unique( diff --git a/src/xrpld/app/main/CollectorManager.cpp b/src/xrpld/app/main/CollectorManager.cpp index c65f48720d..065d620838 100644 --- a/src/xrpld/app/main/CollectorManager.cpp +++ b/src/xrpld/app/main/CollectorManager.cpp @@ -25,7 +25,12 @@ public: std::unique_ptr groups_; // NOLINTEND(readability-identifier-naming) - CollectorManagerImp(Section const& params, beast::Journal journal) : journal_(journal) + CollectorManagerImp( + Section const& params, + std::string const& serviceName, + std::string const& networkType, + beast::Journal journal) + : journal_(journal) { std::string const& server = get(params, Keys::kServer); @@ -52,7 +57,16 @@ public: // metric sources via the exported_instance Prometheus label. std::string const instanceId = get(params, "service_instance_id"); - collector_ = beast::insight::OTelCollector::New(endpoint, prefix, instanceId, journal); + // service.name from [insight] (falls back to the value the + // caller derived from [telemetry]); network type derived from + // [network_id]. Both mirror the trace exporter so metrics and + // traces carry the same service and network identity. + std::string serviceNameCfg = get(params, "service_name"); + if (serviceNameCfg.empty()) + serviceNameCfg = serviceName; + + collector_ = beast::insight::OTelCollector::New( + endpoint, prefix, instanceId, serviceNameCfg, networkType, journal); } // LCOV_EXCL_STOP else @@ -81,9 +95,13 @@ public: //------------------------------------------------------------------------------ std::unique_ptr -makeCollectorManager(Section const& params, beast::Journal journal) +makeCollectorManager( + Section const& params, + std::string const& serviceName, + std::string const& networkType, + beast::Journal journal) { - return std::make_unique(params, journal); + return std::make_unique(params, serviceName, networkType, journal); } } // namespace xrpl diff --git a/src/xrpld/app/main/CollectorManager.h b/src/xrpld/app/main/CollectorManager.h index d07da15353..bf41425ad4 100644 --- a/src/xrpld/app/main/CollectorManager.h +++ b/src/xrpld/app/main/CollectorManager.h @@ -3,6 +3,9 @@ #include #include +#include +#include + namespace xrpl { /** Provides the beast::insight::Collector service. */ @@ -18,7 +21,20 @@ public: group(std::string const& name) = 0; }; +/** Construct the collector manager. + + @param params The [insight] config section. + @param serviceName service.name resource attribute for OTel metrics + (empty -> the collector defaults it to "xrpld"). + @param networkType xrpl.network.type resource attribute for OTel + metrics (e.g. "mainnet"), derived from [network_id]. + @param journal Journal for logging. +*/ std::unique_ptr -makeCollectorManager(Section const& params, beast::Journal journal); +makeCollectorManager( + Section const& params, + std::string const& serviceName, + std::string const& networkType, + beast::Journal journal); } // namespace xrpl