ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-04-05 03:22:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Phase 7: Native OTel metrics migration

Browse Source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Pratik Mankawde
2026-03-20 17:22:48 +00:00
parent 8f364ed6f4
commit 5ec9f3f30a
5 changed files with 0 additions and 2353 deletions
Download Patch File Download Diff File Expand all files Collapse all files

506
docker/telemetry/grafana/dashboards/statsd-ledger-data-sync.json
View File

@@ -1,506 +0,0 @@
{
"annotations": {
"list": []
},
"description": "Ledger data exchange and object fetch traffic from beast::insight StatsD. Covers ledger sync, node data retrieval, and transaction set exchange. Requires [insight] server=statsd in rippled config.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"title": "Ledger Data Exchange (Bytes In)",
"description": "Inbound bytes for ledger data sub-categories. 'ledger_data' = aggregated ledger data, sub-types include Transaction_Set_candidate (proposed tx sets), Transaction_Node (tx tree nodes), and Account_State_Node (state tree nodes). High Account_State_Node traffic indicates state sync; high Transaction_Set_candidate indicates consensus catch-up. Sourced from TrafficCount.h ledger_data_* categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_get_Bytes_In",
"legendFormat": "Ledger Data Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_share_Bytes_In",
"legendFormat": "Ledger Data Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_Transaction_Set_candidate_get_Bytes_In",
"legendFormat": "TX Set Candidate Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_Transaction_Set_candidate_share_Bytes_In",
"legendFormat": "TX Set Candidate Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_Transaction_Node_get_Bytes_In",
"legendFormat": "TX Node Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_Transaction_Node_share_Bytes_In",
"legendFormat": "TX Node Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_Account_State_Node_get_Bytes_In",
"legendFormat": "Account State Node Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_data_Account_State_Node_share_Bytes_In",
"legendFormat": "Account State Node Share"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Ledger Share/Get Traffic (Bytes)",
"description": "Legacy ledger share and get traffic by sub-type. These are the older ledger fetch protocol categories (as opposed to ledger_data_* which is the newer protocol). Sub-types: Transaction_Set_candidate, Transaction_node, Account_State_node, plus aggregate ledger_share and ledger_get. Sourced from TrafficCount.h ledger_* categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_share_Bytes_In",
"legendFormat": "Ledger Share In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_get_Bytes_In",
"legendFormat": "Ledger Get In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_Transaction_Set_candidate_share_Bytes_In",
"legendFormat": "TX Set Candidate Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_Transaction_Set_candidate_get_Bytes_In",
"legendFormat": "TX Set Candidate Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_Transaction_node_share_Bytes_In",
"legendFormat": "TX Node Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_Transaction_node_get_Bytes_In",
"legendFormat": "TX Node Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_Account_State_node_share_Bytes_In",
"legendFormat": "Account State Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_Account_State_node_get_Bytes_In",
"legendFormat": "Account State Get"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "GetObject Traffic by Type (Bytes In)",
"description": "Object fetch traffic by object type. GetObject is the protocol for fetching specific SHAMap nodes. Types: Ledger (full ledger headers), Transaction (individual txs), Transaction_node (tx tree nodes), Account_State_node (state tree nodes), CAS (Content Addressable Storage objects), Fetch_Pack (batch fetch during catch-up), Transactions (bulk tx fetch). High Fetch_Pack traffic indicates a node is catching up. Sourced from TrafficCount.h getobject_* categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Ledger_get_Bytes_In",
"legendFormat": "Ledger Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Ledger_share_Bytes_In",
"legendFormat": "Ledger Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transaction_get_Bytes_In",
"legendFormat": "Transaction Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transaction_share_Bytes_In",
"legendFormat": "Transaction Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transaction_node_get_Bytes_In",
"legendFormat": "TX Node Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transaction_node_share_Bytes_In",
"legendFormat": "TX Node Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Account_State_node_get_Bytes_In",
"legendFormat": "Account State Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Account_State_node_share_Bytes_In",
"legendFormat": "Account State Share"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "GetObject Aggregate & Special Types (Bytes In)",
"description": "Aggregate getobject traffic plus special categories: CAS (Content Addressable Storage) for SHAMap node fetch, Fetch_Pack for bulk batch downloads during catch-up, Transactions for bulk tx fetch, and the aggregate getobject_get/getobject_share totals. Sourced from TrafficCount.h getobject_* categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_CAS_get_Bytes_In",
"legendFormat": "CAS Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_CAS_share_Bytes_In",
"legendFormat": "CAS Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Fetch_Pack_share_Bytes_In",
"legendFormat": "Fetch Pack Share"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Fetch_Pack_get_Bytes_In",
"legendFormat": "Fetch Pack Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transactions_get_Bytes_In",
"legendFormat": "Transactions Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_get_Bytes_In",
"legendFormat": "Aggregate Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_share_Bytes_In",
"legendFormat": "Aggregate Share"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "GetObject Messages by Type",
"description": "Message counts for object fetch operations. Shows how many individual fetch requests and responses are exchanged per type. High message counts with low byte counts indicate small object fetches; the inverse indicates large batch transfers. Sourced from TrafficCount.h getobject_* categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Ledger_get_Messages_In",
"legendFormat": "Ledger Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transaction_get_Messages_In",
"legendFormat": "Transaction Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transaction_node_get_Messages_In",
"legendFormat": "TX Node Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Account_State_node_get_Messages_In",
"legendFormat": "Account State Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_CAS_get_Messages_In",
"legendFormat": "CAS Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Fetch_Pack_get_Messages_In",
"legendFormat": "Fetch Pack Get"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_getobject_Transactions_get_Messages_In",
"legendFormat": "Transactions Get"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages In",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Overlay Traffic Heatmap (All Categories, Bytes In)",
"description": "Bar gauge showing all overlay traffic categories ranked by inbound bytes. Provides a complete at-a-glance view of which protocol message types consume the most bandwidth across all 57+ traffic categories. Sourced from all TrafficCount.h categories via wildcard match.",
"type": "bargauge",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
},
"displayMode": "gradient",
"orientation": "horizontal",
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "topk(20, {__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"})",
"legendFormat": "{{__name__}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 1048576
},
{
"color": "red",
"value": 104857600
}
]
}
},
"overrides": []
}
}
],
"schemaVersion": 39,
"tags": ["rippled", "statsd", "ledger", "sync", "telemetry"],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"title": "Ledger Data & Sync (StatsD)",
"uid": "rippled-statsd-ledger-sync"
}

470
docker/telemetry/grafana/dashboards/statsd-network-traffic.json
View File

@@ -1,470 +0,0 @@
{
"annotations": { "list": [] },
"description": "Network traffic and peer metrics from beast::insight StatsD. Requires [insight] server=statsd in rippled config.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"title": "Active Peers",
"description": "Number of active inbound and outbound peer connections. Sourced from Peer_Finder.Active_Inbound_Peers and Peer_Finder.Active_Outbound_Peers gauges (PeerfinderManager.cpp:214-215). A healthy mainnet node typically has 10-21 outbound and 0-85 inbound peers depending on configuration.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_Peer_Finder_Active_Inbound_Peers",
"legendFormat": "Inbound Peers"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_Peer_Finder_Active_Outbound_Peers",
"legendFormat": "Outbound Peers"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Peers",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Peer Disconnects",
"description": "Cumulative count of peer disconnections. Sourced from the Overlay.Peer_Disconnects gauge (OverlayImpl.h:557). A rising trend indicates network instability, aggressive peer management, or resource exhaustion causing connection drops.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_Overlay_Peer_Disconnects",
"legendFormat": "Disconnects"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Disconnects",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Total Network Bytes",
"description": "Total bytes sent and received across all peer connections. Sourced from the total.Bytes_In and total.Bytes_Out traffic category gauges (OverlayImpl.h:535-548). Provides a high-level view of network bandwidth consumption.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_total_Bytes_In",
"legendFormat": "Bytes In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_total_Bytes_Out",
"legendFormat": "Bytes Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Total Network Messages",
"description": "Total messages sent and received across all peer connections. Sourced from the total.Messages_In and total.Messages_Out traffic category gauges (OverlayImpl.h:535-548). Shows the overall message throughput of the overlay network.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_total_Messages_In",
"legendFormat": "Messages In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_total_Messages_Out",
"legendFormat": "Messages Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Transaction Traffic",
"description": "Bytes and messages for transaction-related overlay traffic. Includes the transactions traffic category (OverlayImpl/TrafficCount.h). Spikes indicate high transaction volume on the network or transaction flooding.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 16 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_transactions_Messages_In",
"legendFormat": "TX Messages In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_transactions_Messages_Out",
"legendFormat": "TX Messages Out"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_transactions_duplicate_Messages_In",
"legendFormat": "TX Duplicate In"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Proposal Traffic",
"description": "Messages for consensus proposal overlay traffic. Includes proposals, proposals_untrusted, and proposals_duplicate categories (TrafficCount.h). High untrusted or duplicate counts may indicate UNL misconfiguration or network spam.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 16 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_proposals_Messages_In",
"legendFormat": "Proposals In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_proposals_Messages_Out",
"legendFormat": "Proposals Out"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_proposals_untrusted_Messages_In",
"legendFormat": "Untrusted In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_proposals_duplicate_Messages_In",
"legendFormat": "Duplicate In"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Validation Traffic",
"description": "Messages for validation overlay traffic. Includes validations, validations_untrusted, and validations_duplicate categories (TrafficCount.h). Monitoring trusted vs untrusted validation traffic helps detect UNL health issues.",
"type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 24 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "rippled_validations_Messages_In",
"legendFormat": "Validations In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_validations_Messages_Out",
"legendFormat": "Validations Out"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_validations_untrusted_Messages_In",
"legendFormat": "Untrusted In"
},
{
"datasource": { "type": "prometheus" },
"expr": "rippled_validations_duplicate_Messages_In",
"legendFormat": "Duplicate In"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Overlay Traffic by Category (Bytes In)",
"description": "Top traffic categories by inbound bytes. Includes all 57 overlay traffic categories from TrafficCount.h. Shows which protocol message types consume the most bandwidth. Categories include transactions, proposals, validations, ledger data, getobject, and overlay overhead.",
"type": "bargauge",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 24 },
"options": {
"tooltip": { "mode": "multi", "sort": "desc" }
},
"targets": [
{
"datasource": { "type": "prometheus" },
"expr": "topk(10, {__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"})",
"legendFormat": "{{__name__}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes"
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "rippled_transactions_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Transactions" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_proposals_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Proposals" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_validations_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Validations" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_overhead_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Overhead" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_overhead_overlay_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Overhead Overlay" }]
},
{
"matcher": { "id": "byName", "options": "rippled_ping_Bytes_In" },
"properties": [{ "id": "displayName", "value": "Ping" }]
},
{
"matcher": { "id": "byName", "options": "rippled_status_Bytes_In" },
"properties": [{ "id": "displayName", "value": "Status" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_getObject_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Get Object" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_haveTxSet_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Have Tx Set" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledgerData_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Ledger Data" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_share_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Ledger Share" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_get_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Ledger Data Get" }]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_share_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Ledger Data Share" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_Account_State_Node_get_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Account State Node Get" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_Account_State_Node_share_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Account State Node Share" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_Transaction_Node_get_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Transaction Node Get" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_Transaction_Node_share_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Transaction Node Share" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_data_Transaction_Set_candidate_get_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Tx Set Candidate Get" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_Account_State_node_share_Bytes_In"
},
"properties": [
{
"id": "displayName",
"value": "Account State Node Share (Legacy)"
}
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_Transaction_Set_candidate_share_Bytes_In"
},
"properties": [
{ "id": "displayName", "value": "Tx Set Candidate Share" }
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_ledger_Transaction_node_share_Bytes_In"
},
"properties": [
{
"id": "displayName",
"value": "Transaction Node Share (Legacy)"
}
]
},
{
"matcher": {
"id": "byName",
"options": "rippled_set_get_Bytes_In"
},
"properties": [{ "id": "displayName", "value": "Set Get" }]
}
]
}
}
],
"schemaVersion": 39,
"tags": ["rippled", "statsd", "network", "telemetry"],
"templating": { "list": [] },
"time": { "from": "now-1h", "to": "now" },
"title": "rippled Network Traffic (StatsD)",
"uid": "rippled-statsd-network"
}

415
docker/telemetry/grafana/dashboards/statsd-node-health.json
View File

@@ -1,415 +0,0 @@
{
"annotations": {
"list": []
},
"description": "Node health metrics from beast::insight StatsD. Requires [insight] server=statsd in rippled config.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"title": "Validated Ledger Age",
"description": "Age of the most recently validated ledger in seconds. Sourced from the LedgerMaster.Validated_Ledger_Age gauge (LedgerMaster.h:373) which is updated every collection interval via the insight hook. Values above 20s indicate the node is falling behind the network.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_LedgerMaster_Validated_Ledger_Age",
"legendFormat": "Validated Age"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 10
},
{
"color": "red",
"value": 20
}
]
}
},
"overrides": []
}
},
{
"title": "Published Ledger Age",
"description": "Age of the most recently published ledger in seconds. Sourced from the LedgerMaster.Published_Ledger_Age gauge (LedgerMaster.h:374). Published ledger age should track close to validated ledger age. A growing gap indicates publish pipeline backlog.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_LedgerMaster_Published_Ledger_Age",
"legendFormat": "Published Age"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 10
},
{
"color": "red",
"value": 20
}
]
}
},
"overrides": []
}
},
{
"title": "Operating Mode Duration",
"description": "Cumulative time spent in each operating mode (Disconnected, Connected, Syncing, Tracking, Full). Sourced from State_Accounting.*_duration gauges (NetworkOPs.cpp:774-778). A healthy node should spend the vast majority of time in Full mode.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Full_duration",
"legendFormat": "Full"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Tracking_duration",
"legendFormat": "Tracking"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Syncing_duration",
"legendFormat": "Syncing"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Connected_duration",
"legendFormat": "Connected"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Disconnected_duration",
"legendFormat": "Disconnected"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"custom": {
"axisLabel": "Duration (Sec)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Operating Mode Transitions",
"description": "Count of transitions into each operating mode. Sourced from State_Accounting.*_transitions gauges (NetworkOPs.cpp:780-786). Frequent transitions out of Full mode indicate instability. Transitions to Disconnected or Syncing warrant investigation.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Full_transitions",
"legendFormat": "Full"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Tracking_transitions",
"legendFormat": "Tracking"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Syncing_transitions",
"legendFormat": "Syncing"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Connected_transitions",
"legendFormat": "Connected"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_State_Accounting_Disconnected_transitions",
"legendFormat": "Disconnected"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Transitions",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "I/O Latency",
"description": "P95 and P50 of the I/O service loop latency in milliseconds. Sourced from the ios_latency event (Application.cpp:438) which measures how long it takes for the io_context to process a timer callback. Values above 10ms are logged; above 500ms trigger warnings. High values indicate thread pool saturation or blocking operations.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ios_latency{quantile=\"0.95\"}",
"legendFormat": "P95 I/O Latency"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ios_latency{quantile=\"0.5\"}",
"legendFormat": "P50 I/O Latency"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Latency (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Job Queue Depth",
"description": "Current number of jobs waiting in the job queue. Sourced from the job_count gauge (JobQueue.cpp:26). A sustained high value indicates the node cannot process work fast enough \u2014 common during ledger replay or heavy RPC load.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_job_count",
"legendFormat": "Job Queue Depth"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Jobs",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Ledger Fetch Rate",
"description": "Rate of ledger fetch requests initiated by the node. Sourced from the ledger_fetches counter (InboundLedgers.cpp:44) which increments each time the node requests a ledger from a peer. High rates indicate the node is catching up or missing ledgers.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_ledger_fetches_total[5m])",
"legendFormat": "Fetches / Sec"
}
],
"fieldConfig": {
"defaults": {
"unit": "ops"
},
"overrides": []
}
},
{
"title": "Ledger History Mismatches",
"description": "Rate of ledger history hash mismatches. Sourced from the ledger.history.mismatch counter (LedgerHistory.cpp:16) which increments when a built ledger hash does not match the expected validated hash. Non-zero values indicate consensus divergence or database corruption.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_ledger_history_mismatch_total[5m])",
"legendFormat": "Mismatches / Sec"
}
],
"fieldConfig": {
"defaults": {
"unit": "ops",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 0.01
}
]
}
},
"overrides": []
}
}
],
"schemaVersion": 39,
"tags": ["rippled", "statsd", "node-health", "telemetry"],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"title": "rippled Node Health (StatsD)",
"uid": "rippled-statsd-node-health"
}

566
docker/telemetry/grafana/dashboards/statsd-overlay-traffic-detail.json
View File

@@ -1,566 +0,0 @@
{
"annotations": {
"list": []
},
"description": "Detailed overlay traffic breakdown for categories not covered by the main Network Traffic dashboard. Includes squelch, overhead, validator lists, object fetch, ledger sync, and protocol negotiation traffic. Requires [insight] server=statsd in rippled config.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"title": "Squelch Traffic (Messages)",
"description": "Squelch-related overlay messages. Squelch is the peer traffic management protocol that suppresses redundant message forwarding. 'squelch' = squelch control messages, 'squelch_suppressed' = messages suppressed by squelch, 'squelch_ignored' = squelch directives that were ignored. High suppressed counts indicate effective bandwidth savings; high ignored counts may indicate misconfigured peers. Sourced from TrafficCount.h squelch categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_squelch_Messages_In",
"legendFormat": "Squelch In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_squelch_Messages_Out",
"legendFormat": "Squelch Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_squelch_suppressed_Messages_In",
"legendFormat": "Suppressed In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_squelch_suppressed_Messages_Out",
"legendFormat": "Suppressed Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_squelch_ignored_Messages_In",
"legendFormat": "Ignored In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_squelch_ignored_Messages_Out",
"legendFormat": "Ignored Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Overhead Traffic Breakdown (Bytes)",
"description": "Overlay protocol overhead by sub-category. 'overhead' = base protocol overhead (ping, status, etc.), 'overhead_cluster' = intra-cluster communication overhead, 'overhead_manifest' = validator manifest distribution overhead. High cluster overhead may indicate frequent cluster state syncs; high manifest overhead occurs during UNL changes. Sourced from TrafficCount.h overhead categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_overhead_Bytes_In",
"legendFormat": "Base Overhead In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_overhead_Bytes_Out",
"legendFormat": "Base Overhead Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_overhead_cluster_Bytes_In",
"legendFormat": "Cluster In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_overhead_cluster_Bytes_Out",
"legendFormat": "Cluster Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_overhead_manifest_Bytes_In",
"legendFormat": "Manifest In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_overhead_manifest_Bytes_Out",
"legendFormat": "Manifest Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Validator List Traffic",
"description": "Validator list (UNL) distribution traffic. Validator lists are exchanged when peers share their trusted validator configurations. Spikes occur during UNL updates or when new peers connect. Sourced from TrafficCount.h validator_lists category.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_lists_Bytes_In",
"legendFormat": "Bytes In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_lists_Bytes_Out",
"legendFormat": "Bytes Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_lists_Messages_In",
"legendFormat": "Messages In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_lists_Messages_Out",
"legendFormat": "Messages Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Count",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/Bytes/"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "right"
},
{
"id": "unit",
"value": "decbytes"
}
]
}
]
}
},
{
"title": "Set Get/Share Traffic (Bytes)",
"description": "Transaction set get and share traffic. 'set_get' = requests to fetch transaction sets (sent during ledger close), 'set_share' = responses sharing transaction sets. High set_get traffic indicates peers frequently requesting missing transaction sets, which may signal sync delays. Sourced from TrafficCount.h set_get/set_share categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_set_get_Bytes_In",
"legendFormat": "Set Get In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_set_get_Bytes_Out",
"legendFormat": "Set Get Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_set_share_Bytes_In",
"legendFormat": "Set Share In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_set_share_Bytes_Out",
"legendFormat": "Set Share Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Have/Requested Transactions (Messages)",
"description": "Transaction availability protocol messages. 'have_transactions' = advertisements that a peer has specific transactions available, 'requested_transactions' = explicit requests for transaction data. A high ratio of requested to have may indicate peers are behind on transaction propagation. Sourced from TrafficCount.h have_transactions/requested_transactions categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_have_transactions_Messages_In",
"legendFormat": "Have TX In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_have_transactions_Messages_Out",
"legendFormat": "Have TX Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_requested_transactions_Messages_In",
"legendFormat": "Requested TX In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_requested_transactions_Messages_Out",
"legendFormat": "Requested TX Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Unknown / Unclassified Traffic",
"description": "Traffic that does not match any known overlay message category. Non-zero values may indicate protocol version mismatches, corrupted messages, or new message types not yet classified. Sourced from TrafficCount.h unknown category.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_unknown_Bytes_In",
"legendFormat": "Unknown Bytes In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_unknown_Bytes_Out",
"legendFormat": "Unknown Bytes Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_unknown_Messages_In",
"legendFormat": "Unknown Messages In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_unknown_Messages_Out",
"legendFormat": "Unknown Messages Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Count",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/Bytes/"
},
"properties": [
{
"id": "custom.axisPlacement",
"value": "right"
},
{
"id": "unit",
"value": "decbytes"
}
]
}
]
}
},
{
"title": "Proof Path Traffic",
"description": "Proof path request/response traffic for ledger state proof exchange. Used by peers to verify specific ledger entries without downloading the full ledger. High request volume may indicate peers validating state during catch-up. Sourced from TrafficCount.h proof_path_request/proof_path_response categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_proof_path_request_Bytes_In",
"legendFormat": "Request Bytes In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_proof_path_request_Bytes_Out",
"legendFormat": "Request Bytes Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_proof_path_response_Bytes_In",
"legendFormat": "Response Bytes In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_proof_path_response_Bytes_Out",
"legendFormat": "Response Bytes Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Replay Delta Traffic",
"description": "Replay delta request/response traffic for ledger replay protocol. Used during catch-up to efficiently replay ledger state changes. Sourced from TrafficCount.h replay_delta_request/replay_delta_response categories.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_replay_delta_request_Bytes_In",
"legendFormat": "Request Bytes In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_replay_delta_request_Bytes_Out",
"legendFormat": "Request Bytes Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_replay_delta_response_Bytes_In",
"legendFormat": "Response Bytes In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_replay_delta_response_Bytes_Out",
"legendFormat": "Response Bytes Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
}
],
"schemaVersion": 39,
"tags": ["rippled", "statsd", "overlay", "network", "telemetry"],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"title": "Overlay Traffic Detail (StatsD)",
"uid": "rippled-statsd-overlay-detail"
}

396
docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json
View File

@@ -1,396 +0,0 @@
{
"annotations": {
"list": []
},
"description": "RPC and pathfinding metrics from beast::insight StatsD. Requires [insight] server=statsd in rippled config.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"title": "RPC Request Rate (StatsD)",
"description": "Rate of RPC requests as counted by the beast::insight counter. Sourced from rpc.requests (ServerHandler.cpp:108) which increments on every HTTP and WebSocket RPC request. Compare with the span-based rpc.request rate in the RPC Performance dashboard for cross-validation.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_rpc_requests_total[5m])",
"legendFormat": "Requests / Sec"
}
],
"fieldConfig": {
"defaults": {
"unit": "reqps"
},
"overrides": []
}
},
{
"title": "RPC Response Time (StatsD)",
"description": "P95 and P50 of RPC response time from the beast::insight timer. Sourced from the rpc.time event (ServerHandler.cpp:110) which records elapsed milliseconds for each RPC response. This measures the full HTTP handler time, not just command execution. Compare with span-based rpc.request duration.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_time{quantile=\"0.95\"}",
"legendFormat": "P95 Response Time"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_time{quantile=\"0.5\"}",
"legendFormat": "P50 Response Time"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Latency (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "RPC Response Size",
"description": "P95 and P50 of RPC response payload size in bytes. Sourced from the rpc.size event (ServerHandler.cpp:109) which records the byte length of each RPC JSON response. Large responses may indicate expensive queries (e.g. account_tx with many results) or API misuse.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_size{quantile=\"0.95\"}",
"legendFormat": "P95 Response Size"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_size{quantile=\"0.5\"}",
"legendFormat": "P50 Response Size"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Size (Bytes)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "RPC Response Time Distribution",
"description": "Distribution of RPC response times from the beast::insight timer showing P50, P90, P95, and P99 quantiles. Sourced from the rpc.time event (ServerHandler.cpp:110). Useful for detecting bimodal latency or long-tail requests.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_time{quantile=\"0.5\"}",
"legendFormat": "P50"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_time{quantile=\"0.9\"}",
"legendFormat": "P90"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_time{quantile=\"0.95\"}",
"legendFormat": "P95"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_rpc_time{quantile=\"0.99\"}",
"legendFormat": "P99"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Latency (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Pathfinding Fast Duration",
"description": "P95 and P50 of fast pathfinding execution time. Sourced from the pathfind_fast event (PathRequests.h:23) which records the duration of the fast pathfinding algorithm. Fast pathfinding uses a simplified search that trades accuracy for speed.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_pathfind_fast{quantile=\"0.95\"}",
"legendFormat": "P95 Fast Pathfind"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_pathfind_fast{quantile=\"0.5\"}",
"legendFormat": "P50 Fast Pathfind"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Duration (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Pathfinding Full Duration",
"description": "P95 and P50 of full pathfinding execution time. Sourced from the pathfind_full event (PathRequests.h:24) which records the duration of the exhaustive pathfinding search. Full pathfinding is more expensive and can take significantly longer than fast mode.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_pathfind_full{quantile=\"0.95\"}",
"legendFormat": "P95 Full Pathfind"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_pathfind_full{quantile=\"0.5\"}",
"legendFormat": "P50 Full Pathfind"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Duration (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Resource Warnings Rate",
"description": "Rate of resource warning events from the Resource Manager. Sourced from the warn meter (Logic.h:33) which increments when a consumer (peer or RPC client) exceeds the warning threshold for resource usage. A rising rate indicates aggressive clients that may need throttling. NOTE: This panel will show no data until the |m -> |c fix is applied in StatsDCollector.cpp:706 (Phase 6 Task 6.1).",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_warn_total[5m])",
"legendFormat": "Warnings / Sec"
}
],
"fieldConfig": {
"defaults": {
"unit": "ops",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.1
},
{
"color": "red",
"value": 1
}
]
}
},
"overrides": []
}
},
{
"title": "Resource Drops Rate",
"description": "Rate of resource drop events from the Resource Manager. Sourced from the drop meter (Logic.h:34) which increments when a consumer is disconnected or blocked due to excessive resource usage. Non-zero values mean the node is actively rejecting abusive connections. NOTE: This panel will show no data until the |m -> |c fix is applied in StatsDCollector.cpp:706 (Phase 6 Task 6.1).",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_drop_total[5m])",
"legendFormat": "Drops / Sec"
}
],
"fieldConfig": {
"defaults": {
"unit": "ops",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 0.01
},
{
"color": "red",
"value": 0.1
}
]
}
},
"overrides": []
}
}
],
"schemaVersion": 39,
"tags": ["rippled", "statsd", "rpc", "pathfinding", "telemetry"],
"templating": {
"list": []
},
"time": {
"from": "now-1h",
"to": "now"
},
"title": "rippled RPC & Pathfinding (StatsD)",
"uid": "rippled-statsd-rpc"
}