mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-24 07:30:30 +00:00
feat(telemetry): add Grafana Cloud dashboard copies
Grafana Cloud variants of the 14 xrpld dashboards. Identical to the local grafana/dashboards/ originals except the DS_PROMETHEUS / DS_TEMPO datasource template variables have their `current` value pinned to the Grafana Cloud datasource UIDs (grafanacloud-ripplex-prometheus / -traces). Includes the ledger-data-sync data-type split and node-health mixed-unit split + Cache Hit Ratio fix merged forward from phases 7 and 9. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Pratik Mankawde
1350
docker/telemetry/grafanacloud/consensus-health.json
Normal file
1350
docker/telemetry/grafanacloud/consensus-health.json
Normal file
File diff suppressed because it is too large
Load Diff
575
docker/telemetry/grafanacloud/fee-market.json
Normal file
575
docker/telemetry/grafanacloud/fee-market.json
Normal file
@@ -0,0 +1,575 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: Transaction queue depth and capacity, fee-escalation levels, and load-factor breakdown that together set the minimum fee to enter the open ledger.\nUse it to: Understand why the minimum transaction fee is rising and how full the open ledger and queue are.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "Transaction Queue Depth",
|
||||
"description": "###### What this is:\n*Transactions currently waiting in the transaction queue versus the queue's maximum capacity.*\n\n###### How it's computed:\n*Instantaneous gauge readings of current queue count and configured max size.*\n\n###### Reading it:\n*Queue depth well below capacity is normal; depth approaching capacity means the node is saturating.*\n\n###### Healthy range:\n*Depth near 0 in quiet periods; workload-dependent under load.*\n\n###### Watch for:\n*Depth pinned at capacity for sustained periods, which signals demand exceeding throughput or a fee-spam burst.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerTxqGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_count\"}",
|
||||
"legendFormat": "Queue Depth [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_max_size\"}",
|
||||
"legendFormat": "Max Capacity [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Transactions",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Transactions Per Ledger",
|
||||
"description": "###### What this is:\n*Transactions already placed in the current open ledger versus the expected per-ledger target.*\n\n###### How it's computed:\n*Instantaneous gauge readings of in-ledger count and the target count that governs fee escalation.*\n\n###### Reading it:\n*Staying at or below the expected target is normal; exceeding it triggers open-ledger fee escalation.*\n\n###### Healthy range:\n*At or under the expected per-ledger target.*\n\n###### Watch for:\n*In-ledger count persistently above target, indicating sustained congestion pushing fees up.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerTxqGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_in_ledger\"}",
|
||||
"legendFormat": "In Ledger [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_per_ledger\"}",
|
||||
"legendFormat": "Expected Per Ledger [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Transactions",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Fee Escalation Levels",
|
||||
"description": "###### What this is:\n*The fee levels that govern queue admission: reference (baseline), minimum processing, median, and open-ledger levels.*\n\n###### How it's computed:\n*Instantaneous gauge readings of each fee level, shown on a log scale.*\n\n###### Reading it:\n*Open-ledger level near the reference level means cheap entry; a large gap above reference means escalation is active.*\n\n###### Healthy range:\n*Open-ledger level at or near reference during normal traffic.*\n\n###### Watch for:\n*Open-ledger level spiking far above reference, the hallmark of congestion or a fee-bidding war.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerTxqGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_reference_fee_level\"}",
|
||||
"legendFormat": "Reference Fee Level [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_min_processing_fee_level\"}",
|
||||
"legendFormat": "Min Processing Fee Level [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_med_fee_level\"}",
|
||||
"legendFormat": "Median Fee Level [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "txq_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"txq_open_ledger_fee_level\"}",
|
||||
"legendFormat": "Open Ledger Fee Level [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Fee Level",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "log",
|
||||
"log": 2
|
||||
}
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Load Factor Breakdown",
|
||||
"description": "###### What this is:\n*The combined load factor and its server, fee-escalation, and fee-queue contributors as unitless fee multipliers (1.0 = no load).*\n\n###### How it's computed:\n*Instantaneous gauge readings of each load-factor component.*\n\n###### Reading it:\n*Values at 1.0 mean base fees; higher values raise the fee to transact.*\n\n###### Healthy range:\n*Around 1.0 under normal conditions.*\n\n###### Watch for:\n*Combined factor climbing well above 1.0, showing the node is charging premium fees due to congestion or overload.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLoadFactorGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor\"}",
|
||||
"legendFormat": "Combined Load Factor [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor_server\"}",
|
||||
"legendFormat": "Server [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor_fee_escalation\"}",
|
||||
"legendFormat": "Fee Escalation [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor_fee_queue\"}",
|
||||
"legendFormat": "Fee Queue [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Multiplier",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 5
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 2
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 10
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Load Factor Components",
|
||||
"description": "###### What this is:\n*The individual load-factor inputs, local server load, network load, and cluster load, as unitless multipliers.*\n\n###### How it's computed:\n*Instantaneous gauge readings of each component.*\n\n###### Reading it:\n*All at 1.0 means no load pressure from any source; a raised component identifies where load originates.*\n\n###### Healthy range:\n*Around 1.0 for each component.*\n\n###### Watch for:\n*A single component rising sharply, which pinpoints whether the pressure is local, network-wide, or cluster-driven.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLoadFactorGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor_local\"}",
|
||||
"legendFormat": "Local [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor_net\"}",
|
||||
"legendFormat": "Network [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor_cluster\"}",
|
||||
"legendFormat": "Cluster [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Multiplier",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 5
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Queue Abandonment Rate (Expired)",
|
||||
"description": "###### What this is:\n*Transactions dropped from the queue because their last-ledger deadline passed before they could be included.*\n\n###### How it's computed:\n*Per-second rate of the cumulative expired-transaction counter over the dashboard's rate interval.*\n\n###### Reading it:\n*Near zero is healthy; a rising rate means submitters under-bid the escalating fee and their transactions timed out.*\n\n###### Healthy range:\n*Near 0 expirations per second.*\n\n###### Watch for:\n*Sustained expiry rate, a demand-frustration signal often coinciding with fee spikes or spam that crowds out honest traffic.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqExpired (caller TxQ.cpp)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(txq_expired_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))",
|
||||
"legendFormat": "Expired / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Expired / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Queue Admission Rejections (Dropped)",
|
||||
"description": "###### What this is:\n*Transactions refused entry to the queue, broken down by reason such as queue_full.*\n\n###### How it's computed:\n*Per-second rate of the cumulative dropped-transaction counter over the dashboard's rate interval, split by reason.*\n\n###### Reading it:\n*Near zero is healthy; queue_full rejections mean the queue is at capacity and applying backpressure.*\n\n###### Healthy range:\n*Near 0 rejections per second.*\n\n###### Watch for:\n*A burst of queue_full drops, distinct from expiry, indicating the node is being flooded faster than it can drain.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqDropped (caller TxQ.cpp)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (reason, service_instance_id) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{reason}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Dropped / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["transactions", "fees"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "deployment_environment",
|
||||
"label": "Environment",
|
||||
"description": "Filter by deployment tier [local / ci / test / prod]",
|
||||
"type": "query",
|
||||
"query": "label_values(deployment_environment)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "browser",
|
||||
"title": "Fee Market & TxQ",
|
||||
"uid": "fee-market",
|
||||
"version": 1,
|
||||
"refresh": "10s"
|
||||
}
|
||||
661
docker/telemetry/grafanacloud/job-queue.json
Normal file
661
docker/telemetry/grafanacloud/job-queue.json
Normal file
@@ -0,0 +1,661 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: Per-job-type throughput, queue wait times, and execution times for the node's internal worker job queue.\nUse it to: Find job types that are backing up or running slowly and causing internal processing delays.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "Current Job Latency (p99 Gauge)",
|
||||
"description": "###### What this is:\n*At-a-glance p99 of how long jobs wait in the queue and how long they run once started.*\n\n###### How it's computed:\n*99th percentile derived from the job wait-time and run-time histograms over the last 5 minutes.*\n\n###### Reading it:\n*Lower is better; green under 100ms, yellow to 1s, red beyond 1s.*\n\n###### Healthy range:\n*Wait and exec p99 under 100ms.*\n\n###### Watch for:\n*p99 wait climbing into the red, meaning worker threads are saturated and jobs are backing up.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobStarted / recordJobFinished`",
|
||||
"type": "gauge",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"reduceOptions": {
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"orientation": "auto",
|
||||
"showThresholdLabels": false,
|
||||
"showThresholdMarkers": true
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m])))",
|
||||
"legendFormat": "p99 Wait"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum by (le) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m])))",
|
||||
"legendFormat": "p99 Exec"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "µs",
|
||||
"min": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 100000
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 1000000
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 1
|
||||
},
|
||||
{
|
||||
"title": "Job Throughput Rate (Per Second)",
|
||||
"description": "###### What this is:\n*Rate of jobs queued, started, and finished across all job types.*\n\n###### How it's computed:\n*Per-second rate of each cumulative job counter over a 5-minute window.*\n\n###### Reading it:\n*Queued, started, and finished tracking together means the queue keeps up.*\n\n###### Healthy range:\n*Workload-dependent; the three rates should stay roughly equal.*\n\n###### Watch for:\n*Queued rate persistently above finished rate, which indicates a growing backlog.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobQueued / recordJobStarted / recordJobFinished`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(job_queued_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[$__rate_interval]))",
|
||||
"legendFormat": "Queued/s [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(job_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[$__rate_interval]))",
|
||||
"legendFormat": "Started/s [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(job_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[$__rate_interval]))",
|
||||
"legendFormat": "Finished/s [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10,
|
||||
"axisLabel": "Operations / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 2
|
||||
},
|
||||
{
|
||||
"title": "Per-Job-Type Queued Rate",
|
||||
"description": "###### What this is:\n*Rate of jobs entering the queue, broken down by job type (top 10).*\n\n###### How it's computed:\n*Per-second rate of the queued-job counter per job_type over a 5-minute window.*\n\n###### Reading it:\n*Identifies which job types generate the most queue activity.*\n\n###### Healthy range:\n*Workload-dependent.*\n\n###### Watch for:\n*A single job type surging unexpectedly, which can point to a flood of a particular request or peer message.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobQueued`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
},
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"calcs": ["mean", "max"]
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "topk(10, rate(job_queued_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{job_type}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 1,
|
||||
"fillOpacity": 5,
|
||||
"axisLabel": "Operations / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 3
|
||||
},
|
||||
{
|
||||
"title": "Per-Job-Type Finish Rate",
|
||||
"description": "###### What this is:\n*Rate of jobs completing, broken down by job type (top 10).*\n\n###### How it's computed:\n*Per-second rate of the finished-job counter per job_type over a 5-minute window.*\n\n###### Reading it:\n*Compare against the queued rate per type to spot which types are falling behind.*\n\n###### Healthy range:\n*Workload-dependent; should match the per-type queued rate.*\n\n###### Watch for:\n*A type whose finish rate lags its queued rate, revealing where the backlog concentrates.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobFinished`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
},
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"calcs": ["mean", "max"]
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "topk(10, rate(job_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{job_type}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 1,
|
||||
"fillOpacity": 5,
|
||||
"axisLabel": "Operations / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 4
|
||||
},
|
||||
{
|
||||
"title": "Job Queue Wait Time",
|
||||
"description": "###### What this is:\n*Distribution of how long jobs sit in the queue before a worker picks them up (p75 typical, p99 tail).*\n\n###### How it's computed:\n*Percentiles derived from the job wait-time histogram over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; a widening gap between p75 and p99 signals occasional stalls.*\n\n###### Healthy range:\n*Sub-millisecond to low-millisecond waits on an unloaded node.*\n\n###### Watch for:\n*Rising p99 wait, an early sign of worker-thread saturation.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobStarted`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.75, sum by (le, service_instance_id) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m])))",
|
||||
"legendFormat": "p75 Wait [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum by (le, service_instance_id) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m])))",
|
||||
"legendFormat": "p99 Wait [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "µs",
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 5,
|
||||
"axisLabel": "Duration (μs)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 5
|
||||
},
|
||||
{
|
||||
"title": "Job Execution Time",
|
||||
"description": "###### What this is:\n*Distribution of how long jobs run once started (p75 typical, p99 tail).*\n\n###### How it's computed:\n*Percentiles derived from the job run-time histogram over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; stable p75 with a controlled p99 is healthy.*\n\n###### Healthy range:\n*Workload-dependent, but stable over time.*\n\n###### Watch for:\n*Growing execution times, which point to CPU pressure or expensive individual jobs.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobFinished`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.75, sum by (le, service_instance_id) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m])))",
|
||||
"legendFormat": "p75 Exec [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum by (le, service_instance_id) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m])))",
|
||||
"legendFormat": "p99 Exec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "µs",
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 5,
|
||||
"axisLabel": "Duration (μs)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 6
|
||||
},
|
||||
{
|
||||
"title": "Per-Job-Type Execution Time (p99)",
|
||||
"description": "###### What this is:\n*The 10 slowest job types ranked by p99 execution time.*\n\n###### How it's computed:\n*p99 derived from the run-time histogram per job_type over a 5-minute window, top 10 selected.*\n\n###### Reading it:\n*Highlights which job types cost the most CPU time at the tail.*\n\n###### Healthy range:\n*Workload-dependent.*\n\n###### Watch for:\n*A job type whose p99 grows over time, indicating a slow or degrading operation.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobFinished`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 32
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
},
|
||||
"legend": {
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"calcs": ["mean", "max"]
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "topk(10, histogram_quantile(0.99, sum by (le, job_type, service_instance_id) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\"}[5m]))))",
|
||||
"legendFormat": "{{job_type}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "µs",
|
||||
"custom": {
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 1,
|
||||
"fillOpacity": 5,
|
||||
"axisLabel": "Duration (μs)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 7
|
||||
},
|
||||
{
|
||||
"title": "Transaction Overflow Rate",
|
||||
"description": "###### What this is:\n*Rate at which transaction jobs are shed when the queue's transaction limit is exceeded.*\n\n###### How it's computed:\n*Per-second rate of the overflow counter over the dashboard's rate interval, scaled to per minute. The counter is observed from the overlay's cumulative overflow tally.*\n\n###### Reading it:\n*Near zero is healthy; a rising rate means the job queue is shedding transaction work under load.*\n\n###### Healthy range:\n*0 overflows per minute.*\n\n###### Watch for:\n*Any sustained non-zero rate — the node is dropping transaction jobs because the queue is saturated.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerParityCounters (observed from Overlay::getJqTransOverflow)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 40
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(jq_trans_overflow_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]) * 60",
|
||||
"legendFormat": "Overflows/min [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cpm",
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 10
|
||||
}
|
||||
]
|
||||
},
|
||||
"custom": {
|
||||
"axisLabel": "Overflows / Min",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10,
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 8
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["node", "jobqueue"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"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": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "job_type",
|
||||
"label": "Job Type",
|
||||
"description": "Filter by job type",
|
||||
"type": "query",
|
||||
"query": "label_values(job_queued_total, job_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "browser",
|
||||
"title": "Job Queue Analysis",
|
||||
"uid": "job-queue",
|
||||
"version": 1,
|
||||
"refresh": "10s"
|
||||
}
|
||||
991
docker/telemetry/grafanacloud/ledger-data-sync.json
Normal file
991
docker/telemetry/grafanacloud/ledger-data-sync.json
Normal file
@@ -0,0 +1,991 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: Ledger data exchange and object-fetch traffic between this node and its peers: ledger sync, tree-node retrieval, and transaction-set exchange.\nUse it to: See how much ledger data the node is pulling or serving and spot catch-up activity.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "Ledger Data — Ledger",
|
||||
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Data Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Data Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Data — Transaction",
|
||||
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Set Candidate Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Set Candidate Share [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Data — Account State",
|
||||
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Node Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Node Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Traffic — Ledger",
|
||||
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Get In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Share In [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Traffic — Transaction",
|
||||
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Set Candidate Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Set Candidate Share [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Traffic — Account State",
|
||||
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject — Ledger",
|
||||
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject — Transaction",
|
||||
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transaction_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Transaction Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Transaction Share [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject — Account State",
|
||||
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 32
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject Messages — Ledger",
|
||||
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 32
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_ledger_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ledger Get [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"custom": {
|
||||
"axisLabel": "Messages In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject Messages — Transaction",
|
||||
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 40
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transaction_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Transaction Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transaction_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "TX Node Get [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"custom": {
|
||||
"axisLabel": "Messages In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject Messages — Account State",
|
||||
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 40
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_account_state_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Account State Get [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"custom": {
|
||||
"axisLabel": "Messages In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject Messages — Specials",
|
||||
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 48
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_cas_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "CAS Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_fetch_pack_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Fetch Pack Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transactions_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Transactions Get [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"custom": {
|
||||
"axisLabel": "Messages In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "GetObject — Specials",
|
||||
"description": "###### What this is:\n*Aggregate object-fetch inbound bytes plus special buckets: content-addressed storage fetches, bulk fetch-pack downloads used during catch-up, and bulk transaction fetches.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Fetch-pack rises sharply while catching up a range of ledgers; near zero when fully synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous fetch-pack traffic (node never fully catches up) or unexpectedly high content-store volume.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 48
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_cas_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "CAS Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "CAS Share [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Fetch Pack Share [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Fetch Pack Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_transactions_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Transactions Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Aggregate Get [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Aggregate Share [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes In",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Overlay Traffic Heatmap (All Categories, Bytes In)",
|
||||
"description": "###### What this is:\n*All overlay traffic categories ranked by inbound bytes, giving an at-a-glance view of which message types consume the most receive bandwidth.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value across all traffic categories.*\n\n###### Reading it:\n*The longest bars are the biggest bandwidth consumers; on a synced node transactions, proposals, and validations usually lead.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*A single ledger-data or fetch category dominating (ongoing sync) or an unexpected category topping the list.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "bargauge",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 56
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
},
|
||||
"displayMode": "gradient",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "topk(20, {service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"})",
|
||||
"legendFormat": "{{__name__}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "decbytes",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 1048576
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 104857600
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["ledger", "sync"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "deployment_environment",
|
||||
"label": "Environment",
|
||||
"description": "Filter by deployment tier [local / ci / test / prod]",
|
||||
"type": "query",
|
||||
"query": "label_values(deployment_environment)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"title": "Ledger Data & Sync",
|
||||
"uid": "ledger-data-sync",
|
||||
"refresh": "10s"
|
||||
}
|
||||
486
docker/telemetry/grafanacloud/ledger-operations.json
Normal file
486
docker/telemetry/grafanacloud/ledger-operations.json
Normal file
@@ -0,0 +1,486 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "Ledger Build Rate",
|
||||
"description": "###### What this is:\n*How many new ledgers this node finishes building per second.*\n\n###### How it's computed:\n*Per-second rate of completed ledger-build operations, averaged over 5 minutes and split by node.*\n\n###### Reading it:\n*A steady flat line; the value should track the network close cadence.*\n\n###### Healthy range:\n*About 0.2-0.3 ledgers/sec on mainnet (roughly one every 3-5s); workload-dependent on test networks.*\n\n###### Watch for:\n*A drop toward zero (node fell out of sync or stalled) or a value well above the network rate (rebuilding history).*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`buildLedgerImpl`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[$__rate_interval]))",
|
||||
"legendFormat": "Builds / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Build Duration",
|
||||
"description": "###### What this is:\n*The time taken to build a single ledger, at the 95th percentile.*\n\n###### How it's computed:\n*95th-percentile of ledger-build durations over a 5-minute window, per node.*\n\n###### Reading it:\n*Lower is better; the line should stay well under the ledger interval.*\n\n###### Healthy range:\n*Typically tens to low hundreds of milliseconds; workload-dependent.*\n\n###### Watch for:\n*Sustained rises approaching the close interval, which indicate heavy transaction sets or disk/I/O pressure.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`buildLedgerImpl`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m])))",
|
||||
"legendFormat": "P95 Build Duration [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Validation Rate",
|
||||
"description": "###### What this is:\n*How often ledgers reach full validation (accepted by the trusted validator quorum) per second.*\n\n###### How it's computed:\n*Per-second rate of ledger-validation events over 5 minutes, per node.*\n\n###### Reading it:\n*Should closely match the build rate under normal, in-sync operation.*\n\n###### Healthy range:\n*About 0.2-0.3/sec on mainnet; workload-dependent elsewhere.*\n\n###### Watch for:\n*A validation rate that lags the build rate, signalling the node is building ahead of the network consensus it trusts.*\n\n###### Source:\n[LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::checkAccept`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.validate\"}[$__rate_interval]))",
|
||||
"legendFormat": "Validations / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Build Duration Heatmap",
|
||||
"description": "###### What this is:\n*The full distribution of ledger-build times over the window, not just a single percentile.*\n\n###### How it's computed:\n*Counts of ledger builds falling in each duration band per 5-minute window, shown as color density.*\n\n###### Reading it:\n*A tight low band is healthy; scattered high cells mean occasional slow builds.*\n\n###### Healthy range:\n*Most mass concentrated in the low-millisecond bands; workload-dependent.*\n\n###### Watch for:\n*A second cluster of hot cells at high durations (bimodal build times) hidden by percentile charts.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`buildLedgerImpl`",
|
||||
"type": "heatmap",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
},
|
||||
"yAxis": {
|
||||
"axisLabel": "Duration (ms)"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum(increase(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m])) by (le)",
|
||||
"legendFormat": "{{le}}",
|
||||
"format": "heatmap"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Transaction Apply Duration",
|
||||
"description": "###### What this is:\n*The time spent applying the agreed transaction set into the new ledger, at the 95th percentile.*\n\n###### How it's computed:\n*95th-percentile of transaction-apply durations over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; this is a large share of total build time.*\n\n###### Healthy range:\n*A few to tens of milliseconds; scales with transaction volume per ledger.*\n\n###### Watch for:\n*Spikes during large or expensive transaction sets, which push out overall ledger build time.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`applyTransactions`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[5m])))",
|
||||
"legendFormat": "P95 tx.apply [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Transaction Apply Rate",
|
||||
"description": "###### What this is:\n*How often the transaction-apply phase runs per second (once per ledger build).*\n\n###### How it's computed:\n*Per-second rate of transaction-apply operations over 5 minutes, per node.*\n\n###### Reading it:\n*Should track the ledger build rate almost exactly.*\n\n###### Healthy range:\n*About 0.2-0.3/sec on mainnet; workload-dependent.*\n\n###### Watch for:\n*Divergence from the build rate, which would indicate a metric or pipeline anomaly.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`applyTransactions`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"tx.apply\"}[$__rate_interval]))",
|
||||
"legendFormat": "tx.apply / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Operations / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Ledger Store Rate",
|
||||
"description": "###### What this is:\n*How often completed ledgers are written into ledger history per second.*\n\n###### How it's computed:\n*Per-second rate of ledger-store operations over 5 minutes, per node.*\n\n###### Reading it:\n*Should match the build rate during normal operation.*\n\n###### Healthy range:\n*About 0.2-0.3/sec on mainnet; can burst higher while backfilling history.*\n\n###### Watch for:\n*A store rate below the build rate (storage falling behind) or a stall at zero.*\n\n###### Source:\n[LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::storeLedger`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.store\"}[$__rate_interval]))",
|
||||
"legendFormat": "Stores / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Build vs Close Duration",
|
||||
"description": "###### What this is:\n*Ledger build time compared with the total consensus ledger-close time, both at the 95th percentile.*\n\n###### How it's computed:\n*Two 95th-percentile duration series over 5 minutes: ledger construction and the full consensus close, per node.*\n\n###### Reading it:\n*Build should sit below close; the gap is consensus overhead outside construction.*\n\n###### Healthy range:\n*Close a bit above build; both workload-dependent and under the round interval.*\n\n###### Watch for:\n*A widening gap (consensus-pipeline overhead growing) or build time approaching close time.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp) · [RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`buildLedgerImpl ; RCLConsensus::Adaptor::onClose`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"ledger.build\"}[5m])))",
|
||||
"legendFormat": "P95 ledger.build [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[5m])))",
|
||||
"legendFormat": "P95 consensus.ledger_close [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["ledger"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"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": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id — e.g. Node-1)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"title": "Ledger Operations",
|
||||
"uid": "ledger-operations",
|
||||
"refresh": "10s",
|
||||
"description": "What this shows: Ledger construction, validation, and storage activity and timing for this node.\nUse it to: Confirm ledgers are being built, validated, and stored on schedule and find the slow stage when they are not."
|
||||
}
|
||||
968
docker/telemetry/grafanacloud/network-traffic.json
Normal file
968
docker/telemetry/grafanacloud/network-traffic.json
Normal file
File diff suppressed because one or more lines are too long
2720
docker/telemetry/grafanacloud/node-health.json
Normal file
2720
docker/telemetry/grafanacloud/node-health.json
Normal file
File diff suppressed because it is too large
Load Diff
760
docker/telemetry/grafanacloud/overlay-traffic-detail.json
Normal file
760
docker/telemetry/grafanacloud/overlay-traffic-detail.json
Normal file
@@ -0,0 +1,760 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: Fine-grained breakdown of peer-to-peer overlay traffic beyond the main network view: squelch relay control, protocol overhead, validator-list distribution, transaction-set exchange, transaction availability, ledger-proof and replay traffic, and unclassified messages.\nUse it to: Drill into individual overlay message categories to diagnose relay efficiency, overhead, and catch-up traffic.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "Squelch Traffic (Messages)",
|
||||
"description": "###### What this is:\n*Squelch relay-control messages in/out, plus messages suppressed by squelch and squelch directives that were ignored. Squelch reduces redundant message forwarding between peers.*\n\n###### How it's computed:\n*Per-second message rate for the squelch, squelch-suppressed, and squelch-ignored categories, in and out.*\n\n###### Reading it:\n*High suppressed counts mean squelch is saving bandwidth; ignored should stay low.*\n\n###### Healthy range:\n*workload-dependent; suppressed far above ignored.*\n\n###### Watch for:\n*High ignored counts (peers not honoring squelch) or squelch traffic itself dominating.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(squelch_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Squelch In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(squelch_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Squelch Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(squelch_suppressed_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Suppressed In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(squelch_suppressed_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Suppressed Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(squelch_ignored_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ignored In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(squelch_ignored_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Ignored Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"custom": {
|
||||
"axisLabel": "Messages",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Overhead Traffic Breakdown (Bytes)",
|
||||
"description": "###### What this is:\n*Overlay protocol overhead bytes split into base overhead, intra-cluster overhead, and validator-manifest distribution overhead.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the overhead, overhead-cluster, and overhead-manifest categories.*\n\n###### Reading it:\n*Base overhead is routine; cluster and manifest rise around cluster syncs and manifest changes.*\n\n###### Healthy range:\n*workload-dependent; low and stable.*\n\n###### Watch for:\n*Sustained high cluster or manifest overhead (frequent cluster state churn or manifest reissue).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Base Overhead In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(overhead_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Base Overhead Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Cluster In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(overhead_cluster_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Cluster Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Manifest In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(overhead_manifest_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Manifest Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Validator List Traffic",
|
||||
"description": "###### What this is:\n*Bytes and messages exchanged distributing validator lists (trusted-list configuration) between peers.*\n\n###### How it's computed:\n*Per-second in/out byte and message rate for the validator-lists category.*\n\n###### Reading it:\n*Bursts when lists update or new peers connect; quiet otherwise.*\n\n###### Healthy range:\n*workload-dependent; occasional bursts.*\n\n###### Watch for:\n*Continuous high volume (repeated list re-fetching or churn).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Bytes In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(validator_lists_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Bytes Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(validator_lists_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Messages In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(validator_lists_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Messages Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"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": "binBps"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Set Get/Share Traffic (Bytes)",
|
||||
"description": "###### What this is:\n*Transaction-set fetch (get) and share bytes exchanged during ledger close.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the set-get and set-share categories.*\n\n###### Reading it:\n*Some exchange each ledger is normal as peers reconcile transaction sets.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High set-get (peers frequently missing transaction sets: possible sync delays).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Set Get In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(set_get_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Set Get Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Set Share In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(set_share_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Set Share Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Have/Requested Transactions (Messages)",
|
||||
"description": "###### What this is:\n*Transaction-availability messages: advertisements that a peer has certain transactions, and explicit requests for transaction data.*\n\n###### How it's computed:\n*Per-second in/out message rate for the have-transactions and requested-transactions categories.*\n\n###### Reading it:\n*Compare requested versus have to gauge how well transactions are propagating.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Requested far exceeding have (peers behind on transaction propagation).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(have_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Have TX In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(have_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Have TX Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(requested_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Requested TX In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(requested_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Requested TX Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "cps",
|
||||
"custom": {
|
||||
"axisLabel": "Messages",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Unknown / Unclassified Traffic",
|
||||
"description": "###### What this is:\n*Overlay traffic that matches no known message category, in bytes and messages.*\n\n###### How it's computed:\n*Current in/out byte and message counts for the unknown category.*\n\n###### Reading it:\n*Should be at or near zero.*\n\n###### Healthy range:\n*zero.*\n\n###### Watch for:\n*Any sustained non-zero value (protocol version mismatch, corrupted messages, or an unclassified new message type).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "unknown_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Unknown Bytes In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "unknown_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Unknown Bytes Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "unknown_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Unknown Messages In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "unknown_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Unknown Messages Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"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": "###### What this is:\n*Proof-path request/response bytes used to verify individual ledger entries without downloading the whole ledger.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the proof-path request and response categories.*\n\n###### Reading it:\n*Rises when peers verify specific state, often during catch-up.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High sustained request volume (heavy state-verification load).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Request Bytes In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(proof_path_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Request Bytes Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Response Bytes In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(proof_path_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Response Bytes Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Replay Delta Traffic",
|
||||
"description": "###### What this is:\n*Replay-delta request/response bytes used to efficiently replay ledger state changes during catch-up.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the replay-delta request and response categories.*\n\n###### Reading it:\n*Active during catch-up and replay; quiet when synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous replay traffic (node repeatedly replaying rather than staying current).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Request Bytes In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(replay_delta_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Request Bytes Out [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Response Bytes In [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(replay_delta_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Response Bytes Out [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "Bps",
|
||||
"custom": {
|
||||
"axisLabel": "Bytes",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["network", "peer"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "deployment_environment",
|
||||
"label": "Environment",
|
||||
"description": "Filter by deployment tier [local / ci / test / prod]",
|
||||
"type": "query",
|
||||
"query": "label_values(deployment_environment)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"title": "Overlay Traffic Detail",
|
||||
"uid": "overlay-traffic-detail",
|
||||
"refresh": "10s"
|
||||
}
|
||||
464
docker/telemetry/grafanacloud/peer-network.json
Normal file
464
docker/telemetry/grafanacloud/peer-network.json
Normal file
@@ -0,0 +1,464 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: Consensus proposals and validations received from peers, and transaction relay efficiency for this node.\nUse it to: Check that peers are feeding this node proposals, validations, and transactions, and gauge relay overhead.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "Peer Proposal Receive Rate",
|
||||
"description": "###### What this is:\n*How many consensus proposals this node receives from peers per second.*\n\n###### How it's computed:\n*Per-second rate of received proposals over 5 minutes, per node.*\n\n###### Reading it:\n*A steady rate roughly proportional to the number of proposing validators.*\n\n###### Healthy range:\n*Workload-dependent; scales with validator count and connectivity.*\n\n###### Watch for:\n*A drop toward zero (isolation from the network) or a sudden flood far above baseline (proposal spam).*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMProposeSet)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"peer.proposal.receive\"}[$__rate_interval]))",
|
||||
"legendFormat": "Proposals Received / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Proposals / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Peer Validation Receive Rate",
|
||||
"description": "###### What this is:\n*How many ledger validations this node receives from peers per second.*\n\n###### How it's computed:\n*Per-second rate of received validations over 5 minutes, per node.*\n\n###### Reading it:\n*Steady and proportional to the number of validators the node hears from.*\n\n###### Healthy range:\n*Workload-dependent; roughly one burst per validator per closed ledger.*\n\n###### Watch for:\n*A fall toward zero (loss of validator connectivity) or an abnormal surge from untrusted sources.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMValidation)`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"peer.validation.receive\"}[$__rate_interval]))",
|
||||
"legendFormat": "Validations Received / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Validations / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Proposals Trusted vs Untrusted",
|
||||
"description": "###### What this is:\n*The share of received proposals that come from trusted (UNL) validators versus everyone else.*\n\n###### How it's computed:\n*Received-proposal rate split by trust status over 5 minutes, shown as proportions.*\n\n###### Reading it:\n*A healthy node with a good UNL shows a solid trusted slice.*\n\n###### Healthy range:\n*Workload-dependent; a meaningful trusted fraction is expected.*\n\n###### Watch for:\n*A collapsing trusted share or a large untrusted volume, consistent with proposal flooding from non-UNL peers.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMProposeSet)`",
|
||||
"type": "piechart",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (proposal_trusted, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[$__rate_interval]))",
|
||||
"legendFormat": "Trusted = {{proposal_trusted}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Validations Trusted vs Untrusted",
|
||||
"description": "###### What this is:\n*The share of received validations from trusted (UNL) validators versus untrusted sources.*\n\n###### How it's computed:\n*Received-validation rate split by trust status over 5 minutes, shown as proportions.*\n\n###### Reading it:\n*The trusted slice should dominate for a well-configured node.*\n\n###### Healthy range:\n*Workload-dependent; trusted validations expected to be the majority.*\n\n###### Watch for:\n*A shrinking trusted share or a spike of untrusted validations, which can indicate misconfiguration or abuse.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMValidation)`",
|
||||
"type": "piechart",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (validation_trusted, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[$__rate_interval]))",
|
||||
"legendFormat": "Trusted = {{validation_trusted}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Reduce-Relay Peer Selection",
|
||||
"description": "###### What this is:\n*How transaction relay picks peers: chosen relay sources, suppressed peers, and peers with the feature off.*\n\n###### How it's computed:\n*Current peer counts in each category (selected, suppressed, not-enabled), per node.*\n\n###### Reading it:\n*A high suppressed-to-selected ratio means relay is saving bandwidth as intended.*\n\n###### Healthy range:\n*Workload-dependent; suppressed should exceed selected in a well-connected mesh.*\n\n###### Watch for:\n*A large not-enabled count (older peers forcing full relay) or selected climbing while suppressed falls.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerReduceRelayGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "reduce_relay_metrics{metric=\"selected_peers\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Selected [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "reduce_relay_metrics{metric=\"suppressed_peers\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Suppressed [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "reduce_relay_metrics{metric=\"not_enabled_peers\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Not Enabled [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Peer Count",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Reduce-Relay Missing-Tx Frequency",
|
||||
"description": "###### What this is:\n*How often a peer has to fetch a transaction it missed because relay suppressed it.*\n\n###### How it's computed:\n*The reported frequency of on-demand missing-transaction fetches, per node.*\n\n###### Reading it:\n*Lower is better; near-flat means suppression is well tuned.*\n\n###### Healthy range:\n*Workload-dependent; a low, stable value is expected.*\n\n###### Watch for:\n*A rising trend, meaning suppression is too aggressive and the on-demand fetch path is growing.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerReduceRelayGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "reduce_relay_metrics{metric=\"missing_tx_freq\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Missing Tx Freq [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Frequency",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["network", "peer"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"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": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id — e.g. Node-1)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "proposal_trusted",
|
||||
"label": "Proposal Trusted",
|
||||
"description": "Filter by proposal trust status (true = from trusted validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(span_calls_total{span_name=\"peer.proposal.receive\"}, proposal_trusted)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "validation_trusted",
|
||||
"label": "Validation Trusted",
|
||||
"description": "Filter by validation trust status (true = from trusted validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(span_calls_total{span_name=\"peer.validation.receive\"}, validation_trusted)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"title": "Peer Network",
|
||||
"uid": "peer-network",
|
||||
"refresh": "10s"
|
||||
}
|
||||
541
docker/telemetry/grafanacloud/peer-quality.json
Normal file
541
docker/telemetry/grafanacloud/peer-quality.json
Normal file
@@ -0,0 +1,541 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: Peer connection quality: latency, divergence, version distribution and upgrade guidance, resource disconnects, and inbound/outbound balance.\nUse it to: Assess how good this node's peer set is and whether connectivity or an upgrade needs attention.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "P90 Peer Latency",
|
||||
"description": "###### What this is:\n*90th-percentile round-trip latency to connected peers, in milliseconds.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the p90 peer latency.*\n\n###### Reading it:\n*Lower is better; green under 200ms, yellow to 500ms, red above.*\n\n###### Healthy range:\n*Under 200ms.*\n\n###### Watch for:\n*Rising latency, which points to network congestion or geographically distant, poorly performing peers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "peer_quality{metric=\"peer_latency_p90_ms\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "P90 Latency [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Latency (ms)",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10,
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 200
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 500
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Insane/Diverged Peers",
|
||||
"description": "###### What this is:\n*Count of connected peers whose ledger state has diverged from the network.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the diverged-peer count.*\n\n###### Reading it:\n*Zero is healthy; any count means those peers disagree on ledger state.*\n\n###### Healthy range:\n*0 diverged peers.*\n\n###### Watch for:\n*A persistent non-zero count, which can indicate peers on a fork or misbehaving peers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "peer_quality{metric=\"peers_insane_count\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Insane Peers [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 1
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 3
|
||||
}
|
||||
]
|
||||
},
|
||||
"custom": {}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Higher Version Peers %",
|
||||
"description": "###### What this is:\n*Percentage of connected peers running a newer rippled version than this node.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the higher-version peer percentage.*\n\n###### Reading it:\n*A high percentage suggests this node is behind and should be upgraded.*\n\n###### Healthy range:\n*Under 30%.*\n\n###### Watch for:\n*A majority of peers on a newer version, a strong upgrade signal.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "peer_quality{metric=\"peers_higher_version_pct\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Higher Version % [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "percent",
|
||||
"min": 0,
|
||||
"max": 100,
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 30
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 60
|
||||
}
|
||||
]
|
||||
},
|
||||
"custom": {}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Upgrade Recommended",
|
||||
"description": "###### What this is:\n*A flag indicating whether an upgrade is advised based on peer version analysis (Yes/No).*\n\n###### How it's computed:\n*Instantaneous gauge reading of the upgrade-recommended flag.*\n\n###### Reading it:\n*No is healthy; Yes means most peers run a newer version.*\n\n###### Healthy range:\n*No.*\n\n###### Watch for:\n*A Yes state, indicating the node risks falling out of step with the network.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "peer_quality{metric=\"upgrade_recommended\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Upgrade [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "none",
|
||||
"mappings": [
|
||||
{
|
||||
"type": "value",
|
||||
"options": {
|
||||
"0": {
|
||||
"text": "No",
|
||||
"color": "green"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "value",
|
||||
"options": {
|
||||
"1": {
|
||||
"text": "Yes",
|
||||
"color": "red"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"custom": {}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Resource Disconnects",
|
||||
"description": "###### What this is:\n*Cumulative count of peers dropped for exceeding resource (load) limits.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the resource-disconnect total over time.*\n\n###### Reading it:\n*A flat line is healthy; a rising line means peers are being dropped for overuse.*\n\n###### Healthy range:\n*Flat / near constant.*\n\n###### Watch for:\n*A steep climb, which flags aggressive or misbehaving peers being shed as backpressure.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 32
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "server_info{metric=\"peer_disconnects_resources\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Disconnects [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"custom": {
|
||||
"axisLabel": "Disconnects",
|
||||
"drawStyle": "line",
|
||||
"lineWidth": 2,
|
||||
"fillOpacity": 10,
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
},
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Inbound vs Outbound Peers",
|
||||
"description": "###### What this is:\n*Active inbound versus outbound peer connection counts.*\n\n###### How it's computed:\n*Instantaneous gauge readings of active inbound and outbound peer counts.*\n\n###### Reading it:\n*A balanced mix is healthy for connectivity and resilience.*\n\n###### Healthy range:\n*A mix of both; some outbound connections present.*\n\n###### Watch for:\n*All-inbound with no outbound, which usually means NAT or firewall issues block outbound peering.*\n\n###### Source:\n[PeerfinderManager.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/peerfinder/detail/PeerfinderManager.cpp)\n\n###### Function:\n`Logic Stats ctor`",
|
||||
"type": "bargauge",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 40
|
||||
},
|
||||
"options": {
|
||||
"orientation": "horizontal",
|
||||
"displayMode": "gradient",
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "peer_finder_active_inbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Inbound [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "peer_finder_active_outbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
|
||||
"legendFormat": "Outbound [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "short",
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
},
|
||||
"custom": {}
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "Inbound.*"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "blue"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byRegexp",
|
||||
"options": "Outbound.*"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"mode": "fixed",
|
||||
"fixedColor": "orange"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["network", "peer"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "deployment_environment",
|
||||
"label": "Environment",
|
||||
"description": "Filter by deployment tier [local / ci / test / prod]",
|
||||
"type": "query",
|
||||
"query": "label_values(deployment_environment)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"title": "Peer Quality",
|
||||
"uid": "peer-quality",
|
||||
"refresh": "10s"
|
||||
}
|
||||
757
docker/telemetry/grafanacloud/rpc-pathfinding.json
Normal file
757
docker/telemetry/grafanacloud/rpc-pathfinding.json
Normal file
@@ -0,0 +1,757 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": []
|
||||
},
|
||||
"description": "What this shows: RPC request throughput and response timing, pathfinding cost, gRPC read traffic, and resource-manager enforcement for this node.\nUse it to: Watch client request load and cost, and confirm resource limits are protecting the node.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"panels": [
|
||||
{
|
||||
"title": "RPC Request Rate",
|
||||
"description": "###### What this is:\n*How many RPC requests the server counts per second.*\n\n###### How it's computed:\n*Per-second rate of the RPC request counter over 5 minutes, per node.*\n\n###### Reading it:\n*A steady line proportional to client demand; cross-checks the trace-based RPC dashboard.*\n\n###### Healthy range:\n*Workload-dependent; tracks client activity.*\n\n###### Watch for:\n*A sudden surge above baseline, consistent with a client flooding the RPC endpoint.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(rpc_requests_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Requests / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "RPC Response Time",
|
||||
"description": "###### What this is:\n*The 95th-percentile end-to-end RPC response time, including HTTP handling.*\n\n###### How it's computed:\n*95th-percentile of measured response times over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; this is broader than command-only latency.*\n\n###### Healthy range:\n*A few to tens of milliseconds; workload-dependent.*\n\n###### Watch for:\n*A sustained climb, indicating handler overload or slow downstream work.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 0
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P95 Response Time [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Latency (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "RPC Response Size",
|
||||
"description": "⚠ Instrument mismatch — values unreliable. Response size is recorded through the millisecond-scaled event histogram (rpc_size_milliseconds_bucket), so byte values saturate at the top time bucket (5000) and the percentiles are not true byte sizes. A dedicated byte-unit histogram is needed to fix this; tracked separately. Treat this panel as indicative only until then.\n\n###### What this is:\n*The 95th-percentile size of RPC response payloads in bytes.*\n\n###### How it's computed:\n*95th-percentile of response payload sizes over the dashboard rate interval, per node.*\n\n###### Reading it:\n*Smaller is cheaper; large responses cost bandwidth and memory.*\n\n###### Healthy range:\n*Workload-dependent; small for status queries, large for bulk data queries.*\n\n###### Watch for:\n*Growth in large responses, consistent with expensive queries or API misuse.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(rpc_size_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P95 Response Size [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "decbytes",
|
||||
"custom": {
|
||||
"axisLabel": "Size (Bytes)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "RPC Response Time Distribution",
|
||||
"description": "###### What this is:\n*RPC response time at the 90th, 95th, and 99th percentiles together.*\n\n###### How it's computed:\n*Three response-time quantiles over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; the gap between P90 and P99 shows the long tail.*\n\n###### Healthy range:\n*Percentiles clustered low; workload-dependent.*\n\n###### Watch for:\n*A widening P99, revealing long-tail or bimodal slow requests.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 8
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.9, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P90 [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P95 [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P99 [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Latency (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Pathfinding Fast Duration",
|
||||
"description": "###### What this is:\n*The 95th-percentile time of the fast pathfinding search.*\n\n###### How it's computed:\n*95th-percentile of fast pathfinding durations over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; fast mode trades accuracy for speed.*\n\n###### Healthy range:\n*Typically a few to tens of milliseconds; workload-dependent.*\n\n###### Watch for:\n*A rising trend, indicating heavy pathfinding demand or an expensive order book.*\n\n###### Source:\n[PathRequestManager.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/PathRequestManager.h)\n\n###### Function:\n`ctor`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(pathfind_fast_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P95 Fast Pathfind [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Pathfinding Full Duration",
|
||||
"description": "###### What this is:\n*The 95th-percentile time of the full, exhaustive pathfinding search.*\n\n###### How it's computed:\n*95th-percentile of full pathfinding durations over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; full mode is much more expensive than fast mode.*\n\n###### Healthy range:\n*Tens to hundreds of milliseconds; workload-dependent.*\n\n###### Watch for:\n*Sustained high durations, consistent with pathfinding-heavy clients straining the node.*\n\n###### Source:\n[PathRequestManager.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/PathRequestManager.h)\n\n###### Function:\n`ctor`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 16
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(pathfind_full_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[5m])))",
|
||||
"legendFormat": "P95 Full Pathfind [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Resource Warnings Rate",
|
||||
"description": "###### What this is:\n*How often the resource manager warns a peer or client for excessive usage, per second.*\n\n###### How it's computed:\n*Per-second rate of resource-warning events over 5 minutes, per node.*\n\n###### Reading it:\n*Green near zero, yellow above 0.1/sec, red above 1/sec.*\n\n###### Healthy range:\n*Near zero in normal operation.*\n\n###### Watch for:\n*A rising rate, consistent with aggressive clients that may need throttling.*\n\n###### Source:\n[Logic.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/resource/detail/Logic.h)\n\n###### Function:\n`Logic::Stats ctor`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(warn_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Warnings / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 0.1
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 1
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Resource Drops Rate",
|
||||
"description": "###### What this is:\n*How often the resource manager drops or blocks a peer or client for abuse, per second.*\n\n###### How it's computed:\n*Per-second rate of resource-drop events over 5 minutes, per node.*\n\n###### Reading it:\n*Green near zero, yellow above 0.01/sec, red above 0.1/sec.*\n\n###### Healthy range:\n*Zero when no abusive consumers are present.*\n\n###### Watch for:\n*Non-zero values, meaning the node is actively rejecting abusive connections.*\n\n###### Source:\n[Logic.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/resource/detail/Logic.h)\n\n###### Function:\n`Logic::Stats ctor`",
|
||||
"type": "stat",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 24
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "rate(drop_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval])",
|
||||
"legendFormat": "Drops / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"thresholds": {
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 0.01
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 0.1
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "gRPC Request Rate by Method (Spans)",
|
||||
"description": "###### What this is:\n*How many gRPC calls of each method the node serves per second.*\n\n###### How it's computed:\n*Per-second rate of gRPC calls over 5 minutes, grouped by method and node.*\n\n###### Reading it:\n*Non-zero only when reporting/Clio-style clients use the gRPC API.*\n\n###### Healthy range:\n*Workload-dependent; zero without gRPC traffic.*\n\n###### Watch for:\n*A single method spiking, consistent with a heavy or misbehaving gRPC consumer.*\n\n###### Source:\n[GRPCServer.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/main/GRPCServer.cpp)\n\n###### Function:\n`GRPCServerImpl::CallData::process`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 32
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (method, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Calls / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "gRPC Latency P95 by Method (Spans)",
|
||||
"description": "###### What this is:\n*The 95th-percentile latency of each gRPC method.*\n\n###### How it's computed:\n*95th-percentile of gRPC call durations over 5 minutes, grouped by method and node.*\n\n###### Reading it:\n*Lower is better; identifies slow gRPC read paths.*\n\n###### Healthy range:\n*Workload-dependent; scales with ledger data volume served.*\n\n###### Watch for:\n*A method whose latency climbs, indicating an expensive read path.*\n\n###### Source:\n[GRPCServer.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/main/GRPCServer.cpp)\n\n###### Function:\n`GRPCServerImpl::CallData::process`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 32
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, method, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m])))",
|
||||
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "gRPC Error Rate by Status (Spans)",
|
||||
"description": "###### What this is:\n*gRPC call rate broken down by outcome status (success or error).*\n\n###### How it's computed:\n*Per-second rate of gRPC calls over 5 minutes, grouped by status and node.*\n\n###### Reading it:\n*Success should dominate; the error rate should stay low.*\n\n###### Healthy range:\n*Workload-dependent; errors near the floor.*\n\n###### Watch for:\n*A rising error rate, indicating gRPC clients hitting failures.*\n\n###### Source:\n[GRPCServer.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/main/GRPCServer.cpp)\n\n###### Function:\n`GRPCServerImpl::CallData::process`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 40
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (grpc_status, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[$__rate_interval]))",
|
||||
"legendFormat": "{{grpc_status}} [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Calls / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Pathfinding Compute Duration (Spans)",
|
||||
"description": "###### What this is:\n*The 95th-percentile time to compute paths for a single request.*\n\n###### How it's computed:\n*95th-percentile of path-computation durations over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; complements the fast/full pathfinding timers with span-level detail.*\n\n###### Healthy range:\n*Workload-dependent; grows with order-book depth and request complexity.*\n\n###### Watch for:\n*A rising trend under pathfinding load, indicating expensive path computation.*\n\n###### Source:\n[PathRequest.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/PathRequest.cpp)\n\n###### Function:\n`PathRequest::doUpdate`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 40
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.compute\"}[5m])))",
|
||||
"legendFormat": "P95 Compute [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ms",
|
||||
"custom": {
|
||||
"axisLabel": "Duration (ms)",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Pathfinding Request & Discovery Rate (Spans)",
|
||||
"description": "###### What this is:\n*The rate of client path requests versus path-discovery passes.*\n\n###### How it's computed:\n*Per-second rates of path requests and discovery passes over 5 minutes, per node.*\n\n###### Reading it:\n*Discovery cost tracks request demand; useful for subscription-heavy nodes.*\n\n###### Healthy range:\n*Workload-dependent; both zero without pathfinding clients.*\n\n###### Watch for:\n*Discovery rate climbing out of proportion to requests, a cost driver for subscription-heavy nodes.*\n\n###### Source:\n[PathFind.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/handlers/orderbook/PathFind.cpp) · [PathRequest.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/PathRequest.cpp)\n\n###### Function:\n`doPathFind ; PathRequest::findPaths`",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 48
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.request\"}[$__rate_interval]))",
|
||||
"legendFormat": "Requests / Sec [{{service_instance_id}}]"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"pathfind.discover\"}[$__rate_interval]))",
|
||||
"legendFormat": "Discoveries / Sec [{{service_instance_id}}]"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"unit": "ops",
|
||||
"custom": {
|
||||
"axisLabel": "Operations / Sec",
|
||||
"spanNulls": true,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
}
|
||||
}
|
||||
],
|
||||
"schemaVersion": 39,
|
||||
"tags": ["rpc", "pathfinding"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "DS_PROMETHEUS",
|
||||
"type": "datasource",
|
||||
"label": "Prometheus",
|
||||
"query": "prometheus",
|
||||
"regex": "",
|
||||
"current": {
|
||||
"text": "grafanacloud-ripplex-prometheus",
|
||||
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
||||
},
|
||||
"hide": 0,
|
||||
"refresh": 1,
|
||||
"includeAll": false,
|
||||
"multi": false,
|
||||
"options": []
|
||||
},
|
||||
{
|
||||
"name": "service_name",
|
||||
"label": "Service Name",
|
||||
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
||||
"type": "query",
|
||||
"query": "label_values(service_name)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "xrpld",
|
||||
"value": "xrpld"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "deployment_environment",
|
||||
"label": "Environment",
|
||||
"description": "Filter by deployment tier [local / ci / test / prod]",
|
||||
"type": "query",
|
||||
"query": "label_values(deployment_environment)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_network_type",
|
||||
"label": "Network",
|
||||
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_network_type)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_work_item",
|
||||
"label": "Work Item",
|
||||
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_work_item)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_branch",
|
||||
"label": "Branch",
|
||||
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_branch)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "xrpl_node_role",
|
||||
"label": "Node Role",
|
||||
"description": "Filter by node role (validator / peer)",
|
||||
"type": "query",
|
||||
"query": "label_values(xrpl_node_role)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "node",
|
||||
"label": "Node",
|
||||
"description": "Filter by rippled node (service.instance.id)",
|
||||
"type": "query",
|
||||
"query": "label_values(target_info, service_instance_id)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
},
|
||||
{
|
||||
"name": "grpc_method",
|
||||
"label": "gRPC Method",
|
||||
"description": "Filter by gRPC method (GetLedger, GetLedgerData, GetLedgerDiff, GetLedgerEntry)",
|
||||
"type": "query",
|
||||
"query": "label_values(span_calls_total{span_name=~\"grpc\\\\..*\"}, method)",
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"allValue": ".*",
|
||||
"current": {
|
||||
"text": "All",
|
||||
"value": "$__all"
|
||||
},
|
||||
"multi": true,
|
||||
"refresh": 2,
|
||||
"sort": 1
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-1h",
|
||||
"to": "now"
|
||||
},
|
||||
"title": "RPC & Pathfinding",
|
||||
"uid": "rpc-pathfinding",
|
||||
"refresh": "10s"
|
||||
}
|
||||
1079
docker/telemetry/grafanacloud/rpc-performance.json
Normal file
1079
docker/telemetry/grafanacloud/rpc-performance.json
Normal file
File diff suppressed because it is too large
Load Diff
1084
docker/telemetry/grafanacloud/transaction-overview.json
Normal file
1084
docker/telemetry/grafanacloud/transaction-overview.json
Normal file
File diff suppressed because it is too large
Load Diff
1108
docker/telemetry/grafanacloud/validator-health.json
Normal file
1108
docker/telemetry/grafanacloud/validator-health.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user