From 0fbe7f4e4f47a7bb3588966f57447310e8cba599 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Fri, 10 Jul 2026 16:39:24 +0100 Subject: [PATCH] fix(telemetry): remove misleading stacked load-factor attribution panel Co-Authored-By: Claude Opus 4.8 (1M context) --- .../grafana/dashboards/fee-market.json | 86 ++----------------- 1 file changed, 7 insertions(+), 79 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/fee-market.json b/docker/telemetry/grafana/dashboards/fee-market.json index 72c64beb52..9f0a259da0 100644 --- a/docker/telemetry/grafana/dashboards/fee-market.json +++ b/docker/telemetry/grafana/dashboards/fee-market.json @@ -305,12 +305,12 @@ } }, { - "title": "Load Factor Attribution (Stacked Components)", - "description": "###### What this is:\n*The stacked contribution of each load-factor component (fee escalation, queue, local, net, cluster) to the effective transaction cost.*\n\n###### How it's computed:\n*Instantaneous gauge readings of each component stacked to show relative share.*\n\n###### Reading it:\n*The tallest band identifies which component is driving the fee, detail the aggregate load factor hides.*\n\n###### Healthy range:\n*Thin bands near 1.0 total under normal traffic.*\n\n###### Watch for:\n*One band dominating during a fee spike, revealing the specific driver of elevated cost.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLoadFactorGauge`", + "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": 24, + "w": 12, "x": 0, "y": 24 }, @@ -325,79 +325,7 @@ "datasource": { "type": "prometheus" }, - "expr": "load_factor_metrics{metric=\"load_factor_fee_escalation\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", - "legendFormat": "Fee Escalation [{{service_instance_id}}]" - }, - { - "datasource": { - "type": "prometheus" - }, - "expr": "load_factor_metrics{metric=\"load_factor_fee_queue\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", - "legendFormat": "Fee Queue [{{service_instance_id}}]" - }, - { - "datasource": { - "type": "prometheus" - }, - "expr": "load_factor_metrics{metric=\"load_factor_local\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", - "legendFormat": "Local [{{service_instance_id}}]" - }, - { - "datasource": { - "type": "prometheus" - }, - "expr": "load_factor_metrics{metric=\"load_factor_net\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", - "legendFormat": "Net [{{service_instance_id}}]" - }, - { - "datasource": { - "type": "prometheus" - }, - "expr": "load_factor_metrics{metric=\"load_factor_cluster\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", - "legendFormat": "Cluster [{{service_instance_id}}]" - } - ], - "fieldConfig": { - "defaults": { - "unit": "none", - "custom": { - "axisLabel": "Load Factor Multiplier", - "spanNulls": true, - "insertNulls": false, - "showPoints": "auto", - "pointSize": 3, - "stacking": { - "mode": "normal", - "group": "A" - }, - "fillOpacity": 30 - } - }, - "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 a 5-minute window.*\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": 32 - }, - "options": { - "tooltip": { - "mode": "multi", - "sort": "desc" - } - }, - "targets": [ - { - "datasource": { - "type": "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\"}[5m]))", + "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\"}[$__rate_interval]))", "legendFormat": "Expired / Sec [{{service_instance_id}}]" } ], @@ -417,13 +345,13 @@ }, { "title": "Queue Admission Rejections (Dropped)", - "description": "###### What this is:\n*Transactions refused entry to the queue, broken down by reason such as queue_full.*\n\n###### How it's computed:\n*Per-second rate of the cumulative dropped-transaction counter over a 5-minute window, split by reason.*\n\n###### Reading it:\n*Near zero is healthy; queue_full rejections mean the queue is at capacity and applying backpressure.*\n\n###### Healthy range:\n*Near 0 rejections per second.*\n\n###### Watch for:\n*A burst of queue_full drops, distinct from expiry, indicating the node is being flooded faster than it can drain.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqDropped (caller TxQ.cpp)`", + "description": "###### What this is:\n*Transactions refused entry to the queue, broken down by reason such as queue_full.*\n\n###### How it's computed:\n*Per-second rate of the cumulative dropped-transaction counter over the dashboard's rate interval, split by reason.*\n\n###### Reading it:\n*Near zero is healthy; queue_full rejections mean the queue is at capacity and applying backpressure.*\n\n###### Healthy range:\n*Near 0 rejections per second.*\n\n###### Watch for:\n*A burst of queue_full drops, distinct from expiry, indicating the node is being flooded faster than it can drain.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqDropped (caller TxQ.cpp)`", "type": "timeseries", "gridPos": { "h": 8, "w": 12, "x": 12, - "y": 32 + "y": 24 }, "options": { "tooltip": { @@ -436,7 +364,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (reason, service_instance_id) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]))", + "expr": "sum by (reason, service_instance_id) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))", "legendFormat": "{{reason}} [{{service_instance_id}}]" } ],