mirror of
https://github.com/XRPLF/rippled.git
synced 2026-08-21 06:10:58 +00:00
Merge branch 'pratik/otel-phase8-log-correlation' into pratik/otel-phase9-metric-gap-fill
# Conflicts: # docker/telemetry/grafana/dashboards/transaction-overview.json
This commit is contained in:
Pratik Mankawde
@@ -1248,7 +1248,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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=\"node_reads_duration_us\"}[$__rate_interval])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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=\"node_reads_total\"}[$__rate_interval])), 1), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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=\"node_reads_duration_us\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
@@ -1332,7 +1332,7 @@
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_reads_hit\"}[$__rate_interval])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])), 1), \"series\", \"NuDB Found Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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=\"node_reads_hit\"}[$__rate_interval])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$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=\"node_reads_total\"}[$__rate_interval])) > 0), \"series\", \"NuDB Found Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
|
||||
@@ -739,56 +739,14 @@
|
||||
},
|
||||
"id": 16
|
||||
},
|
||||
{
|
||||
"title": "Queue Bypass Ratio (Direct Apply vs Enqueue)",
|
||||
"description": "###### What this is:\n*The fraction of transactions that applied straight to the open ledger instead of being queued.*\n\n###### How it's computed:\n*Direct-apply rate divided by direct-apply plus enqueue rate over 5 minutes, per node.*\n\n###### Reading it:\n*Higher is better; near 1.0 means the network is not congested.*\n\n###### Healthy range:\n*Close to 1.0 when not congested; falls as demand exceeds capacity.*\n\n###### Watch for:\n*A falling ratio, the cleanest single signal the network has entered sustained fee escalation.*\n\n###### Keywords:\n- **Direct apply vs enqueue** *(per node)* \u2014 whether a transaction applied straight to the open ledger or was placed in the queue for a later ledger.\n- **Fee escalation** *(per node)* \u2014 the exponential rise in the open-ledger cost once the ledger exceeds its soft transaction target.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[TxQ.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/detail/TxQ.cpp)\n\n###### Function:\n`TxQ::tryDirectApply ; TxQ::apply`\n\n###### References:\n[Direct apply vs enqueue](https://xrpl.org/docs/concepts/transactions/transaction-queue) \u00b7 [Fee escalation](https://xrpl.org/docs/concepts/transactions/transaction-cost#open-ledger-cost) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#direct-apply-vs-enqueue)",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 92
|
||||
},
|
||||
"options": {
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc",
|
||||
"maxHeight": 600
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", span_name=\"txq.apply_direct\"}[$__rate_interval])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", span_name=\"txq.apply_direct\"}[$__rate_interval])) + sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", span_name=\"txq.enqueue\"}[$__rate_interval])), 1), \"series\", \"Direct-Apply Fraction\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
||||
}
|
||||
],
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
||||
"unit": "percentunit",
|
||||
"custom": {
|
||||
"axisLabel": "Bypass Fraction",
|
||||
"spanNulls": 1800000,
|
||||
"insertNulls": false,
|
||||
"showPoints": "auto",
|
||||
"pointSize": 3
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"id": 18
|
||||
},
|
||||
{
|
||||
"title": "Queue Accept (Drain) Duration per Ledger",
|
||||
"description": "###### What this is:\n*The 95th-percentile time to drain queued transactions into a newly closed ledger.*\n\n###### How it's computed:\n*95th-percentile of queue-drain durations over 5 minutes, per node.*\n\n###### Reading it:\n*Lower is better; rising time signals queue pressure at ledger close.*\n\n###### Healthy range:\n*A few milliseconds when the queue is light; workload-dependent.*\n\n###### Watch for:\n*A sustained climb, indicating a large or contended queue slowing ledger close.*\n\n###### Keywords:\n- **Queue accept (drain)** *(per node)* \u2014 moving queued transactions into a newly closed ledger; the applied share shows drain health.\n- **Ledger close** *(network event)* \u2014 the current open ledger is closed and a new closed ledger is built from the agreed transaction set.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[TxQ.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/detail/TxQ.cpp)\n\n###### Function:\n`TxQ::accept`\n\n###### References:\n[Queue accept (drain)](https://xrpl.org/docs/concepts/transactions/transaction-queue) \u00b7 [Ledger close](https://xrpl.org/docs/concepts/ledgers/open-closed-validated-ledgers) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#queue-accept-drain)",
|
||||
"type": "timeseries",
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 92
|
||||
},
|
||||
"options": {
|
||||
|
||||
Reference in New Issue
Block a user