diff --git a/docker/telemetry/grafana/dashboards/ledger-data-sync.json b/docker/telemetry/grafana/dashboards/ledger-data-sync.json index c162f99857..5dc3165001 100644 --- a/docker/telemetry/grafana/dashboards/ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/ledger-data-sync.json @@ -11,7 +11,7 @@ "panels": [ { "title": "Ledger Data Exchange (Bytes In)", - "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 counters, shown at their latest cumulative value 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)`", + "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, @@ -30,62 +30,62 @@ "datasource": { "type": "prometheus" }, - "expr": "ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Ledger Data Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ledger Data Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "TX Set Candidate Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Set Candidate Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "TX Node Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Node Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "Account State Node Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Account State Node Share [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes In", "spanNulls": true, @@ -99,7 +99,7 @@ }, { "title": "Ledger Share/Get Traffic (Bytes)", - "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 counters at their latest value 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)`", + "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, @@ -118,62 +118,62 @@ "datasource": { "type": "prometheus" }, - "expr": "ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ledger Share In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ledger Get In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "TX Set Candidate Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Set Candidate Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "TX Node Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Node Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "Account State Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Account State Get [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes In", "spanNulls": true, @@ -187,7 +187,7 @@ }, { "title": "GetObject Traffic by Type (Bytes In)", - "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 counters at their latest value 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)`", + "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, @@ -206,62 +206,62 @@ "datasource": { "type": "prometheus" }, - "expr": "getobject_ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Ledger Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ledger Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transaction_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Transaction Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Transaction Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "TX Node Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Node Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "Account State Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Account State Share [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes In", "spanNulls": true, @@ -275,7 +275,7 @@ }, { "title": "GetObject Aggregate & Special Types (Bytes In)", - "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 counters at their latest value 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)`", + "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, @@ -294,55 +294,55 @@ "datasource": { "type": "prometheus" }, - "expr": "getobject_cas_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "CAS Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "CAS Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Fetch Pack Share [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Fetch Pack Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transactions_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Transactions Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Aggregate Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Aggregate Share [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes In", "spanNulls": true, @@ -356,7 +356,7 @@ }, { "title": "GetObject Messages by Type", - "description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message counters at their latest value per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -375,55 +375,55 @@ "datasource": { "type": "prometheus" }, - "expr": "getobject_ledger_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_ledger_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ledger Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transaction_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Transaction Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transaction_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_transaction_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Node Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "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\"}", + "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\"}[$__rate_interval])", "legendFormat": "Account State Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_cas_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_cas_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "CAS Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_fetch_pack_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Fetch Pack Get [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "getobject_transactions_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(getobject_transactions_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Transactions Get [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages In", "spanNulls": true, diff --git a/docker/telemetry/grafana/dashboards/network-traffic.json b/docker/telemetry/grafana/dashboards/network-traffic.json index ae3860a1f1..16483a871f 100644 --- a/docker/telemetry/grafana/dashboards/network-traffic.json +++ b/docker/telemetry/grafana/dashboards/network-traffic.json @@ -57,7 +57,7 @@ }, { "title": "Peer Disconnects", - "description": "###### What this is:\n*Cumulative count of peer connections that have dropped.*\n\n###### How it's computed:\n*Running total of disconnect events per node.*\n\n###### Reading it:\n*A flat or slowly rising line is normal; the slope matters more than the absolute value.*\n\n###### Healthy range:\n*workload-dependent; slow, steady growth.*\n\n###### Watch for:\n*Sharp step-ups in the slope (network instability, resource exhaustion, or many peers dropping the node at once).*\n\n###### Source:\n[OverlayImpl.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.h)\n\n###### Function:\n`OverlayImpl::Stats ctor`", + "description": "###### What this is:\n*Peer connections that dropped, as a per-interval increase.*\n\n###### How it's computed:\n*Disconnect events per rate-interval, per node.*\n\n###### Reading it:\n*A flat or slowly rising line is normal; the slope matters more than the absolute value.*\n\n###### Healthy range:\n*workload-dependent; slow, steady growth.*\n\n###### Watch for:\n*Sharp step-ups in the slope (network instability, resource exhaustion, or many peers dropping the node at once).*\n\n###### Source:\n[OverlayImpl.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.h)\n\n###### Function:\n`OverlayImpl::Stats ctor`", "type": "timeseries", "gridPos": { "h": 8, @@ -76,7 +76,7 @@ "datasource": { "type": "prometheus" }, - "expr": "overlay_peer_disconnects{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "increase(overlay_peer_disconnects{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Disconnects [{{service_instance_id}}]" } ], @@ -84,7 +84,7 @@ "defaults": { "unit": "none", "custom": { - "axisLabel": "Disconnects", + "axisLabel": "Disconnects per interval", "spanNulls": true, "insertNulls": false, "showPoints": "auto", @@ -96,7 +96,7 @@ }, { "title": "Total Network Bytes", - "description": "###### What this is:\n*Total bytes received and sent across all peer connections.*\n\n###### How it's computed:\n*Current cumulative in/out byte totals per node.*\n\n###### Reading it:\n*Overall bandwidth footprint; in and out usually track network activity together.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Sudden sustained jumps not matched by ledger or transaction activity (relay storms or a noisy peer).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Total bytes received and sent across all peer connections.*\n\n###### How it's computed:\n*Per-second in/out byte rate per node.*\n\n###### Reading it:\n*Overall bandwidth footprint; in and out usually track network activity together.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Sudden sustained jumps not matched by ledger or transaction activity (relay storms or a noisy peer).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -115,20 +115,20 @@ "datasource": { "type": "prometheus" }, - "expr": "total_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(total_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Bytes In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "total_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(total_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Bytes Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes", "spanNulls": true, @@ -142,7 +142,7 @@ }, { "title": "Total Network Messages", - "description": "###### What this is:\n*Total messages received and sent across all peer connections.*\n\n###### How it's computed:\n*Current cumulative in/out message totals per node.*\n\n###### Reading it:\n*Overall message throughput of the overlay; complements the byte totals.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Message count climbing far faster than bytes (many tiny messages, possible flooding).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Total messages received and sent across all peer connections.*\n\n###### How it's computed:\n*Per-second in/out message rate per node.*\n\n###### Reading it:\n*Overall message throughput of the overlay; complements the byte totals.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Message count climbing far faster than bytes (many tiny messages, possible flooding).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -161,20 +161,20 @@ "datasource": { "type": "prometheus" }, - "expr": "total_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(total_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Messages In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "total_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(total_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Messages Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages", "spanNulls": true, @@ -188,7 +188,7 @@ }, { "title": "Transaction Traffic", - "description": "###### What this is:\n*Transaction relay messages in and out, plus duplicate transaction messages received.*\n\n###### How it's computed:\n*Current message counts for the transaction and transaction-duplicate categories.*\n\n###### Reading it:\n*In/out rise with network transaction volume; duplicates are transactions the node already had.*\n\n###### Healthy range:\n*workload-dependent; duplicates a modest fraction of inbound.*\n\n###### Watch for:\n*Duplicate inbound approaching or exceeding unique inbound (redundant relay), or a sharp spike suggesting transaction flooding.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Transaction relay messages in and out, plus duplicate transaction messages received.*\n\n###### How it's computed:\n*Per-second message rate for the transaction and transaction-duplicate categories.*\n\n###### Reading it:\n*In/out rise with network transaction volume; duplicates are transactions the node already had.*\n\n###### Healthy range:\n*workload-dependent; duplicates a modest fraction of inbound.*\n\n###### Watch for:\n*Duplicate inbound approaching or exceeding unique inbound (redundant relay), or a sharp spike suggesting transaction flooding.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -207,27 +207,27 @@ "datasource": { "type": "prometheus" }, - "expr": "transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Messages In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Messages Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "transactions_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(transactions_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "TX Duplicate In [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages", "spanNulls": true, @@ -241,7 +241,7 @@ }, { "title": "Proposal Traffic", - "description": "###### What this is:\n*Consensus proposal messages in/out, plus untrusted and duplicate proposal messages received.*\n\n###### How it's computed:\n*Current message counts for the proposal, proposal-untrusted, and proposal-duplicate categories.*\n\n###### Reading it:\n*Trusted in/out track consensus rounds; untrusted come from validators not on this node's trusted list.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*High untrusted (trusted-list misconfiguration) or high duplicates (inefficient relay or proposal spam).*\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)`", + "description": "###### What this is:\n*Consensus proposal messages in/out, plus untrusted and duplicate proposal messages received.*\n\n###### How it's computed:\n*Per-second message rate for the proposal, proposal-untrusted, and proposal-duplicate categories.*\n\n###### Reading it:\n*Trusted in/out track consensus rounds; untrusted come from validators not on this node's trusted list.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*High untrusted (trusted-list misconfiguration) or high duplicates (inefficient relay or proposal spam).*\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, @@ -260,34 +260,34 @@ "datasource": { "type": "prometheus" }, - "expr": "proposals_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(proposals_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Proposals In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "proposals_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(proposals_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Proposals Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "proposals_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(proposals_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Untrusted In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "proposals_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(proposals_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Duplicate In [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages", "spanNulls": true, @@ -301,7 +301,7 @@ }, { "title": "Validation Traffic", - "description": "###### What this is:\n*Validation messages in/out, plus untrusted and duplicate validation messages received.*\n\n###### How it's computed:\n*Current message counts for the validation, validation-untrusted, and validation-duplicate categories.*\n\n###### Reading it:\n*Trusted validations should arrive steadily each ledger; untrusted come from non-trusted validators.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*Rising untrusted or duplicate validations (trusted-list health issues or validation spam).*\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)`", + "description": "###### What this is:\n*Validation messages in/out, plus untrusted and duplicate validation messages received.*\n\n###### How it's computed:\n*Per-second message rate for the validation, validation-untrusted, and validation-duplicate categories.*\n\n###### Reading it:\n*Trusted validations should arrive steadily each ledger; untrusted come from non-trusted validators.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*Rising untrusted or duplicate validations (trusted-list health issues or validation spam).*\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, @@ -320,34 +320,34 @@ "datasource": { "type": "prometheus" }, - "expr": "validations_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validations_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Validations In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "validations_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validations_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Validations Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "validations_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validations_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Untrusted In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "validations_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validations_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Duplicate In [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages", "spanNulls": true, @@ -361,7 +361,7 @@ }, { "title": "Overlay Traffic by Category (Bytes In)", - "description": "###### What this is:\n*Top overlay traffic categories ranked by inbound bytes, excluding the all-traffic total.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value per node.*\n\n###### Reading it:\n*Shows which message types dominate receive bandwidth right now.*\n\n###### Healthy range:\n*workload-dependent; transactions, proposals, and validations typically lead on a synced node.*\n\n###### Watch for:\n*A fetch or ledger-data category topping the list (sync activity) or an unexpected category 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)`", + "description": "###### What this is:\n*Top overlay traffic categories ranked by inbound bytes, excluding the all-traffic total.*\n\n###### How it's computed:\n*Top categories by inbound byte rate per node.*\n\n###### Reading it:\n*Shows which message types dominate receive bandwidth right now.*\n\n###### Healthy range:\n*workload-dependent; transactions, proposals, and validations typically lead on a synced node.*\n\n###### Watch for:\n*A fetch or ledger-data category topping the list (sync activity) or an unexpected category 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": "bargauge", "gridPos": { "h": 8, @@ -380,13 +380,13 @@ "datasource": { "type": "prometheus" }, - "expr": "topk(10, {service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"})", + "expr": "topk(10, rate({service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"}[$__rate_interval]))", "legendFormat": "{{__name__}} [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes" + "unit": "Bps" }, "overrides": [ { diff --git a/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json b/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json index 0333f10357..eec4c908f6 100644 --- a/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json +++ b/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json @@ -11,7 +11,7 @@ "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*Current message counts 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)`", + "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, @@ -30,48 +30,48 @@ "datasource": { "type": "prometheus" }, - "expr": "squelch_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(squelch_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Squelch In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "squelch_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(squelch_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Squelch Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "squelch_suppressed_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(squelch_suppressed_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Suppressed In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "squelch_suppressed_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(squelch_suppressed_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Suppressed Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "squelch_ignored_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(squelch_ignored_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ignored In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "squelch_ignored_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(squelch_ignored_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Ignored Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages", "spanNulls": true, @@ -85,7 +85,7 @@ }, { "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*Current in/out byte counts 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)`", + "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, @@ -104,48 +104,48 @@ "datasource": { "type": "prometheus" }, - "expr": "overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Base Overhead In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "overhead_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(overhead_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Base Overhead Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Cluster In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "overhead_cluster_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(overhead_cluster_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Cluster Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Manifest In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "overhead_manifest_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(overhead_manifest_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Manifest Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes", "spanNulls": true, @@ -159,7 +159,7 @@ }, { "title": "Validator List Traffic", - "description": "###### What this is:\n*Bytes and messages exchanged distributing validator lists (trusted-list configuration) between peers.*\n\n###### How it's computed:\n*Current in/out byte and message counts for the validator-lists category.*\n\n###### Reading it:\n*Bursts when lists update or new peers connect; quiet otherwise.*\n\n###### Healthy range:\n*workload-dependent; occasional bursts.*\n\n###### Watch for:\n*Continuous high volume (repeated list re-fetching or churn).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Bytes and messages exchanged distributing validator lists (trusted-list configuration) between peers.*\n\n###### How it's computed:\n*Per-second in/out byte and message rate for the validator-lists category.*\n\n###### Reading it:\n*Bursts when lists update or new peers connect; quiet otherwise.*\n\n###### Healthy range:\n*workload-dependent; occasional bursts.*\n\n###### Watch for:\n*Continuous high volume (repeated list re-fetching or churn).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -178,34 +178,34 @@ "datasource": { "type": "prometheus" }, - "expr": "validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Bytes In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "validator_lists_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validator_lists_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Bytes Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "validator_lists_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validator_lists_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Messages In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "validator_lists_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(validator_lists_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Messages Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Count", "spanNulls": true, @@ -227,7 +227,7 @@ }, { "id": "unit", - "value": "decbytes" + "value": "binBps" } ] } @@ -236,7 +236,7 @@ }, { "title": "Set Get/Share Traffic (Bytes)", - "description": "###### What this is:\n*Transaction-set fetch (get) and share bytes exchanged during ledger close.*\n\n###### How it's computed:\n*Current in/out byte counts for the set-get and set-share categories.*\n\n###### Reading it:\n*Some exchange each ledger is normal as peers reconcile transaction sets.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High set-get (peers frequently missing transaction sets: possible sync delays).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Transaction-set fetch (get) and share bytes exchanged during ledger close.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the set-get and set-share categories.*\n\n###### Reading it:\n*Some exchange each ledger is normal as peers reconcile transaction sets.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High set-get (peers frequently missing transaction sets: possible sync delays).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -255,34 +255,34 @@ "datasource": { "type": "prometheus" }, - "expr": "set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Set Get In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "set_get_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(set_get_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Set Get Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Set Share In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "set_share_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(set_share_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Set Share Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes", "spanNulls": true, @@ -296,7 +296,7 @@ }, { "title": "Have/Requested Transactions (Messages)", - "description": "###### What this is:\n*Transaction-availability messages: advertisements that a peer has certain transactions, and explicit requests for transaction data.*\n\n###### How it's computed:\n*Current in/out message counts for the have-transactions and requested-transactions categories.*\n\n###### Reading it:\n*Compare requested versus have to gauge how well transactions are propagating.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Requested far exceeding have (peers behind on transaction propagation).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Transaction-availability messages: advertisements that a peer has certain transactions, and explicit requests for transaction data.*\n\n###### How it's computed:\n*Per-second in/out message rate for the have-transactions and requested-transactions categories.*\n\n###### Reading it:\n*Compare requested versus have to gauge how well transactions are propagating.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Requested far exceeding have (peers behind on transaction propagation).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -315,34 +315,34 @@ "datasource": { "type": "prometheus" }, - "expr": "have_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(have_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Have TX In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "have_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(have_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Have TX Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "requested_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(requested_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Requested TX In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "requested_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(requested_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Requested TX Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "short", + "unit": "cps", "custom": { "axisLabel": "Messages", "spanNulls": true, @@ -433,7 +433,7 @@ }, { "title": "Proof Path Traffic", - "description": "###### What this is:\n*Proof-path request/response bytes used to verify individual ledger entries without downloading the whole ledger.*\n\n###### How it's computed:\n*Current in/out byte counts for the proof-path request and response categories.*\n\n###### Reading it:\n*Rises when peers verify specific state, often during catch-up.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High sustained request volume (heavy state-verification load).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Proof-path request/response bytes used to verify individual ledger entries without downloading the whole ledger.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the proof-path request and response categories.*\n\n###### Reading it:\n*Rises when peers verify specific state, often during catch-up.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High sustained request volume (heavy state-verification load).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -452,34 +452,34 @@ "datasource": { "type": "prometheus" }, - "expr": "proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Request Bytes In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "proof_path_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Request Bytes Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Response Bytes In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "proof_path_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Response Bytes Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes", "spanNulls": true, @@ -493,7 +493,7 @@ }, { "title": "Replay Delta Traffic", - "description": "###### What this is:\n*Replay-delta request/response bytes used to efficiently replay ledger state changes during catch-up.*\n\n###### How it's computed:\n*Current in/out byte counts for the replay-delta request and response categories.*\n\n###### Reading it:\n*Active during catch-up and replay; quiet when synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous replay traffic (node repeatedly replaying rather than staying current).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", + "description": "###### What this is:\n*Replay-delta request/response bytes used to efficiently replay ledger state changes during catch-up.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the replay-delta request and response categories.*\n\n###### Reading it:\n*Active during catch-up and replay; quiet when synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous replay traffic (node repeatedly replaying rather than staying current).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`", "type": "timeseries", "gridPos": { "h": 8, @@ -512,34 +512,34 @@ "datasource": { "type": "prometheus" }, - "expr": "replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Request Bytes In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "replay_delta_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Request Bytes Out [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "expr": "rate(replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])", "legendFormat": "Response Bytes In [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "replay_delta_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}", + "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\"}[$__rate_interval])", "legendFormat": "Response Bytes Out [{{service_instance_id}}]" } ], "fieldConfig": { "defaults": { - "unit": "decbytes", + "unit": "Bps", "custom": { "axisLabel": "Bytes", "spanNulls": true, diff --git a/docker/telemetry/grafana/dashboards/rpc-pathfinding.json b/docker/telemetry/grafana/dashboards/rpc-pathfinding.json index 38e5525697..33c8a91b15 100644 --- a/docker/telemetry/grafana/dashboards/rpc-pathfinding.json +++ b/docker/telemetry/grafana/dashboards/rpc-pathfinding.json @@ -82,7 +82,7 @@ }, { "title": "RPC Response Size", - "description": "###### 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 5 minutes, 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`", + "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, diff --git a/docker/telemetry/grafana/dashboards/transaction-overview.json b/docker/telemetry/grafana/dashboards/transaction-overview.json index 82bcbeb4a1..870c882187 100644 --- a/docker/telemetry/grafana/dashboards/transaction-overview.json +++ b/docker/telemetry/grafana/dashboards/transaction-overview.json @@ -239,7 +239,7 @@ }, { "title": "Transaction Processing Rate", - "description": "###### What this is:\n*Transactions entering the processing pipeline versus raw transactions arriving from peers.*\n\n###### How it's computed:\n*Per-second rates of processed transactions and received peer transactions over 5 minutes, per node.*\n\n###### Reading it:\n*Received sits above processed; the difference is deduplicated relay traffic.*\n\n###### Healthy range:\n*Workload-dependent; both scale with network volume.*\n\n###### Watch for:\n*A receive rate spiking well above processing, consistent with relay flooding.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp) · [PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`NetworkOPsImp::processTransaction ; PeerImp::handleTransaction`", + "description": "###### What this is:\n*Transactions entering the processing pipeline versus raw transactions arriving from peers.*\n\n###### How it's computed:\n*Per-second rates of processed transactions and received peer transactions over 5 minutes, per node.*\n\n###### Reading it:\n*Received sits above processed; the difference is deduplicated relay traffic.*\n\n###### Healthy range:\n*Workload-dependent; both scale with network volume.*\n\n###### Watch for:\n*A receive rate spiking well above processing, consistent with relay flooding.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp) \u00b7 [PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`NetworkOPsImp::processTransaction ; PeerImp::handleTransaction`", "type": "timeseries", "gridPos": { "h": 8, @@ -351,47 +351,6 @@ }, "id": 8 }, - { - "title": "Peer Transaction Receive Rate", - "description": "###### What this is:\n*How many transaction messages arrive from network peers per second.*\n\n###### How it's computed:\n*Per-second rate of received peer transactions over 5 minutes, per node.*\n\n###### Reading it:\n*Reflects network-wide transaction volume reaching this node.*\n\n###### Healthy range:\n*Workload-dependent; tracks overall network activity.*\n\n###### Watch for:\n*A sharp spike above baseline, consistent with network-wide volume surges or peer flooding.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::handleTransaction`", - "type": "timeseries", - "gridPos": { - "h": 8, - "w": 12, - "x": 0, - "y": 44 - }, - "options": { - "tooltip": { - "mode": "multi", - "sort": "desc", - "maxHeight": 500 - } - }, - "targets": [ - { - "datasource": { - "type": "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=~\"$service_name\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[$__rate_interval]))", - "legendFormat": "tx.receive / Sec [{{service_instance_id}}]" - } - ], - "fieldConfig": { - "defaults": { - "unit": "ops", - "custom": { - "axisLabel": "Transactions / Sec", - "spanNulls": true, - "insertNulls": false, - "showPoints": "auto", - "pointSize": 3 - } - }, - "overrides": [] - }, - "id": 9 - }, { "title": "Transactor Duration by Type (p95)", "description": "###### What this is:\n*The 95th-percentile execution time of the core transactor step, by transaction type.*\n\n###### How it's computed:\n*95th-percentile of transactor durations over 5 minutes, grouped by type and node.*\n\n###### Reading it:\n*Lower is better; reveals which types are most expensive to execute.*\n\n###### Healthy range:\n*Sub-millisecond to a few ms for most types; workload-dependent.*\n\n###### Watch for:\n*A type whose execution time grows, indicating expensive logic or ledger contention.*\n\n###### Source:\n[Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`Transactor::operator()`", @@ -440,7 +399,7 @@ }, { "title": "Tx Apply Pipeline Rate by Stage", - "description": "###### What this is:\n*How many transactions pass through each apply-pipeline stage (preflight, preclaim, apply) per second.*\n\n###### How it's computed:\n*Per-second rate over 5 minutes, grouped by pipeline stage and node.*\n\n###### Reading it:\n*Stages should step down slightly as invalid transactions are filtered out.*\n\n###### Healthy range:\n*Workload-dependent; preflight highest, apply lowest.*\n\n###### Watch for:\n*A large drop between stages, showing where most transactions are being rejected.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", + "description": "###### What this is:\n*How many transactions pass through each apply-pipeline stage (preflight, preclaim, apply) per second.*\n\n###### How it's computed:\n*Per-second rate over 5 minutes, grouped by pipeline stage and node.*\n\n###### Reading it:\n*Stages should step down slightly as invalid transactions are filtered out.*\n\n###### Healthy range:\n*Workload-dependent; preflight highest, apply lowest.*\n\n###### Watch for:\n*A large drop between stages, showing where most transactions are being rejected.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", "type": "timeseries", "gridPos": { "h": 8, @@ -486,7 +445,7 @@ }, { "title": "Tx Apply Pipeline Latency by Stage (p95)", - "description": "###### What this is:\n*The 95th-percentile duration of each apply-pipeline stage.*\n\n###### How it's computed:\n*95th-percentile of per-stage durations over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Lower is better; isolates which stage dominates processing time.*\n\n###### Healthy range:\n*Each stage typically sub-millisecond to a few ms; workload-dependent.*\n\n###### Watch for:\n*One stage's latency rising, pinpointing the bottleneck in transaction handling.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", + "description": "###### What this is:\n*The 95th-percentile duration of each apply-pipeline stage.*\n\n###### How it's computed:\n*95th-percentile of per-stage durations over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Lower is better; isolates which stage dominates processing time.*\n\n###### Healthy range:\n*Each stage typically sub-millisecond to a few ms; workload-dependent.*\n\n###### Watch for:\n*One stage's latency rising, pinpointing the bottleneck in transaction handling.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", "type": "timeseries", "gridPos": { "h": 8, @@ -532,7 +491,7 @@ }, { "title": "Tx Apply Pipeline Failure Rate by Stage", - "description": "###### What this is:\n*How many transactions fail at each apply-pipeline stage per second.*\n\n###### How it's computed:\n*Per-second rate of non-success outcomes over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Shows whether rejections concentrate in preflight, preclaim, or apply.*\n\n###### Healthy range:\n*Workload-dependent; a modest background of expected rejections is normal.*\n\n###### Watch for:\n*A failure spike concentrated in one stage, consistent with malformed or spam submissions.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", + "description": "###### What this is:\n*How many transactions fail at each apply-pipeline stage per second.*\n\n###### How it's computed:\n*Per-second rate of non-success outcomes over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Shows whether rejections concentrate in preflight, preclaim, or apply.*\n\n###### Healthy range:\n*Workload-dependent; a modest background of expected rejections is normal.*\n\n###### Watch for:\n*A failure spike concentrated in one stage, consistent with malformed or spam submissions.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", "type": "timeseries", "gridPos": { "h": 8, @@ -578,7 +537,7 @@ }, { "title": "Tx Apply Pipeline Latency by Type and Stage (p95)", - "description": "###### What this is:\n*The 95th-percentile stage duration broken down by both transaction type and pipeline stage.*\n\n###### How it's computed:\n*95th-percentile durations over 5 minutes, grouped by type and stage; higher cardinality than the by-stage view.*\n\n###### Reading it:\n*Lower is better; shows which stage dominates each type's latency.*\n\n###### Healthy range:\n*Workload-dependent; most type/stage pairs sub-millisecond to a few ms.*\n\n###### Watch for:\n*A specific type/stage combination rising sharply, pinpointing a costly path.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", + "description": "###### What this is:\n*The 95th-percentile stage duration broken down by both transaction type and pipeline stage.*\n\n###### How it's computed:\n*95th-percentile durations over 5 minutes, grouped by type and stage; higher cardinality than the by-stage view.*\n\n###### Reading it:\n*Lower is better; shows which stage dominates each type's latency.*\n\n###### Healthy range:\n*Workload-dependent; most type/stage pairs sub-millisecond to a few ms.*\n\n###### Watch for:\n*A specific type/stage combination rising sharply, pinpointing a costly path.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`", "type": "timeseries", "gridPos": { "h": 8, @@ -933,7 +892,7 @@ { "name": "node", "label": "Node", - "description": "Filter by rippled node (service.instance.id — e.g. Node-1)", + "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)", "type": "query", "query": "label_values(span_calls_total, service_instance_id)", "datasource": { diff --git a/docs/telemetry-runbook.md b/docs/telemetry-runbook.md index 6d804c822a..f1529f2436 100644 --- a/docs/telemetry-runbook.md +++ b/docs/telemetry-runbook.md @@ -590,8 +590,8 @@ The `OTelCollector` implementation exports metrics via OTLP/HTTP to the same OTe | `peer_finder_active_outbound_peers` | PeerfinderManager.cpp:215 | Active outbound peer connections | | `overlay_peer_disconnects` | OverlayImpl.h:557 | Peer disconnect count | | `job_count` | JobQueue.cpp:26 | Current job queue depth | -| `{category}_bytes_in/Out` | OverlayImpl.h:535 | Overlay traffic bytes per category (57 categories) | -| `{category}_messages_in/Out` | OverlayImpl.h:535 | Overlay traffic messages per category | +| `{category}_bytes_in/out` | OverlayImpl.h:535 | Overlay traffic bytes per category (57 categories) | +| `{category}_messages_in/out` | OverlayImpl.h:535 | Overlay traffic messages per category | #### OTel MetricsRegistry Gauges @@ -742,16 +742,16 @@ Ten dashboards are pre-provisioned in `docker/telemetry/grafana/dashboards/`: ### Transaction Overview (`transaction-overview`) -| Panel | Type | PromQL | Labels Used | -| --------------------------------- | ---------- | --------------------------------------------------------------------- | ------------- | -| Transaction Processing Rate | timeseries | `rate(span_calls_total{span_name="tx.process"}[5m])` and `tx.receive` | `span_name` | -| Transaction Processing Latency | timeseries | `histogram_quantile(0.95 / 0.50, ... {span_name="tx.process"})` | — | -| Transaction Path Distribution | piechart | `sum by (local) (rate(span_calls_total{span_name="tx.process"}[5m]))` | `local` | -| Transaction Receive vs Suppressed | timeseries | `rate(span_calls_total{span_name="tx.receive"}[5m])` | — | -| TX Processing Duration Heatmap | heatmap | `tx.process` histogram buckets | `le` | -| TX Apply Duration per Ledger | timeseries | p95/p50 of `tx.apply` | — | -| Peer TX Receive Rate | timeseries | `tx.receive` rate | — | -| TX Apply Failed Rate | stat | `tx.apply` with `STATUS_CODE_ERROR` | `status_code` | +| Panel | Type | PromQL | Labels Used | +| --------------------------------- | ---------- | -------------------------------------------------------------------------------------------- | --------------------- | +| Transaction Processing Rate | timeseries | `rate(span_calls_total{span_name="tx.process"}[5m])` and `tx.receive` | `span_name` | +| Transaction Processing Latency | timeseries | `histogram_quantile(0.95 / 0.50, ... {span_name="tx.process"})` | — | +| Transaction Path Distribution | piechart | `sum by (local) (rate(span_calls_total{span_name="tx.process"}[5m]))` | `local` | +| Transaction Receive vs Suppressed | timeseries | `rate(span_calls_total{span_name="tx.receive"}[5m])` | — | +| TX Processing Duration Heatmap | heatmap | `tx.process` histogram buckets | `le` | +| TX Apply Duration per Ledger | timeseries | p95/p50 of `tx.apply` | — | +| Peer TX Receive Rate | timeseries | `tx.receive` rate | — | +| TX Apply Failed Rate | stat | `rate(span_calls_total{span_name="tx.transactor",stage="apply",ter_result!~"tesSUCCESS\|"})` | `stage`, `ter_result` | ### Consensus Health (`consensus-health`) @@ -794,47 +794,47 @@ Requires `trace_peer=1` in the `[telemetry]` config section. ### Node Health -- System Metrics (`node-health`) -| Panel | Type | PromQL | Labels Used | -| -------------------------------------- | ---------- | --------------------------------------------------------- | ---------------- | -| Validated Ledger Age | stat | `ledgermaster_validated_ledger_age` | — | -| Published Ledger Age | stat | `ledgermaster_published_ledger_age` | — | -| Operating Mode Duration | timeseries | `state_accounting_*_duration` | — | -| Operating Mode Transitions | timeseries | `state_accounting_*_transitions` | — | -| I/O Latency | timeseries | `histogram_quantile(0.95, ios_latency_bucket)` | — | -| Job Queue Depth | timeseries | `job_count` | — | -| Ledger Fetch Rate | stat | `rate(ledger_fetches[5m])` | — | -| Ledger History Mismatches | stat | `rate(ledger_history_mismatch[5m])` | — | -| Key Jobs Execution Time | timeseries | `acceptledger{quantile="$quantile"}` (+ 10 more key jobs) | `quantile` | -| Key Jobs Dequeue Wait Time | timeseries | `acceptledger_q{quantile="$quantile"}` (+ 10 more) | `quantile` | -| FullBelowCache Size | timeseries | `node_family_full_below_cache_size` | — | -| FullBelowCache Hit Rate | gauge | `node_family_full_below_cache_hit_rate` | — | -| Ledger Publish Gap | stat | `Published_Ledger_Age - Validated_Ledger_Age` | — | -| State Duration Rate (Full vs Tracking) | timeseries | `rate(state_accounting_full_duration[5m]) / 1000000` | — | -| All Jobs Execution Time (Detail) | timeseries | `{__name__=~"", quantile="$quantile"}` | `quantile` | -| All Jobs Dequeue Wait (Detail) | timeseries | `{__name__=~"_q", quantile="$quantile"}` | `quantile` | -| Server State | stat | `server_info{metric="server_state"}` | `metric` | -| Uptime | stat | `server_info{metric="uptime"}` | `metric` | -| Peer Count | stat | `server_info{metric="peers"}` | `metric` | -| Validated Ledger Seq | stat | `server_info{metric="validated_ledger_seq"}` | `metric` | -| Build Version | stat | `build_info` | `version` | -| Complete Ledger Ranges | table | `complete_ledgers` | `bound`, `index` | -| Database Sizes | timeseries | `db_metrics{metric=~"db_kb_.*"}` | `metric` | -| Historical Fetch Rate | stat | `db_metrics{metric="historical_perminute"}` | `metric` | +| Panel | Type | PromQL | Labels Used | +| -------------------------------------- | ---------- | ---------------------------------------------------------- | ---------------- | +| Validated Ledger Age | stat | `ledgermaster_validated_ledger_age` | — | +| Published Ledger Age | stat | `ledgermaster_published_ledger_age` | — | +| Operating Mode (Time Share) | timeseries | `rate(state_accounting_X_duration) / sum(rate(all modes))` | — | +| Operating Mode Transitions | timeseries | `state_accounting_*_transitions` | — | +| I/O Latency | timeseries | `histogram_quantile(0.95, ios_latency_bucket)` | — | +| Job Queue Depth | timeseries | `job_count` | — | +| Ledger Fetch Rate | stat | `rate(ledger_fetches[5m])` | — | +| Ledger History Mismatches | stat | `rate(ledger_history_mismatch[5m])` | — | +| Key Jobs Execution Time | timeseries | `acceptledger{quantile="$quantile"}` (+ 10 more key jobs) | `quantile` | +| Key Jobs Dequeue Wait Time | timeseries | `acceptledger_q{quantile="$quantile"}` (+ 10 more) | `quantile` | +| FullBelowCache Size | timeseries | `node_family_full_below_cache_size` | — | +| FullBelowCache Hit Rate | gauge | `node_family_full_below_cache_hit_rate` | — | +| Ledger Publish Gap | stat | `Published_Ledger_Age - Validated_Ledger_Age` | — | +| State Duration Rate (Full vs Tracking) | timeseries | `rate(state_accounting_full_duration[5m]) / 1000000` | — | +| All Jobs Execution Time (Detail) | timeseries | `{__name__=~"", quantile="$quantile"}` | `quantile` | +| All Jobs Dequeue Wait (Detail) | timeseries | `{__name__=~"_q", quantile="$quantile"}` | `quantile` | +| Server State | stat | `server_info{metric="server_state"}` | `metric` | +| Uptime | stat | `server_info{metric="uptime"}` | `metric` | +| Peer Count | stat | `server_info{metric="peers"}` | `metric` | +| Validated Ledger Seq | stat | `server_info{metric="validated_ledger_seq"}` | `metric` | +| Build Version | stat | `build_info` | `version` | +| Complete Ledger Ranges | table | `complete_ledgers` | `bound`, `index` | +| Database Sizes | timeseries | `db_metrics{metric=~"db_kb_.*"}` | `metric` | +| Historical Fetch Rate | stat | `db_metrics{metric="historical_perminute"}` | `metric` | ### Network Traffic -- System Metrics (`network-traffic`) -| Panel | Type | PromQL | Labels Used | -| ------------------------------------ | ---------- | ------------------------------------ | ----------- | -| Active Peers | timeseries | `peer_finder_active_*_Peers` | — | -| Peer Disconnects | timeseries | `overlay_peer_disconnects` | — | -| Total Network Bytes | timeseries | `rate(total_bytes_in/Out[5m])` | — | -| Total Network Messages | timeseries | `total_messages_in/Out` | — | -| Transaction Traffic | timeseries | `transactions_messages_in/Out` | — | -| Proposal Traffic | timeseries | `proposals_messages_in/Out` | — | -| Validation Traffic | timeseries | `validations_messages_in/Out` | — | -| Traffic by Category | bargauge | `topk(10, *_bytes_in)` | — | -| Duplicate Traffic (Wasted Bandwidth) | timeseries | `rate(*_duplicate_bytes_in/out[5m])` | — | -| All Traffic Categories (Detail) | timeseries | `topk(15, rate(*_bytes_in[5m]))` | — | +| Panel | Type | PromQL | Labels Used | +| ------------------------------------ | ---------- | ------------------------------------------------------ | ----------- | +| Active Peers | timeseries | `peer_finder_active_*_peers` | — | +| Peer Disconnects | timeseries | `increase(overlay_peer_disconnects[$__rate_interval])` | — | +| Total Network Bytes | timeseries | `rate(total_bytes_in/out[$__rate_interval])` | — | +| Total Network Messages | timeseries | `rate(total_messages_in/out[$__rate_interval])` | — | +| Transaction Traffic | timeseries | `rate(transactions_messages_in/out[$__rate_interval])` | — | +| Proposal Traffic | timeseries | `rate(proposals_messages_in/out[$__rate_interval])` | — | +| Validation Traffic | timeseries | `rate(validations_messages_in/out[$__rate_interval])` | — | +| Traffic by Category | bargauge | `topk(10, rate(*_bytes_in[$__rate_interval]))` | — | +| Duplicate Traffic (Wasted Bandwidth) | timeseries | `rate(*_duplicate_bytes_in/out[$__rate_interval])` | — | +| All Traffic Categories (Detail) | timeseries | `topk(15, rate(*_bytes_in[$__rate_interval]))` | — | ### RPC & Pathfinding -- System Metrics (`rpc-pathfinding`)