diff --git a/docker/telemetry/grafana/dashboards/ledger-data-sync.json b/docker/telemetry/grafana/dashboards/ledger-data-sync.json index 20f3d56644..d95161dfb6 100644 --- a/docker/telemetry/grafana/dashboards/ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/ledger-data-sync.json @@ -783,11 +783,11 @@ }, { "title": "Overlay Traffic Heatmap (All Categories, Bytes In)", - "description": "###### What this is:\n*All overlay traffic categories ranked by inbound bytes, giving an at-a-glance view of which message types consume the most receive bandwidth.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value across all traffic categories.*\n\n###### Reading it:\n*The longest bars are the biggest bandwidth consumers; on a synced node transactions, proposals, and validations usually lead.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*A single ledger-data or fetch category dominating (ongoing sync) or an unexpected category topping the list.*\n\n###### Keywords:\n- **Overlay** *(per node)* \u2014 the peer-to-peer network layer over which nodes exchange transactions, proposals, and validations.\n- **Proposal** *(network event)* \u2014 a validator's advertised set of candidate transactions for the next ledger, revised each round.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\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)`\n\n###### References:\n[Overlay](https://xrpl.org/docs/concepts/networks-and-servers/peer-protocol) \u00b7 [Proposal](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#overlay)", + "description": "###### What this is:\n*All overlay traffic categories ranked by inbound bytes, giving an at-a-glance view of which message types consume the most receive bandwidth.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value across all traffic categories. Each bar is labelled with its traffic category followed by the node identity; the shared `_bytes_in` suffix is dropped from the category name because the panel already reports inbound bytes.*\n\n###### Reading it:\n*The longest bars are the biggest bandwidth consumers; on a synced node transactions, proposals, and validations usually lead.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*A single ledger-data or fetch category dominating (ongoing sync) or an unexpected category topping the list.*\n\n###### Keywords:\n- **Overlay** *(per node)* \u2014 the peer-to-peer network layer over which nodes exchange transactions, proposals, and validations.\n- **Proposal** *(network event)* \u2014 a validator's advertised set of candidate transactions for the next ledger, revised each round.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\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)`\n\n###### References:\n[Overlay](https://xrpl.org/docs/concepts/networks-and-servers/peer-protocol) \u00b7 [Proposal](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#overlay)", "type": "bargauge", "gridPos": { - "h": 8, - "w": 12, + "h": 18, + "w": 24, "x": 0, "y": 56 }, @@ -811,7 +811,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "expr": "label_replace(label_join(label_replace(topk(20, {service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"}), \"series\", \"$1\", \"__name__\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + "expr": "label_replace(label_join(label_replace(topk(20, {service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"}), \"series\", \"$1\", \"__name__\", \"(.*)_bytes_in\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], "fieldConfig": { @@ -838,6 +838,567 @@ }, "overrides": [] } + }, + { + "title": "Sync Diagnostics", + "type": "row", + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 74 + }, + "panels": [] + }, + { + "title": "Sync State", + "description": "###### What this is:\n*Current server operating state as a numeric code: 0 disconnected, 1 connected, 2 syncing, 3 tracking, 4 full. A healthy synced node sits at 4.*\n\n###### How it's computed:\n*state_tracking{metric=\"state_value\"} (gauge). Companion time_in_current_state_seconds shows how long it has been stuck there.*\n\n###### Reading it:\n*Flat at 4 = full/healthy. Dropping to 1-2 and staying = the node fell out of sync and is re-acquiring (the primary red flag this row explains).*\n\n###### Healthy range:\n*4 (full), briefly 2-3 right after restart.*\n\n###### Watch for:\n*A node stuck below 4 for more than a few minutes, or oscillating - read the lower panels for the cause.*\n\n###### Source:\n[app/misc/NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::setMode`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 75 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(state_tracking{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"state_value\"}, \"series\", \"Server State\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "short", + "custom": { + "axisLabel": "Server State", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + }, + "mappings": [ + { + "type": "value", + "options": { + "0": { + "text": "Disconnected", + "color": "red", + "index": 0 + }, + "1": { + "text": "Connected", + "color": "orange", + "index": 1 + }, + "2": { + "text": "Syncing", + "color": "yellow", + "index": 2 + }, + "3": { + "text": "Tracking", + "color": "blue", + "index": 3 + }, + "4": { + "text": "Full", + "color": "green", + "index": 4 + } + } + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "orange", + "value": 1 + }, + { + "color": "yellow", + "value": 2 + }, + { + "color": "blue", + "value": 3 + }, + { + "color": "green", + "value": 4 + } + ] + }, + "color": { + "mode": "thresholds" + }, + "min": 0, + "max": 4 + }, + "overrides": [] + } + }, + { + "title": "Validated Ledger Age", + "description": "###### What this is:\n*Seconds since this node last had a freshly validated ledger. The single clearest 'am I keeping up with the network' signal.*\n\n###### How it's computed:\n*ledgermaster_validated_ledger_age gauge (seconds), per node.*\n\n###### Reading it:\n*Should hover at the network close interval (~3-5s). A rising sawtooth or a high plateau means the node is falling behind or not validating.*\n\n###### Healthy range:\n*<= ~6s on a synced node.*\n\n###### Watch for:\n*Sustained climb above ~15s, or a monotonic ramp = the node is not keeping up; correlate with job-queue wait and NuDB read latency below.*\n\n###### Source:\n[app/ledger/LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::getValidatedLedgerAge`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 75 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(ledgermaster_validated_ledger_age{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Validated Age\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(ledgermaster_published_ledger_age{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Published Age\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "s", + "custom": { + "axisLabel": "Age (seconds)", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "Ledger Close Rate", + "description": "###### What this is:\n*Rate at which the node closes ledgers, versus the ~0.25/s network cadence. A throughput deficit means it is not advancing in step with the network.*\n\n###### How it's computed:\n*rate(ledgers_closed_total[$__rate_interval]) per node.*\n\n###### Reading it:\n*Should track ~0.22-0.25 ledgers/s (one every ~4s). Near-zero while behind = stalled; a burst above network rate = catching up.*\n\n###### Healthy range:\n*~0.25/s steady on a synced node.*\n\n###### Watch for:\n*Near-zero close rate while Validated Ledger Age climbs = hard stall (e.g. genesis-flapping or disk-bound acquisition).*\n\n###### Source:\n[app/ledger/LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::closeLedger`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 83 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]), \"series\", \"Ledgers Closed\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(rate(ledger_fetches_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]), \"series\", \"Ledger Fetches\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "reqps", + "custom": { + "axisLabel": "Rate (per second)", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "Job Queue Wait p95 By Type", + "description": "###### What this is:\n*95th-percentile time a job waits in the queue before a worker thread picks it up, for the sync-critical job types. This is the metric form of the 'ProcessLData wait: NNNNms' warnings in the debug log.*\n\n###### How it's computed:\n*histogram_quantile(0.95, rate(jobq__q_milliseconds_bucket[$__rate_interval])) for ledgerdata, acceptledger, fetchtxndata, transaction, advanceledger, ledgerrequest.*\n\n###### Reading it:\n*Queue wait should be single-digit to low-tens of ms. High ledgerdata/fetchtxndata wait = the node cannot process inbound ledger data fast enough.*\n\n###### Healthy range:\n*< ~50ms p95 per type on a healthy node.*\n\n###### Watch for:\n*ledgerdata or fetchtxndata q-wait spiking to seconds = worker threads are blocked (usually on NuDB reads - see the cause tier).*\n\n###### Source:\n[core/JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue::getJson (per-type queue timing)`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 83 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_ledgerdata_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerdata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_acceptledger_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"acceptledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_fetchtxndata_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"fetchtxndata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_transaction_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"transaction q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_advanceledger_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"advanceledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_ledgerrequest_q_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerrequest q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "ms", + "custom": { + "axisLabel": "p95 Wait (ms)", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "NuDB Read Latency", + "description": "###### What this is:\n*Average nodestore (NuDB) read latency: how long each on-disk object read takes. The direct disk-layer cost that backs up the job queue.*\n\n###### How it's computed:\n*rate(nodestore_state{metric=\"node_reads_duration_us\"}[$__rate_interval]) / rate(nodestore_state{metric=\"node_reads_total\"}[$__rate_interval]), in us.*\n\n###### Reading it:\n*Low single-digit us when the OS page cache is warm; tens-to-hundreds of us when reads hit the disk. Rises sharply during cold-cache catch-up.*\n\n###### Healthy range:\n*< ~10us/read warm; higher is expected briefly after a wipe/restart.*\n\n###### Watch for:\n*Sustained high us/read together with low cache hit % (below) = disk-bound reads are the bottleneck; check EBS IOPS / io scheduler latency.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`NuDB backend read path`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 91 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_duration_us\"}[$__rate_interval])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])), 1), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "\u00b5s", + "custom": { + "axisLabel": "Latency (\u00b5s/read)", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "I/O Scheduler Latency p95", + "description": "###### What this is:\n*95th-percentile latency of the node's internal I/O service queue - the async task scheduler that dispatches network and disk callbacks.*\n\n###### How it's computed:\n*histogram_quantile(0.95, rate(ios_latency_milliseconds_bucket[$__rate_interval])).*\n\n###### Reading it:\n*Low and flat when the event loop is responsive. Rising p95 means callbacks are queuing behind long-running work (often blocking disk reads).*\n\n###### Healthy range:\n*< ~10ms p95.*\n\n###### Watch for:\n*p95 climbing into hundreds of ms = the I/O service is saturated; the node cannot service network/disk events promptly, stalling sync.*\n\n###### Source:\n[core/impl/Workers.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/Workers.cpp)\n\n###### Function:\n`io_service latency histogram`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 91 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"IO Service p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "ms", + "custom": { + "axisLabel": "p95 Latency (ms)", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "NuDB Cache Hit Ratio", + "description": "###### What this is:\n*Fraction of nodestore reads served from cache rather than disk. A cold cache (fresh NuDB after a wipe) forces almost every read to disk - the root cause of high read latency during catch-up.*\n\n###### How it's computed:\n*rate(nodestore_state{metric=\"node_reads_hit\"}[$__rate_interval]) / rate(nodestore_state{metric=\"node_reads_total\"}[$__rate_interval]).*\n\n###### Reading it:\n*Near 1.0 (100%) on a warm node. Near 0 right after a wipe/restart, climbing as the working set warms.*\n\n###### Healthy range:\n*> ~0.9 warm; near 0 briefly after a cold start.*\n\n###### Watch for:\n*Persistently low hit ratio on a node that should be warm = working set does not fit cache, or continuous re-acquisition churning the cache.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`TaggedCache hit accounting`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 99 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_hit\"}[$__rate_interval])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval])), 1), \"series\", \"NuDB Hit Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "percentunit", + "custom": { + "axisLabel": "Hit Ratio", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "NuDB Read Pressure", + "description": "###### What this is:\n*Nodestore read throughput and backlog: reads per second, the pending read queue depth, and how many read threads are active. Shows disk saturation depth.*\n\n###### How it's computed:\n*rate(node_reads_total), and gauges read_queue / read_threads_running from nodestore_state.*\n\n###### Reading it:\n*reads/s spikes during catch-up. A growing read_queue with all read threads busy = disk cannot keep up with demand.*\n\n###### Healthy range:\n*read_queue ~0 and reads/s low on a warm synced node.*\n\n###### Watch for:\n*read_queue climbing while read_threads_running is pinned at read_threads_total = disk-bound; the IOPS ceiling is the limiter.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`NuDB read scheduler`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 99 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval]), \"series\", \"Reads/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"read_queue\"}, \"series\", \"Read Queue\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"read_threads_running\"}, \"series\", \"Read Threads Running\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "short", + "custom": { + "axisLabel": "Reads/s & Depth", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "Job Queue Depth", + "description": "###### What this is:\n*Total number of jobs currently queued across the JobQueue. A backlog means work is arriving faster than worker threads can drain it.*\n\n###### How it's computed:\n*jobq_job_count gauge (total queued jobs), per node.*\n\n###### Reading it:\n*Near 0 when keeping up. Sustained positive depth = the node is overloaded or blocked on a downstream resource (usually disk reads).*\n\n###### Healthy range:\n*~0 on a healthy node.*\n\n###### Watch for:\n*Depth climbing in step with Validated Ledger Age = the queue backlog is why the node is falling behind.*\n\n###### Source:\n[core/JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue::getJobCountTotal`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 107 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(jobq_job_count{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Job Queue Depth\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "short", + "custom": { + "axisLabel": "Queued Jobs", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } + }, + { + "title": "Load Factor & Peers", + "description": "###### What this is:\n*Server load factor (fee/throttle multiplier; 1 = unloaded) alongside active inbound/outbound peer counts. Rules out overload and insufficient fetch sources as causes.*\n\n###### How it's computed:\n*load_factor_metrics{metric=\"load_factor\"}, and peer_finder_active_inbound_peers / _outbound_peers gauges.*\n\n###### Reading it:\n*load_factor at 1 = no local overload. Outbound peers should be healthy (~10+); too few peers limits how fast the node can fetch ledger data.*\n\n###### Healthy range:\n*load_factor = 1; outbound peers >= ~8.*\n\n###### Watch for:\n*load_factor > 1 = local overload throttling; very low peer count = not enough sources to acquire history from (a distinct sync bottleneck).*\n\n###### Source:\n[overlay/detail/OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl load / PeerFinder counts`", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 107 + }, + "options": { + "tooltip": { + "maxHeight": 600, + "mode": "multi", + "sort": "desc" + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(load_factor_metrics{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"load_factor\"}, \"series\", \"Load Factor\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(peer_finder_active_outbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Outbound Peers\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(peer_finder_active_inbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Inbound Peers\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "fieldConfig": { + "defaults": { + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "unit": "short", + "custom": { + "axisLabel": "Factor / Peer Count", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 3 + } + }, + "overrides": [] + } } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/node-health.json b/docker/telemetry/grafana/dashboards/node-health.json index f2ea5d532b..f62f00c16e 100644 --- a/docker/telemetry/grafana/dashboards/node-health.json +++ b/docker/telemetry/grafana/dashboards/node-health.json @@ -38,6 +38,85 @@ "graphTooltip": 1, "links": [], "panels": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "description": "###### What this is:\n*A single at-a-glance verdict: is this node healthy and doing its job (fully synced and keeping up with the network)?*\n\n###### How it's computed:\n*1 (Healthy) only when server_state == Full AND the validated ledger age is under 30s; otherwise 0 (Not Healthy). Combines server_info{metric=\"server_state\"} and ledgermaster_validated_ledger_age.*\n\n###### Reading it:\n*Green \"Healthy\" = full sync and current. Red \"Not Healthy\" = not full, or lagging the network (catching up, flapping, or stalled).*\n\n###### Healthy range:\n*Healthy (green) in steady state.*\n\n###### Watch for:\n*Any sustained Not Healthy \u2014 drill into the Operating Mode and Validated Ledger Age panels below to see whether it is a state or a lag problem.*\n\n###### Keywords:\n- **Full** *(per node)* \u2014 the node has the current validated ledger and complete recent history.\n- **Validated ledger age** *(per node)* \u2014 seconds since the last freshly validated ledger.\n\n###### Computation boundary:\n*Result: Per node \u2014 a boolean AND of two native metrics.*\n*Recorded in xrpld code as native metrics (beast::insight); the collector only forwards them; the Grafana query combines them.*\n\n###### Source:\n[app/misc/NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::setMode / getValidatedLedgerAge`\n\n###### References:\n[Server states](https://xrpl.org/docs/concepts/networks-and-servers/rippled-server-states) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md)", + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}", + "mappings": [ + { + "type": "value", + "options": { + "0": { + "text": "Not Healthy", + "color": "red", + "index": 0 + }, + "1": { + "text": "Healthy", + "color": "green", + "index": 1 + } + } + } + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "red", + "value": null + }, + { + "color": "green", + "value": 1 + } + ] + } + } + }, + "gridPos": { + "h": 4, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 129, + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": ["lastNotNull"], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "value_and_name", + "wideLayout": true + }, + "pluginVersion": "13.2.0-28926505616", + "targets": [ + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace((server_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", metric=\"server_state\"} == bool 4) * on(service_instance_id) (ledgermaster_validated_ledger_age{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"} < bool 30), \"series\", \"Node Health\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" + } + ], + "title": "Node Health", + "type": "stat" + }, { "datasource": { "type": "prometheus", @@ -71,7 +150,7 @@ "h": 12, "w": 12, "x": 0, - "y": 0 + "y": 4 }, "id": 67, "options": { @@ -141,7 +220,7 @@ "h": 12, "w": 12, "x": 12, - "y": 0 + "y": 4 }, "id": 68, "options": { @@ -207,7 +286,7 @@ "h": 12, "w": 12, "x": 0, - "y": 12 + "y": 16 }, "id": 69, "options": { @@ -273,7 +352,7 @@ "h": 12, "w": 12, "x": 12, - "y": 12 + "y": 16 }, "id": 70, "options": { @@ -343,7 +422,7 @@ "h": 12, "w": 12, "x": 0, - "y": 24 + "y": 28 }, "id": 71, "options": { @@ -446,7 +525,7 @@ "h": 12, "w": 12, "x": 12, - "y": 24 + "y": 28 }, "id": 72, "options": { @@ -489,7 +568,7 @@ "h": 1, "w": 24, "x": 0, - "y": 36 + "y": 40 }, "id": 121, "title": "Operating Mode", @@ -563,7 +642,7 @@ "h": 12, "w": 12, "x": 0, - "y": 37 + "y": 41 }, "id": 74, "options": { @@ -698,7 +777,7 @@ "h": 12, "w": 12, "x": 12, - "y": 37 + "y": 41 }, "id": 75, "options": { @@ -772,7 +851,7 @@ "type": "prometheus", "uid": "${DS_PROMETHEUS}" }, - "description": "###### What this is:\n*Rate of change of time spent in Full and Tracking modes, normalized to seconds per second.*\n\n###### How it's computed:\n*Per-second rate of the Full and Tracking duration counters, scaled to seconds.*\n\n###### Reading it:\n*The Full line near 1.0 means the node gains a second of Full-mode time each wall-clock second.*\n\n###### Healthy range:\n*Full rate close to 1.0, Tracking near 0.*\n\n###### Watch for:\n*A Full rate below 1.0 means the node is spending time in other modes.*\n\n###### Keywords:\n- **Operating mode / server state** *(per node)* \u2014 the node's sync level: Disconnected, Connected, Syncing, Tracking, Full (and Validating/Proposing).\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`\n\n###### References:\n[Operating mode / server state](https://xrpl.org/docs/references/http-websocket-apis/api-conventions/xrpld-server-states) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#operating-mode-server-state)", + "description": "###### What this is:\n*Which operating mode the node is accumulating time in right now, one line per state, normalized to seconds per second.*\n\n###### How it's computed:\n*Per-second rate of each state's duration counter, scaled from microseconds to seconds. The five lines sum to about 1.0 because the node is always in exactly one state.*\n\n###### Reading it:\n*The line sitting near 1.0 is the state the node is currently in; the others sit at 0. A handover between two lines marks a state change, and its width is how long that state lasted.*\n\n###### Healthy range:\n*Full near 1.0 with every other line at 0.*\n\n###### Watch for:\n*Time accumulating in Connected or Syncing means the node is catching up rather than serving; repeated handovers mean it is flapping.*\n\n###### Keywords:\n- **Operating mode / server state** *(per node)* \u2014 the node's sync level: Disconnected, Connected, Syncing, Tracking, Full.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`\n\n###### References:\n[Server states](https://xrpl.org/docs/concepts/networks-and-servers/rippled-server-states)", "fieldConfig": { "defaults": { "color": { @@ -833,7 +912,7 @@ "h": 12, "w": 12, "x": 0, - "y": 49 + "y": 53 }, "id": 76, "options": { @@ -873,9 +952,33 @@ }, "expr": "label_replace(label_join(label_replace(rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]) / 1000000, \"series\", \"Tracking Mode Rate\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", "refId": "B" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]) / 1000000, \"series\", \"Syncing Mode Rate\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "refId": "C" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]) / 1000000, \"series\", \"Connected Mode Rate\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "refId": "D" + }, + { + "datasource": { + "type": "prometheus", + "uid": "${DS_PROMETHEUS}" + }, + "expr": "label_replace(label_join(label_replace(rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]) / 1000000, \"series\", \"Disconnected Mode Rate\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")", + "refId": "E" } ], - "title": "State Duration Rate (Full vs Tracking)", + "title": "State Duration Rate (All States)", "type": "timeseries" }, { @@ -913,7 +1016,7 @@ "h": 12, "w": 12, "x": 12, - "y": 49 + "y": 53 }, "id": 77, "options": { @@ -1040,7 +1143,7 @@ "h": 24, "w": 24, "x": 0, - "y": 61 + "y": 65 }, "id": 78, "options": { @@ -1085,7 +1188,7 @@ "h": 1, "w": 24, "x": 0, - "y": 85 + "y": 89 }, "id": 122, "title": "NodeStore I/O", @@ -1157,7 +1260,7 @@ "h": 12, "w": 12, "x": 0, - "y": 86 + "y": 90 }, "id": 80, "options": { @@ -1276,7 +1379,7 @@ "h": 12, "w": 12, "x": 12, - "y": 86 + "y": 90 }, "id": 81, "options": { @@ -1383,7 +1486,7 @@ "h": 12, "w": 12, "x": 0, - "y": 98 + "y": 102 }, "id": 82, "options": { @@ -1494,7 +1597,7 @@ "h": 12, "w": 12, "x": 12, - "y": 98 + "y": 102 }, "id": 83, "options": { @@ -1605,7 +1708,7 @@ "h": 12, "w": 12, "x": 0, - "y": 110 + "y": 114 }, "id": 84, "options": { @@ -1724,7 +1827,7 @@ "h": 12, "w": 12, "x": 12, - "y": 110 + "y": 114 }, "id": 85, "options": { @@ -1767,7 +1870,7 @@ "h": 1, "w": 24, "x": 0, - "y": 122 + "y": 126 }, "id": 123, "title": "Jobs", @@ -1839,7 +1942,7 @@ "h": 12, "w": 12, "x": 0, - "y": 123 + "y": 127 }, "id": 87, "options": { @@ -1942,7 +2045,7 @@ "h": 12, "w": 12, "x": 12, - "y": 123 + "y": 127 }, "id": 88, "options": { @@ -2125,7 +2228,7 @@ "h": 12, "w": 12, "x": 0, - "y": 135 + "y": 139 }, "id": 89, "options": { @@ -2308,7 +2411,7 @@ "h": 16, "w": 24, "x": 0, - "y": 147 + "y": 151 }, "id": 90, "options": { @@ -2411,7 +2514,7 @@ "h": 16, "w": 24, "x": 0, - "y": 163 + "y": 167 }, "id": 91, "options": { @@ -2454,7 +2557,7 @@ "h": 1, "w": 24, "x": 0, - "y": 179 + "y": 183 }, "id": 124, "panels": [ @@ -2902,7 +3005,7 @@ "h": 1, "w": 24, "x": 0, - "y": 180 + "y": 184 }, "id": 125, "title": "Server Info", @@ -3043,7 +3146,7 @@ "h": 12, "w": 12, "x": 0, - "y": 181 + "y": 185 }, "id": 98, "options": { @@ -3107,7 +3210,7 @@ "h": 12, "w": 12, "x": 12, - "y": 181 + "y": 185 }, "id": 99, "options": { @@ -3176,7 +3279,7 @@ "h": 12, "w": 12, "x": 0, - "y": 193 + "y": 197 }, "id": 100, "options": { @@ -3235,7 +3338,7 @@ "h": 12, "w": 12, "x": 12, - "y": 193 + "y": 197 }, "id": 103, "options": { @@ -3333,7 +3436,7 @@ "h": 7, "w": 12, "x": 0, - "y": 205 + "y": 209 }, "id": 58, "options": { @@ -3397,7 +3500,7 @@ "h": 7, "w": 12, "x": 12, - "y": 205 + "y": 209 }, "id": 56, "options": { @@ -3458,7 +3561,7 @@ "h": 12, "w": 12, "x": 0, - "y": 212 + "y": 216 }, "id": 102, "options": { @@ -3557,7 +3660,7 @@ "h": 12, "w": 12, "x": 12, - "y": 212 + "y": 216 }, "id": 105, "options": { @@ -3656,7 +3759,7 @@ "h": 12, "w": 12, "x": 0, - "y": 224 + "y": 228 }, "id": 104, "options": { @@ -3755,7 +3858,7 @@ "h": 12, "w": 12, "x": 12, - "y": 236 + "y": 240 }, "id": 128, "options": { @@ -3862,7 +3965,7 @@ "h": 12, "w": 12, "x": 12, - "y": 224 + "y": 228 }, "id": 106, "options": { @@ -3965,7 +4068,7 @@ "h": 16, "w": 24, "x": 0, - "y": 236 + "y": 240 }, "id": 107, "options": { @@ -4008,7 +4111,7 @@ "h": 1, "w": 24, "x": 0, - "y": 252 + "y": 256 }, "id": 126, "title": "Complete Ledgers & DB", @@ -4052,7 +4155,7 @@ "h": 12, "w": 12, "x": 0, - "y": 253 + "y": 257 }, "id": 109, "options": { @@ -4142,7 +4245,7 @@ "h": 12, "w": 12, "x": 12, - "y": 253 + "y": 257 }, "id": 110, "options": { @@ -4224,7 +4327,7 @@ "h": 12, "w": 12, "x": 0, - "y": 265 + "y": 269 }, "id": 111, "options": { @@ -4327,7 +4430,7 @@ "h": 12, "w": 12, "x": 12, - "y": 265 + "y": 269 }, "id": 112, "options": { @@ -4370,7 +4473,7 @@ "h": 1, "w": 24, "x": 0, - "y": 277 + "y": 281 }, "id": 127, "title": "Ledger Economy", @@ -4405,7 +4508,7 @@ "h": 12, "w": 12, "x": 0, - "y": 278 + "y": 282 }, "id": 114, "options": { @@ -4471,7 +4574,7 @@ "h": 12, "w": 12, "x": 12, - "y": 278 + "y": 282 }, "id": 115, "options": { @@ -4537,7 +4640,7 @@ "h": 12, "w": 12, "x": 0, - "y": 290 + "y": 294 }, "id": 116, "options": { @@ -4644,7 +4747,7 @@ "h": 16, "w": 12, "x": 12, - "y": 290 + "y": 294 }, "id": 117, "options": { @@ -4747,7 +4850,7 @@ "h": 16, "w": 24, "x": 0, - "y": 306 + "y": 310 }, "id": 118, "options": { @@ -4850,7 +4953,7 @@ "h": 16, "w": 12, "x": 0, - "y": 322 + "y": 326 }, "id": 119, "options": { @@ -4953,7 +5056,7 @@ "h": 16, "w": 12, "x": 12, - "y": 322 + "y": 326 }, "id": 120, "options": {