diff --git a/docker/telemetry/grafana/dashboards/consensus-health.json b/docker/telemetry/grafana/dashboards/consensus-health.json index e77e207c10..140153313e 100644 --- a/docker/telemetry/grafana/dashboards/consensus-health.json +++ b/docker/telemetry/grafana/dashboards/consensus-health.json @@ -39,11 +39,11 @@ "links": [], "panels": [ { - "title": "Validation Send Rate", + "title": "Validation Send Rate [$xrpl_network_type]", "description": "###### What this is:\n*How often this node issues a ledger validation to the network. Each validation asserts the node fully validated one ledger.*\n\n###### How it's computed:\n*Per-second rate of validation events sent, summed per node over a 5-minute window.*\n\n###### Reading it:\n*A flat line at the network's ledger cadence is normal; higher is not better and lower means the node is validating less often.*\n\n###### Healthy range:\n*Roughly one validation per closed ledger (about 0.2-0.3/s on a healthy chain).*\n\n###### Watch for:\n*A drop to zero on a validator means it stopped validating; a value well below the close rate means validation is lagging.*\n\n###### Keywords:\n- **Ledger validation** *(network event)* \u2014 the second consensus stage where the node confirms a built ledger matches the trusted validator quorum and marks it final.\n- **Ledger close interval** *(network-wide)* \u2014 the network's steady ledger rhythm \u2014 roughly one closed ledger every 3-5 seconds on Mainnet.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::createValidationSpan`\n\n###### References:\n[Ledger validation](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure#validation) \u00b7 [Ledger close interval](https://xrpl.org/docs/concepts/ledgers/ledger-close-times) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#ledger-validation)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, "y": 0 @@ -71,7 +71,10 @@ }, "overrides": [] }, - "id": 1 + "id": 1, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "title": "Consensus Mode Over Time", @@ -80,8 +83,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 0 + "x": 0, + "y": 4 }, "options": { "tooltip": { @@ -108,13 +111,29 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, "id": 2 }, + { + "title": "Proposals & Validations", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 12 + }, + "collapsed": false, + "panels": [], + "id": 3 + }, { "title": "Consensus Proposals Sent Rate", "description": "###### What this is:\n*How often this node proposes its candidate transaction set to peers during consensus.*\n\n###### How it's computed:\n*Per-second rate of proposal-send events, summed per node over a 5-minute window.*\n\n###### Reading it:\n*A steady line tracking the ledger cadence is healthy; only proposing (validator) nodes show activity.*\n\n###### Healthy range:\n*Steady output in step with the close rate for a proposing node; zero for a non-proposing node.*\n\n###### Watch for:\n*A proposing validator dropping to zero, or erratic spikes suggesting repeated re-proposals within rounds.*\n\n###### Keywords:\n- **Proposal** *(network event)* \u2014 a validator's advertised set of candidate transactions for the next ledger, revised each round.\n- **Consensus** *(network event)* \u2014 the protocol by which validators agree on the next ledger's transaction set and close time.\n- **Ledger close interval** *(network-wide)* \u2014 the network's steady ledger rhythm \u2014 roughly one closed ledger every 3-5 seconds on Mainnet.\n- **Consensus mode** *(per node)* \u2014 the node's role/health in the current round: Proposing, Observing, Wrong Ledger, or Switched Ledger.\n- **Consensus round** *(network event)* \u2014 one propose-and-revise iteration of consensus; several may run before validators converge on a ledger.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::propose`\n\n###### References:\n[Proposal](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Ledger close interval](https://xrpl.org/docs/concepts/ledgers/ledger-close-times) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#proposal)", @@ -123,7 +142,7 @@ "h": 8, "w": 12, "x": 0, - "y": 8 + "y": 13 }, "options": { "tooltip": { @@ -150,12 +169,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 3 + "id": 4 }, { "title": "Accept vs Close Rate", @@ -165,7 +187,7 @@ "h": 8, "w": 12, "x": 12, - "y": 8 + "y": 13 }, "options": { "tooltip": { @@ -199,12 +221,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 4 + "id": 5 }, { "title": "Validation vs Close Rate", @@ -214,7 +239,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 21 }, "options": { "tooltip": { @@ -248,12 +273,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 5 + "id": 6 }, { "title": "Time to Reach Consensus (p50/p95)", @@ -263,7 +291,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 21 }, "options": { "tooltip": { @@ -302,12 +330,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 6 + "id": 7 }, { "title": "Average Time to Reach Consensus", @@ -317,7 +348,7 @@ "h": 8, "w": 12, "x": 0, - "y": 24 + "y": 29 }, "options": { "tooltip": { @@ -346,12 +377,28 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 7 + "id": 8 + }, + { + "title": "Consensus Rounds", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 37 + }, + "collapsed": false, + "panels": [], + "id": 9 }, { "title": "Consensus Rounds per Ledger (Establish Count)", @@ -361,7 +408,7 @@ "h": 8, "w": 24, "x": 0, - "y": 32 + "y": 38 }, "options": { "tooltip": { @@ -395,13 +442,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "decimals": 0 }, "overrides": [] }, - "id": 8 + "id": 10 }, { "title": "Previous Round Time per Ledger", @@ -411,7 +461,7 @@ "h": 8, "w": 12, "x": 0, - "y": 40 + "y": 46 }, "options": { "tooltip": { @@ -440,12 +490,28 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 9 + "id": 11 + }, + { + "title": "Timing", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 54 + }, + "collapsed": false, + "panels": [], + "id": 12 }, { "title": "Position Update Duration", @@ -454,8 +520,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 40 + "x": 0, + "y": 55 }, "options": { "tooltip": { @@ -482,12 +548,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 10 + "id": 13 }, { "title": "Ledger Close Duration", @@ -496,8 +565,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 48 + "x": 12, + "y": 55 }, "options": { "tooltip": { @@ -524,12 +593,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 11 + "id": 14 }, { "title": "Ledger Apply Duration (doAccept)", @@ -538,8 +610,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 48 + "x": 0, + "y": 63 }, "targets": [ { @@ -559,12 +631,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 12, + "id": 15, "options": { "tooltip": { "mode": "multi", @@ -580,8 +655,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 56 + "x": 12, + "y": 63 }, "options": { "tooltip": { @@ -610,7 +685,7 @@ "unit": "ms" } }, - "id": 13 + "id": 16 }, { "title": "Close-Time Agreement Rate (Agreed vs Disagreed)", @@ -619,8 +694,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 56 + "x": 0, + "y": 71 }, "targets": [ { @@ -640,12 +715,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 14, + "id": 17, "options": { "tooltip": { "mode": "multi", @@ -661,8 +739,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 64 + "x": 12, + "y": 71 }, "fieldConfig": { "defaults": { @@ -672,7 +750,10 @@ "pointSize": 5, "showPoints": "auto", "axisLabel": "Count / Milliseconds", - "spanNulls": 1800000 + "spanNulls": 1800000, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "unit": "short" }, @@ -745,17 +826,17 @@ "refId": "B" } ], - "id": 15 + "id": 18 }, { - "title": "Close-Time Resolution Change (per Round)", + "title": "Close-Time Resolution Change (per Round) [$xrpl_network_type]", "description": "###### What this is:\n*Whether the close-time rounding granularity moved Coarser, Finer, or stayed Steady versus the previous round.*\n\n###### How it's computed:\n*Rounds are counted over the window and grouped by direction of change.*\n\n###### Reading it:\n*Mostly Steady is healthy; Coarser means widening bins (more disagreement), Finer means tightening.*\n\n###### Healthy range:\n*Predominantly Steady.*\n\n###### Watch for:\n*Frequent Coarser shifts indicate the network is repeatedly failing to agree on close time.*\n\n###### Keywords:\n- **Close-time resolution** *(network event)* \u2014 the granularity (in seconds) that close times are rounded to; widens when validators disagree.\n- **Consensus round** *(network event)* \u2014 one propose-and-revise iteration of consensus; several may run before validators converge on a ledger.\n- **Close time** *(network event)* \u2014 the timestamp validators agree to stamp on a ledger, rounded to a shared resolution.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as trace spans and stored in Tempo; the value is computed directly from those raw spans by the panel's TraceQL query (no Prometheus metric involved).*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`\n\n###### References:\n[Close-time resolution](https://xrpl.org/docs/concepts/ledgers/ledger-close-times) \u00b7 [Consensus round](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#close-time-resolution)", "type": "bargauge", "gridPos": { - "h": 8, + "h": 4, "w": 12, - "x": 12, - "y": 64 + "x": 0, + "y": 79 }, "fieldConfig": { "defaults": { @@ -794,7 +875,7 @@ "refId": "A" } ], - "id": 16, + "id": 19, "transformations": [ { "id": "renameByRegex", @@ -817,17 +898,20 @@ "renamePattern": "Steady" } } - ] + ], + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { - "title": "Close-Time Proposal Spread (Distinct Positions per Round)", + "title": "Close-Time Proposal Spread (Distinct Positions per Round) [$xrpl_network_type]", "description": "###### What this is:\n*How spread out validators' proposed close times were, as the number of distinct positions per round.*\n\n###### How it's computed:\n*Rounds are counted over the window and grouped by their distinct-position count; each bar is one count value.*\n\n###### Reading it:\n*Weight on '1 distinct position' means everyone agreed; weight on 2 or more means the proposals split.*\n\n###### Healthy range:\n*Most rounds at a single distinct position.*\n\n###### Watch for:\n*A shift toward two or more distinct positions signals growing clock drift or latency across validators.*\n\n###### Keywords:\n- **Distinct positions** *(network event)* \u2014 the number of different close-time values validators proposed in a round; one means full agreement.\n- **Consensus round** *(network event)* \u2014 one propose-and-revise iteration of consensus; several may run before validators converge on a ledger.\n- **Proposal** *(network event)* \u2014 a validator's advertised set of candidate transactions for the next ledger, revised each round.\n- **Clock drift** *(network event)* \u2014 differences between validators' clocks, which spread their proposed close times.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as trace spans and stored in Tempo; the value is computed directly from those raw spans by the panel's TraceQL query (no Prometheus metric involved).*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`\n\n###### References:\n[Distinct positions](https://xrpl.org/docs/concepts/ledgers/ledger-close-times) \u00b7 [Consensus round](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#distinct-positions)", "type": "bargauge", "gridPos": { - "h": 8, + "h": 4, "w": 12, - "x": 0, - "y": 72 + "x": 12, + "y": 79 }, "fieldConfig": { "defaults": { @@ -866,7 +950,23 @@ "refId": "A" } ], - "id": 17 + "id": 20, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 + }, + { + "title": "Outcomes & Failures", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 83 + }, + "collapsed": false, + "panels": [], + "id": 21 }, { "title": "Consensus Outcome Distribution (per Round)", @@ -876,7 +976,7 @@ "h": 8, "w": 24, "x": 0, - "y": 80 + "y": 84 }, "options": { "legend": { @@ -905,7 +1005,7 @@ }, "overrides": [] }, - "id": 18 + "id": 22 }, { "title": "Consensus Failures Over Time", @@ -915,7 +1015,7 @@ "h": 8, "w": 12, "x": 0, - "y": 88 + "y": 92 }, "options": { "tooltip": { @@ -949,12 +1049,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 19 + "id": 23 }, { "title": "Consensus Stall Rate", @@ -964,7 +1067,7 @@ "h": 8, "w": 12, "x": 12, - "y": 88 + "y": 92 }, "options": { "tooltip": { @@ -998,12 +1101,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 20 + "id": 24 }, { "title": "Consensus Mode-Change Rate by Target Mode", @@ -1013,7 +1119,7 @@ "h": 8, "w": 12, "x": 0, - "y": 96 + "y": 100 }, "options": { "tooltip": { @@ -1040,12 +1146,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 21 + "id": 25 }, { "title": "Ledger History Mismatch Rate by Reason", @@ -1055,7 +1164,7 @@ "h": 8, "w": 12, "x": 12, - "y": 96 + "y": 100 }, "options": { "tooltip": { @@ -1082,12 +1191,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 22 + "id": 26 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/ledger-data-sync.json b/docker/telemetry/grafana/dashboards/ledger-data-sync.json index a31c2e87b8..dce81b4dae 100644 --- a/docker/telemetry/grafana/dashboards/ledger-data-sync.json +++ b/docker/telemetry/grafana/dashboards/ledger-data-sync.json @@ -49,7 +49,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -108,7 +111,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -155,7 +161,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -202,7 +211,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -261,7 +273,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -308,7 +323,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -355,7 +373,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -414,7 +435,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -461,7 +485,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -502,7 +529,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -549,7 +579,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -590,7 +623,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -643,7 +679,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -720,7 +759,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -728,12 +770,12 @@ "id": 14 }, { - "title": "Overlay Traffic Heatmap (All Categories, Bytes In)", + "title": "Overlay Traffic Heatmap (All Categories, Bytes In) [$xrpl_network_type]", "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** *(network-wide)* \u2014 the peer-to-peer mesh xrpld nodes form to gossip transactions, proposals and validations.\n- **Peer** *(per node)* \u2014 another server this node holds a protocol connection to.\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[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#overlay)", "type": "bargauge", "gridPos": { - "h": 18, - "w": 24, + "h": 4, + "w": 12, "x": 0, "y": 56 }, @@ -783,7 +825,10 @@ }, "overrides": [] }, - "id": 15 + "id": 15, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "title": "Sync Diagnostics", @@ -793,7 +838,7 @@ "h": 1, "w": 24, "x": 0, - "y": 74 + "y": 60 }, "id": 16, "panels": [] @@ -806,7 +851,7 @@ "h": 8, "w": 12, "x": 0, - "y": 75 + "y": 61 }, "options": { "tooltip": { @@ -833,7 +878,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "mappings": [ { @@ -928,7 +976,7 @@ "h": 8, "w": 12, "x": 12, - "y": 75 + "y": 61 }, "options": { "tooltip": { @@ -962,7 +1010,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -970,14 +1021,14 @@ "id": 18 }, { - "title": "Time Spent Per State", + "title": "Time Spent Per State [$xrpl_network_type]", "description": "###### What this is:\n*Operating mode as a colour-coded timeline. Each band's width is the time spent in that state, so short-lived states show as thin slivers instead of vanishing.*\n\n###### How it's computed:\n*server_info{metric=\"server_state\"} (gauge), the raw OperatingMode 0-4. Uses server_state rather than state_value because state_value folds 5 and 6 onto FULL, which would split one Full band into three colours.*\n\n###### Reading it:\n*One green band across the window = healthy. Red/orange/yellow bands show when and for how long the node was degraded.*\n\n###### Healthy range:\n*Continuously green (Full), brief orange/yellow/blue only after a restart.*\n\n###### Watch for:\n*Repeated thin bands = the node is oscillating. This is sampled every 10s, so a state shorter than one sample can still be missed.*\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*Computed in xrpld code (MetricsRegistry, OpenTelemetry SDK) and exported as a metric; the collector only forwards it; the Grafana query selects and aggregates it.*\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`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#operating-mode-server-state)", "type": "state-timeline", "gridPos": { - "h": 6, - "w": 24, + "h": 8, + "w": 12, "x": 0, - "y": 83 + "y": 69 }, "options": { "mergeValues": true, @@ -1080,7 +1131,10 @@ }, "overrides": [] }, - "id": 27 + "id": 19, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "title": "Ledger Close Rate", @@ -1089,8 +1143,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 89 + "x": 12, + "y": 69 }, "options": { "tooltip": { @@ -1124,7 +1178,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [ @@ -1146,7 +1203,7 @@ } ] }, - "id": 19 + "id": 20 }, { "title": "Job Queue Wait p95 By Type", @@ -1155,8 +1212,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 89 + "x": 0, + "y": 77 }, "options": { "tooltip": { @@ -1218,12 +1275,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 20 + "id": 21 }, { "title": "NuDB Read Latency", @@ -1232,8 +1292,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 97 + "x": 12, + "y": 77 }, "options": { "tooltip": { @@ -1260,12 +1320,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 21 + "id": 22 }, { "title": "I/O Scheduler Latency p95", @@ -1274,8 +1337,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 97 + "x": 0, + "y": 85 }, "options": { "tooltip": { @@ -1302,12 +1365,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 22 + "id": 23 }, { "title": "NuDB Read Found Ratio", @@ -1316,8 +1382,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 105 + "x": 12, + "y": 85 }, "options": { "tooltip": { @@ -1344,12 +1410,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 23 + "id": 24 }, { "title": "NuDB Read Pressure", @@ -1358,8 +1427,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 105 + "x": 0, + "y": 93 }, "options": { "tooltip": { @@ -1400,7 +1469,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [ @@ -1438,7 +1510,7 @@ } ] }, - "id": 24 + "id": 25 }, { "title": "Job Queue Depth", @@ -1447,8 +1519,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 113 + "x": 12, + "y": 93 }, "options": { "tooltip": { @@ -1475,12 +1547,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 - } + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "decimals": 0 }, "overrides": [] }, - "id": 25 + "id": 26 }, { "title": "Load Factor & Peers", @@ -1489,8 +1565,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 113 + "x": 0, + "y": 101 }, "options": { "tooltip": { @@ -1531,12 +1607,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 - } + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "decimals": 0 }, "overrides": [] }, - "id": 26 + "id": 27 }, { "title": "Job Queue Saturation", @@ -1545,11 +1625,11 @@ "h": 1, "w": 24, "x": 0, - "y": 121 + "y": 109 }, "collapsed": false, "panels": [], - "id": 38 + "id": 28 }, { "title": "Job Queue Backlog and Deferred by Type", @@ -1559,7 +1639,7 @@ "h": 8, "w": 12, "x": 0, - "y": 122 + "y": 110 }, "options": { "tooltip": { @@ -1593,12 +1673,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 28 + "id": 29 }, { "title": "LedgerReq Wait by Handler", @@ -1608,7 +1691,7 @@ "h": 8, "w": 12, "x": 12, - "y": 122 + "y": 110 }, "options": { "tooltip": { @@ -1635,12 +1718,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 29 + "id": 30 }, { "title": "Sync Bottleneck Discrimination", @@ -1649,11 +1735,11 @@ "h": 1, "w": 24, "x": 0, - "y": 130 + "y": 118 }, "collapsed": false, "panels": [], - "id": 30 + "id": 31 }, { "title": "NodeStore Read Latency (Bottleneck Discriminator)", @@ -1663,7 +1749,7 @@ "h": 8, "w": 12, "x": 0, - "y": 131 + "y": 119 }, "options": { "tooltip": { @@ -1720,12 +1806,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 31 + "id": 32 }, { "title": "NuDB Writer Queue Depth", @@ -1735,7 +1824,7 @@ "h": 8, "w": 12, "x": 12, - "y": 131 + "y": 119 }, "options": { "tooltip": { @@ -1769,12 +1858,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 - } + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "decimals": 0 }, "overrides": [] }, - "id": 32 + "id": 33 }, { "title": "NuDB Insert Time (Mean & Max)", @@ -1784,7 +1877,7 @@ "h": 8, "w": 12, "x": 0, - "y": 139 + "y": 127 }, "options": { "tooltip": { @@ -1829,12 +1922,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 33 + "id": 34 }, { "title": "Acquire Deferrals vs Timeouts (All Lanes)", @@ -1844,7 +1940,7 @@ "h": 8, "w": 12, "x": 12, - "y": 139 + "y": 127 }, "options": { "tooltip": { @@ -1878,12 +1974,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 34 + "id": 35 }, { "title": "Acquisition Progress (Completions, Give-Ups & Aborts)", @@ -1893,7 +1992,7 @@ "h": 8, "w": 12, "x": 0, - "y": 147 + "y": 135 }, "options": { "tooltip": { @@ -1934,12 +2033,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 35 + "id": 36 }, { "title": "Discarded Acquire Work (Sweeps & Partial Aborts)", @@ -1949,7 +2051,7 @@ "h": 8, "w": 12, "x": 12, - "y": 147 + "y": 135 }, "options": { "tooltip": { @@ -1983,12 +2085,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 36 + "id": 37 }, { "title": "Ledger Acquire Deferrals vs Timeouts (Ledger Lane Only)", @@ -1998,7 +2103,7 @@ "h": 8, "w": 12, "x": 0, - "y": 155 + "y": 143 }, "options": { "tooltip": { @@ -2032,12 +2137,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 37 + "id": 38 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/ledger-operations.json b/docker/telemetry/grafana/dashboards/ledger-operations.json index d3c6ae2342..df1b0a5e31 100644 --- a/docker/telemetry/grafana/dashboards/ledger-operations.json +++ b/docker/telemetry/grafana/dashboards/ledger-operations.json @@ -39,14 +39,27 @@ "links": [], "panels": [ { - "title": "Ledger Build Rate", + "title": "Ledger Build & Validate", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "collapsed": false, + "panels": [], + "id": 1 + }, + { + "title": "Ledger Build Rate [$xrpl_network_type]", "description": "###### What this is:\n*How many new ledgers this node finishes building per second.*\n\n###### How it's computed:\n*Per-second rate of completed ledger-build operations, averaged over 5 minutes and split by node.*\n\n###### Reading it:\n*A steady flat line; the value should track the network close cadence.*\n\n###### Healthy range:\n*About 0.2-0.3 ledgers/sec on mainnet (roughly one every 3-5s); workload-dependent on test networks.*\n\n###### Watch for:\n*A drop toward zero (node fell out of sync or stalled) or a value well above the network rate (rebuilding history).*\n\n###### Keywords:\n- **Ledger build** *(per node)* \u2014 constructing the new ledger by applying the agreed transaction set to the prior ledger.\n- **Ledger close interval** *(network-wide)* \u2014 the network's steady ledger rhythm \u2014 roughly one closed ledger every 3-5 seconds on Mainnet.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[BuildLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/BuildLedger.cpp)\n\n###### Function:\n`buildLedgerImpl`\n\n###### References:\n[Ledger build](https://xrpl.org/docs/concepts/ledgers/open-closed-validated-ledgers) \u00b7 [Ledger close interval](https://xrpl.org/docs/concepts/ledgers/ledger-close-times) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#ledger-build)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, - "y": 0 + "y": 1 }, "options": { "tooltip": { @@ -70,7 +83,11 @@ "unit": "suffix: ledgers/s" }, "overrides": [] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 2 }, { "title": "Ledger Build Duration", @@ -79,8 +96,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 0 + "x": 0, + "y": 5 }, "options": { "tooltip": { @@ -107,21 +124,25 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 3 }, { - "title": "Ledger Validation Rate", + "title": "Ledger Validation Rate [$xrpl_network_type]", "description": "###### What this is:\n*How often ledgers reach full validation (accepted by the trusted validator quorum) per second.*\n\n###### How it's computed:\n*Per-second rate of ledger-validation events over 5 minutes, per node.*\n\n###### Reading it:\n*Should closely match the build rate under normal, in-sync operation.*\n\n###### Healthy range:\n*About 0.2-0.3/sec on mainnet; workload-dependent elsewhere.*\n\n###### Watch for:\n*A validation rate that lags the build rate, signalling the node is building ahead of the network consensus it trusts.*\n\n###### Keywords:\n- **Ledger validation** *(network event)* \u2014 the second consensus stage where the node confirms a built ledger matches the trusted validator quorum and marks it final.\n- **Validation quorum** *(network-wide)* \u2014 the minimum number of agreeing trusted validations needed to declare a ledger fully validated.\n- **Ledger build** *(per node)* \u2014 constructing the new ledger by applying the agreed transaction set to the prior ledger.\n- **Consensus** *(network event)* \u2014 the protocol by which validators agree on the next ledger's transaction set and close time.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::checkAccept`\n\n###### References:\n[Ledger validation](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure#validation) \u00b7 [Validation quorum](https://xrpl.org/docs/concepts/consensus-protocol/negative-unl) \u00b7 [Ledger build](https://xrpl.org/docs/concepts/ledgers/open-closed-validated-ledgers) \u00b7 [Consensus](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#ledger-validation)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, - "y": 8 + "y": 13 }, "options": { "tooltip": { @@ -145,7 +166,11 @@ "unit": "suffix: ledgers/s" }, "overrides": [] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 4 }, { "title": "Ledger Build Duration Heatmap", @@ -154,8 +179,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 8 + "x": 0, + "y": 17 }, "options": { "tooltip": { @@ -183,7 +208,21 @@ "unit": "ms" }, "overrides": [] - } + }, + "id": 5 + }, + { + "title": "Transaction Apply", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 25 + }, + "collapsed": false, + "panels": [], + "id": 6 }, { "title": "Transaction Apply Duration", @@ -193,7 +232,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 26 }, "options": { "tooltip": { @@ -220,11 +259,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 7 }, { "title": "Transaction Apply Rate", @@ -234,7 +277,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 26 }, "options": { "tooltip": { @@ -261,21 +304,38 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 8 }, { - "title": "Ledger Store Rate", + "title": "Store & Close Timing", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 34 + }, + "collapsed": false, + "panels": [], + "id": 9 + }, + { + "title": "Ledger Store Rate [$xrpl_network_type]", "description": "###### What this is:\n*How often completed ledgers are written into ledger history per second.*\n\n###### How it's computed:\n*Per-second rate of ledger-store operations over 5 minutes, per node.*\n\n###### Reading it:\n*Should match the build rate during normal operation.*\n\n###### Healthy range:\n*About 0.2-0.3/sec on mainnet; can burst higher while backfilling history.*\n\n###### Watch for:\n*A store rate below the build rate (storage falling behind) or a stall at zero.*\n\n###### Keywords:\n- **Ledger store** *(per node)* \u2014 writing a completed ledger into the node's ledger history on disk.\n- **Ledger build** *(per node)* \u2014 constructing the new ledger by applying the agreed transaction set to the prior ledger.\n- **Back-fill / catch-up** *(per node)* \u2014 fetching missing historical ledgers from peers to fill gaps or reach the network tip.\n- **Consensus stall** *(per node)* \u2014 a health check reporting that consensus is not making forward progress.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::storeLedger`\n\n###### References:\n[Ledger build](https://xrpl.org/docs/concepts/ledgers/open-closed-validated-ledgers) \u00b7 [Consensus stall](https://xrpl.org/docs/concepts/consensus-protocol/consensus-principles-and-rules) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#ledger-store)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, - "y": 24 + "y": 35 }, "options": { "tooltip": { @@ -299,7 +359,11 @@ "unit": "suffix: ledgers/s" }, "overrides": [] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 10 }, { "title": "Build vs Close Duration", @@ -308,8 +372,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 24 + "x": 0, + "y": 39 }, "options": { "tooltip": { @@ -343,11 +407,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 11 }, { "title": "Ledger Close Interval & Age", @@ -356,8 +424,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 32 + "x": 12, + "y": 39 }, "options": { "tooltip": { @@ -391,7 +459,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [ @@ -432,7 +503,8 @@ ] } ] - } + }, + "id": 12 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/network-traffic.json b/docker/telemetry/grafana/dashboards/network-traffic.json index a74a889a6c..8851b9f09f 100644 --- a/docker/telemetry/grafana/dashboards/network-traffic.json +++ b/docker/telemetry/grafana/dashboards/network-traffic.json @@ -39,6 +39,19 @@ "id": null, "links": [], "panels": [ + { + "title": "Peer Connectivity", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "collapsed": false, + "panels": [], + "id": 1 + }, { "title": "Active Peers", "description": "###### What this is:\n*Number of active inbound and outbound peer connections the node currently holds.*\n\n###### How it's computed:\n*Current value of the inbound and outbound active-peer counts per node.*\n\n###### Reading it:\n*Outbound is what the node dials out; inbound is what others open to it. Both should be stable.*\n\n###### Healthy range:\n*roughly 10-21 outbound and 0-85 inbound on mainnet, depending on config.*\n\n###### Watch for:\n*Outbound dropping toward zero (isolation) or inbound pinned at the limit with churn (connection pressure).*\n\n###### Keywords:\n- **Peer** *(per node)* \u2014 another server this node holds a protocol connection to.\n- **Overlay** *(network-wide)* \u2014 the peer-to-peer mesh xrpld nodes form to gossip transactions, proposals and validations.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Computed in xrpld code (MetricsRegistry, OpenTelemetry SDK) and exported as a metric; the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[PeerfinderManager.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/peerfinder/detail/PeerfinderManager.cpp)\n\n###### Function:\n`Logic Stats ctor`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#peer)", @@ -47,7 +60,7 @@ "h": 8, "w": 12, "x": 0, - "y": 0 + "y": 1 }, "options": { "tooltip": { @@ -81,11 +94,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 - } + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "decimals": 0 }, "overrides": [] - } + }, + "id": 2 }, { "title": "Peer Disconnects", @@ -95,7 +113,7 @@ "h": 8, "w": 12, "x": 12, - "y": 0 + "y": 1 }, "options": { "tooltip": { @@ -122,11 +140,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 - } + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "decimals": 0 }, "overrides": [] - } + }, + "id": 3 }, { "title": "Total Network Bytes", @@ -136,7 +159,7 @@ "h": 8, "w": 12, "x": 0, - "y": 8 + "y": 9 }, "options": { "tooltip": { @@ -170,11 +193,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 4 }, { "title": "Total Network Messages", @@ -184,7 +211,7 @@ "h": 8, "w": 12, "x": 12, - "y": 8 + "y": 9 }, "options": { "tooltip": { @@ -218,11 +245,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 5 }, { "title": "Transaction Traffic", @@ -232,7 +263,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 17 }, "options": { "tooltip": { @@ -273,11 +304,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 6 }, { "title": "Proposal Traffic", @@ -287,7 +322,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 17 }, "options": { "tooltip": { @@ -335,11 +370,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 7 }, { "title": "Validation Traffic", @@ -349,7 +388,7 @@ "h": 8, "w": 12, "x": 0, - "y": 24 + "y": 25 }, "options": { "tooltip": { @@ -397,21 +436,38 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 8 }, { - "title": "Overlay Traffic by Category (Bytes In)", + "title": "Traffic by Category", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 33 + }, + "collapsed": false, + "panels": [], + "id": 9 + }, + { + "title": "Overlay Traffic by Category (Bytes In) [$xrpl_network_type]", "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###### 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, + "h": 4, "w": 12, - "x": 12, - "y": 24 + "x": 0, + "y": 34 }, "options": { "tooltip": { @@ -699,7 +755,11 @@ ] } ] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 10 }, { "title": "Duplicate Traffic (Wasted Bandwidth)", @@ -709,7 +769,7 @@ "h": 8, "w": 12, "x": 0, - "y": 32 + "y": 38 }, "options": { "tooltip": { @@ -771,11 +831,28 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 11 + }, + { + "title": "Detail", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 46 + }, + "collapsed": false, + "panels": [], + "id": 12 }, { "title": "All Traffic Categories (Detail)", @@ -784,8 +861,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 32 + "x": 0, + "y": 47 }, "options": { "tooltip": { @@ -812,11 +889,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 13 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/node-health.json b/docker/telemetry/grafana/dashboards/node-health.json index 518f7bd5ca..a76d639c16 100644 --- a/docker/telemetry/grafana/dashboards/node-health.json +++ b/docker/telemetry/grafana/dashboards/node-health.json @@ -84,11 +84,11 @@ }, "gridPos": { "h": 4, - "w": 24, + "w": 12, "x": 0, "y": 0 }, - "id": 129, + "id": 1, "options": { "colorMode": "background", "graphMode": "none", @@ -115,8 +115,11 @@ "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\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], - "title": "Node Health", - "type": "stat" + "title": "Node Health [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -148,12 +151,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, - "x": 0, - "y": 4 + "x": 12, + "y": 0 }, - "id": 67, + "id": 2, "options": { "colorMode": "value", "graphMode": "area", @@ -185,8 +188,11 @@ "refId": "A" } ], - "title": "Validated Ledger Age", - "type": "stat" + "title": "Validated Ledger Age [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -218,12 +224,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, - "x": 12, + "x": 0, "y": 4 }, - "id": 68, + "id": 3, "options": { "colorMode": "value", "graphMode": "area", @@ -255,8 +261,11 @@ "refId": "A" } ], - "title": "Published Ledger Age", - "type": "stat" + "title": "Published Ledger Age [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -284,12 +293,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, - "x": 0, - "y": 16 + "x": 12, + "y": 4 }, - "id": 69, + "id": 4, "options": { "colorMode": "value", "graphMode": "area", @@ -321,8 +330,11 @@ "refId": "A" } ], - "title": "Ledger Fetch Rate", - "type": "stat" + "title": "Ledger Fetch Rate [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -350,12 +362,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, - "x": 12, - "y": 16 + "x": 0, + "y": 8 }, - "id": 70, + "id": 5, "options": { "colorMode": "value", "graphMode": "area", @@ -387,8 +399,11 @@ "refId": "A" } ], - "title": "Ledger History Mismatches", - "type": "stat" + "title": "Ledger History Mismatches [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -420,12 +435,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, - "x": 0, - "y": 28 + "x": 12, + "y": 8 }, - "id": 71, + "id": 6, "options": { "colorMode": "value", "graphMode": "area", @@ -457,8 +472,11 @@ "refId": "A" } ], - "title": "Ledger Publish Gap", - "type": "stat" + "title": "Ledger Publish Gap [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -490,7 +508,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -523,12 +541,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 12, - "y": 28 + "x": 0, + "y": 12 }, - "id": 72, + "id": 7, "options": { "annotations": { "clustering": -1, @@ -569,9 +587,9 @@ "h": 1, "w": 24, "x": 0, - "y": 40 + "y": 20 }, - "id": 121, + "id": 8, "title": "Operating Mode", "type": "row" }, @@ -605,7 +623,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -640,12 +658,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 41 + "y": 21 }, - "id": 74, + "id": 9, "options": { "annotations": { "clustering": -1, @@ -742,7 +760,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -775,12 +793,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 12, - "y": 41 + "y": 21 }, - "id": 75, + "id": 10, "options": { "annotations": { "clustering": -1, @@ -877,7 +895,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -910,12 +928,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 53 + "y": 29 }, - "id": 76, + "id": 11, "options": { "annotations": { "clustering": -1, @@ -1014,12 +1032,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, - "x": 12, - "y": 53 + "x": 0, + "y": 37 }, - "id": 77, + "id": 12, "options": { "colorMode": "value", "graphMode": "area", @@ -1051,8 +1069,11 @@ "refId": "A" } ], - "title": "% Time in Full", - "type": "stat" + "title": "% Time in Full [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -1141,12 +1162,12 @@ } }, "gridPos": { - "h": 24, - "w": 24, + "h": 8, + "w": 12, "x": 0, - "y": 65 + "y": 41 }, - "id": 78, + "id": 13, "options": { "alignValue": "left", "annotations": { @@ -1181,8 +1202,11 @@ "refId": "A" } ], - "title": "Operating Mode (State Timeline)", - "type": "state-timeline" + "title": "Operating Mode (State Timeline) [$xrpl_network_type]", + "type": "state-timeline", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "collapsed": false, @@ -1190,9 +1214,9 @@ "h": 1, "w": 24, "x": 0, - "y": 89 + "y": 49 }, - "id": 122, + "id": 14, "title": "NodeStore I/O", "type": "row" }, @@ -1216,7 +1240,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -1225,7 +1249,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -1259,12 +1283,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 90 + "y": 50 }, - "id": 80, + "id": 15, "options": { "annotations": { "clustering": -1, @@ -1335,7 +1359,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -1344,7 +1368,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -1378,12 +1402,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 12, - "y": 90 + "y": 50 }, - "id": 81, + "id": 16, "options": { "annotations": { "clustering": -1, @@ -1438,7 +1462,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -1447,7 +1471,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -1485,12 +1509,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 102 + "y": 58 }, - "id": 82, + "id": 17, "options": { "annotations": { "clustering": -1, @@ -1553,7 +1577,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -1562,7 +1586,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -1596,12 +1620,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 12, - "y": 102 + "y": 58 }, - "id": 83, + "id": 18, "options": { "annotations": { "clustering": -1, @@ -1664,7 +1688,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -1673,7 +1697,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -1703,16 +1727,17 @@ } ] }, - "unit": "short" + "unit": "short", + "decimals": 0 } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 114 + "y": 66 }, - "id": 84, + "id": 19, "options": { "annotations": { "clustering": -1, @@ -1783,7 +1808,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -1792,7 +1817,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -1826,12 +1851,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 12, - "y": 114 + "y": 66 }, - "id": 85, + "id": 20, "options": { "annotations": { "clustering": -1, @@ -1872,9 +1897,9 @@ "h": 1, "w": 24, "x": 0, - "y": 126 + "y": 74 }, - "id": 123, + "id": 21, "title": "Jobs", "type": "row" }, @@ -1908,7 +1933,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -1937,16 +1962,17 @@ } ] }, - "unit": "short" + "unit": "short", + "decimals": 0 } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 127 + "y": 75 }, - "id": 87, + "id": 22, "options": { "annotations": { "clustering": -1, @@ -2011,7 +2037,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -2044,12 +2070,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 12, - "y": 127 + "y": 75 }, - "id": 88, + "id": 23, "options": { "annotations": { "clustering": -1, @@ -2194,7 +2220,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -2227,12 +2253,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, "x": 0, - "y": 139 + "y": 83 }, - "id": 89, + "id": 24, "options": { "annotations": { "clustering": -1, @@ -2377,7 +2403,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -2410,12 +2436,12 @@ } }, "gridPos": { - "h": 16, - "w": 24, - "x": 0, - "y": 151 + "h": 8, + "w": 12, + "x": 12, + "y": 83 }, - "id": 90, + "id": 25, "options": { "annotations": { "clustering": -1, @@ -2480,7 +2506,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -2513,12 +2539,12 @@ } }, "gridPos": { - "h": 16, - "w": 24, + "h": 8, + "w": 12, "x": 0, - "y": 167 + "y": 91 }, - "id": 91, + "id": 26, "options": { "annotations": { "clustering": -1, @@ -2559,9 +2585,9 @@ "h": 1, "w": 24, "x": 0, - "y": 183 + "y": 99 }, - "id": 124, + "id": 27, "panels": [ { "datasource": { @@ -3007,9 +3033,9 @@ "h": 1, "w": 24, "x": 0, - "y": 184 + "y": 100 }, - "id": 125, + "id": 28, "title": "Server Info", "type": "row" }, @@ -3145,12 +3171,12 @@ ] }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 0, - "y": 185 + "y": 101 }, - "id": 98, + "id": 29, "options": { "colorMode": "background", "graphMode": "none", @@ -3183,8 +3209,11 @@ "refId": "A" } ], - "title": "Server State", - "type": "stat" + "title": "Server State [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3210,12 +3239,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 12, - "y": 185 + "y": 101 }, - "id": 99, + "id": 30, "options": { "colorMode": "value", "graphMode": "none", @@ -3245,8 +3274,11 @@ "refId": "A" } ], - "title": "Uptime", - "type": "stat" + "title": "Uptime [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3276,16 +3308,17 @@ } ] }, - "unit": "short" + "unit": "short", + "decimals": 0 } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 0, - "y": 197 + "y": 105 }, - "id": 100, + "id": 31, "options": { "colorMode": "value", "graphMode": "none", @@ -3315,8 +3348,11 @@ "refId": "A" } ], - "title": "Peer Count", - "type": "stat" + "title": "Peer Count [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3340,12 +3376,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 12, - "y": 197 + "y": 105 }, - "id": 103, + "id": 32, "options": { "colorMode": "none", "graphMode": "area", @@ -3377,8 +3413,11 @@ "refId": "A" } ], - "title": "Current Ledger Index", - "type": "stat" + "title": "Current Ledger Index [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3438,12 +3477,12 @@ ] }, "gridPos": { - "h": 7, + "h": 4, "w": 12, "x": 0, - "y": 209 + "y": 109 }, - "id": 58, + "id": 33, "options": { "colorMode": "background", "graphMode": "area", @@ -3475,8 +3514,11 @@ "refId": "A" } ], - "title": "Validated Ledger Seq \u2014 Convergence (Max \u2212 Min, per network)", - "type": "stat" + "title": "Validated Ledger Seq — Convergence (Max − Min, per network) [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3502,12 +3544,12 @@ } }, "gridPos": { - "h": 7, + "h": 4, "w": 12, "x": 12, - "y": 209 + "y": 109 }, - "id": 56, + "id": 34, "options": { "colorMode": "value", "graphMode": "none", @@ -3541,8 +3583,11 @@ "refId": "A" } ], - "title": "Validated Ledger Seq \u2014 Lag Behind Network Tip", - "type": "stat" + "title": "Validated Ledger Seq — Lag Behind Network Tip [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3564,12 +3609,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 0, - "y": 216 + "y": 113 }, - "id": 102, + "id": 35, "options": { "colorMode": "none", "graphMode": "none", @@ -3602,8 +3647,11 @@ "refId": "A" } ], - "title": "Build Version", - "type": "stat" + "title": "Build Version [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -3625,7 +3673,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -3634,7 +3682,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -3664,12 +3712,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 12, - "y": 216 + "x": 0, + "y": 117 }, - "id": 105, + "id": 36, "options": { "annotations": { "clustering": -1, @@ -3724,7 +3772,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -3733,7 +3781,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -3759,16 +3807,17 @@ } ] }, - "unit": "short" + "unit": "short", + "decimals": 0 } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 0, - "y": 228 + "x": 12, + "y": 117 }, - "id": 104, + "id": 37, "options": { "annotations": { "clustering": -1, @@ -3823,7 +3872,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -3832,7 +3881,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -3900,12 +3949,12 @@ ] }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 12, - "y": 228 + "x": 0, + "y": 125 }, - "id": 128, + "id": 38, "options": { "annotations": { "clustering": -1, @@ -3968,7 +4017,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -3977,7 +4026,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -4007,12 +4056,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 0, - "y": 240 + "x": 12, + "y": 125 }, - "id": 106, + "id": 39, "options": { "annotations": { "clustering": -1, @@ -4067,7 +4116,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "bars", - "fillOpacity": 80, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -4076,7 +4125,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 0, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -4106,16 +4155,17 @@ } ] }, - "unit": "short" + "unit": "short", + "decimals": 0 } }, "gridPos": { - "h": 16, - "w": 24, + "h": 8, + "w": 12, "x": 0, - "y": 252 + "y": 133 }, - "id": 107, + "id": 40, "options": { "annotations": { "clustering": -1, @@ -4156,9 +4206,9 @@ "h": 1, "w": 24, "x": 0, - "y": 268 + "y": 141 }, - "id": 126, + "id": 41, "title": "Complete Ledgers & DB", "type": "row" }, @@ -4198,11 +4248,11 @@ }, "gridPos": { "h": 12, - "w": 12, + "w": 24, "x": 0, - "y": 269 + "y": 142 }, - "id": 109, + "id": 42, "options": { "cellHeight": "sm", "showHeader": true, @@ -4222,8 +4272,11 @@ "refId": "A" } ], - "title": "Complete Ledger Ranges", - "type": "table" + "title": "Complete Ledger Ranges [$xrpl_network_type]", + "type": "table", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -4245,7 +4298,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -4254,7 +4307,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -4288,12 +4341,12 @@ } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 12, - "y": 269 + "x": 0, + "y": 154 }, - "id": 110, + "id": 43, "options": { "annotations": { "clustering": -1, @@ -4370,12 +4423,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 0, - "y": 281 + "y": 162 }, - "id": 111, + "id": 44, "options": { "colorMode": "value", "graphMode": "area", @@ -4407,8 +4460,11 @@ "refId": "A" } ], - "title": "Historical Fetch Rate", - "type": "stat" + "title": "Historical Fetch Rate [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -4430,7 +4486,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -4439,7 +4495,7 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, + "lineWidth": 1, "pointSize": 5, "scaleDistribution": { "type": "linear" @@ -4469,16 +4525,17 @@ } ] }, - "unit": "short" + "unit": "short", + "decimals": 0 } }, "gridPos": { - "h": 12, + "h": 8, "w": 12, - "x": 12, - "y": 281 + "x": 0, + "y": 166 }, - "id": 112, + "id": 45, "options": { "annotations": { "clustering": -1, @@ -4519,9 +4576,9 @@ "h": 1, "w": 24, "x": 0, - "y": 293 + "y": 174 }, - "id": 127, + "id": 46, "title": "Ledger Economy", "type": "row" }, @@ -4551,12 +4608,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 0, - "y": 294 + "y": 175 }, - "id": 114, + "id": 47, "options": { "colorMode": "value", "graphMode": "area", @@ -4588,8 +4645,11 @@ "refId": "A" } ], - "title": "Base Fee (drops)", - "type": "stat" + "title": "Base Fee (drops) [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -4617,12 +4677,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 12, - "y": 294 + "y": 175 }, - "id": 115, + "id": 48, "options": { "colorMode": "value", "graphMode": "area", @@ -4654,8 +4714,11 @@ "refId": "A" } ], - "title": "Reserve Base (drops)", - "type": "stat" + "title": "Reserve Base (drops) [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -4683,12 +4746,12 @@ } }, "gridPos": { - "h": 12, + "h": 4, "w": 12, "x": 0, - "y": 306 + "y": 179 }, - "id": 116, + "id": 49, "options": { "colorMode": "value", "graphMode": "area", @@ -4720,8 +4783,11 @@ "refId": "A" } ], - "title": "Reserve Inc (drops)", - "type": "stat" + "title": "Reserve Inc (drops) [$xrpl_network_type]", + "type": "stat", + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "datasource": { @@ -4743,7 +4809,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -4752,8 +4818,8 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, - "pointSize": 3, + "lineWidth": 1, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -4790,12 +4856,12 @@ } }, "gridPos": { - "h": 16, + "h": 8, "w": 12, - "x": 12, - "y": 306 + "x": 0, + "y": 183 }, - "id": 117, + "id": 50, "options": { "annotations": { "clustering": -1, @@ -4850,7 +4916,7 @@ "barAlignment": 0, "barWidthFactor": 0.6, "drawStyle": "line", - "fillOpacity": 10, + "fillOpacity": 0, "gradientMode": "none", "hideFrom": { "legend": false, @@ -4859,8 +4925,8 @@ }, "insertNulls": false, "lineInterpolation": "linear", - "lineWidth": 2, - "pointSize": 3, + "lineWidth": 1, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -4893,12 +4959,12 @@ } }, "gridPos": { - "h": 16, - "w": 24, - "x": 0, - "y": 322 + "h": 8, + "w": 12, + "x": 12, + "y": 183 }, - "id": 118, + "id": 51, "options": { "annotations": { "clustering": -1, @@ -4963,7 +5029,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -4996,12 +5062,12 @@ } }, "gridPos": { - "h": 16, + "h": 8, "w": 12, "x": 0, - "y": 338 + "y": 191 }, - "id": 119, + "id": 52, "options": { "annotations": { "clustering": -1, @@ -5066,7 +5132,7 @@ "insertNulls": false, "lineInterpolation": "linear", "lineWidth": 1, - "pointSize": 3, + "pointSize": 5, "scaleDistribution": { "type": "linear" }, @@ -5099,12 +5165,12 @@ } }, "gridPos": { - "h": 16, + "h": 8, "w": 12, "x": 12, - "y": 338 + "y": 191 }, - "id": 120, + "id": 53, "options": { "annotations": { "clustering": -1, @@ -5146,10 +5212,11 @@ "h": 1, "w": 24, "x": 0, - "y": 354 + "y": 199 }, "collapsed": false, - "panels": [] + "panels": [], + "id": 54 }, { "title": "Job Queue Saturation (Running vs Limit)", @@ -5157,9 +5224,9 @@ "type": "timeseries", "gridPos": { "h": 8, - "w": 24, + "w": 12, "x": 0, - "y": 355 + "y": 200 }, "options": { "tooltip": { @@ -5230,22 +5297,24 @@ "custom": { "axisLabel": "Running / Limit", "drawStyle": "line", - "lineWidth": 2, - "fillOpacity": 10, + "lineWidth": 1, + "fillOpacity": 0, "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3, + "pointSize": 5, "thresholdsStyle": { "mode": "line" - } + }, + "gradientMode": "none" }, "color": { "mode": "palette-classic" } }, "overrides": [] - } + }, + "id": 55 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json b/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json index b21a017f81..316bdf5234 100644 --- a/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json +++ b/docker/telemetry/grafana/dashboards/overlay-traffic-detail.json @@ -109,11 +109,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 1 }, { "title": "Overhead Traffic Breakdown (Bytes)", @@ -185,11 +189,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 2 }, { "title": "Validator List Traffic", @@ -247,7 +255,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [ @@ -268,7 +279,8 @@ ] } ] - } + }, + "id": 3 }, { "title": "Set Get/Share Traffic (Bytes)", @@ -326,11 +338,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 4 }, { "title": "Have/Requested Transactions (Messages)", @@ -388,11 +404,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 5 }, { "title": "Unknown / Unclassified Traffic", @@ -450,7 +470,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [ @@ -471,7 +494,8 @@ ] } ] - } + }, + "id": 6 }, { "title": "Proof Path Traffic", @@ -529,11 +553,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 7 }, { "title": "Replay Delta Traffic", @@ -591,11 +619,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 8 }, { "title": "GetObject Handler (TMGetObjectByHash)", @@ -607,7 +639,8 @@ "y": 32 }, "collapsed": false, - "panels": [] + "panels": [], + "id": 9 }, { "title": "GetObject Handler Latency Breakdown", @@ -615,7 +648,7 @@ "type": "timeseries", "gridPos": { "h": 8, - "w": 24, + "w": 12, "x": 0, "y": 33 }, @@ -655,17 +688,19 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3, + "pointSize": 5, "drawStyle": "line", - "lineWidth": 2, - "fillOpacity": 5 + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "color": { "mode": "palette-classic" } }, "overrides": [] - } + }, + "id": 10 }, { "title": "GetObject Request Size Distribution", @@ -674,8 +709,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 41 + "x": 12, + "y": 33 }, "options": { "tooltip": { @@ -703,7 +738,8 @@ "unit": "short" }, "overrides": [] - } + }, + "id": 11 }, { "title": "GetObject Lookups by Result", @@ -712,7 +748,7 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, + "x": 0, "y": 41 }, "options": { @@ -739,11 +775,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 12 }, { "title": "GetObject Rejections", @@ -752,8 +792,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 49 + "x": 12, + "y": 41 }, "options": { "tooltip": { @@ -779,11 +819,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 13 }, { "title": "GetObject Charge Distribution", @@ -792,7 +836,7 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, + "x": 0, "y": 49 }, "options": { @@ -831,17 +875,19 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3, + "pointSize": 5, "drawStyle": "line", - "lineWidth": 2, - "fillOpacity": 5 + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "color": { "mode": "palette-classic" } }, "overrides": [] - } + }, + "id": 14 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/peer-network.json b/docker/telemetry/grafana/dashboards/peer-network.json index 44fde48888..b27d693f8a 100644 --- a/docker/telemetry/grafana/dashboards/peer-network.json +++ b/docker/telemetry/grafana/dashboards/peer-network.json @@ -39,6 +39,19 @@ "id": null, "links": [], "panels": [ + { + "title": "Proposal & Validation Receive", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "collapsed": false, + "panels": [], + "id": 1 + }, { "title": "Peer Proposal Receive Rate", "description": "###### What this is:\n*How many consensus proposals this node receives from peers per second.*\n\n###### How it's computed:\n*Per-second rate of received proposals over 5 minutes, per node.*\n\n###### Reading it:\n*A steady rate roughly proportional to the number of proposing validators.*\n\n###### Healthy range:\n*Workload-dependent; scales with validator count and connectivity.*\n\n###### Watch for:\n*A drop toward zero (isolation from the network) or a sudden flood far above baseline (proposal spam).*\n\n###### Keywords:\n- **Consensus** *(network event)* \u2014 the protocol by which validators agree on the next ledger's transaction set and close time.\n- **Proposal** *(network event)* \u2014 a validator's advertised set of candidate transactions for the next ledger, revised each round.\n- **Proposers** *(network event)* \u2014 the count of validators whose proposals this node heard in the last closed round.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMProposeSet)`\n\n###### References:\n[Consensus](https://xrpl.org/docs/concepts/consensus-protocol/consensus-structure) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#consensus)", @@ -47,7 +60,7 @@ "h": 8, "w": 12, "x": 0, - "y": 0 + "y": 1 }, "options": { "tooltip": { @@ -74,11 +87,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 2 }, { "title": "Peer Validation Receive Rate", @@ -88,7 +105,7 @@ "h": 8, "w": 12, "x": 12, - "y": 0 + "y": 1 }, "options": { "tooltip": { @@ -115,11 +132,28 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 3 + }, + { + "title": "Trust Split", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 9 + }, + "collapsed": false, + "panels": [], + "id": 4 }, { "title": "Proposals Trusted vs Untrusted", @@ -129,7 +163,7 @@ "h": 8, "w": 12, "x": 0, - "y": 8 + "y": 10 }, "options": { "tooltip": { @@ -153,7 +187,8 @@ "unit": "short" }, "overrides": [] - } + }, + "id": 5 }, { "title": "Validations Trusted vs Untrusted", @@ -163,7 +198,7 @@ "h": 8, "w": 12, "x": 12, - "y": 8 + "y": 10 }, "options": { "tooltip": { @@ -187,7 +222,21 @@ "unit": "short" }, "overrides": [] - } + }, + "id": 6 + }, + { + "title": "Reduce-Relay", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 18 + }, + "collapsed": false, + "panels": [], + "id": 7 }, { "title": "Reduce-Relay Peer Selection", @@ -197,7 +246,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 19 }, "options": { "tooltip": { @@ -238,11 +287,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 - } + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + }, + "decimals": 0 }, "overrides": [] - } + }, + "id": 8 }, { "title": "Reduce-Relay Missing-Tx Frequency", @@ -252,7 +306,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 19 }, "options": { "tooltip": { @@ -279,11 +333,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 9 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/rpc-pathfinding.json b/docker/telemetry/grafana/dashboards/rpc-pathfinding.json index 610a7965f0..5117f65c41 100644 --- a/docker/telemetry/grafana/dashboards/rpc-pathfinding.json +++ b/docker/telemetry/grafana/dashboards/rpc-pathfinding.json @@ -40,11 +40,11 @@ "links": [], "panels": [ { - "title": "RPC Request Rate", + "title": "RPC Request Rate [$xrpl_network_type]", "description": "###### What this is:\n*How many RPC requests the server counts per second.*\n\n###### How it's computed:\n*Per-second rate of the RPC request counter over 5 minutes, per node.*\n\n###### Reading it:\n*A steady line proportional to client demand; cross-checks the trace-based RPC dashboard.*\n\n###### Healthy range:\n*Workload-dependent; tracks client activity.*\n\n###### Watch for:\n*A sudden surge above baseline, consistent with a client flooding the RPC endpoint.*\n\n###### Keywords:\n- **RPC command / method** *(per node)* \u2014 a named API request served by the node (e.g. account_info, ledger, submit), the unit RPC panels break down by.\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[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`\n\n###### References:\n[RPC command / method](https://xrpl.org/docs/references/http-websocket-apis/public-api-methods) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#rpc-command-method)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, "y": 0 @@ -71,7 +71,24 @@ "unit": "reqps" }, "overrides": [] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 1 + }, + { + "title": "RPC Response", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 4 + }, + "collapsed": false, + "panels": [], + "id": 2 }, { "title": "RPC Response Time", @@ -80,8 +97,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 0 + "x": 0, + "y": 5 }, "options": { "tooltip": { @@ -108,11 +125,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 3 }, { "title": "RPC Response Size", @@ -121,8 +142,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 8 + "x": 12, + "y": 5 }, "options": { "tooltip": { @@ -149,11 +170,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 4 }, { "title": "RPC Response Time Distribution", @@ -162,8 +187,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 8 + "x": 0, + "y": 13 }, "options": { "tooltip": { @@ -204,11 +229,28 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 5 + }, + { + "title": "Pathfinding", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "collapsed": false, + "panels": [], + "id": 6 }, { "title": "Pathfinding Fast Duration", @@ -218,7 +260,7 @@ "h": 8, "w": 12, "x": 0, - "y": 16 + "y": 22 }, "options": { "tooltip": { @@ -245,11 +287,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 7 }, { "title": "Pathfinding Full Duration", @@ -259,7 +305,7 @@ "h": 8, "w": 12, "x": 12, - "y": 16 + "y": 22 }, "options": { "tooltip": { @@ -286,21 +332,25 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 8 }, { - "title": "Resource Warnings Rate", + "title": "Resource Warnings Rate [$xrpl_network_type]", "description": "###### What this is:\n*How often the resource manager warns a peer or client for excessive usage, per second.*\n\n###### How it's computed:\n*Per-second rate of resource-warning events over 5 minutes, per node.*\n\n###### Reading it:\n*Green near zero, yellow above 0.1/sec, red above 1/sec.*\n\n###### Healthy range:\n*Near zero in normal operation.*\n\n###### Watch for:\n*A rising rate, consistent with aggressive clients that may need throttling.*\n\n###### Keywords:\n- **Resource drops / warnings** *(per node)* \u2014 the resource manager warning (then dropping/blocking) a peer or client for excessive usage.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[Logic.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/resource/detail/Logic.h)\n\n###### Function:\n`Logic::Stats ctor`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#resource-drops-warnings)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, - "y": 24 + "y": 30 }, "options": { "tooltip": { @@ -340,17 +390,21 @@ } }, "overrides": [] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 9 }, { - "title": "Resource Drops Rate", + "title": "Resource Drops Rate [$xrpl_network_type]", "description": "###### What this is:\n*How often the resource manager drops or blocks a peer or client for abuse, per second.*\n\n###### How it's computed:\n*Per-second rate of resource-drop events over 5 minutes, per node.*\n\n###### Reading it:\n*Green near zero, yellow above 0.01/sec, red above 0.1/sec.*\n\n###### Healthy range:\n*Zero when no abusive consumers are present.*\n\n###### Watch for:\n*Non-zero values, meaning the node is actively rejecting abusive connections.*\n\n###### Keywords:\n- **Resource drops / warnings** *(per node)* \u2014 the resource manager warning (then dropping/blocking) a peer or client for excessive usage.\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[Logic.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/resource/detail/Logic.h)\n\n###### Function:\n`Logic::Stats ctor`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#resource-drops-warnings)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 12, - "y": 24 + "y": 30 }, "options": { "tooltip": { @@ -390,7 +444,24 @@ } }, "overrides": [] - } + }, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2, + "id": 10 + }, + { + "title": "gRPC (Spans)", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 34 + }, + "collapsed": false, + "panels": [], + "id": 11 }, { "title": "gRPC Request Rate by Method (Spans)", @@ -400,7 +471,7 @@ "h": 8, "w": 12, "x": 0, - "y": 32 + "y": 35 }, "options": { "tooltip": { @@ -427,11 +498,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 12 }, { "title": "gRPC Latency P95 by Method (Spans)", @@ -441,7 +516,7 @@ "h": 8, "w": 12, "x": 12, - "y": 32 + "y": 35 }, "options": { "tooltip": { @@ -468,11 +543,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 13 }, { "title": "gRPC Error Rate by Status (Spans)", @@ -482,7 +561,7 @@ "h": 8, "w": 12, "x": 0, - "y": 40 + "y": 43 }, "options": { "tooltip": { @@ -509,11 +588,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 14 }, { "title": "Pathfinding Compute Duration (Spans)", @@ -523,7 +606,7 @@ "h": 8, "w": 12, "x": 12, - "y": 40 + "y": 43 }, "options": { "tooltip": { @@ -550,11 +633,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 15 }, { "title": "Pathfinding Request & Discovery Rate (Spans)", @@ -562,9 +649,9 @@ "type": "timeseries", "gridPos": { "h": 8, - "w": 24, + "w": 12, "x": 0, - "y": 48 + "y": 51 }, "options": { "tooltip": { @@ -598,11 +685,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] - } + }, + "id": 16 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/rpc-performance.json b/docker/telemetry/grafana/dashboards/rpc-performance.json index a378b29e40..797d260d8f 100644 --- a/docker/telemetry/grafana/dashboards/rpc-performance.json +++ b/docker/telemetry/grafana/dashboards/rpc-performance.json @@ -39,7 +39,7 @@ "links": [], "panels": [ { - "id": 11, + "id": 1, "type": "row", "title": "Aggregate RPC (all commands)", "collapsed": false, @@ -86,12 +86,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 1 + "id": 2 }, { "title": "RPC Latency P95 by Command", @@ -128,19 +131,22 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 2 + "id": 3 }, { - "title": "RPC Error Rate", + "title": "RPC Error Rate [$xrpl_network_type]", "description": "###### What this is:\n*The percentage of each command's calls that finished with an error.*\n\n###### How it's computed:\n*Error calls divided by total calls per command over 5 minutes, expressed as a percent.*\n\n###### Reading it:\n*Green under 1%, yellow 1-5%, red above 5%.*\n\n###### Healthy range:\n*Below 1% per command in normal operation.*\n\n###### Watch for:\n*A command sitting red, indicating malformed input, overload, or a broken handler.*\n\n###### Keywords:\n- **RPC command / method** *(per node)* \u2014 a named API request served by the node (e.g. account_info, ledger, submit), the unit RPC panels break down by.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`\n\n###### References:\n[RPC command / method](https://xrpl.org/docs/references/http-websocket-apis/public-api-methods) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#rpc-command-method)", "type": "bargauge", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, "y": 9 @@ -184,7 +190,10 @@ }, "overrides": [] }, - "id": 3 + "id": 4, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "title": "RPC Latency Heatmap", @@ -193,8 +202,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 9 + "x": 0, + "y": 13 }, "options": { "tooltip": { @@ -223,7 +232,7 @@ "unit": "ms" } }, - "id": 4 + "id": 5 }, { "title": "Overall RPC Throughput", @@ -232,8 +241,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 0, - "y": 17 + "x": 12, + "y": 13 }, "options": { "tooltip": { @@ -267,12 +276,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 5 + "id": 6 }, { "title": "RPC Success vs Error", @@ -281,8 +293,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 17 + "x": 0, + "y": 21 }, "options": { "tooltip": { @@ -316,22 +328,25 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 6 + "id": 7 }, { - "title": "Top Commands by Volume", + "title": "Top Commands by Volume [$xrpl_network_type]", "description": "###### What this is:\n*The ten most-called RPC commands over the recent window.*\n\n###### How it's computed:\n*Total invocation counts per command over the last 5 minutes, ranked and capped at ten.*\n\n###### Reading it:\n*The top bars are the hottest endpoints driving node load.*\n\n###### Healthy range:\n*Workload-dependent; typically led by lightweight status queries.*\n\n###### Watch for:\n*An unexpected command dominating the ranking, consistent with automated abuse.*\n\n###### Keywords:\n- **RPC command / method** *(per node)* \u2014 a named API request served by the node (e.g. account_info, ledger, submit), the unit RPC panels break down by.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`\n\n###### References:\n[RPC command / method](https://xrpl.org/docs/references/http-websocket-apis/public-api-methods) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#rpc-command-method)", "type": "bargauge", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, - "y": 25 + "y": 29 }, "options": { "tooltip": { @@ -356,17 +371,20 @@ }, "overrides": [] }, - "id": 7 + "id": 8, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { - "title": "WebSocket Message Rate", + "title": "WebSocket Message Rate [$xrpl_network_type]", "description": "###### What this is:\n*How many RPC messages arrive over WebSocket connections per second.*\n\n###### How it's computed:\n*Per-second rate of processed WebSocket RPC messages over 5 minutes, per node.*\n\n###### Reading it:\n*Non-zero only when clients use WebSocket; zero is normal for HTTP-only nodes.*\n\n###### Healthy range:\n*Workload-dependent; zero if no WebSocket clients.*\n\n###### Watch for:\n*A sudden surge from a single source, consistent with a chatty or abusive subscription client.*\n\n###### Keywords:\n- **RPC command / method** *(per node)* \u2014 a named API request served by the node (e.g. account_info, ledger, submit), the unit RPC panels break down by.\n- **WebSocket** *(per node)* \u2014 a persistent-connection API transport used by subscription clients; zero on HTTP-only nodes.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler::processSession`\n\n###### References:\n[RPC command / method](https://xrpl.org/docs/references/http-websocket-apis/public-api-methods) \u00b7 [WebSocket](https://xrpl.org/docs/references/http-websocket-apis/api-conventions) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#rpc-command-method)", "type": "stat", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 12, - "y": 25 + "y": 29 }, "options": { "tooltip": { @@ -391,7 +409,10 @@ }, "overrides": [] }, - "id": 8 + "id": 9, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "title": "RPC Resource Cost by Command", @@ -399,7 +420,7 @@ "type": "timeseries", "gridPos": { "h": 8, - "w": 12, + "w": 24, "x": 0, "y": 33 }, @@ -433,12 +454,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 9 + "id": 10 }, { "title": "Batch vs Single RPC Requests", @@ -447,8 +471,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 33 + "x": 0, + "y": 41 }, "options": { "tooltip": { @@ -482,12 +506,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 10 + "id": 11 }, { "id": 12, @@ -498,7 +525,7 @@ "h": 1, "w": 24, "x": 0, - "y": 41 + "y": 49 }, "panels": [] }, @@ -508,9 +535,9 @@ "type": "timeseries", "gridPos": { "h": 8, - "w": 24, + "w": 12, "x": 0, - "y": 42 + "y": 50 }, "options": { "tooltip": { @@ -548,13 +575,14 @@ "unit": "suffix: calls/s", "custom": { "drawStyle": "line", - "lineWidth": 2, - "fillOpacity": 10, + "lineWidth": 1, + "fillOpacity": 0, "axisLabel": "Calls / Sec", "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "gradientMode": "none" }, "color": { "mode": "palette-classic" @@ -572,7 +600,7 @@ "h": 8, "w": 24, "x": 0, - "y": 50 + "y": 58 }, "options": { "tooltip": { @@ -602,12 +630,13 @@ "custom": { "drawStyle": "line", "lineWidth": 1, - "fillOpacity": 5, + "fillOpacity": 0, "axisLabel": "Calls / Sec", "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "gradientMode": "none" }, "color": { "mode": "palette-classic" @@ -625,7 +654,7 @@ "h": 8, "w": 24, "x": 0, - "y": 58 + "y": 66 }, "options": { "tooltip": { @@ -655,12 +684,13 @@ "custom": { "drawStyle": "line", "lineWidth": 1, - "fillOpacity": 5, + "fillOpacity": 0, "axisLabel": "Errors / Sec", "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "gradientMode": "none" }, "color": { "mode": "palette-classic" @@ -678,7 +708,7 @@ "h": 8, "w": 12, "x": 0, - "y": 66 + "y": 74 }, "options": { "tooltip": { @@ -709,13 +739,14 @@ "unit": "\u00b5s", "custom": { "drawStyle": "line", - "lineWidth": 2, - "fillOpacity": 5, + "lineWidth": 1, + "fillOpacity": 0, "axisLabel": "Duration (\u03bcs)", "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "gradientMode": "none" }, "color": { "mode": "palette-classic" @@ -733,7 +764,7 @@ "h": 8, "w": 24, "x": 0, - "y": 74 + "y": 82 }, "options": { "tooltip": { @@ -763,12 +794,13 @@ "custom": { "drawStyle": "line", "lineWidth": 1, - "fillOpacity": 5, + "fillOpacity": 0, "axisLabel": "Duration (\u03bcs)", "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "gradientMode": "none" }, "color": { "mode": "palette-classic" @@ -786,7 +818,7 @@ "h": 8, "w": 24, "x": 0, - "y": 82 + "y": 90 }, "options": { "tooltip": { @@ -818,12 +850,13 @@ "custom": { "drawStyle": "line", "lineWidth": 1, - "fillOpacity": 5, + "fillOpacity": 0, "axisLabel": "Error Ratio", "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "gradientMode": "none" }, "color": { "mode": "palette-classic" @@ -850,14 +883,14 @@ "id": 18 }, { - "title": "Current RPC Latency (p99 Gauge)", + "title": "Current RPC Latency (p99 Gauge) [$xrpl_network_type]", "description": "###### What this is:\n*Current tail latency (p99) of RPC handling across all methods, as a live gauge.*\n\n###### How it's computed:\n*p99 of the method-duration histogram over the recent window.*\n\n###### Reading it:\n*A single at-a-glance number for current RPC responsiveness.*\n\n###### Healthy range:\n*Low-millisecond under normal load.*\n\n###### Watch for:\n*Sustained elevation, indicating the node is under query pressure.*\n\n###### Keywords:\n- **RPC command / method** *(per node)* \u2014 a named API request served by the node (e.g. account_info, ledger, submit), the unit RPC panels break down by.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Computed in xrpld code (MetricsRegistry, OpenTelemetry SDK) and exported as a metric; the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcFinished`\n\n###### References:\n[RPC command / method](https://xrpl.org/docs/references/http-websocket-apis/public-api-methods) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#rpc-command-method)", "type": "gauge", "gridPos": { - "h": 8, + "h": 4, "w": 12, "x": 0, - "y": 90 + "y": 98 }, "options": { "reduceOptions": { @@ -904,7 +937,10 @@ }, "overrides": [] }, - "id": 19 + "id": 19, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 } ], "schemaVersion": 39, diff --git a/docker/telemetry/grafana/dashboards/transaction-overview.json b/docker/telemetry/grafana/dashboards/transaction-overview.json index f71b2ce73e..bb697f3336 100644 --- a/docker/telemetry/grafana/dashboards/transaction-overview.json +++ b/docker/telemetry/grafana/dashboards/transaction-overview.json @@ -39,12 +39,12 @@ "links": [], "panels": [ { - "title": "Transaction Apply Failed Rate", + "title": "Transaction Apply Failed Rate [$xrpl_network_type]", "description": "###### What this is:\n*Transactions that fail during the apply (transactor) stage, per second \u2014 i.e. the transactor ran but the result was not tesSUCCESS.*\n\n###### How it's computed:\n*Per-second rate of tx.transactor spans at the apply stage whose ter_result is not tesSUCCESS, over the dashboard rate interval, per node.*\n\n###### Reading it:\n*A steady low background is normal (tefPAST_SEQ, tecUNFUNDED, etc.); the transactor legitimately rejects many transactions.*\n\n###### Healthy range:\n*A low, stable rate; workload-dependent.*\n\n###### Watch for:\n*A sharp rise above baseline, which points to a submission pattern that is systematically failing at apply.*\n\n###### Keywords:\n- **Transactor** *(per node)* \u2014 the rippled component that executes one transaction's type-specific logic against the ledger.\n- **Transaction result codes** *(network-wide)* \u2014 the outcome code a transaction returns \u2014 tesSUCCESS, or a tec/tef/tem/ter/tel class code on failure.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/tx/detail/Transactor.cpp)\n\n###### Function:\n`Transactor::operator()`\n\n###### References:\n[Transactor](https://xrpl.org/docs/references/protocol/transactions/transaction-results) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#transactor)", "type": "stat", "gridPos": { "h": 4, - "w": 6, + "w": 12, "x": 0, "y": 0 }, @@ -87,7 +87,10 @@ }, "overrides": [] }, - "id": 1 + "id": 1, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 }, { "title": "Transaction Processing Latency by Type", @@ -129,13 +132,29 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, "id": 2 }, + { + "title": "Throughput & Results", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 12 + }, + "collapsed": false, + "panels": [], + "id": 3 + }, { "title": "Transaction Rate by Type", "description": "###### What this is:\n*How many transactions of each type enter processing per second.*\n\n###### How it's computed:\n*Per-second processing rate over 5 minutes, grouped by transaction type and node.*\n\n###### Reading it:\n*Shows the transaction mix; payments usually lead.*\n\n###### Healthy range:\n*Workload-dependent; mix reflects network activity.*\n\n###### Watch for:\n*A single type spiking far above baseline, consistent with a spam campaign of that type.*\n\n###### Keywords:\n- **Transaction type** *(network-wide)* \u2014 the kind of transaction (Payment, OfferCreate, TrustSet, AMM*, NFToken*, etc.), used as a breakdown dimension.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::processTransaction`\n\n###### References:\n[Transaction type](https://xrpl.org/docs/references/protocol/transactions/types) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#transaction-type)", @@ -144,7 +163,7 @@ "h": 8, "w": 24, "x": 0, - "y": 12 + "y": 13 }, "options": { "tooltip": { @@ -176,12 +195,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 3 + "id": 4 }, { "title": "Transaction Results by Type", @@ -191,7 +213,7 @@ "h": 8, "w": 24, "x": 0, - "y": 20 + "y": 21 }, "options": { "tooltip": { @@ -222,13 +244,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}" }, "overrides": [] }, - "id": 4 + "id": 5 }, { "title": "Transaction Receive vs Suppressed", @@ -238,7 +263,7 @@ "h": 8, "w": 12, "x": 0, - "y": 28 + "y": 29 }, "options": { "tooltip": { @@ -265,12 +290,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 5 + "id": 6 }, { "title": "Transaction Processing Rate", @@ -280,7 +308,7 @@ "h": 8, "w": 12, "x": 12, - "y": 28 + "y": 29 }, "options": { "tooltip": { @@ -314,12 +342,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 6 + "id": 7 }, { "title": "Transaction Path Distribution", @@ -329,7 +360,7 @@ "h": 8, "w": 12, "x": 0, - "y": 36 + "y": 37 }, "fieldConfig": { "defaults": { @@ -354,7 +385,7 @@ "expr": "label_replace(label_join(label_replace(sum by (local, service_instance_id, xrpl_branch, xrpl_node_role) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", local=~\"$tx_origin\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval])), \"series\", \"Local $1\", \"local\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")" } ], - "id": 7 + "id": 8 }, { "title": "Transaction Processing Duration Heatmap", @@ -364,7 +395,7 @@ "h": 8, "w": 12, "x": 12, - "y": 36 + "y": 37 }, "options": { "tooltip": { @@ -393,7 +424,7 @@ "unit": "ms" } }, - "id": 8 + "id": 9 }, { "title": "Transactor Duration by Type (p95)", @@ -403,7 +434,7 @@ "h": 8, "w": 24, "x": 0, - "y": 44 + "y": 45 }, "options": { "tooltip": { @@ -435,7 +466,10 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] @@ -443,14 +477,14 @@ "id": 10 }, { - "title": "TxQ Accept: Applied Ratio per Node (State Timeline)", + "title": "TxQ Accept: Applied Ratio per Node (State Timeline) [$xrpl_network_type]", "description": "###### What this is:\n*The applied fraction of TxQ accepts per node over time: the share of queued transactions that were included in a ledger versus removed on failure.*\n\n###### How it's computed:\n*Per node, applied accepts divided by applied-plus-failed accepts over the window.*\n\n###### Reading it:\n*Green (>=90% applied) is a healthy drain; yellow is degraded; red means accepts are mostly failing.*\n\n###### Healthy range:\n*At or near 100% applied when the queue is draining healthily; workload-dependent.*\n\n###### Watch for:\n*A node dropping into yellow or red, which signals queue pressure, under-bidding, or fee escalation on that node.*\n\n###### Keywords:\n- **Transaction queue (TxQ)** *(per node)* \u2014 holds transactions that meet local cost but not the open-ledger cost, to include in a later ledger.\n- **Queue accept (drain)** *(per node)* \u2014 moving queued transactions into a newly closed ledger; the applied share shows drain health.\n- **Fee escalation** *(per node)* \u2014 the exponential rise in the open-ledger cost once the ledger exceeds its soft transaction target.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in code as a trace span, turned into a metric by the collector (SpanMetrics connector), then aggregated by the Grafana query.*\n\n###### Source:\n[TxQ.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/detail/TxQ.cpp)\n\n###### Function:\n`TxQ::accept`\n\n###### References:\n[Transaction queue (TxQ)](https://xrpl.org/docs/concepts/transactions/transaction-queue) \u00b7 [Fee escalation](https://xrpl.org/docs/concepts/transactions/transaction-cost#open-ledger-cost) \u00b7 [Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#transaction-queue-txq)", "type": "state-timeline", "gridPos": { "h": 8, - "w": 24, + "w": 12, "x": 0, - "y": 52 + "y": 53 }, "options": { "mergeValues": true, @@ -512,7 +546,73 @@ }, "overrides": [] }, - "id": 11 + "id": 11, + "repeat": "xrpl_network_type", + "repeatDirection": "h", + "maxPerRow": 2 + }, + { + "title": "Tx Apply Pipeline Rate by Stage", + "description": "**What:** Throughput of each apply-pipeline stage (preflight, preclaim, apply), showing where transactions drop out.\n**How it's computed:** Per-second rate per stage over a 5-minute window, per node.\n**Reading it:** A decline from earlier to later stages shows where transactions are filtered.\n**Healthy range:** Workload-dependent; later stages sit at or below earlier ones.\n**Watch for:** A large early-stage drop means many transactions fail basic checks, consistent with malformed floods.\n**Source:** src/libxrpl/tx/Transactor.cpp:Transactor::operator()", + "type": "timeseries", + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 61 + }, + "options": { + "tooltip": { + "mode": "multi", + "sort": "desc", + "maxHeight": 600 + }, + "legend": { + "displayMode": "table", + "placement": "right", + "calcs": ["mean", "max"] + } + }, + "targets": [ + { + "datasource": { + "type": "prometheus" + }, + "expr": "sum by (stage, 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.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[$__rate_interval]))", + "interval": "15s", + "legendFormat": "{{stage}} [{{service_instance_id}}]" + } + ], + "fieldConfig": { + "defaults": { + "unit": "ops", + "custom": { + "axisLabel": "Spans / Sec", + "spanNulls": 1800000, + "insertNulls": false, + "showPoints": "auto", + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" + } + }, + "overrides": [] + }, + "id": 12 + }, + { + "title": "Apply Pipeline", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 69 + }, + "collapsed": false, + "panels": [], + "id": 13 }, { "title": "Tx Apply Pipeline Latency by Stage (p95)", @@ -522,7 +622,7 @@ "h": 8, "w": 24, "x": 0, - "y": 60 + "y": 70 }, "options": { "tooltip": { @@ -554,12 +654,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 12 + "id": 14 }, { "title": "Tx Apply Pipeline Failure Rate by Stage", @@ -569,7 +672,7 @@ "h": 8, "w": 24, "x": 0, - "y": 68 + "y": 78 }, "options": { "tooltip": { @@ -601,12 +704,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 13 + "id": 15 }, { "title": "Tx Apply Pipeline Latency by Type and Stage (p95)", @@ -616,7 +722,7 @@ "h": 8, "w": 24, "x": 0, - "y": 76 + "y": 86 }, "options": { "tooltip": { @@ -647,13 +753,16 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" }, "displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}" }, "overrides": [] }, - "id": 14 + "id": 16 }, { "title": "Transaction Apply Duration per Ledger", @@ -663,7 +772,7 @@ "h": 8, "w": 12, "x": 0, - "y": 84 + "y": 94 }, "options": { "tooltip": { @@ -690,12 +799,28 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 15 + "id": 17 + }, + { + "title": "Transaction Queue", + "type": "row", + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 102 + }, + "collapsed": false, + "panels": [], + "id": 18 }, { "title": "TxQ Enqueue Rate by Transaction Type", @@ -704,8 +829,8 @@ "gridPos": { "h": 8, "w": 12, - "x": 12, - "y": 84 + "x": 0, + "y": 103 }, "options": { "tooltip": { @@ -732,12 +857,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 16 + "id": 19 }, { "title": "Queue Accept (Drain) Duration per Ledger", @@ -745,9 +873,9 @@ "type": "timeseries", "gridPos": { "h": 8, - "w": 24, - "x": 0, - "y": 92 + "w": 12, + "x": 12, + "y": 103 }, "options": { "tooltip": { @@ -774,12 +902,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 19 + "id": 20 }, { "title": "Queue Cleanup Rate (Expired Entries)", @@ -789,7 +920,7 @@ "h": 8, "w": 12, "x": 0, - "y": 100 + "y": 111 }, "options": { "tooltip": { @@ -816,12 +947,15 @@ "spanNulls": 1800000, "insertNulls": false, "showPoints": "auto", - "pointSize": 3 + "pointSize": 5, + "lineWidth": 1, + "fillOpacity": 0, + "gradientMode": "none" } }, "overrides": [] }, - "id": 20 + "id": 21 } ], "schemaVersion": 39,