ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-08-21 22:30:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'pratik/otel-phase9-metric-gap-fill' into pratik/otel-phase10-workload-validation

Browse Source
This commit is contained in:
Pratik Mankawde
2026-08-05 15:54:38 +01:00
parent a52f952924 5ed32063f5
commit fd4783319e
370 changed files with 15639 additions and 11722 deletions
Download Patch File Download Diff File Expand all files Collapse all files

186
docker/telemetry/grafana/dashboards/log-derived-insights.json
View File

@@ -220,7 +220,7 @@
"type": "text",
"title": "Read This First — Debug Log Requirement",
"gridPos": {
"h": 12,
"h": 10,
"w": 24,
"x": 0,
"y": 0
@@ -259,14 +259,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"w": 12,
"x": 0,
"y": 13
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: errors",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -315,7 +314,8 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (count_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | severity =~ `ERR|FTL` [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Errors [{{service_instance_id}}]"
}
],
"id": 3
@@ -330,14 +330,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"x": 6,
"w": 12,
"x": 12,
"y": 13
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: charges",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -386,7 +385,8 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (count_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `Resource` |~ `useless data|unwanted data|init drop` [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Charges [{{service_instance_id}}]"
}
],
"id": 4
@@ -401,14 +401,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"x": 12,
"y": 13
"w": 12,
"x": 0,
"y": 21
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: fee",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -457,7 +456,8 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `Resource` | regexp `\\(\\$(?P<fee>[0-9]+)\\)` | unwrap fee [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Fee Charged [{{service_instance_id}}]"
}
],
"id": 5
@@ -472,14 +472,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"x": 18,
"y": 13
"w": 12,
"x": 12,
"y": 21
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: rejections",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -528,7 +527,8 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (count_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `ManifestCache` |~ `Manifest: (Stale|Invalid|Revoked|UntrustedCapacity)` [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Rejections [{{service_instance_id}}]"
}
],
"id": 6
@@ -543,14 +543,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"w": 12,
"x": 0,
"y": 21
"y": 29
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: events",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -599,7 +598,8 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (count_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `LedgerConsensus` | severity =~ `WRN|ERR|FTL` [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Consensus Events [{{service_instance_id}}]"
}
],
"id": 7
@@ -614,14 +614,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"x": 6,
"y": 21
"w": 12,
"x": 12,
"y": 29
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: breaches",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -670,7 +669,8 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (count_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `LoadMonitor` |~ `Job: .* run: [0-9]+ms wait: [0-9]+ms` [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Breaches [{{service_instance_id}}]"
}
],
"id": 8
@@ -685,14 +685,13 @@
},
"gridPos": {
"h": 8,
"w": 6,
"x": 12,
"y": 21
"w": 12,
"x": 0,
"y": 37
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "suffix: transitions",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -741,29 +740,29 @@
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (count_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" |~ `STATE->(syncing|connected|tracking|disconnected)` [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Transitions [{{service_instance_id}}]"
}
],
"id": 9
},
{
"type": "stat",
"title": "Nodes By Ledger Fetch Waste",
"description": "###### What this is:\n*Which nodes waste the most bandwidth fetching ledger data they already hold.*\n\n###### How it's computed:\n*Duplicate ledger nodes divided by total fetched, per node, from the InboundLedger stats lines.*\n\n###### Reading it:\n*A ratio of 0.8 means four in five fetched nodes were already present locally.*\n\n###### Healthy range:\n*Below roughly 0.3. Some duplication is unavoidable when fetching from several peers.*\n\n###### Watch for:\n*Sustained values above 0.8, which waste both bandwidth and peer resource credit.*\n\n###### Keywords:\n- **Duplicate** *(per fetch)* — a ledger node already held locally.\n\n###### Computation boundary:\n*Result: Per node — a RATIO of two summed counters, not a count.*\n*Derived in the Grafana query via `unwrap`.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::onTimer`\n\n###### Note:\n*Requires debug logs on the InboundLedger partition.*\n\n###### References:\n[Ledgers](https://xrpl.org/docs/concepts/ledgers)",
"title": "Nodes By Duplicate Ledger Fetches",
"description": "###### What this is:\n*Which nodes wasted the most ledger-fetch bandwidth, counted as duplicate SHAMap nodes received.*\n\n###### How it's computed:\n*Sum of the `dupe` counter from `Ledger AS/TX node stats` log lines, per node, over the dashboard window. `dupe` is matched by its own regex because the emitter omits any counter that is zero.*\n\n###### Reading it:\n*Every duplicate is a ledger node the peer sent that this node already held: bytes crossed the network, the peer spent resource credit serving it, and it was discarded.*\n\n###### Healthy range:\n*Workload-dependent. Compare nodes of the same role rather than reading an absolute value; some duplication is unavoidable when fetching one ledger from several peers.*\n\n###### Watch for:\n*A node far ahead of its siblings, which points at that node's fetch logic or peer set rather than a network condition.*\n\n###### Keywords:\n- **Ledger node** *(per fetch)* — one SHAMap node fetched while acquiring a ledger.\n- **Duplicate** *(per fetch)* — a node already held locally; wasted bandwidth and peer credit.\n\n###### Computation boundary:\n*Result: Per node — a COUNT of duplicates, not a ratio.*\n*NOT recorded as a metric. Derived in the Grafana query via `unwrap` over raw log text.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::onTimer`\n\n###### Note:\n*Requires debug logs on the InboundLedger partition. For the duplicate RATIO see \"Ledger Node Fetch Duplicate Ratio\" in the Ledger Acquisition Efficiency row — a stat panel cannot render a division, because Loki does not name binary-operation frames and Grafana falls back to \"Value #A\".*\n\n###### References:\n[Ledgers](https://xrpl.org/docs/concepts/ledgers)",
"datasource": {
"type": "loki",
"uid": "${DS_LOKI}"
},
"gridPos": {
"h": 8,
"w": 6,
"x": 18,
"y": 21
"w": 12,
"x": 12,
"y": 37
},
"fieldConfig": {
"defaults": {
"displayName": "${__field.labels.service_instance_id}",
"unit": "percentunit",
"unit": "short",
"thresholds": {
"mode": "absolute",
"steps": [
@@ -773,17 +772,15 @@
},
{
"color": "yellow",
"value": 0.5
"value": 100000
},
{
"color": "red",
"value": 0.8
"value": 1000000
}
]
},
"custom": {},
"min": 0,
"max": 1
"custom": {}
},
"overrides": []
},
@@ -795,7 +792,7 @@
"textMode": "value_and_name",
"wideLayout": true,
"reduceOptions": {
"calcs": ["mean"],
"calcs": ["max"],
"fields": "",
"values": false
},
@@ -812,9 +809,10 @@
"uid": "${DS_LOKI}"
},
"refId": "A",
"expr": "topk($topn, sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__range])) / (sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__range])) + sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap good [$__range]))))",
"expr": "topk($topn, sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | regexp `dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__range])))",
"instant": true,
"queryType": "instant"
"queryType": "instant",
"legendFormat": "Duplicates [{{service_instance_id}}]"
}
],
"id": 10
@@ -827,7 +825,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 41
"y": 45
},
"panels": [],
"id": 11
@@ -844,7 +842,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 42
"y": 46
},
"fieldConfig": {
"defaults": {
@@ -904,7 +902,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 42
"y": 46
},
"fieldConfig": {
"defaults": {
@@ -912,7 +910,8 @@
"custom": {
"fillOpacity": 80,
"lineWidth": 0,
"spanNulls": true
"spanNulls": 1800000,
"insertNulls": false
},
"color": {
"mode": "palette-classic"
@@ -956,7 +955,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 52
"y": 56
},
"panels": [],
"id": 14
@@ -969,7 +968,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 53
"y": 57
},
"fieldConfig": {
"defaults": {
@@ -1028,7 +1027,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 53
"y": 57
},
"fieldConfig": {
"defaults": {
@@ -1087,7 +1086,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 63
"y": 67
},
"panels": [],
"id": 17
@@ -1100,7 +1099,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 64
"y": 68
},
"fieldConfig": {
"defaults": {
@@ -1159,7 +1158,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 64
"y": 68
},
"fieldConfig": {
"defaults": {
@@ -1227,7 +1226,7 @@
"h": 14,
"w": 24,
"x": 0,
"y": 74
"y": 78
},
"fieldConfig": {
"defaults": {
@@ -1364,7 +1363,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 88
"y": 92
},
"panels": [],
"id": 21
@@ -1377,7 +1376,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 89
"y": 93
},
"fieldConfig": {
"defaults": {
@@ -1436,7 +1435,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 89
"y": 93
},
"fieldConfig": {
"defaults": {
@@ -1495,7 +1494,7 @@
"h": 14,
"w": 24,
"x": 0,
"y": 99
"y": 103
},
"fieldConfig": {
"defaults": {
@@ -1644,7 +1643,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 113
"y": 117
},
"panels": [],
"id": 25
@@ -1652,12 +1651,12 @@
{
"type": "timeseries",
"title": "Ledger Node Fetch Duplicate Ratio",
"description": "###### What this is:\n*The fraction of fetched ledger nodes that were duplicates this node already held.*\n\n###### How it's computed:\n*Sum of the dupe counter divided by the sum of good plus dupe, parsed from the `Ledger AS/TX node stats` log lines.*\n\n###### Reading it:\n*This is wasted ledger-fetch bandwidth. A ratio of 0.5 means half of everything fetched was already present.*\n\n###### Healthy range:\n*Below roughly 0.3. Some duplication is unavoidable when fetching from several peers at once.*\n\n###### Watch for:\n*Sustained values above 0.8. Live observation has recorded good:142 dupe:891, an 86 percent duplicate rate, which wastes both bandwidth and peer resource credit.*\n\n###### Keywords:\n- **Ledger node** *(per fetch)* — one SHAMap node fetched while acquiring a ledger.\n- **Duplicate** *(per fetch)* — a node already held locally; wasted bandwidth and peer credit.\n\n###### Computation boundary:\n*Result: Per node — a ratio of two summed counters, dupe / (good + dupe).*\n*NOT recorded as a metric. Derived in the Grafana query via `unwrap` over the counters in the InboundLedger stats line.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::onTimer / takeAsRootNode`\n\n###### References:\n[Ledgers](https://xrpl.org/docs/concepts/ledgers)",
"description": "###### What this is:\n*The fraction of fetched ledger nodes that were duplicates this node already held.*\n\n###### How it's computed:\n*Sum of the dupe counter divided by the sum of good plus dupe, parsed from the `Ledger AS/TX node stats` log lines. Each field is matched independently because the emitter omits any counter that is zero.*\n\n###### Reading it:\n*This is wasted ledger-fetch bandwidth. A ratio of 0.5 means half of everything fetched was already present.*\n\n###### Healthy range:\n*Below roughly 0.3. Some duplication is unavoidable when fetching from several peers at once.*\n\n###### Watch for:\n*Sustained values above 0.8. Live observation has recorded good:142 dupe:891, an 86 percent duplicate rate, which wastes both bandwidth and peer resource credit.*\n\n###### Keywords:\n- **Ledger node** *(per fetch)* — one SHAMap node fetched while acquiring a ledger.\n- **Duplicate** *(per fetch)* — a node already held locally; wasted bandwidth and peer credit.\n\n###### Computation boundary:\n*Result: Per node — a ratio of two summed counters, dupe / (good + dupe).*\n*NOT recorded as a metric. Derived in the Grafana query via `unwrap` over the counters in the InboundLedger stats line.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::onTimer / takeAsRootNode`\n\n###### References:\n[Ledgers](https://xrpl.org/docs/concepts/ledgers)",
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 114
"y": 118
},
"fieldConfig": {
"defaults": {
@@ -1718,7 +1717,7 @@
},
"refId": "A",
"legendFormat": "Duplicate Ratio [{{service_instance_id}}]",
"expr": "sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__auto])) / (sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__auto])) + sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap good [$__auto])))"
"expr": "sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__auto])) / (sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__auto])) + sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `good:(?P<good>[0-9]+)` | unwrap good [$__auto])))"
}
],
"id": 26,
@@ -1735,7 +1734,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 114
"y": 118
},
"fieldConfig": {
"defaults": {
@@ -1777,7 +1776,7 @@
},
"refId": "A",
"legendFormat": "Good [{{service_instance_id}}]",
"expr": "sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `node stats: good:(?P<good>[0-9]+)` | unwrap good [$__auto]))"
"expr": "sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `good:(?P<good>[0-9]+)` | unwrap good [$__auto]))"
},
{
"datasource": {
@@ -1786,7 +1785,7 @@
},
"refId": "B",
"legendFormat": "Duplicate [{{service_instance_id}}]",
"expr": "sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `node stats: good:(?P<good>[0-9]+) dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__auto]))"
"expr": "sum by (service_instance_id) (sum_over_time({service_name=~\"$service_name\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\"} | xrpl_network_type =~ \"$xrpl_network_type\" | partition = `InboundLedger` | severity =~ \"$severity\" | regexp `dupe:(?P<dupe>[0-9]+)` | unwrap dupe [$__auto]))"
},
{
"datasource": {
@@ -1812,7 +1811,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 124
"y": 128
},
"panels": [],
"id": 28
@@ -1825,7 +1824,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 125
"y": 129
},
"fieldConfig": {
"defaults": {
@@ -1884,7 +1883,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 125
"y": 129
},
"fieldConfig": {
"defaults": {
@@ -1952,7 +1951,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 135
"y": 139
},
"panels": [],
"id": 31
@@ -1965,7 +1964,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 136
"y": 140
},
"fieldConfig": {
"defaults": {
@@ -2024,7 +2023,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 136
"y": 140
},
"fieldConfig": {
"defaults": {
@@ -2083,7 +2082,7 @@
"h": 10,
"w": 24,
"x": 0,
"y": 146
"y": 150
},
"fieldConfig": {
"defaults": {
@@ -2152,7 +2151,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 156
"y": 160
},
"panels": [],
"id": 35
@@ -2165,7 +2164,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 157
"y": 161
},
"fieldConfig": {
"defaults": {
@@ -2225,7 +2224,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 157
"y": 161
},
"fieldConfig": {
"defaults": {
@@ -2284,7 +2283,7 @@
"h": 10,
"w": 24,
"x": 0,
"y": 167
"y": 171
},
"fieldConfig": {
"defaults": {
@@ -2344,7 +2343,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 177
"y": 181
},
"panels": [],
"id": 39
@@ -2357,7 +2356,7 @@
"h": 10,
"w": 12,
"x": 0,
"y": 178
"y": 182
},
"fieldConfig": {
"defaults": {
@@ -2435,7 +2434,7 @@
"h": 10,
"w": 12,
"x": 12,
"y": 178
"y": 182
},
"fieldConfig": {
"defaults": {},
@@ -2449,7 +2448,12 @@
"prettifyLogMessage": false,
"enableLogDetails": true,
"dedupStrategy": "none",
"sortOrder": "Descending"
"sortOrder": "Descending",
"tooltip": {
"maxHeight": 600,
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{

4
docker/telemetry/grafana/provisioning/datasources/loki.yaml
View File

@@ -25,11 +25,11 @@ datasources:
# hashes (or tx hashes). They are NOT OTel trace IDs and cannot
# be resolved via the trace-by-id endpoint. Build a Grafana
# Explore deep-link that runs TraceQL on the span attribute
# `xrpl.consensus.ledger_id` — set on `consensus.round` spans to
# `consensus_ledger_id` — set on `consensus.round` spans to
# the full prev_ledger hash. This finds the round span whose
# first 16 bytes were folded into the OTel trace_id by
# SpanGuard::hashSpan().
- matcherRegex: "\\b([A-F0-9]{64})\\b"
name: ConsensusLedgerHash
urlDisplayLabel: "Search Tempo"
url: '/explore?schemaVersion=1&orgId=1&panes={"tempo":{"datasource":"tempo","queries":[{"refId":"A","queryType":"traceql","query":"{.xrpl.consensus.ledger_id=\"$${__value.raw}\"}"}],"range":{"from":"now-1h","to":"now"}}}'
url: '/explore?schemaVersion=1&orgId=1&panes={"tempo":{"datasource":"tempo","queries":[{"refId":"A","queryType":"traceql","query":"{span.consensus_ledger_id=\"$${__value.raw}\"}"}],"range":{"from":"now-1h","to":"now"}}}'