ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-07-23 15:10:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

use datasource variable. updated runbook

Browse Source 
Signed-off-by: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com>
This commit is contained in:
Pratik Mankawde
2026-06-26 19:26:17 +01:00
parent 7f1f3af43f
commit ddd5004dab
16 changed files with 304 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
docker/telemetry/grafana/dashboards/consensus-health.json
View File

@@ -235,7 +235,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.accept\" && resource.service.instance.id=~\"$node\"} | quantile_over_time(span.round_time_ms, .5)",
@@ -245,7 +245,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"refId": "B",
@@ -288,7 +288,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.accept\" && resource.service.instance.id=~\"$node\"} | avg_over_time(span.round_time_ms)",
@@ -337,7 +337,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"refId": "A",
@@ -381,7 +381,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.round\" && resource.service.instance.id=~\"$node\"} | quantile_over_time(span.previous_round_time_ms, .95)",
@@ -676,7 +676,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\"} | avg_over_time(span.close_time_vote_bins)",
@@ -686,7 +686,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\"} | avg_over_time(span.close_resolution_ms)",
@@ -734,7 +734,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\" && span.resolution_direction=~\"$resolution_direction\"} | count_over_time() by (span.resolution_direction)",
@@ -805,7 +805,7 @@
{
"datasource": {
"type": "tempo",
"uid": "tempo"
"uid": "${DS_TEMPO}"
},
"queryType": "traceql",
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\"} | count_over_time() by (span.close_time_vote_bins)",
@@ -1061,6 +1061,32 @@
"tags": ["xrpld", "consensus"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "DS_TEMPO",
"type": "datasource",
"label": "Tempo",
"query": "tempo",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -1069,7 +1095,7 @@
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -1089,7 +1115,7 @@
"query": "label_values(traces_span_metrics_calls_total{span_name=\"consensus.ledger_close\"}, consensus_mode)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/ledger-operations.json
View File

@@ -308,6 +308,19 @@
"tags": ["xrpld", "ledger"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -316,7 +329,7 @@
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

19
docker/telemetry/grafana/dashboards/peer-network.json
View File

@@ -248,6 +248,19 @@
"tags": ["xrpld", "peer"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -256,7 +269,7 @@
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -276,7 +289,7 @@
"query": "label_values(traces_span_metrics_calls_total{span_name=\"peer.proposal.receive\"}, proposal_trusted)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -296,7 +309,7 @@
"query": "label_values(traces_span_metrics_calls_total{span_name=\"peer.validation.receive\"}, validation_trusted)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

17
docker/telemetry/grafana/dashboards/rpc-performance.json
View File

@@ -421,6 +421,19 @@
"tags": ["xrpld", "rpc"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -429,7 +442,7 @@
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -449,7 +462,7 @@
"query": "label_values(traces_span_metrics_calls_total{span_name=~\"rpc.command.*\"}, command)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/system-ledger-data-sync.json
View File

@@ -496,6 +496,19 @@
"tags": ["xrpld", "statsd", "ledger", "sync"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -504,7 +517,7 @@
"query": "label_values(xrpld_ledger_data_get_Bytes_In, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/system-network-traffic.json
View File

@@ -774,6 +774,19 @@
"tags": ["xrpld", "statsd", "network"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -782,7 +795,7 @@
"query": "label_values(xrpld_Peer_Finder_Active_Inbound_Peers, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

17
docker/telemetry/grafana/dashboards/system-node-health.json
View File

@@ -2128,6 +2128,19 @@
"tags": ["xrpld", "statsd", "node-health"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -2136,7 +2149,7 @@
"query": "label_values(xrpld_LedgerMaster_Validated_Ledger_Age, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -2156,7 +2169,7 @@
"query": "label_values(xrpld_object_count, type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/system-overlay-traffic-detail.json
View File

@@ -556,6 +556,19 @@
"tags": ["xrpld", "statsd", "overlay", "network"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -564,7 +577,7 @@
"query": "label_values(xrpld_squelch_Messages_In, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

17
docker/telemetry/grafana/dashboards/system-rpc-pathfinding.json
View File

@@ -553,6 +553,19 @@
"tags": ["xrpld", "statsd", "rpc", "pathfinding"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -561,7 +574,7 @@
"query": "label_values(xrpld_rpc_requests_total, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -581,7 +594,7 @@
"query": "label_values(traces_span_metrics_calls_total{span_name=~\"grpc\\\\..*\"}, method)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

17
docker/telemetry/grafana/dashboards/transaction-overview.json
View File

@@ -870,6 +870,19 @@
"tags": ["xrpld", "transactions"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -878,7 +891,7 @@
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -898,7 +911,7 @@
"query": "label_values(traces_span_metrics_calls_total{span_name=\"tx.process\"}, local)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/xrpld-fee-market.json
View File

@@ -459,6 +459,19 @@
"tags": ["xrpld", "fee-market"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -467,7 +480,7 @@
"query": "label_values(exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

17
docker/telemetry/grafana/dashboards/xrpld-job-queue.json
View File

@@ -457,6 +457,19 @@
"tags": ["xrpld", "job-queue"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -465,7 +478,7 @@
"query": "label_values(exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -485,7 +498,7 @@
"query": "label_values(xrpld_job_queued_total, job_type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/xrpld-peer-quality.json
View File

@@ -366,6 +366,19 @@
"tags": ["xrpld", "peer", "network"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -374,7 +387,7 @@
"query": "label_values(xrpld_peer_quality, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

17
docker/telemetry/grafana/dashboards/xrpld-rpc-perf-otel.json
View File

@@ -397,6 +397,19 @@
"tags": ["xrpld", "rpc"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -405,7 +418,7 @@
"query": "label_values(exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
@@ -425,7 +438,7 @@
"query": "label_values(xrpld_rpc_method_started_total, method)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

15
docker/telemetry/grafana/dashboards/xrpld-validator-health.json
View File

@@ -919,6 +919,19 @@
"tags": ["xrpld", "validator", "health"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {},
"hide": 2,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "node",
"label": "Node",
@@ -927,7 +940,7 @@
"query": "label_values(xrpld_validation_agreement, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",

63
docs/telemetry-runbook.md
View File

@@ -42,6 +42,39 @@ cmake --preset default -Dtelemetry=ON
cmake --build --preset default
```
### 4. Run against a live network
Two ready-made configs connect a tracking node (no validator credentials) to a
public network with all tracing and native metrics enabled:
| Config | Network |
| ---------------------------------------------- | ------- |
| `docker/telemetry/xrpld-telemetry.cfg` | Devnet |
| `docker/telemetry/xrpld-telemetry-mainnet.cfg` | Mainnet |
```bash
.build/xrpld --conf docker/telemetry/xrpld-telemetry-mainnet.cfg
```
Both set `[insight] server=otel` (native metrics → collector → Prometheus, which
drives the dashboards) and `service_instance_id`, exposed by Prometheus as the
`exported_instance` label that the `$node` dashboard variable filters on. The
mainnet config logs to `/home/pratik/xrpld-logs/mainnet/debug.log` — the path
the collector's filelog receiver tails for log-trace correlation.
Metrics begin flowing as soon as the node connects to peers (`server_state`
≥ `connected`); full ledger and consensus panels populate after sync
(`server_state` = `full`). Check progress with:
```bash
curl -s http://localhost:5005 -d '{"method":"server_info"}' |
jq '.result.info | {server_state, peers, complete_ledgers}'
```
> Mainnet sync is bandwidth- and disk-heavy. For a quick check use the devnet
> config or the standalone test in `docker/telemetry/TESTING.md`, which
> generates spans without waiting for a live sync.
## Configuration Reference
| Option | Default | Description |
@@ -124,6 +157,36 @@ remove the local exporters (`debug`, `otlp/tempo`, `prometheus`,
> logging on (at least `warning` level) so the collector's filelog receiver
> has a `debug.log` to tail. Traces and metrics are unaffected by log level.
### Importing dashboards to Grafana Cloud
Shipping data (above) is independent of installing the dashboards. The local
stack auto-provisions dashboards from a mounted folder
(`grafana/provisioning/dashboards/dashboards.yaml`, `type: file`); Grafana
Cloud cannot read your filesystem, so its dashboards must be imported over the
HTTP API or the UI.
The dashboard JSON in `docker/telemetry/grafana/dashboards/` references its
backends through datasource **template variables** (`${DS_PROMETHEUS}`,
`${DS_TEMPO}`) rather than fixed UIDs. On import, Grafana binds each variable
to a datasource of the matching type — auto-selecting it when only one exists
(the usual case: one Mimir, one Tempo). This is what makes the same files work
unchanged on both the local stack and Cloud.
> Dashboards are parameterized by `grafana/parameterize-datasources.py`. If you
> add a dashboard exported with hardcoded UIDs, re-run that script (idempotent)
> before committing so it stays portable.
To import:
1. In Grafana Cloud, go to **Dashboards → New → Import**.
2. Upload a file from `docker/telemetry/grafana/dashboards/` (or paste its
JSON), then click **Load**.
3. At the datasource prompt, confirm the auto-selected **Prometheus/Mimir**
datasource — and **Tempo** for dashboards that query traces — then
**Import**.
4. Repeat per dashboard. Only `consensus-health` uses Tempo; the rest need
only the Prometheus/Mimir datasource.
## Span Reference
All spans instrumented in xrpld, grouped by subsystem: