Files
rippled/docker/telemetry/grafana/provisioning/datasources/tempo.yaml
Pratik Mankawde 81b47afde7 Merge branch 'pratik/otel-phase7-native-metrics' into pratik/otel-phase8-log-correlation
# Conflicts:
#	OpenTelemetryPlan/06-implementation-phases.md
#	OpenTelemetryPlan/08-appendix.md
#	OpenTelemetryPlan/OpenTelemetryPlan.md
#	docker/telemetry/grafana/dashboards/statsd-network-traffic.json
#	docker/telemetry/grafana/dashboards/statsd-node-health.json
#	docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json
2026-04-29 20:07:43 +01:00

228 lines
7.6 KiB
YAML

# Grafana datasource provisioning for Grafana Tempo.
# Auto-configures Tempo as a trace data source on Grafana startup.
# Access Grafana at http://localhost:3000, then use Explore -> Tempo
# to browse xrpld traces using TraceQL.
#
# Search filters provide pre-configured dropdowns in the Explore UI.
# Each phase adds filters for the span attributes it introduces.
# Phase 1b (infra): Base filters — node identity, service, span name, status.
# Phase 2 (RPC): RPC command, status, role filters.
# Phase 3 (TX): Transaction hash, local/peer origin, status.
# Phase 4 (Cons): Consensus mode, round, ledger sequence, close time.
apiVersion: 1
datasources:
- name: Tempo
type: tempo
access: proxy
url: http://tempo:3200
uid: tempo
jsonData:
nodeGraph:
enabled: true
# Service map and traces-to-metrics require a Prometheus datasource
# (not included in this stack). These features are inactive until a
# Prometheus service is added to docker-compose.yml.
serviceMap:
datasourceUid: prometheus
# Phase 8: Trace-to-log correlation — enables one-click navigation
# from a Tempo trace to the corresponding Loki log lines. Filters
# by trace_id so only logs from the same trace are shown.
tracesToLogs:
datasourceUid: loki
filterByTraceID: true
filterBySpanID: false
tags: ["partition", "severity"]
tracesToMetrics:
datasourceUid: prometheus
spanStartTimeShift: "-1h"
spanEndTimeShift: "1h"
search:
filters:
# --- Node identification filters ---
# service.name: logical service name (default: "xrpld").
# Useful when running multiple service types in the same collector.
- id: service-name
tag: service.name
operator: "="
scope: resource
type: static
# service.instance.id: unique node identifier — configurable via
# the service_instance_id setting in [telemetry], defaults to the
# node's public key. E.g. "Node-1" or "nHB1X37...".
- id: node-id
tag: service.instance.id
operator: "="
scope: resource
type: static
# service.version: xrpld build version (e.g., "2.4.0-b1").
# Filter traces from specific software releases.
- id: node-version
tag: service.version
operator: "="
scope: resource
type: dynamic
# xrpl.network.id: numeric network identifier
# (0 = mainnet, 1 = testnet, 2 = devnet, etc.).
# Derived from the [network_id] config section.
- id: network-id
tag: xrpl.network.id
operator: "="
scope: resource
type: dynamic
# xrpl.network.type: human-readable network name derived from
# network ID ("mainnet", "testnet", "devnet", "unknown").
- id: network-type
tag: xrpl.network.type
operator: "="
scope: resource
type: static
# --- Span intrinsic filters ---
# name: the span operation name (e.g., "rpc.command.server_info").
# Use to find traces for a specific RPC command or subsystem.
- id: span-name
tag: name
operator: "="
scope: intrinsic
type: static
# status: span completion status ("ok", "error", "unset").
# Filter for failed operations to diagnose errors.
- id: span-status
tag: status
operator: "="
scope: intrinsic
type: static
# duration: span wall-clock duration. Use with ">" operator
# to find slow operations (e.g., duration > 500ms).
- id: span-duration
tag: duration
operator: ">"
scope: intrinsic
type: static
# Phase 2: RPC tracing filters
- id: rpc-command
tag: xrpl.rpc.command
operator: "="
scope: span
type: static
- id: rpc-status
tag: xrpl.rpc.status
operator: "="
scope: span
type: dynamic
- id: rpc-role
tag: xrpl.rpc.role
operator: "="
scope: span
type: dynamic
# Phase 2: Node health filters (Task 2.8)
- id: node-amendment-blocked
tag: xrpl.node.amendment_blocked
operator: "="
scope: span
type: static
- id: node-server-state
tag: xrpl.node.server_state
operator: "="
scope: span
type: dynamic
# Phase 3: Transaction tracing filters
- id: tx-hash
tag: xrpl.tx.hash
operator: "="
scope: span
type: static
- id: tx-origin
tag: xrpl.tx.local
operator: "="
scope: span
type: dynamic
- id: tx-status
tag: xrpl.tx.status
operator: "="
scope: span
type: dynamic
# Phase 4: Consensus tracing filters
- id: consensus-mode
tag: xrpl.consensus.mode
operator: "="
scope: span
type: static
- id: consensus-round
tag: xrpl.consensus.round
operator: "="
scope: span
type: dynamic
- id: consensus-ledger-seq
tag: xrpl.consensus.ledger.seq
operator: "="
scope: span
type: static
- id: consensus-close-time-correct
tag: xrpl.consensus.close_time_correct
operator: "="
scope: span
type: dynamic
- id: consensus-state
tag: xrpl.consensus.state
operator: "="
scope: span
type: dynamic
- id: consensus-close-resolution
tag: xrpl.consensus.close_resolution_ms
operator: "="
scope: span
type: dynamic
- id: consensus-proposers
tag: xrpl.consensus.proposers
operator: "="
scope: span
type: dynamic
- id: consensus-result
tag: xrpl.consensus.result
operator: "="
scope: span
type: dynamic
- id: consensus-mode-old
tag: xrpl.consensus.mode.old
operator: "="
scope: span
type: dynamic
- id: consensus-mode-new
tag: xrpl.consensus.mode.new
operator: "="
scope: span
type: dynamic
- id: consensus-ledger-id
tag: xrpl.consensus.ledger_id
operator: "="
scope: span
type: static
# Phase 3/4: Additional transaction and queue filters
- id: tx-path
tag: xrpl.tx.path
operator: "="
scope: span
type: dynamic
- id: tx-suppressed
tag: xrpl.tx.suppressed
operator: "="
scope: span
type: dynamic
- id: peer-version
tag: xrpl.peer.version
operator: "="
scope: span
type: dynamic
- id: txq-status
tag: xrpl.txq.status
operator: "="
scope: span
type: dynamic
- id: txq-ter-code
tag: xrpl.txq.ter_code
operator: "="
scope: span
type: dynamic