mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-27 17:10:46 +00:00
197 lines
7.6 KiB
YAML
197 lines
7.6 KiB
YAML
# OpenTelemetry Collector configuration for xrpld development.
|
|
#
|
|
# Pipelines:
|
|
# traces: OTLP receiver -> batch processor -> debug + Tempo + spanmetrics
|
|
# metrics: OTLP receiver + spanmetrics connector -> Prometheus exporter
|
|
# logs: filelog receiver -> batch processor -> otlphttp/Loki (Phase 8)
|
|
#
|
|
# xrpld sends traces via OTLP/HTTP to port 4318. The collector batches
|
|
# them, forwards to Tempo, and derives RED metrics via the spanmetrics
|
|
# connector, which Prometheus scrapes on port 8889.
|
|
#
|
|
# xrpld sends beast::insight metrics natively via OTLP/HTTP to port 4318
|
|
# (same endpoint as traces). The OTLP receiver feeds both the traces and
|
|
# metrics pipelines. Metrics are exported to Prometheus alongside
|
|
# span-derived metrics.
|
|
#
|
|
# The filelog receiver tails xrpld's debug.log files under
|
|
# /var/log/xrpld/ (mounted from the host). A regex_parser operator
|
|
# extracts timestamp, partition, severity, and optional trace_id/span_id
|
|
# fields injected by Logs::format(). Parsed logs are exported to Grafana
|
|
# Loki for log-trace correlation.
|
|
|
|
extensions:
|
|
health_check:
|
|
endpoint: 0.0.0.0:13133
|
|
|
|
receivers:
|
|
otlp:
|
|
protocols:
|
|
grpc:
|
|
endpoint: 0.0.0.0:4317
|
|
http:
|
|
endpoint: 0.0.0.0:4318
|
|
# Filelog receiver tails xrpld debug.log files for log-trace
|
|
# correlation. Extracts structured fields (timestamp, partition, severity,
|
|
# trace_id, span_id, message) via regex. The trace_id and span_id are
|
|
# optional — only present when the log was emitted within an active span.
|
|
filelog:
|
|
include: [/var/log/xrpld/*/debug.log]
|
|
operators:
|
|
# Log format emitted by Logs::format() is:
|
|
# YYYY-Mmm-DD HH:MM:SS.ffffff UTC <partition>:<severity> [trace_id=... span_id=...] <message>
|
|
# The `partition:` prefix is omitted when partition is empty, so the
|
|
# capture group is non-capturing optional. Fractional seconds up to 6
|
|
# digits are parsed via the `%f` strptime directive.
|
|
- type: regex_parser
|
|
regex: '^(?P<timestamp>\S+\s+\S+)\s+\S+\s+(?:(?P<partition>\S+):)?(?P<severity>\S+)\s+(?:trace_id=(?P<trace_id>[a-f0-9]+)\s+span_id=(?P<span_id>[a-f0-9]+)\s+)?(?P<message>.*)$'
|
|
timestamp:
|
|
parse_from: attributes.timestamp
|
|
layout: "%Y-%b-%d %H:%M:%S.%f"
|
|
location: UTC
|
|
|
|
processors:
|
|
batch:
|
|
timeout: 1s
|
|
send_batch_size: 100
|
|
resource/logs:
|
|
attributes:
|
|
- key: service.name
|
|
value: xrpld
|
|
action: upsert
|
|
# Loki 3.x OTLP ingestion converts `service.name` to the label
|
|
# `service_name`. The runbook and integration-test queries use the
|
|
# canonical Loki label `job` so operators can paste `{job="xrpld"}`
|
|
# without guessing the otel-to-loki naming convention. Upsert the
|
|
# `job` resource attribute here so it round-trips through OTLP
|
|
# into Loki as the `job` label.
|
|
- key: job
|
|
value: xrpld
|
|
action: upsert
|
|
# Deployment-tier tagging. Each collector serves ONE environment and ONE
|
|
# network, so it stamps both onto every signal it forwards. This lets a
|
|
# single Grafana stack hold data from many collectors and filter by tier.
|
|
# - deployment.environment: the collector IS the environment (local, ci,
|
|
# test, prod), so it is authoritative -> upsert (overwrite).
|
|
# - xrpl.network.type: the xrpld node knows its own chain and already
|
|
# stamps this, so the collector only fills it when absent -> insert.
|
|
# This keeps a node's real network (e.g. a local node on mainnet)
|
|
# from being overwritten by a collector's default.
|
|
# Replace the placeholder values per collector; see docker/telemetry
|
|
# tier examples.
|
|
resource/tier:
|
|
attributes:
|
|
- key: deployment.environment
|
|
value: local
|
|
action: upsert
|
|
- key: xrpl.network.type
|
|
value: mainnet
|
|
action: insert
|
|
# Strip SDK-injected resource attributes (telemetry.sdk.language/name/version).
|
|
# The OpenTelemetry SDK auto-adds these to every Resource; they carry no
|
|
# operational value and clutter the attribute set on every backend, so drop
|
|
# them here for all signals.
|
|
resource/stripsdk:
|
|
attributes:
|
|
- key: telemetry.sdk.language
|
|
action: delete
|
|
- key: telemetry.sdk.name
|
|
action: delete
|
|
- key: telemetry.sdk.version
|
|
action: delete
|
|
# Defense-in-depth: hash path-finding account attributes. The xrpld SDK
|
|
# already hashes these before export, but a node that emitted raw values
|
|
# is caught here so raw addresses never reach the backend.
|
|
attributes/hash:
|
|
actions:
|
|
- key: pathfind_source_account
|
|
action: hash
|
|
- key: pathfind_dest_account
|
|
action: hash
|
|
|
|
connectors:
|
|
spanmetrics:
|
|
namespace: "span"
|
|
# Resource attributes that define the resource-metrics grouping key.
|
|
# All resource attributes are propagated onto the output metrics
|
|
# regardless; promotion to Prometheus labels is handled by the
|
|
# prometheus exporter's resource_to_telemetry_conversion. Listing the
|
|
# per-node id and the deployment-tier keys keeps series from distinct
|
|
# nodes/tiers grouped separately.
|
|
resource_metrics_key_attributes:
|
|
- service.instance.id
|
|
- deployment.environment
|
|
- xrpl.network.type
|
|
histogram:
|
|
explicit:
|
|
buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
|
|
dimensions:
|
|
- name: command
|
|
- name: rpc_status
|
|
- name: consensus_mode
|
|
- name: close_time_correct
|
|
- name: consensus_state
|
|
- name: local
|
|
- name: suppressed
|
|
- name: proposal_trusted
|
|
- name: validation_trusted
|
|
- name: tx_type
|
|
- name: ter_result
|
|
# Apply-pipeline stage (preflight|preclaim|apply) — splits the
|
|
# tx.preflight/tx.preclaim/tx.transactor span RED metrics per stage.
|
|
- name: stage
|
|
- name: txq_status
|
|
- name: load_type
|
|
- name: is_batch
|
|
# Consensus lifecycle dimensions (low cardinality, bounded value sets).
|
|
- name: mode_new
|
|
- name: consensus_stalled
|
|
- name: consensus_phase
|
|
- name: consensus_result
|
|
# gRPC surface dimensions (bounded: method names, role, status).
|
|
- name: method
|
|
- name: grpc_role
|
|
- name: grpc_status
|
|
# ledger.acquire dimensions (bounded: outcome, acquire reason).
|
|
- name: outcome
|
|
- name: acquire_reason
|
|
|
|
exporters:
|
|
debug:
|
|
verbosity: detailed
|
|
otlp/tempo:
|
|
endpoint: tempo:4317
|
|
tls:
|
|
insecure: true
|
|
# Export logs to Grafana Loki via OTLP/HTTP. Loki 3.x supports
|
|
# native OTLP ingestion on its /otlp endpoint, replacing the removed
|
|
# loki exporter (dropped in otel-collector-contrib v0.147.0).
|
|
otlphttp/loki:
|
|
endpoint: http://loki:3100/otlp
|
|
prometheus:
|
|
endpoint: 0.0.0.0:8889
|
|
# Promote resource attributes (deployment.environment, xrpl.network.type,
|
|
# service.name, service.instance.id) to Prometheus labels. Without this
|
|
# the tier attributes stamped by resource/tier stay on the resource and
|
|
# never reach the metric series, so dashboards could not filter by them.
|
|
resource_to_telemetry_conversion:
|
|
enabled: true
|
|
|
|
service:
|
|
extensions: [health_check]
|
|
pipelines:
|
|
traces:
|
|
receivers: [otlp]
|
|
processors: [resource/tier, resource/stripsdk, attributes/hash, batch]
|
|
exporters: [debug, otlp/tempo, spanmetrics]
|
|
metrics:
|
|
receivers: [otlp, spanmetrics]
|
|
processors: [resource/tier, resource/stripsdk, batch]
|
|
exporters: [prometheus]
|
|
# Log pipeline ingests xrpld debug.log via filelog receiver,
|
|
# batches entries, and exports to Loki for log-trace correlation.
|
|
logs:
|
|
receivers: [filelog]
|
|
processors: [resource/logs, resource/tier, resource/stripsdk, batch]
|
|
exporters: [otlphttp/loki]
|