Files
rippled/docker/telemetry/otel-collector-config.yaml
Pratik Mankawde e49c5997b7 added loki config.
Signed-off-by: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com>
2026-05-06 17:37:43 +01:00

106 lines
3.5 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.
#
# Phase 8: The filelog receiver tails xrpld's debug.log files under
# /var/log/rippled/ (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
# Phase 8: 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/rippled/*/debug.log]
operators:
- 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"
processors:
batch:
timeout: 1s
send_batch_size: 100
resource/logs:
attributes:
- key: service.name
value: xrpld
action: upsert
connectors:
spanmetrics:
# Expose service.instance.id (node public key) as a Prometheus label so
# Grafana dashboards can filter metrics by individual node.
resource_metrics_key_attributes:
- service.instance.id
histogram:
explicit:
buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
dimensions:
- name: xrpl.rpc.command
- name: xrpl.rpc.status
- name: xrpl.consensus.mode
- name: xrpl.tx.local
- name: xrpl.peer.proposal.trusted
- name: xrpl.peer.validation.trusted
exporters:
debug:
verbosity: detailed
otlp/tempo:
endpoint: tempo:4317
tls:
insecure: true
# Phase 8: 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
service:
extensions: [health_check]
pipelines:
traces:
receivers: [otlp]
processors: [batch]
exporters: [debug, otlp/tempo, spanmetrics]
metrics:
receivers: [otlp, spanmetrics]
processors: [batch]
exporters: [prometheus]
# Phase 8: 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, batch]
exporters: [otlphttp/loki]