mirror of
https://github.com/XRPLF/rippled.git
synced 2026-10-10 21:58:03 +00:00
ff8629bb11
Every generated node cfg carried prefix=xrpld under a comment claiming it
"matches the OTel resource service name and the metric names the dashboards
query". Both halves are false.
Verified inert before removing: CollectorManager.cpp reads the key on the OTel
path and passes it to OTelCollector::New, but the only use of prefix_ anywhere
in OTelCollector.cpp is the startup log line. formatName() -- the single funnel
for every instrument name -- only lowercases the name and turns dots and
spaces into underscores; it never reads prefix_. So exported names carry no
prefix at all. expected_metrics.json's own description records this ("Metric
names have no prefix (the xrpld_ prefix was removed)") and 488 live metric
names confirmed it: jobq_job_count, rpc_requests_total, total_bytes_in.
A reader trusting the comment would look for xrpld_jobq_job_count and find
nothing.
The replacement comment states what is true and checkable: the collector
declares no statsd receiver (its metrics pipeline is [otlp, spanmetrics],
confirmed in otel-collector-config.yaml), so beast::insight must export over
OTLP for system metrics to reach Prometheus at all; server=otel is the only
load-bearing key; exported names carry no prefix.
Metric names, series and dashboards are unchanged. The one observable
difference is the OTelCollector startup log line, which now prints an empty
prefix.
Also updated workload/README.md, which repeated the same prefix=xrpld claim
and would have been left describing a cfg key that no longer exists, and made
the template header state the sync obligation explicitly -- nothing reads that
file, so nothing catches it drifting from the cfg the runner generates.
123 lines
3.7 KiB
Plaintext
123 lines
3.7 KiB
Plaintext
# xrpld validator node configuration template for workload harness.
|
|
#
|
|
# Not consumed by anything today: run-full-validation.sh writes each node's
|
|
# cfg inline. Kept as the reference layout for a validator run as a container,
|
|
# whose entrypoint would substitute the placeholders below.
|
|
#
|
|
# Because nothing reads this file, nothing catches it drifting from the cfg the
|
|
# runner actually generates. Any change to the [telemetry], [insight] or
|
|
# [rpc_startup] stanzas here must be mirrored in run-full-validation.sh, and
|
|
# vice versa.
|
|
#
|
|
# Placeholders:
|
|
# {{NODE_INDEX}} — Node number (1-based)
|
|
# {{RPC_PORT}} — HTTP RPC port
|
|
# {{WS_PORT}} — WebSocket port
|
|
# {{PEER_PORT}} — Peer protocol port
|
|
# {{DATA_DIR}} — Node data directory
|
|
# {{VALIDATION_SEED}} — Validator seed from key generation
|
|
# {{VALIDATORS_FILE}} — Path to shared validators.txt
|
|
# {{IPS_FIXED}} — Peer addresses (one per line)
|
|
# {{OTEL_ENDPOINT}} — OTel Collector OTLP/HTTP traces endpoint
|
|
# {{OTEL_METRICS_ENDPOINT}} — OTel Collector OTLP/HTTP metrics endpoint
|
|
# {{LOG_LEVEL}} — Log level. Must be at least `info` for the
|
|
# log-trace correlation checks to pass: they need a
|
|
# log line emitted while a span is current on the
|
|
# thread. The guaranteed such line is the consensus
|
|
# accept pair in RCLConsensus.cpp, which is at info
|
|
# and sits inside the activation doAccept makes over
|
|
# its whole body. `warning` and above suppress it and
|
|
# leave the checks with nothing to find. Do not use
|
|
# `debug`: it adds log I/O inside the spans whose
|
|
# latency regression-metrics.json gates.
|
|
|
|
[server]
|
|
port_rpc
|
|
port_ws
|
|
port_peer
|
|
|
|
# RPC and WebSocket stay on loopback, matching the cfg that
|
|
# run-full-validation.sh generates and the rest of the repo's node configs.
|
|
# Only the peer port below needs to listen on all interfaces.
|
|
[port_rpc]
|
|
port = {{RPC_PORT}}
|
|
ip = 127.0.0.1
|
|
admin = 127.0.0.1
|
|
protocol = http
|
|
|
|
[port_ws]
|
|
port = {{WS_PORT}}
|
|
ip = 127.0.0.1
|
|
admin = 127.0.0.1
|
|
protocol = ws
|
|
|
|
[port_peer]
|
|
port = {{PEER_PORT}}
|
|
ip = 0.0.0.0
|
|
protocol = peer
|
|
|
|
[node_db]
|
|
type=NuDB
|
|
path={{DATA_DIR}}/nudb
|
|
online_delete=256
|
|
|
|
[database_path]
|
|
{{DATA_DIR}}/db
|
|
|
|
[debug_logfile]
|
|
{{DATA_DIR}}/debug.log
|
|
|
|
[validation_seed]
|
|
{{VALIDATION_SEED}}
|
|
|
|
[validators_file]
|
|
{{VALIDATORS_FILE}}
|
|
|
|
[ips_fixed]
|
|
{{IPS_FIXED}}
|
|
|
|
[peer_private]
|
|
1
|
|
|
|
# --- OpenTelemetry tracing (all categories enabled) ---
|
|
[telemetry]
|
|
enabled=1
|
|
service_instance_id=validator-{{NODE_INDEX}}
|
|
endpoint={{OTEL_ENDPOINT}}
|
|
exporter=otlp_http
|
|
batch_size=512
|
|
batch_delay_ms=2000
|
|
max_queue_size=2048
|
|
trace_rpc=1
|
|
trace_transactions=1
|
|
trace_consensus=1
|
|
trace_peer=1
|
|
trace_ledger=1
|
|
|
|
# --- Native OTel metrics (beast::insight over OTLP/HTTP) ---
|
|
# The collector has no StatsD receiver (its metrics pipeline is
|
|
# [otlp, spanmetrics]), so beast::insight must export natively over OTLP for
|
|
# system metrics to reach Prometheus at all. `server=otel` is the only
|
|
# load-bearing key here -- it selects the OTel collector.
|
|
#
|
|
# No `prefix` is set on purpose. It would be inert: OTelCollector applies no
|
|
# prefix to instrument names, so exported names are the lowercased raw names
|
|
# (`jobq_job_count`, `rpc_requests_total`, `total_bytes_in`). The service is
|
|
# identified by the OTel resource `service.name`, not by a name prefix.
|
|
[insight]
|
|
server=otel
|
|
endpoint={{OTEL_METRICS_ENDPOINT}}
|
|
|
|
[rpc_startup]
|
|
{ "command": "log_level", "severity": "{{LOG_LEVEL}}" }
|
|
|
|
[ssl_verify]
|
|
0
|
|
|
|
# --- Network tuning for local cluster ---
|
|
[network_id]
|
|
0
|
|
|
|
[sntp_servers]
|
|
time.google.com
|