mirror of
https://github.com/XRPLF/rippled.git
synced 2026-04-29 15:37:57 +00:00
787b496484
Add comprehensive workload harness for end-to-end validation of the
Phases 1-9 telemetry stack:
Task 10.1 — Multi-node test harness:
- docker-compose.workload.yaml with full OTel stack (Collector, Jaeger,
Tempo, Prometheus, Loki, Grafana)
- generate-validator-keys.sh for automated key generation
- xrpld-validator.cfg.template for node configuration
Task 10.2 — RPC load generator:
- rpc_load_generator.py with WebSocket client, configurable rates,
realistic command distribution (40% health, 30% wallet, 15% explorer,
10% tx lookups, 5% DEX), W3C traceparent injection
Task 10.3 — Transaction submitter:
- tx_submitter.py with 10 transaction types (Payment, OfferCreate,
OfferCancel, TrustSet, NFTokenMint, NFTokenCreateOffer, EscrowCreate,
EscrowFinish, AMMCreate, AMMDeposit), auto-funded test accounts
Task 10.4 — Telemetry validation suite:
- validate_telemetry.py checking spans (Jaeger), metrics (Prometheus),
log-trace correlation (Loki), dashboards (Grafana)
- expected_spans.json (17 span types, 22 attributes, 3 hierarchies)
- expected_metrics.json (SpanMetrics, StatsD, Phase 9, dashboards)
Task 10.5 — Performance benchmark suite:
- benchmark.sh for baseline vs telemetry comparison
- collect_system_metrics.sh for CPU/memory/latency sampling
- Thresholds: <3% CPU, <5MB memory, <2ms RPC p99, <5% TPS, <1% consensus
Task 10.6 — CI integration:
- telemetry-validation.yml GitHub Actions workflow
- run-full-validation.sh orchestrator script
- Manual trigger + telemetry branch auto-trigger
Task 10.7 — Documentation:
- workload/README.md with quick start and tool reference
- Updated telemetry-runbook.md with validation and benchmark sections
- Updated 09-data-collection-reference.md with validation inventory
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
102 lines
3.3 KiB
JSON
102 lines
3.3 KiB
JSON
{
|
|
"description": "Expected metric inventory for rippled telemetry validation. Sourced from 09-data-collection-reference.md.",
|
|
"spanmetrics": {
|
|
"description": "SpanMetrics-derived RED metrics from the OTel Collector spanmetrics connector.",
|
|
"metrics": [
|
|
"traces_span_metrics_calls_total",
|
|
"traces_span_metrics_duration_milliseconds_bucket",
|
|
"traces_span_metrics_duration_milliseconds_count",
|
|
"traces_span_metrics_duration_milliseconds_sum"
|
|
],
|
|
"required_labels": [
|
|
"span_name",
|
|
"status_code",
|
|
"service_name",
|
|
"span_kind"
|
|
],
|
|
"dimension_labels": [
|
|
"xrpl_rpc_command",
|
|
"xrpl_rpc_status",
|
|
"xrpl_consensus_mode",
|
|
"xrpl_tx_local",
|
|
"xrpl_peer_proposal_trusted",
|
|
"xrpl_peer_validation_trusted"
|
|
]
|
|
},
|
|
"statsd_gauges": {
|
|
"description": "beast::insight gauges emitted via StatsD UDP.",
|
|
"metrics": [
|
|
"rippled_LedgerMaster_Validated_Ledger_Age",
|
|
"rippled_LedgerMaster_Published_Ledger_Age",
|
|
"rippled_State_Accounting_Full_duration",
|
|
"rippled_Peer_Finder_Active_Inbound_Peers",
|
|
"rippled_Peer_Finder_Active_Outbound_Peers",
|
|
"rippled_job_count"
|
|
]
|
|
},
|
|
"statsd_counters": {
|
|
"description": "beast::insight counters emitted via StatsD UDP.",
|
|
"metrics": ["rippled_rpc_requests", "rippled_ledger_fetches"]
|
|
},
|
|
"statsd_histograms": {
|
|
"description": "beast::insight timers/histograms emitted via StatsD UDP.",
|
|
"metrics": ["rippled_rpc_time", "rippled_rpc_size", "rippled_ios_latency"]
|
|
},
|
|
"overlay_traffic": {
|
|
"description": "Overlay traffic metrics (subset — full list has 45+ categories).",
|
|
"metrics": [
|
|
"rippled_total_Bytes_In",
|
|
"rippled_total_Bytes_Out",
|
|
"rippled_total_Messages_In",
|
|
"rippled_total_Messages_Out"
|
|
]
|
|
},
|
|
"phase9_nodestore": {
|
|
"description": "Phase 9 NodeStore I/O metrics (via beast::insight extensions).",
|
|
"metrics": [
|
|
"rippled_nodestore_reads_total",
|
|
"rippled_nodestore_writes",
|
|
"rippled_nodestore_read_bytes",
|
|
"rippled_nodestore_written_bytes"
|
|
]
|
|
},
|
|
"phase9_cache": {
|
|
"description": "Phase 9 cache hit rate metrics (via OTel MetricsRegistry).",
|
|
"metrics": ["rippled_cache_SLE_hit_rate", "rippled_cache_treenode_size"]
|
|
},
|
|
"phase9_txq": {
|
|
"description": "Phase 9 transaction queue metrics (via OTel MetricsRegistry).",
|
|
"metrics": ["rippled_txq_count", "rippled_txq_max_size"]
|
|
},
|
|
"phase9_rpc_method": {
|
|
"description": "Phase 9 per-RPC-method metrics (via OTel Metrics SDK).",
|
|
"metrics": [
|
|
"rippled_rpc_method_started_total",
|
|
"rippled_rpc_method_finished_total"
|
|
]
|
|
},
|
|
"phase9_objects": {
|
|
"description": "Phase 9 counted object instances.",
|
|
"metrics": ["rippled_object_count"]
|
|
},
|
|
"phase9_load": {
|
|
"description": "Phase 9 fee escalation and load factor metrics.",
|
|
"metrics": ["rippled_load_factor"]
|
|
},
|
|
"grafana_dashboards": {
|
|
"description": "All 10 Grafana dashboards that must render data.",
|
|
"uids": [
|
|
"rippled-rpc-perf",
|
|
"rippled-transactions",
|
|
"rippled-consensus",
|
|
"rippled-ledger-ops",
|
|
"rippled-peer-net",
|
|
"rippled-statsd-node-health",
|
|
"rippled-statsd-network",
|
|
"rippled-statsd-rpc",
|
|
"rippled-statsd-overlay-detail",
|
|
"rippled-statsd-ledger-sync"
|
|
]
|
|
}
|
|
}
|