mirror of
https://github.com/XRPLF/rippled.git
synced 2026-06-06 18:26:51 +00:00
fd1c8c6060
The print-env CI fix let the Telemetry Stack Validation job build and run the workload harness end-to-end for the first time. It reported 129/136 checks passing; this commit fixes the 7 real failures plus a latent regression-gate bug. Validation-suite fixes (verified against the CI run's actual emission + live node): - expected_metrics.json: the beast::insight job-depth gauge is `xrpld_jobq_job_count`, not `xrpld_job_count` (the latter is a Phase 9 OTel counter). Reverted the prior rename. Removed the statsd_histograms block (`xrpld_rpc_time`/`xrpld_rpc_size`): these RPC timers do not emit under the WS workload (0 series in CI). - expected_spans.json: `tx_status` is only set on suppressed/known-bad receives, so it is no longer a required attribute of every `tx.receive`. Marked `pathfind.compute` and `pathfind.discover` optional and the `pathfind.request -> pathfind.compute` hierarchy as skip — the self-to-self XRP probe returns before computing paths in a fresh cluster with no liquidity, so only `pathfind.request` fires. Regression-gate bug (telemetry-validation.yml "Print regression summary"): - `jq -e` exits non-zero when its filter result is boolean false — the normal case for a populated (non-placeholder) baseline — which was misreported as "Failed to parse baseline JSON" and failed the job. Dropped `-e` (kept `-r`) so a non-zero exit genuinely means malformed JSON. The optional-span handling and regression comparison both worked correctly in the CI run (txq.* / pathfind.update_all skipped-when-absent, 0 regressions detected). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
426 lines
14 KiB
JSON
426 lines
14 KiB
JSON
{
|
|
"description": "Expected span inventory for xrpld telemetry validation. Attribute keys follow the 2026-05-13 span-attr naming redesign (bare/underscore form; dotted xrpl.* reserved for resource attributes). Sourced from the *SpanNames.h headers. Spans marked \"optional\": true are conditional — they only fire under traffic the harness may not produce (e.g. gRPC client, missing-ledger fetch, mode transitions) and are not failed when absent.",
|
|
"spans": [
|
|
{
|
|
"name": "rpc.ws_message",
|
|
"category": "rpc",
|
|
"parent": null,
|
|
"required_attributes": ["command"],
|
|
"config_flag": "trace_rpc",
|
|
"note": "WebSocket RPC root span. The load generator uses WS, so this is the RPC entry span (not rpc.http_request, which needs an HTTP/JSON-RPC client)."
|
|
},
|
|
{
|
|
"name": "rpc.process",
|
|
"category": "rpc",
|
|
"parent": "rpc.ws_message",
|
|
"required_attributes": [],
|
|
"config_flag": "trace_rpc"
|
|
},
|
|
{
|
|
"name": "rpc.command.*",
|
|
"category": "rpc",
|
|
"parent": "rpc.process",
|
|
"required_attributes": ["command", "version", "rpc_role", "rpc_status"],
|
|
"config_flag": "trace_rpc",
|
|
"note": "Wildcard — matches rpc.command.server_info, rpc.command.ledger, etc."
|
|
},
|
|
{
|
|
"name": "rpc.http_request",
|
|
"category": "rpc",
|
|
"parent": null,
|
|
"required_attributes": ["request_payload_size"],
|
|
"config_flag": "trace_rpc",
|
|
"optional": true,
|
|
"note": "HTTP/JSON-RPC root span. The harness load generator is WebSocket-only, so this does not fire."
|
|
},
|
|
{
|
|
"name": "tx.process",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["tx_hash", "local", "path"],
|
|
"config_flag": "trace_transactions"
|
|
},
|
|
{
|
|
"name": "tx.receive",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["tx_hash", "peer_id", "suppressed"],
|
|
"config_flag": "trace_transactions",
|
|
"note": "Cross-node span: parent context propagated from the sender's tx.process via protobuf. Also carries tx_type and peer_version. tx_status is only set when a tx is suppressed/known-bad, so it is not a required attribute on every tx.receive."
|
|
},
|
|
{
|
|
"name": "tx.apply",
|
|
"category": "transaction",
|
|
"parent": "ledger.build",
|
|
"required_attributes": ["tx_count", "tx_failed"],
|
|
"config_flag": "trace_transactions",
|
|
"note": "Apply-step span inside BuildLedger. Carries tx_count/tx_failed (ledger_seq lives on the parent ledger.build span)."
|
|
},
|
|
{
|
|
"name": "tx.preflight",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["stage", "tx_type", "ter_result"],
|
|
"config_flag": "trace_transactions",
|
|
"note": "Apply-pipeline stage span (stage=preflight). Shares a deterministic trace_id (txID[0:16]) with tx.preclaim/tx.transactor."
|
|
},
|
|
{
|
|
"name": "tx.preclaim",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["stage", "tx_type", "ter_result"],
|
|
"config_flag": "trace_transactions",
|
|
"note": "Apply-pipeline stage span (stage=preclaim)."
|
|
},
|
|
{
|
|
"name": "tx.transactor",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["stage", "tx_type"],
|
|
"config_flag": "trace_transactions",
|
|
"note": "Apply-pipeline stage span (stage=apply). Also carries applied."
|
|
},
|
|
{
|
|
"name": "txq.enqueue",
|
|
"category": "transaction",
|
|
"parent": "tx.process",
|
|
"required_attributes": [
|
|
"tx_hash",
|
|
"tx_type",
|
|
"txq_status",
|
|
"fee_level_paid",
|
|
"required_fee_level"
|
|
],
|
|
"config_flag": "trace_transactions",
|
|
"optional": true,
|
|
"note": "Only fires when a tx is queued (fee below open-ledger level). Requires fee escalation — driven by the txq-burst workload phase."
|
|
},
|
|
{
|
|
"name": "txq.apply_direct",
|
|
"category": "transaction",
|
|
"parent": "txq.enqueue",
|
|
"required_attributes": [],
|
|
"config_flag": "trace_transactions",
|
|
"optional": true,
|
|
"note": "Child of txq.enqueue when the tx applies directly without queueing."
|
|
},
|
|
{
|
|
"name": "txq.batch_clear",
|
|
"category": "transaction",
|
|
"parent": "txq.enqueue",
|
|
"required_attributes": ["num_cleared"],
|
|
"config_flag": "trace_transactions",
|
|
"optional": true
|
|
},
|
|
{
|
|
"name": "txq.accept",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["queue_size", "ledger_changed"],
|
|
"config_flag": "trace_transactions",
|
|
"optional": true,
|
|
"note": "Ledger-close accept loop. Fires on the consensus thread; only meaningful when the queue is non-empty."
|
|
},
|
|
{
|
|
"name": "txq.accept.tx",
|
|
"category": "transaction",
|
|
"parent": "txq.accept",
|
|
"required_attributes": [
|
|
"tx_hash",
|
|
"ter_code",
|
|
"retries_remaining",
|
|
"txq_status"
|
|
],
|
|
"config_flag": "trace_transactions",
|
|
"optional": true
|
|
},
|
|
{
|
|
"name": "txq.cleanup",
|
|
"category": "transaction",
|
|
"parent": null,
|
|
"required_attributes": ["ledger_seq", "expired_count"],
|
|
"config_flag": "trace_transactions",
|
|
"optional": true
|
|
},
|
|
{
|
|
"name": "consensus.round",
|
|
"category": "consensus",
|
|
"parent": null,
|
|
"required_attributes": [
|
|
"consensus_ledger_id",
|
|
"ledger_seq",
|
|
"consensus_mode",
|
|
"consensus_round_id",
|
|
"consensus_phase"
|
|
],
|
|
"config_flag": "trace_consensus",
|
|
"note": "Root consensus span created per round. Also carries trace_strategy, previous_ledger_seq, previous_proposers, previous_round_time_ms."
|
|
},
|
|
{
|
|
"name": "consensus.phase.open",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": [],
|
|
"config_flag": "trace_consensus"
|
|
},
|
|
{
|
|
"name": "consensus.proposal.send",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": ["consensus_round"],
|
|
"config_flag": "trace_consensus",
|
|
"note": "Also carries is_bow_out."
|
|
},
|
|
{
|
|
"name": "consensus.ledger_close",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": ["ledger_seq", "consensus_mode"],
|
|
"config_flag": "trace_consensus",
|
|
"note": "Also carries tx_count_open, close_time_resolution_ms."
|
|
},
|
|
{
|
|
"name": "consensus.establish",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": [
|
|
"converge_percent",
|
|
"establish_count",
|
|
"proposers",
|
|
"disputes_count"
|
|
],
|
|
"config_flag": "trace_consensus"
|
|
},
|
|
{
|
|
"name": "consensus.update_positions",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": [
|
|
"converge_percent",
|
|
"proposers",
|
|
"disputes_count"
|
|
],
|
|
"config_flag": "trace_consensus"
|
|
},
|
|
{
|
|
"name": "consensus.check",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": [
|
|
"agree_count",
|
|
"disagree_count",
|
|
"threshold_percent",
|
|
"consensus_result"
|
|
],
|
|
"config_flag": "trace_consensus"
|
|
},
|
|
{
|
|
"name": "consensus.accept",
|
|
"category": "consensus",
|
|
"parent": "consensus.round",
|
|
"required_attributes": ["proposers", "round_time_ms", "quorum"],
|
|
"config_flag": "trace_consensus"
|
|
},
|
|
{
|
|
"name": "consensus.accept.apply",
|
|
"category": "consensus",
|
|
"parent": "consensus.accept",
|
|
"required_attributes": [
|
|
"ledger_seq",
|
|
"close_time",
|
|
"parent_close_time",
|
|
"close_time_self",
|
|
"close_time_vote_bins",
|
|
"resolution_direction"
|
|
],
|
|
"config_flag": "trace_consensus",
|
|
"note": "Also carries close_time_correct, close_resolution_ms, consensus_state, proposing, round_time_ms, tx_count."
|
|
},
|
|
{
|
|
"name": "consensus.validation.send",
|
|
"category": "consensus",
|
|
"parent": null,
|
|
"required_attributes": [
|
|
"ledger_seq",
|
|
"proposing",
|
|
"ledger_hash",
|
|
"full_validation"
|
|
],
|
|
"config_flag": "trace_consensus",
|
|
"note": "follows-from consensus.accept. ledger_hash is BARE here (consensus-owned attr), unlike peer.validation.receive which uses the shared dotted xrpl.ledger.hash. Also carries validation_sign_time."
|
|
},
|
|
{
|
|
"name": "consensus.proposal.receive",
|
|
"category": "consensus",
|
|
"parent": null,
|
|
"required_attributes": [],
|
|
"config_flag": "trace_consensus",
|
|
"note": "Context-propagated from the sending peer. No required local attributes."
|
|
},
|
|
{
|
|
"name": "consensus.validation.receive",
|
|
"category": "consensus",
|
|
"parent": null,
|
|
"required_attributes": [],
|
|
"config_flag": "trace_consensus",
|
|
"note": "Context-propagated from the sending peer. No required local attributes."
|
|
},
|
|
{
|
|
"name": "consensus.mode_change",
|
|
"category": "consensus",
|
|
"parent": null,
|
|
"required_attributes": ["mode_old", "mode_new"],
|
|
"config_flag": "trace_consensus",
|
|
"optional": true,
|
|
"note": "Only fires on an operating-mode transition; a steady cluster rarely changes mode after warmup."
|
|
},
|
|
{
|
|
"name": "ledger.build",
|
|
"category": "ledger",
|
|
"parent": null,
|
|
"required_attributes": [
|
|
"ledger_seq",
|
|
"close_time",
|
|
"close_time_correct",
|
|
"close_resolution_ms"
|
|
],
|
|
"config_flag": "trace_ledger",
|
|
"note": "tx_count/tx_failed live on the child tx.apply span, not here."
|
|
},
|
|
{
|
|
"name": "ledger.validate",
|
|
"category": "ledger",
|
|
"parent": null,
|
|
"required_attributes": ["ledger_seq", "validations"],
|
|
"config_flag": "trace_ledger"
|
|
},
|
|
{
|
|
"name": "ledger.store",
|
|
"category": "ledger",
|
|
"parent": null,
|
|
"required_attributes": ["ledger_seq"],
|
|
"config_flag": "trace_ledger"
|
|
},
|
|
{
|
|
"name": "ledger.acquire",
|
|
"category": "ledger",
|
|
"parent": null,
|
|
"required_attributes": [
|
|
"ledger_seq",
|
|
"acquire_reason",
|
|
"timeouts",
|
|
"peer_count",
|
|
"outcome"
|
|
],
|
|
"config_flag": "trace_ledger",
|
|
"optional": true,
|
|
"note": "Only fires when a node must fetch a missing ledger (InboundLedger). A healthy local cluster rarely back-fills history."
|
|
},
|
|
{
|
|
"name": "peer.proposal.receive",
|
|
"category": "peer",
|
|
"parent": null,
|
|
"required_attributes": ["peer_id", "proposal_trusted"],
|
|
"config_flag": "trace_peer"
|
|
},
|
|
{
|
|
"name": "peer.validation.receive",
|
|
"category": "peer",
|
|
"parent": null,
|
|
"required_attributes": [
|
|
"peer_id",
|
|
"validation_trusted",
|
|
"xrpl.ledger.hash",
|
|
"validation_full"
|
|
],
|
|
"config_flag": "trace_peer",
|
|
"note": "Uses the shared dotted xrpl.ledger.hash constant (intentionally dotted, unlike consensus.validation.send)."
|
|
},
|
|
{
|
|
"name": "pathfind.request",
|
|
"category": "pathfind",
|
|
"parent": null,
|
|
"required_attributes": [
|
|
"pathfind_source_account",
|
|
"pathfind_dest_account"
|
|
],
|
|
"config_flag": "trace_rpc",
|
|
"note": "Fires on ripple_path_find / path_find RPC. Driven by the ripple_path_find load in rpc_load_generator.py."
|
|
},
|
|
{
|
|
"name": "pathfind.compute",
|
|
"category": "pathfind",
|
|
"parent": "pathfind.request",
|
|
"required_attributes": ["pathfind_fast"],
|
|
"config_flag": "trace_rpc",
|
|
"optional": true,
|
|
"note": "Only fires when PathRequest::doUpdate runs a computation; the self-to-self XRP probe from the load generator returns early without computing paths in a fresh cluster with no liquidity."
|
|
},
|
|
{
|
|
"name": "pathfind.discover",
|
|
"category": "pathfind",
|
|
"parent": "pathfind.compute",
|
|
"required_attributes": ["pathfind_search_level", "pathfind_num_paths"],
|
|
"config_flag": "trace_rpc",
|
|
"optional": true,
|
|
"note": "Graph exploration; only fires under pathfind.compute, which needs real path liquidity not present in the fresh test cluster."
|
|
},
|
|
{
|
|
"name": "pathfind.update_all",
|
|
"category": "pathfind",
|
|
"parent": null,
|
|
"required_attributes": ["pathfind_ledger_index", "pathfind_num_requests"],
|
|
"config_flag": "trace_rpc",
|
|
"optional": true,
|
|
"note": "Async recomputation at ledger close; only fires when there are active path_find subscriptions (the one-shot ripple_path_find load does not register one)."
|
|
},
|
|
{
|
|
"name": "grpc.*",
|
|
"category": "grpc",
|
|
"parent": null,
|
|
"required_attributes": ["method", "grpc_role", "grpc_status"],
|
|
"config_flag": "trace_rpc",
|
|
"optional": true,
|
|
"note": "Wildcard — grpc.<MethodName>. The harness has no gRPC client, so these do not fire. Tracked for completeness."
|
|
}
|
|
],
|
|
"parent_child_relationships": [
|
|
{
|
|
"parent": "rpc.ws_message",
|
|
"child": "rpc.process",
|
|
"description": "WebSocket message contains processing span",
|
|
"skip": true,
|
|
"skip_reason": "rpc.ws_message and rpc.process run on different threads (the WS handler posts a coroutine to JobQueue for processing). Span context is not propagated across the thread boundary. Requires a C++ fix to capture and forward the span context through the coroutine lambda."
|
|
},
|
|
{
|
|
"parent": "rpc.process",
|
|
"child": "rpc.command.*",
|
|
"description": "Processing span contains per-command span"
|
|
},
|
|
{
|
|
"parent": "ledger.build",
|
|
"child": "tx.apply",
|
|
"description": "Ledger build contains transaction application"
|
|
},
|
|
{
|
|
"parent": "consensus.round",
|
|
"child": "consensus.accept",
|
|
"description": "Consensus round contains the accept sub-span"
|
|
},
|
|
{
|
|
"parent": "consensus.accept",
|
|
"child": "consensus.accept.apply",
|
|
"description": "Accept contains the ledger-apply sub-span"
|
|
},
|
|
{
|
|
"parent": "pathfind.request",
|
|
"child": "pathfind.compute",
|
|
"description": "Pathfind request contains the compute sub-span",
|
|
"skip": true,
|
|
"skip_reason": "pathfind.compute only fires when a path computation actually runs; the self-to-self XRP probe in a fresh cluster with no liquidity returns before computing, so the child is not emitted under the harness workload."
|
|
}
|
|
],
|
|
"total_span_types": 40,
|
|
"total_unique_attributes": 58
|
|
}
|