mirror of
https://github.com/XRPLF/rippled.git
synced 2026-06-05 17:56:49 +00:00
feat(telemetry): add preflight/preclaim stage spans and stage attribute
The tx.transactor span covered only the apply stage; preflight and preclaim had no telemetry, so a transaction that hard-failed those stages produced no apply-pipeline span and per-stage latency/failure was invisible. Add tx.preflight and tx.preclaim spans in applySteps.cpp via a makeStageSpan() helper using SpanGuard::hashSpan, so all three stages share a deterministic trace_id derived from txID[0:16] even though they run sequentially and often cross-thread. Each span carries stage, tx_type, and ter_result; exceptions are recorded as tefEXCEPTION before the public wrappers map them. The type lookup is guarded behind the span-active check so it costs nothing when tracing is off. Add a stage="apply" attribute to the tx.transactor span and move its three hardcoded attribute strings to a new library-safe header include/xrpl/tx/detail/TxApplySpanNames.h, which mirrors the daemon-side TxSpanNames.h strings so the collector spanmetrics connector aggregates both span sets under one dimension set. A constants-contract test pins the span-name, attribute-key, and stage-value strings; span content stays covered by the docker integration test, as the rest of the telemetry suite is. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
@@ -240,6 +240,7 @@ xrpl.tx > xrpl.basics
|
||||
xrpl.tx > xrpl.core
|
||||
xrpl.tx > xrpl.ledger
|
||||
xrpl.tx > xrpl.protocol
|
||||
xrpl.tx > xrpl.telemetry
|
||||
xrpld.app > test.unit_test
|
||||
xrpld.app > xrpl.basics
|
||||
xrpld.app > xrpl.core
|
||||
|
||||
109
include/xrpl/tx/detail/TxApplySpanNames.h
Normal file
109
include/xrpl/tx/detail/TxApplySpanNames.h
Normal file
@@ -0,0 +1,109 @@
|
||||
#pragma once
|
||||
|
||||
/** Compile-time span name constants for the transaction apply pipeline.
|
||||
*
|
||||
* Defines the span names and attribute keys used by the three apply-pipeline
|
||||
* stages — preflight, preclaim, and transactor (apply) — that run inside the
|
||||
* library (`src/libxrpl/tx/`). Built on the StaticStr/join() primitives from
|
||||
* <xrpl/telemetry/SpanNames.h>.
|
||||
*
|
||||
* Why a separate header from TxSpanNames.h:
|
||||
* TxSpanNames.h lives under src/xrpld/ (daemon) and serves the overlay/app
|
||||
* lifecycle spans (tx.receive, tx.process). Library code (applySteps.cpp,
|
||||
* Transactor.cpp) must not depend on daemon headers, so the apply-pipeline
|
||||
* constants live here instead. The attribute strings ("tx_type",
|
||||
* "ter_result", "applied") intentionally match TxSpanNames.h so the collector
|
||||
* spanmetrics connector aggregates both sets under the same dimensions.
|
||||
*
|
||||
* Span hierarchy (deterministic trace_id derived from txID[0:16]):
|
||||
*
|
||||
* The three stages run sequentially and often on different threads, so they
|
||||
* do not auto-parent. Each uses a hash-derived trace_id keyed on the same
|
||||
* transaction id, placing all three under one trace without context
|
||||
* propagation. A transaction that hard-fails preflight or preclaim never
|
||||
* reaches the transactor span — the stage attribute identifies where it
|
||||
* stopped.
|
||||
*
|
||||
* +-----------------------------------------------------------+
|
||||
* | trace_id = txID[0:16] |
|
||||
* | |
|
||||
* | +-------------------+ +------------------+ +-------+ |
|
||||
* | | tx.preflight | | tx.preclaim | | tx. | |
|
||||
* | | stage=preflight |-->| stage=preclaim |-->| trans | |
|
||||
* | | tx_type | | tx_type | | actor | |
|
||||
* | | ter_result | | ter_result | | stage=| |
|
||||
* | +-------------------+ +------------------+ | apply | |
|
||||
* | stateless checks ledger-aware checks +-------+ |
|
||||
* | (signature, fields) (sequence, fee) applies |
|
||||
* +-----------------------------------------------------------+
|
||||
*
|
||||
* Usage:
|
||||
* @code
|
||||
* #include <xrpl/tx/detail/TxApplySpanNames.h>
|
||||
* using namespace telemetry;
|
||||
*
|
||||
* // preflight() / preclaim() use hashSpan with a full span name:
|
||||
* auto span = SpanGuard::hashSpan(
|
||||
* TraceCategory::Transactions, tx_apply_span::preflight,
|
||||
* txID.data(), txID.kBytes);
|
||||
* span.setAttribute(tx_apply_span::attr::stage, tx_apply_span::val::preflight);
|
||||
* span.setAttribute(tx_apply_span::attr::terResult, transToken(ter).c_str());
|
||||
* @endcode
|
||||
*
|
||||
* @code
|
||||
* // Transactor::operator() uses span() with prefix + suffix:
|
||||
* auto span = SpanGuard::span(
|
||||
* TraceCategory::Transactions, seg::tx, tx_apply_span::op::transactor);
|
||||
* span.setAttribute(tx_apply_span::attr::stage, tx_apply_span::val::apply);
|
||||
* @endcode
|
||||
*/
|
||||
|
||||
#include <xrpl/telemetry/SpanNames.h>
|
||||
|
||||
namespace xrpl::telemetry::tx_apply_span {
|
||||
|
||||
// ===== Span operation suffixes =============================================
|
||||
|
||||
namespace op {
|
||||
/// "preflight" — stateless transaction checks (suffix form).
|
||||
inline constexpr auto preflight = makeStr("preflight");
|
||||
/// "preclaim" — ledger-aware checks before fee claim (suffix form).
|
||||
inline constexpr auto preclaim = makeStr("preclaim");
|
||||
/// "transactor" — the apply stage (suffix form, used with span()).
|
||||
inline constexpr auto transactor = makeStr("transactor");
|
||||
} // namespace op
|
||||
|
||||
// ===== Full span names (tx.<op>) ===========================================
|
||||
|
||||
/// "tx.preflight" — full name for hashSpan() at the preflight stage.
|
||||
inline constexpr auto preflight = join(seg::tx, op::preflight);
|
||||
/// "tx.preclaim" — full name for hashSpan() at the preclaim stage.
|
||||
inline constexpr auto preclaim = join(seg::tx, op::preclaim);
|
||||
|
||||
// ===== Attribute keys ======================================================
|
||||
|
||||
namespace attr {
|
||||
/// "stage" — which apply-pipeline stage this span represents. Drives the
|
||||
/// collector spanmetrics `stage` dimension for per-stage RED metrics.
|
||||
inline constexpr auto stage = makeStr("stage");
|
||||
/// "tx_type" — transaction type name (e.g., "Payment", "OfferCreate").
|
||||
/// Matches tx_span::attr::txType so both share the spanmetrics dimension.
|
||||
inline constexpr auto txType = makeStr("tx_type");
|
||||
/// "ter_result" — engine result code after the stage (e.g., "tesSUCCESS").
|
||||
inline constexpr auto terResult = makeStr("ter_result");
|
||||
/// "applied" — whether the transaction was applied to the ledger (apply only).
|
||||
inline constexpr auto applied = makeStr("applied");
|
||||
} // namespace attr
|
||||
|
||||
// ===== Attribute values (stage names) ======================================
|
||||
|
||||
namespace val {
|
||||
/// "preflight" — value of the stage attribute on tx.preflight.
|
||||
inline constexpr auto preflight = makeStr("preflight");
|
||||
/// "preclaim" — value of the stage attribute on tx.preclaim.
|
||||
inline constexpr auto preclaim = makeStr("preclaim");
|
||||
/// "apply" — value of the stage attribute on tx.transactor.
|
||||
inline constexpr auto apply = makeStr("apply");
|
||||
} // namespace val
|
||||
|
||||
} // namespace xrpl::telemetry::tx_apply_span
|
||||
@@ -44,6 +44,7 @@
|
||||
#include <xrpl/tx/SignerEntries.h>
|
||||
#include <xrpl/tx/apply.h>
|
||||
#include <xrpl/tx/applySteps.h>
|
||||
#include <xrpl/tx/detail/TxApplySpanNames.h>
|
||||
|
||||
#include <cstddef>
|
||||
#include <cstdint>
|
||||
@@ -1199,9 +1200,11 @@ Transactor::operator()()
|
||||
auto span = telemetry::SpanGuard::span(
|
||||
telemetry::TraceCategory::Transactions,
|
||||
telemetry::seg::tx,
|
||||
telemetry::makeStr("transactor"));
|
||||
telemetry::tx_apply_span::op::transactor);
|
||||
// "apply" — the third apply-pipeline stage, after preflight and preclaim.
|
||||
span.setAttribute(telemetry::tx_apply_span::attr::stage, telemetry::tx_apply_span::val::apply);
|
||||
if (auto const* fmt = TxFormats::getInstance().findByType(ctx_.tx.getTxnType()))
|
||||
span.setAttribute("tx_type", fmt->getName().c_str());
|
||||
span.setAttribute(telemetry::tx_apply_span::attr::txType, fmt->getName().c_str());
|
||||
|
||||
JLOG(j_.trace()) << "apply: " << ctx_.tx.getTransactionID();
|
||||
|
||||
@@ -1429,8 +1432,8 @@ Transactor::operator()()
|
||||
|
||||
JLOG(j_.trace()) << (applied ? "applied " : "not applied ") << transToken(result);
|
||||
|
||||
span.setAttribute("ter_result", transToken(result).c_str());
|
||||
span.setAttribute("applied", applied);
|
||||
span.setAttribute(telemetry::tx_apply_span::attr::terResult, transToken(result).c_str());
|
||||
span.setAttribute(telemetry::tx_apply_span::attr::applied, applied);
|
||||
|
||||
return {result, applied, metadata};
|
||||
}
|
||||
|
||||
@@ -13,13 +13,16 @@
|
||||
#include <xrpl/protocol/SeqProxy.h>
|
||||
#include <xrpl/protocol/TER.h>
|
||||
#include <xrpl/protocol/XRPAmount.h>
|
||||
#include <xrpl/telemetry/SpanGuard.h>
|
||||
#include <xrpl/tx/ApplyContext.h>
|
||||
#include <xrpl/tx/Transactor.h>
|
||||
#include <xrpl/tx/detail/TxApplySpanNames.h>
|
||||
|
||||
#include <cstdint>
|
||||
#include <exception>
|
||||
#include <memory>
|
||||
#include <optional>
|
||||
#include <string_view>
|
||||
#include <utility>
|
||||
#pragma push_macro("TRANSACTION")
|
||||
#undef TRANSACTION
|
||||
@@ -51,6 +54,47 @@ struct UnknownTxnType : std::exception
|
||||
}
|
||||
};
|
||||
|
||||
/** Look up the human-readable transaction type name for span attributes.
|
||||
* Returns nullptr if the type is unknown so the caller can skip the
|
||||
* attribute rather than emit an empty value.
|
||||
*/
|
||||
char const*
|
||||
txTypeName(TxType txnType)
|
||||
{
|
||||
if (auto const* fmt = TxFormats::getInstance().findByType(txnType))
|
||||
return fmt->getName().c_str();
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
/** Create a deterministic-trace span for an apply-pipeline stage.
|
||||
*
|
||||
* The trace_id is derived from txID[0:16] so the preflight, preclaim, and
|
||||
* transactor spans of one transaction share a trace even though they run
|
||||
* sequentially and often on different threads. Sets the stage, tx_type, and
|
||||
* (after the stage runs) ter_result attributes that drive the collector
|
||||
* spanmetrics dimensions. A no-op when telemetry is disabled.
|
||||
*
|
||||
* @param name Full span name (tx_apply_span::preflight / ::preclaim).
|
||||
* @param stage Stage attribute value (tx_apply_span::val::*).
|
||||
* @param tx The transaction supplying the id and type.
|
||||
*/
|
||||
[[nodiscard]] telemetry::SpanGuard
|
||||
makeStageSpan(std::string_view name, std::string_view stage, STTx const& tx)
|
||||
{
|
||||
auto const txID = tx.getTransactionID();
|
||||
auto span = telemetry::SpanGuard::hashSpan(
|
||||
telemetry::TraceCategory::Transactions, name, txID.data(), txID.kBytes);
|
||||
// Guard the type lookup behind the active check: preflight runs for every
|
||||
// transaction, so findByType() must not run when tracing is off/disabled.
|
||||
if (span)
|
||||
{
|
||||
span.setAttribute(telemetry::tx_apply_span::attr::stage, stage);
|
||||
if (char const* typeName = txTypeName(tx.getTxnType()))
|
||||
span.setAttribute(telemetry::tx_apply_span::attr::txType, typeName);
|
||||
}
|
||||
return span;
|
||||
}
|
||||
|
||||
// Call a lambda with the concrete transaction type as a template parameter
|
||||
// throw an "UnknownTxnType" exception on error
|
||||
template <class F>
|
||||
@@ -133,82 +177,118 @@ consequencesHelper(PreflightContext const& ctx)
|
||||
static std::pair<NotTEC, TxConsequences>
|
||||
invokePreflight(PreflightContext const& ctx)
|
||||
{
|
||||
// Trace the preflight stage. The span shares the transaction's
|
||||
// deterministic trace_id so it correlates with preclaim and transactor.
|
||||
auto span = makeStageSpan(
|
||||
telemetry::tx_apply_span::preflight, telemetry::tx_apply_span::val::preflight, ctx.tx);
|
||||
try
|
||||
{
|
||||
return withTxnType(ctx.rules, ctx.tx.getTxnType(), [&]<typename T>() {
|
||||
auto result = withTxnType(ctx.rules, ctx.tx.getTxnType(), [&]<typename T>() {
|
||||
auto const tec = Transactor::invokePreflight<T>(ctx);
|
||||
return std::make_pair(
|
||||
tec, isTesSuccess(tec) ? consequencesHelper<T>(ctx) : TxConsequences{tec});
|
||||
});
|
||||
if (span)
|
||||
span.setAttribute(
|
||||
telemetry::tx_apply_span::attr::terResult, transToken(result.first).c_str());
|
||||
return result;
|
||||
}
|
||||
catch (UnknownTxnType const& e)
|
||||
{
|
||||
// Should never happen
|
||||
// LCOV_EXCL_START
|
||||
JLOG(ctx.j.fatal()) << "Unknown transaction type in preflight: " << e.txnType;
|
||||
span.recordException(e);
|
||||
UNREACHABLE("xrpl::invokePreflight : unknown transaction type");
|
||||
return {temUNKNOWN, TxConsequences{temUNKNOWN}};
|
||||
// LCOV_EXCL_STOP
|
||||
}
|
||||
catch (std::exception const& e)
|
||||
{
|
||||
// The caller's preflight() maps this to tefEXCEPTION. Record it on the
|
||||
// span before unwinding so per-stage error counts include exceptions.
|
||||
span.setAttribute(
|
||||
telemetry::tx_apply_span::attr::terResult, transToken(tefEXCEPTION).c_str());
|
||||
span.recordException(e);
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
static TER
|
||||
invokePreclaim(PreclaimContext const& ctx)
|
||||
{
|
||||
// Trace the preclaim stage under the transaction's deterministic trace_id.
|
||||
auto span = makeStageSpan(
|
||||
telemetry::tx_apply_span::preclaim, telemetry::tx_apply_span::val::preclaim, ctx.tx);
|
||||
try
|
||||
{
|
||||
// use name hiding to accomplish compile-time polymorphism of static
|
||||
// class functions for Transactor and derived classes.
|
||||
return withTxnType(ctx.view.rules(), ctx.tx.getTxnType(), [&]<typename T>() -> TER {
|
||||
// preclaim functionality is divided into two sections:
|
||||
// 1. Up to and including the signature check: returns NotTEC.
|
||||
// All transaction checks before and including checkSign
|
||||
// MUST return NotTEC, or something more restrictive.
|
||||
// Allowing tec results in these steps risks theft or
|
||||
// destruction of funds, as a fee will be charged before the
|
||||
// signature is checked.
|
||||
// 2. After the signature check: returns TER.
|
||||
TER const preclaimTer =
|
||||
withTxnType(ctx.view.rules(), ctx.tx.getTxnType(), [&]<typename T>() -> TER {
|
||||
// preclaim functionality is divided into two sections:
|
||||
// 1. Up to and including the signature check: returns NotTEC.
|
||||
// All transaction checks before and including checkSign
|
||||
// MUST return NotTEC, or something more restrictive.
|
||||
// Allowing tec results in these steps risks theft or
|
||||
// destruction of funds, as a fee will be charged before the
|
||||
// signature is checked.
|
||||
// 2. After the signature check: returns TER.
|
||||
|
||||
// If the transactor requires a valid account and the
|
||||
// transaction doesn't list one, preflight will have already
|
||||
// a flagged a failure.
|
||||
auto const id = ctx.tx.getAccountID(sfAccount);
|
||||
// If the transactor requires a valid account and the
|
||||
// transaction doesn't list one, preflight will have already
|
||||
// a flagged a failure.
|
||||
auto const id = ctx.tx.getAccountID(sfAccount);
|
||||
|
||||
if (id != beast::kZero)
|
||||
{
|
||||
if (NotTEC const preSigResult = [&]() -> NotTEC {
|
||||
if (NotTEC const result = T::checkSeqProxy(ctx.view, ctx.tx, ctx.j))
|
||||
return result;
|
||||
if (id != beast::kZero)
|
||||
{
|
||||
if (NotTEC const preSigResult = [&]() -> NotTEC {
|
||||
if (NotTEC const result = T::checkSeqProxy(ctx.view, ctx.tx, ctx.j))
|
||||
return result;
|
||||
|
||||
if (NotTEC const result = T::checkPriorTxAndLastLedger(ctx))
|
||||
return result;
|
||||
if (NotTEC const result = T::checkPriorTxAndLastLedger(ctx))
|
||||
return result;
|
||||
|
||||
if (NotTEC const result = T::checkPermission(ctx.view, ctx.tx))
|
||||
return result;
|
||||
if (NotTEC const result = T::checkPermission(ctx.view, ctx.tx))
|
||||
return result;
|
||||
|
||||
if (NotTEC const result = T::checkSign(ctx))
|
||||
return result;
|
||||
if (NotTEC const result = T::checkSign(ctx))
|
||||
return result;
|
||||
|
||||
return tesSUCCESS;
|
||||
}())
|
||||
return preSigResult;
|
||||
return tesSUCCESS;
|
||||
}())
|
||||
return preSigResult;
|
||||
|
||||
if (TER const result = T::checkFee(ctx, calculateBaseFee(ctx.view, ctx.tx)))
|
||||
return result;
|
||||
}
|
||||
if (TER const result = T::checkFee(ctx, calculateBaseFee(ctx.view, ctx.tx)))
|
||||
return result;
|
||||
}
|
||||
|
||||
return T::preclaim(ctx);
|
||||
});
|
||||
return T::preclaim(ctx);
|
||||
});
|
||||
if (span)
|
||||
span.setAttribute(
|
||||
telemetry::tx_apply_span::attr::terResult, transToken(preclaimTer).c_str());
|
||||
return preclaimTer;
|
||||
}
|
||||
catch (UnknownTxnType const& e)
|
||||
{
|
||||
// Should never happen
|
||||
// LCOV_EXCL_START
|
||||
JLOG(ctx.j.fatal()) << "Unknown transaction type in preclaim: " << e.txnType;
|
||||
span.recordException(e);
|
||||
UNREACHABLE("xrpl::invokePreclaim : unknown transaction type");
|
||||
return temUNKNOWN;
|
||||
// LCOV_EXCL_STOP
|
||||
}
|
||||
catch (std::exception const& e)
|
||||
{
|
||||
// The caller's preclaim() maps this to tefEXCEPTION. Record it on the
|
||||
// span before unwinding so per-stage error counts include exceptions.
|
||||
span.setAttribute(
|
||||
telemetry::tx_apply_span::attr::terResult, transToken(tefEXCEPTION).c_str());
|
||||
span.recordException(e);
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
52
src/tests/libxrpl/telemetry/TxApplySpanNames.cpp
Normal file
52
src/tests/libxrpl/telemetry/TxApplySpanNames.cpp
Normal file
@@ -0,0 +1,52 @@
|
||||
#include <xrpl/tx/detail/TxApplySpanNames.h>
|
||||
|
||||
#include <gtest/gtest.h>
|
||||
|
||||
#include <string_view>
|
||||
|
||||
/** Contract tests for the transaction apply-pipeline span constants.
|
||||
*
|
||||
* The span names and attribute keys in TxApplySpanNames.h are a cross-component
|
||||
* contract: the collector spanmetrics connector aggregates on these exact
|
||||
* strings (dimensions tx_type, ter_result, stage) and the Grafana
|
||||
* transaction-overview dashboard queries them. A silent rename here would
|
||||
* break per-stage metrics with no compile error, so these tests pin the
|
||||
* literal values. They need no telemetry runtime and run in every build.
|
||||
*/
|
||||
|
||||
using namespace xrpl::telemetry;
|
||||
|
||||
TEST(TxApplySpanNames, span_names_are_dot_qualified)
|
||||
{
|
||||
// Full span names feed SpanGuard::hashSpan() in applySteps.cpp.
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::preflight), "tx.preflight");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::preclaim), "tx.preclaim");
|
||||
}
|
||||
|
||||
TEST(TxApplySpanNames, operation_suffixes)
|
||||
{
|
||||
// Suffix used with SpanGuard::span(cat, seg::tx, suffix) in Transactor.cpp.
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::op::preflight), "preflight");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::op::preclaim), "preclaim");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::op::transactor), "transactor");
|
||||
}
|
||||
|
||||
TEST(TxApplySpanNames, attribute_keys_match_collector_dimensions)
|
||||
{
|
||||
// These keys MUST match docker/telemetry/otel-collector-config.yaml
|
||||
// spanmetrics dimensions and TxSpanNames.h (so both span sets aggregate
|
||||
// under one dimension).
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::attr::stage), "stage");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::attr::txType), "tx_type");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::attr::terResult), "ter_result");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::attr::applied), "applied");
|
||||
}
|
||||
|
||||
TEST(TxApplySpanNames, stage_values_are_the_three_pipeline_stages)
|
||||
{
|
||||
// The stage attribute carries exactly these three values; they become the
|
||||
// spanmetrics `stage` dimension cardinality (3) and the dashboard filter.
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::val::preflight), "preflight");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::val::preclaim), "preclaim");
|
||||
EXPECT_EQ(std::string_view(tx_apply_span::val::apply), "apply");
|
||||
}
|
||||
Reference in New Issue
Block a user