diff --git a/docker/telemetry/otel-collector-config.grafanacloud.yaml b/docker/telemetry/otel-collector-config.grafanacloud.yaml index 5fe6957c72..c0e9a11dc2 100644 --- a/docker/telemetry/otel-collector-config.grafanacloud.yaml +++ b/docker/telemetry/otel-collector-config.grafanacloud.yaml @@ -121,6 +121,7 @@ processors: - context: datapoint statements: - set(attributes["service_instance_id"], resource.attributes["service.instance.id"]) + - set(attributes["xrpl_node_id"], resource.attributes["xrpl.node.id"]) - set(attributes["deployment_environment"], resource.attributes["deployment.environment"]) - set(attributes["xrpl_network_type"], resource.attributes["xrpl.network.type"]) @@ -141,6 +142,7 @@ connectors: # series from distinct nodes/tiers grouped separately. resource_metrics_key_attributes: - service.instance.id + - xrpl.node.id - deployment.environment - xrpl.network.type histogram: diff --git a/docker/telemetry/otel-collector-config.yaml b/docker/telemetry/otel-collector-config.yaml index f595c43855..9f3b95ceee 100644 --- a/docker/telemetry/otel-collector-config.yaml +++ b/docker/telemetry/otel-collector-config.yaml @@ -136,6 +136,7 @@ connectors: # nodes/tiers grouped separately. resource_metrics_key_attributes: - service.instance.id + - xrpl.node.id - deployment.environment - xrpl.network.type histogram: diff --git a/include/xrpl/beast/insight/Collector.h b/include/xrpl/beast/insight/Collector.h index 9da2a8bb74..d3e7f4d5e5 100644 --- a/include/xrpl/beast/insight/Collector.h +++ b/include/xrpl/beast/insight/Collector.h @@ -30,6 +30,29 @@ public: virtual ~Collector() = 0; + /** + * Called once the services that hook handlers read are constructed. + * + * Implementations that poll their producers must not do so before this: + * hook handlers read live application state. Default is a no-op, for + * collectors that only push. + */ + virtual void + onCollectionReady() + { + } + + /** + * Called before those services are shut down. + * + * Polling must have stopped by the time this returns. Paired with + * onCollectionReady(). + */ + virtual void + onCollectionStopping() + { + } + /** * Create a hook. * diff --git a/include/xrpl/server/Wallet.h b/include/xrpl/server/Wallet.h index 95486cc468..af6c92b83d 100644 --- a/include/xrpl/server/Wallet.h +++ b/include/xrpl/server/Wallet.h @@ -16,6 +16,7 @@ #include #include +#include #include #include #include @@ -88,6 +89,19 @@ addValidatorManifest(soci::session& session, std::string const& serialized); void clearNodeIdentity(soci::session& session); +/** + * Returns this node's stored keypair, if the database holds a valid one. + * + * Read-only: unlike getNodeIdentity(), never generates or persists a key. A row + * counts only when its public and secret keys are a pair. + * + * @param session Session with the database. + * + * @return The stored keypair, or std::nullopt. + */ +std::optional> +readNodeIdentity(soci::session& session); + /** * Returns a stable public and private key for this node. * diff --git a/src/libxrpl/beast/insight/OTelCollector.cpp b/src/libxrpl/beast/insight/OTelCollector.cpp index e28dc60ad2..a66208b937 100644 --- a/src/libxrpl/beast/insight/OTelCollector.cpp +++ b/src/libxrpl/beast/insight/OTelCollector.cpp @@ -229,13 +229,9 @@ public: * @param name Export-ready metric name, already run through * formatName() by the collector: lowercase, with `.` * and ` ` mapped to `_`. - * @param meter OTel Meter used to create the observable gauge. * @param collector Owning collector, used to invoke hooks before reads. */ - OTelGaugeImpl( - std::string const& name, - opentelemetry::nostd::shared_ptr const& meter, - std::shared_ptr const& collector); + OTelGaugeImpl(std::string name, std::shared_ptr const& collector); ~OTelGaugeImpl() override; @@ -273,6 +269,25 @@ public: static void gaugeCallback(opentelemetry::metrics::ObserverResult result, void* state); + /** + * Create the observable instrument and register the callback, once. + * + * Called when the collector is told collection is ready, because the + * callback reads live application state. + */ + void + arm(); + + /** + * Remove the callback, so the reader thread stops observing this gauge. + * + * RemoveCallback is synchronous: the SDK guards its callback list and the + * observe pass with the same mutex, so no callback is running once this + * returns. Idempotent. + */ + void + disarm(); + private: /** * Current gauge value, updated atomically by set()/increment(). @@ -280,10 +295,20 @@ private: std::atomic value_{0}; /** - * OTel observable gauge handle (prevents deregistration). + * Export-ready metric name, held until arm() creates the instrument. + */ + std::string const name_; + + /** + * OTel observable gauge handle, null until arm() runs. */ opentelemetry::nostd::shared_ptr gauge_; + /** + * Guards gauge_ against concurrent arm()/disarm(). + */ + std::mutex armMutex_; + /** * Owning collector, used to invoke hooks before reading gauge values. */ @@ -450,6 +475,12 @@ public: Gauge makeGauge(std::string const& name) override; + void + onCollectionReady() override; + + void + onCollectionStopping() override; + Meter makeMeter(std::string const& name) override; /** @} */ @@ -503,6 +534,13 @@ public: removeGauge(OTelGaugeImpl* gauge); /** @} */ + /** + * @brief The shared Meter, for gauges creating their instrument in arm(). + * @return The Meter this collector resolved at construction. + */ + opentelemetry::nostd::shared_ptr const& + otelMeter() const; + /** * @brief Format a raw metric name for export. * @@ -627,16 +665,37 @@ OTelEventImpl::notify(value_type const& value) // OTelGaugeImpl //------------------------------------------------------------------------------ -OTelGaugeImpl::OTelGaugeImpl( - std::string const& name, - opentelemetry::nostd::shared_ptr const& meter, - std::shared_ptr const& collector) - : gauge_(meter->CreateInt64ObservableGauge(name)), collector_(collector) +OTelGaugeImpl::OTelGaugeImpl(std::string name, std::shared_ptr const& collector) + : name_(std::move(name)), collector_(collector) { collector_->addGauge(this); +} + +void +OTelGaugeImpl::arm() +{ + // AddCallback arms the SDK reader thread against this gauge, and the + // callback runs hook handlers that read application services. The registry + // does not de-duplicate callbacks, so arm at most once. + std::scoped_lock const lock(armMutex_); + if (gauge_) + return; + + gauge_ = collector_->otelMeter()->CreateInt64ObservableGauge(name_); gauge_->AddCallback(gaugeCallback, this); } +void +OTelGaugeImpl::disarm() +{ + std::scoped_lock const lock(armMutex_); + if (!gauge_) + return; + + gauge_->RemoveCallback(gaugeCallback, this); + gauge_ = nullptr; +} + void OTelGaugeImpl::gaugeCallback(opentelemetry::metrics::ObserverResult result, void* state) { @@ -657,7 +716,8 @@ OTelGaugeImpl::~OTelGaugeImpl() // The SDK's ObservableRegistry guards its callback list and the Observe() // pass with the same mutex, so RemoveCallback cannot return while a // callback for this instrument is in flight — removal is synchronous. - gauge_->RemoveCallback(gaugeCallback, this); + // A no-op when never armed, or already disarmed at shutdown. + disarm(); collector_->removeGauge(this); } @@ -786,7 +846,7 @@ OTelCollectorImp::makeEvent(std::string const& name) Gauge OTelCollectorImp::makeGauge(std::string const& name) { - return Gauge(std::make_shared(formatName(name), otelMeter_, shared_from_this())); + return Gauge(std::make_shared(formatName(name), shared_from_this())); } Meter @@ -852,6 +912,64 @@ OTelCollectorImp::removeGauge(OTelGaugeImpl* gauge) std::erase(gauges_, gauge); } +void +OTelCollectorImp::onCollectionReady() +{ + // Snapshot under the lock, arm outside it. arm() enters the SDK's + // observable registry lock, and the reader thread takes that lock before + // calling callHooks(), which wants mutex_. callHooks() copies its hook list + // for the same reason. + std::vector gauges; + { + std::scoped_lock const lock(mutex_); + gauges = gauges_; + } + + std::size_t armed = 0; + for (auto* gauge : gauges) + { + // Telemetry must never stop the node, so one bad instrument costs only + // its own metric. + try + { + gauge->arm(); + ++armed; + } + catch (std::exception const& e) + { + JLOG(journal_.error()) << "OTelCollector: could not register an observable gauge, " + "so that metric will not be exported: " + << e.what(); + } + } + + JLOG(journal_.info()) << "OTelCollector: registered " << armed << " of " << gauges.size() + << " observable gauges"; +} + +void +OTelCollectorImp::onCollectionStopping() +{ + // Same lock discipline as onCollectionReady(): snapshot, then act outside + // the lock, because disarm() enters the SDK's observable registry lock. + std::vector gauges; + { + std::scoped_lock const lock(mutex_); + gauges = gauges_; + } + + for (auto* gauge : gauges) + gauge->disarm(); + + JLOG(journal_.info()) << "OTelCollector: stopped observing " << gauges.size() << " gauges"; +} + +opentelemetry::nostd::shared_ptr const& +OTelCollectorImp::otelMeter() const +{ + return otelMeter_; +} + std::string OTelCollectorImp::formatName(std::string const& name) { diff --git a/src/libxrpl/beast/insight/StatsDCollector.cpp b/src/libxrpl/beast/insight/StatsDCollector.cpp index dc19aa8953..bc2640ca77 100644 --- a/src/libxrpl/beast/insight/StatsDCollector.cpp +++ b/src/libxrpl/beast/insight/StatsDCollector.cpp @@ -23,6 +23,7 @@ #include #include +#include #include #include #include @@ -218,6 +219,13 @@ private: std::recursive_mutex metricsLock_; List metrics_; + /** + * Whether hook handlers may be called. False until onCollectionReady(), + * because the handlers read application services that are still being + * constructed while this collector exists. + */ + std::atomic polling_{false}; + // Must come last for order of init std::thread thread_; @@ -255,6 +263,22 @@ public: thread_.join(); } + void + onCollectionReady() override + { + polling_.store(true, std::memory_order_release); + } + + void + onCollectionStopping() override + { + polling_.store(false, std::memory_order_release); + + // onTimer holds metricsLock_ across the handler loop, so acquiring it + // here waits for a handler that is already running. + std::scoped_lock const _(metricsLock_); + } + Hook makeHook(HookImpl::HandlerType const& handler) override { @@ -437,12 +461,15 @@ public: return; } - std::scoped_lock const _(metricsLock_); + if (polling_.load(std::memory_order_acquire)) + { + std::scoped_lock const _(metricsLock_); - for (auto& m : metrics_) - m.doProcess(); + for (auto& m : metrics_) + m.doProcess(); - sendBuffers(); + sendBuffers(); + } setTimer(); } diff --git a/src/libxrpl/server/Wallet.cpp b/src/libxrpl/server/Wallet.cpp index 56d0db67d4..92317d40f6 100644 --- a/src/libxrpl/server/Wallet.cpp +++ b/src/libxrpl/server/Wallet.cpp @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -147,27 +148,34 @@ clearNodeIdentity(soci::session& session) session << "DELETE FROM NodeIdentity;"; } +std::optional> +readNodeIdentity(soci::session& session) +{ + // SOCI requires boost::optional (not std::optional) as the parameter. + boost::optional pubKO, priKO; + soci::statement st = + (session.prepare << "SELECT PublicKey, PrivateKey FROM NodeIdentity;", + soci::into(pubKO), + soci::into(priKO)); + st.execute(); + while (st.fetch()) + { + auto const sk = parseBase58(TokenType::NodePrivate, priKO.value_or("")); + auto const pk = parseBase58(TokenType::NodePublic, pubKO.value_or("")); + + // Only use if the public and secret keys are a pair + if (sk && pk && (*pk == derivePublicKey(KeyType::Secp256k1, *sk))) + return std::pair{*pk, *sk}; + } + + return std::nullopt; +} + std::pair getNodeIdentity(soci::session& session) { - { - // SOCI requires boost::optional (not std::optional) as the parameter. - boost::optional pubKO, priKO; - soci::statement st = - (session.prepare << "SELECT PublicKey, PrivateKey FROM NodeIdentity;", - soci::into(pubKO), - soci::into(priKO)); - st.execute(); - while (st.fetch()) - { - auto const sk = parseBase58(TokenType::NodePrivate, priKO.value_or("")); - auto const pk = parseBase58(TokenType::NodePublic, pubKO.value_or("")); - - // Only use if the public and secret keys are a pair - if (sk && pk && (*pk == derivePublicKey(KeyType::Secp256k1, *sk))) - return {*pk, *sk}; - } - } + if (auto const stored = readNodeIdentity(session)) + return *stored; // If a valid identity wasn't found, we randomly generate a new one: auto [newpublicKey, newsecretKey] = randomKeyPair(KeyType::Secp256k1); diff --git a/src/libxrpl/telemetry/Telemetry.cpp b/src/libxrpl/telemetry/Telemetry.cpp index 0b0e9659a3..74faead1fa 100644 --- a/src/libxrpl/telemetry/Telemetry.cpp +++ b/src/libxrpl/telemetry/Telemetry.cpp @@ -66,6 +66,7 @@ #include #include +#include #include #include #include @@ -317,26 +318,41 @@ class TelemetryImpl : public Telemetry */ opentelemetry::nostd::shared_ptr contextStorage_; + /** + * Set by stop(), so a second call does nothing. + */ + bool stopped_{false}; + public: TelemetryImpl(Setup setup, beast::Journal journal) : setup_(std::move(setup)), journal_(journal) { - // Build the metrics pipeline NOW, in the constructor, so the global - // MeterProvider is published before any subsystem is constructed. - // beast::insight instruments are created eagerly in subsystem - // constructors (e.g. LedgerMaster, NetworkOPs, ServerHandler), which - // run during ApplicationImp's member-init list — long before start(). - // opentelemetry-cpp has no proxy MeterProvider, so an instrument - // created before SetMeterProvider() binds to the noop provider forever. - // Tracing does not have this problem because getTracer() is called - // fresh at each span creation (runtime, after start()). + // Publish the MeterProvider before any subsystem is constructed; see + // initMetrics(). setup_.serviceInstanceId is already resolved by the + // caller, so the resource is complete. // - // The metrics resource uses setup_.serviceInstanceId as provided by - // config. A later setServiceInstanceId() (node-key fallback) cannot - // change this immutable resource, so operators relying on the node-key - // identity should set [telemetry] service_instance_id explicitly. - initMetrics(); + // A failure must never stop the node starting: the global provider + // stays noop and every instrument call remains valid. + try + { + initMetrics(); + } + catch (std::exception const& e) + { + JLOG(journal_.error()) << "Telemetry metrics pipeline failed to initialise, " + "continuing without metrics: " + << e.what(); + } } + /** + * Override the service instance id, for callers that learn it late. + * + * Affects only the tracer resource, which start() builds. The metrics + * resource is built by the constructor and is immutable, so supply the id + * through Setup to have it on both. + * + * @param id The instance id to report on spans. + */ void setServiceInstanceId(std::string const& id) override { @@ -572,10 +588,16 @@ public: void stop() override { + if (stopped_) + return; + stopped_ = true; + JLOG(journal_.info()) << "Telemetry stopping"; - // Unregister global instance before tearing down the pipeline. - Telemetry::setInstance(nullptr); + // Unregister global instance before tearing down the pipeline, but only + // if this object is the one that published it. + if (Telemetry::getInstance() == this) + Telemetry::setInstance(nullptr); if (sdkProvider_) { diff --git a/src/xrpld/app/main/Application.cpp b/src/xrpld/app/main/Application.cpp index 5963697f35..a89d4392b9 100644 --- a/src/xrpld/app/main/Application.cpp +++ b/src/xrpld/app/main/Application.cpp @@ -328,7 +328,8 @@ public: ApplicationImp( std::unique_ptr config, std::unique_ptr logs, - std::unique_ptr timeKeeper) + std::unique_ptr timeKeeper, + std::optional const& nodePublicKey) : BasicApp(numberOfThreads(*config)) , config_(std::move(config)) , logs_(std::move(logs)) @@ -342,11 +343,15 @@ public: *this, logs_->journal("PerfLog"), [this] { signalStop("PerfLog"); })) + // Telemetry publishes the MeterProvider on construction, so it must + // precede collectorManager_ below and every subsystem that creates an + // instrument. Its resource is immutable, so the instance id has to be + // supplied now; empty means this run reports none. , telemetry_( telemetry::makeTelemetry( telemetry::makeTelemetrySetup( config_->section("telemetry"), - "", // Updated later via setServiceInstanceId() + nodePublicKey.value_or(""), build_info::getVersionString(), config_->networkId), logs_->journal("Telemetry"))) @@ -535,6 +540,33 @@ public: add(ledgerCleaner_.get()); } + /** + * Stop observing and stop telemetry before the members are destroyed. + * + * The metrics reader thread runs callbacks that read the services member + * destruction is about to tear down. telemetry_ is declared early because + * the collector needs its MeterProvider, so reverse-order member destruction + * would take it down last. + * + * run() does both on the normal path; this covers the paths that never + * reach it -- every `return false` in setup(), and the unit tests. Both + * calls are idempotent. + */ + ~ApplicationImp() override + { + // A shutdown diagnostic must never terminate the process, and a + // destructor is implicitly noexcept. + try + { + collectorManager_->collector()->onCollectionStopping(); + telemetry_->stop(); + } + catch (std::exception const& e) + { + JLOG(journal_.error()) << "Error stopping telemetry: " << e.what(); + } + } + //-------------------------------------------------------------------------- bool @@ -1206,15 +1238,15 @@ private: * * Rule for keeping this call site valid: only telemetry work that reads * NO application subsystem may run here. That holds today — this phase - * uses the config strings and the node identity, and creates only - * push-model counters and histograms, which app code records into once - * it is ready. Anything that registers a callback reading a subsystem - * must go in startTelemetryGauges() instead, because a callback - * registered here can fire on the metrics reader thread while the rest of - * the application is still being built. + * uses the config strings and creates only push-model counters and + * histograms, which app code records into once it is ready. Anything that + * registers a callback reading a subsystem must go in + * startTelemetryGauges() instead, because a callback registered here can + * fire on the metrics reader thread while the rest of the application is + * still being built. * - * @pre nodeIdentity_ is populated (needed for the service_instance_id - * fallback) and metricsRegistry_ is constructed. + * The resource attributes, including service.instance.id, were supplied at + * construction. */ void startTelemetry() const; @@ -1338,11 +1370,8 @@ ApplicationImp::setup(boost::program_options::variables_map const& cmdline) nodeIdentity_ = getNodeIdentity(*this, cmdline); - // Now that the node identity is known, inject it into the telemetry - // resource attributes — but only if the user didn't already set a - // custom service_instance_id in [telemetry]. The Telemetry object - // was constructed with an empty serviceInstanceId because - // nodeIdentity_ is not available in the member initializer list. + // The metrics resource was fixed at construction, but the tracer resource is + // built by start() below, so a key minted just now can still reach spans. if (!config_->section("telemetry").exists("service_instance_id")) telemetry_->setServiceInstanceId(toBase58(TokenType::NodePublic, nodeIdentity_->first)); @@ -1530,14 +1559,15 @@ ApplicationImp::setup(boost::program_options::variables_map const& cmdline) collectorManager_->collector()); add(*overlay_); // add to PropertyStream - // Register the observable instruments now that overlay_ exists. This arms - // the metrics reader thread to invoke their callbacks, several of which - // read getOverlay() — registering earlier would let the reader observe a - // half-built application. The reader thread itself already started in - // startTelemetry() above; this is as early as the callbacks can safely be - // attached, and it is still before beginConsensus() so the gauges cover - // the first round. + // Register the observable instruments now that overlay_ exists — the last of + // the services their callbacks read. Registering earlier would let the + // metrics reader thread observe a half-built application. Two independent + // sets: the MetricsRegistry gauges, and the insight collector's, whose + // callbacks additionally run the hook handlers in ledgerMaster_, + // networkOPs_, the peer finder and the job queue. Both are still before + // beginConsensus() below, so they cover the first round. startTelemetryGauges(); + collectorManager_->collector()->onCollectionReady(); // start first consensus round if (!networkOPs_->beginConsensus(ledgerMaster_->getClosedLedger()->header().hash, {})) @@ -1788,6 +1818,11 @@ ApplicationImp::run() return getValidators().trustedPublisher(pubKey); }); + // Stop observing before any service below is stopped: the collector's gauge + // callbacks run hook handlers that read ledgerMaster_, networkOPs_, the peer + // finder, the job queue and overlay_. Returns once no callback is running. + collectorManager_->collector()->onCollectionStopping(); + // The order of these stop calls is delicate. // Re-ordering them risks undefined behavior. loadManager_->stop(); @@ -2389,9 +2424,19 @@ makeApplication( std::unique_ptr config, std::unique_ptr logs, std::unique_ptr timeKeeper) +{ + return makeApplication(std::move(config), std::move(logs), std::move(timeKeeper), std::nullopt); +} + +std::unique_ptr +makeApplication( + std::unique_ptr config, + std::unique_ptr logs, + std::unique_ptr timeKeeper, + std::optional const& nodePublicKey) { return std::make_unique( - std::move(config), std::move(logs), std::move(timeKeeper)); + std::move(config), std::move(logs), std::move(timeKeeper), nodePublicKey); } void diff --git a/src/xrpld/app/main/Application.h b/src/xrpld/app/main/Application.h index 225275afe4..1d7125cd64 100644 --- a/src/xrpld/app/main/Application.h +++ b/src/xrpld/app/main/Application.h @@ -174,4 +174,19 @@ makeApplication( std::unique_ptr logs, std::unique_ptr timeKeeper); +/** + * Construct the application with a known node public key. + * + * Telemetry builds its resource attributes during construction and they are + * immutable, so the base58 node public key must be supplied here. Pass + * std::nullopt when it is unknown; that run reports no instance id. See + * resolveNodePublicKey(). + */ +std::unique_ptr +makeApplication( + std::unique_ptr config, + std::unique_ptr logs, + std::unique_ptr timeKeeper, + std::optional const& nodePublicKey); + } // namespace xrpl diff --git a/src/xrpld/app/main/Main.cpp b/src/xrpld/app/main/Main.cpp index ba6520db5f..82b959f7bc 100644 --- a/src/xrpld/app/main/Main.cpp +++ b/src/xrpld/app/main/Main.cpp @@ -1,4 +1,5 @@ #include +#include #include #include #include @@ -36,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -804,8 +806,30 @@ run(int argc, char** argv) if (vm.contains("debug")) setDebugLogSink(logs->makeSink("Debug", beast::Severity::Trace)); - auto app = - makeApplication(std::move(config), std::move(logs), std::make_unique()); + // Telemetry needs the node public key at construction, so read it here + // where a config error can still be reported and the process can exit + // cleanly. getNodeIdentity() in setup() stays authoritative. + std::optional nodePublicKey; + try + { + nodePublicKey = resolveNodePublicKey(*config, vm, logs->journal("Application")); + } + catch (std::exception const& e) + { + std::cerr << "Unable to start " << systemName() << ": " << e.what() << std::endl; + return -1; + } + + if (!nodePublicKey) + { + JLOG(logs->journal("Application").warn()) + << "Telemetry: no node identity available yet, so this run reports an empty " + "service.instance.id. Set [telemetry] service_instance_id, or restart once " + "the node key exists."; + } + + auto app = makeApplication( + std::move(config), std::move(logs), std::make_unique(), nodePublicKey); if (!app->setup(vm)) return -1; diff --git a/src/xrpld/app/main/NodeIdentity.cpp b/src/xrpld/app/main/NodeIdentity.cpp index 8198c43af7..fcf460f185 100644 --- a/src/xrpld/app/main/NodeIdentity.cpp +++ b/src/xrpld/app/main/NodeIdentity.cpp @@ -8,13 +8,18 @@ #include #include #include +#include +#include #include #include +#include +#include #include #include #include +#include #include namespace xrpl { @@ -58,4 +63,82 @@ getNodeIdentity(Application& app, boost::program_options::variables_map const& c return getNodeIdentity(*db); } +std::optional +resolveNodePublicKey( + Config const& config, + boost::program_options::variables_map const& cmdline, + beast::Journal journal) +{ + std::optional seed; + bool seedConfigured = false; + + if (cmdline.contains("nodeid")) + { + seedConfigured = true; + seed = parseGenericSeed(cmdline["nodeid"].as(), false); + } + else if (config.exists(Sections::kNodeSeed)) + { + seedConfigured = true; + if (auto const& lines = config.section(Sections::kNodeSeed).lines(); !lines.empty()) + seed = parseBase58(lines.front()); + } + + // A configured seed decides the identity outright. A malformed or missing + // one is reported by getNodeIdentity(), which runs later. + if (seedConfigured) + { + if (!seed) + return std::nullopt; + + auto const secretKey = generateSecretKey(KeyType::Secp256k1, *seed); + return toBase58(TokenType::NodePublic, derivePublicKey(KeyType::Secp256k1, secretKey)); + } + + // --newnodeid discards whatever is stored. + if (cmdline.contains("newnodeid")) + return std::nullopt; + + try + { + auto setup = setupDatabaseCon(config, journal); + + // Standalone uses a temporary database, so nothing is persisted and this + // run will mint a fresh key. + if (setup.standAlone && setup.startUp != StartUpType::Load && + setup.startUp != StartUpType::LoadFile && setup.startUp != StartUpType::Replay) + { + return std::nullopt; + } + + // The global pragmas include journal_mode, which rewrites the database + // header. The wallet is opened without them everywhere else. + setup.useGlobalPragma = false; + + // Only read an existing file: SQLite would otherwise create one. + if (std::error_code ec; !std::filesystem::exists(setup.dataDir / kWalletDbName, ec)) + { + return std::nullopt; + } + + // Empty init SQL: open the existing schema, never create it. + DatabaseCon walletDb{ + setup, + kWalletDbName, + std::array{}, + std::array{}, + journal}; + + auto db = walletDb.checkoutDb(); + if (auto const stored = readNodeIdentity(*db)) + return toBase58(TokenType::NodePublic, stored->first); + } + catch (std::exception const& e) + { + JLOG(journal.warn()) << "Could not read the node identity: " << e.what(); + } + + return std::nullopt; +} + } // namespace xrpl diff --git a/src/xrpld/app/main/NodeIdentity.h b/src/xrpld/app/main/NodeIdentity.h index 117acffdb1..7309f6007a 100644 --- a/src/xrpld/app/main/NodeIdentity.h +++ b/src/xrpld/app/main/NodeIdentity.h @@ -1,12 +1,16 @@ #pragma once #include +#include +#include #include #include #include +#include +#include #include namespace xrpl { @@ -20,4 +24,26 @@ namespace xrpl { std::pair getNodeIdentity(Application& app, boost::program_options::variables_map const& cmdline); +/** + * This server's public key, read without creating or modifying anything. + * + * For callers that need the identity before the Application exists, such as + * telemetry building its resource attributes in the member-init list. Derives + * from a configured seed when there is one, otherwise reads the wallet database + * only if it already exists. + * + * getNodeIdentity() remains authoritative and mints a key when none exists. + * + * @param config The server configuration. + * @param cmdline The command line parameters passed into the application. + * @param journal Journal for reporting an unreadable database. + * @return The base58-encoded node public key, or std::nullopt if none can be + * read. + */ +std::optional +resolveNodePublicKey( + Config const& config, + boost::program_options::variables_map const& cmdline, + beast::Journal journal); + } // namespace xrpl