Implement stable session identifier headers for telemetry

BUILD.bazel

@@ -45,6 +45,7 @@ cc_library(
         "src/datadog/propagation_style.cpp",
         "src/datadog/random.cpp",
         "src/datadog/random.h",
+        "src/datadog/root_session_id.h",
         "src/datadog/rate.cpp",
         "src/datadog/remote_config/product.cpp",
         "src/datadog/remote_config/remote_config.cpp",

include/datadog/environment.h

@@ -20,6 +20,8 @@ namespace environment {
 
 // Central registry for supported environment variables.
 // All configurations must be registered here.
+// See also:
+// https://feature-parity.us1.prod.dog/configurations?viewType=configurations
 //
 // This registry is the single source of truth for:
 //   - env variable name allowlist (`include/datadog/environment.h`)

include/datadog/tracer_config.h

@@ -189,6 +189,11 @@ struct TracerConfig {
   // This option is ignored if `resource_renaming_enabled` is not `true`.
   Optional<bool> resource_renaming_always_simplified_endpoint;
 
+  // Root session ID for stable telemetry correlation across forked workers.
+  // Integrations (nginx, httpd, kong) should set this in the master process
+  // before workers fork so all Tracers share the same root.
+  Optional<std::string> root_session_id;
+
   /// A mapping of process-specific tags used to uniquely identify processes.
   ///
   /// The `process_tags` map allows associating arbitrary string-based keys and
@@ -225,6 +230,7 @@ class FinalizedTracerConfig final {
   bool log_on_startup;
   bool generate_128bit_trace_ids;
   Optional<RuntimeID> runtime_id;
+  Optional<std::string> root_session_id;
   Clock clock;
   std::string integration_name;
   std::string integration_version;

include/datadog/tracer_signature.h

@@ -33,17 +33,27 @@ namespace tracing {
 
 struct TracerSignature {
   RuntimeID runtime_id;
+  std::string root_session_id;
   std::string default_service;
   std::string default_environment;
   std::string library_version;
   StringView library_language;
   StringView library_language_version;
 
   TracerSignature() = delete;
-  TracerSignature(RuntimeID id, std::string service, std::string environment)
-      : runtime_id(id),
-        default_service(std::move(service)),
-        default_environment(std::move(environment)),
+
+  TracerSignature(RuntimeID runtime_id, std::string default_service,
+                  std::string default_environment)
+      : TracerSignature(runtime_id, runtime_id.string(),
+                        std::move(default_service),
+                        std::move(default_environment)) {}
+
+  TracerSignature(RuntimeID runtime_id, std::string root_session_id,
+                  std::string default_service, std::string default_environment)
+      : runtime_id(runtime_id),
+        root_session_id(std::move(root_session_id)),
+        default_service(std::move(default_service)),
+        default_environment(std::move(default_environment)),
         library_version(tracer_version),
         library_language("cpp"),
         library_language_version(DD_TRACE_STRINGIFY(__cplusplus), 6) {}

src/datadog/root_session_id.h

@@ -0,0 +1,12 @@
+#pragma once
+
+#include <string>
+
+namespace datadog::tracing::root_session_id {
+
+inline const std::string& get_or_init(const std::string& runtime_id) {
+  static const std::string id = runtime_id;
+  return id;
+}
+
+}  // namespace datadog::tracing::root_session_id

src/datadog/telemetry/telemetry_impl.cpp

@@ -60,6 +60,15 @@ HTTPClient::URL make_telemetry_endpoint(HTTPClient::URL url) {
   return url;
 }
 
+void set_session_headers(DictWriter& headers,
+                         const tracing::TracerSignature& signature) {
+  const auto& session_id = signature.runtime_id.string();
+  headers.set("DD-Session-ID", session_id);
+  if (signature.root_session_id != session_id) {
+    headers.set("DD-Root-Session-ID", signature.root_session_id);
+  }
+}
+
 void cancel_tasks(std::vector<tracing::EventScheduler::Cancel>& tasks) {
   for (auto& cancel_task : tasks) {
     cancel_task();
@@ -309,13 +318,15 @@ void Telemetry::app_started() {
   auto payload = app_started_payload();
 
   auto on_headers = [payload_size = payload.size(),
-                     debug_enabled = config_.debug](DictWriter& headers) {
+                     debug_enabled = config_.debug,
+                     &signature = tracer_signature_](DictWriter& headers) {
     headers.set("Content-Type", "application/json");
     headers.set("Content-Length", std::to_string(payload_size));
     headers.set("DD-Telemetry-API-Version", "v2");
     headers.set("DD-Client-Library-Language", "cpp");
     headers.set("DD-Client-Library-Version", tracer_version);
     headers.set("DD-Telemetry-Request-Type", "app-started");
+    set_session_headers(headers, signature);
     if (debug_enabled) {
       headers.set("DD-Telemetry-Debug-Enabled", "true");
     }
@@ -363,14 +374,16 @@ void Telemetry::app_closing() {
 
 void Telemetry::send_payload(StringView request_type, std::string payload) {
   auto set_telemetry_headers = [request_type, payload_size = payload.size(),
-                                debug_enabled =
-                                    config_.debug](DictWriter& headers) {
+                                debug_enabled = config_.debug,
+                                &signature =
+                                    tracer_signature_](DictWriter& headers) {
     headers.set("Content-Type", "application/json");
     headers.set("Content-Length", std::to_string(payload_size));
     headers.set("DD-Telemetry-API-Version", "v2");
     headers.set("DD-Client-Library-Language", "cpp");
     headers.set("DD-Client-Library-Version", tracer_version);
     headers.set("DD-Telemetry-Request-Type", request_type);
+    set_session_headers(headers, signature);
     if (debug_enabled) {
       headers.set("DD-Telemetry-Debug-Enabled", "true");
     }

src/datadog/tracer.cpp

@@ -24,6 +24,7 @@
 #include "msgpack.h"
 #include "platform_util.h"
 #include "random.h"
+#include "root_session_id.h"
 #include "span_data.h"
 #include "span_sampler.h"
 #include "tags.h"
@@ -48,8 +49,10 @@ Tracer::Tracer(const FinalizedTracerConfig& config,
     : logger_(config.logger),
       runtime_id_(config.runtime_id ? *config.runtime_id
                                     : RuntimeID::generate()),
-      signature_{runtime_id_, config.defaults.service,
-                 config.defaults.environment},
+      signature_{runtime_id_,
+                 root_session_id::get_or_init(
+                     config.root_session_id.value_or(runtime_id_.string())),
+                 config.defaults.service, config.defaults.environment},
       config_manager_(std::make_shared<ConfigManager>(config)),
       collector_(/* see constructor body */),
       span_sampler_(

src/datadog/tracer_config.cpp

@@ -403,10 +403,8 @@ Expected<FinalizedTracerConfig> finalize_config(const TracerConfig &user_config,
     final_config.injection_styles.erase(it);
   }
 
-  if (user_config.runtime_id) {
-    final_config.runtime_id = user_config.runtime_id;
-  }
-
+  final_config.runtime_id = user_config.runtime_id;
+  final_config.root_session_id = user_config.root_session_id;
   final_config.process_tags = user_config.process_tags;
 
   auto agent_finalized =

test/mocks/http_clients.h

@@ -41,7 +41,10 @@ struct MockHTTPClient : public HTTPClient {
   ErrorHandler on_error_;
   std::string request_body;
 
-  void clear() { request_body = ""; }
+  void clear() {
+    request_body = "";
+    request_headers.items.clear();
+  }
 
   Expected<void> post(
       const URL&, HeadersSetter set_headers, std::string body,

test/telemetry/test_telemetry.cpp

@@ -366,6 +366,67 @@ TELEMETRY_IMPLEMENTATION_TEST("Tracer telemetry lifecycle") {
   }
 }
 
+TELEMETRY_IMPLEMENTATION_TEST("session ID headers") {
+  auto logger = std::make_shared<MockLogger>();
+  auto client = std::make_shared<MockHTTPClient>();
+  auto scheduler = std::make_shared<FakeEventScheduler>();
+  auto url = HTTPClient::URL::parse("http://localhost:8000");
+
+  SECTION("root process: DD-Session-ID present, DD-Root-Session-ID absent") {
+    auto session_rid = RuntimeID::generate();
+    const TracerSignature tracer_signature(session_rid, "testsvc", "test");
+
+    Telemetry telemetry{
+        *finalize_config(), tracer_signature, logger, client, scheduler, *url};
+
+    auto it = client->request_headers.items.find("DD-Session-ID");
+    REQUIRE(it != client->request_headers.items.end());
+    CHECK(it->second == session_rid.string());
+
+    CHECK(client->request_headers.items.find("DD-Root-Session-ID") ==
+          client->request_headers.items.end());
+  }
+
+  SECTION("child process: DD-Root-Session-ID present when different") {
+    auto session_rid = RuntimeID::generate();
+    auto root_rid = RuntimeID::generate();
+    const TracerSignature tracer_signature(session_rid, root_rid.string(),
+                                           "testsvc", "test");
+
+    Telemetry telemetry{
+        *finalize_config(), tracer_signature, logger, client, scheduler, *url};
+
+    auto session_it = client->request_headers.items.find("DD-Session-ID");
+    REQUIRE(session_it != client->request_headers.items.end());
+    CHECK(session_it->second == session_rid.string());
+
+    auto root_it = client->request_headers.items.find("DD-Root-Session-ID");
+    REQUIRE(root_it != client->request_headers.items.end());
+    CHECK(root_it->second == root_rid.string());
+  }
+
+  SECTION("heartbeat includes session headers") {
+    auto session_rid = RuntimeID::generate();
+    auto root_rid = RuntimeID::generate();
+    const TracerSignature tracer_signature(session_rid, root_rid.string(),
+                                           "testsvc", "test");
+
+    Telemetry telemetry{
+        *finalize_config(), tracer_signature, logger, client, scheduler, *url};
+
+    client->clear();
+    scheduler->trigger_heartbeat();
+
+    auto session_it = client->request_headers.items.find("DD-Session-ID");
+    REQUIRE(session_it != client->request_headers.items.end());
+    CHECK(session_it->second == session_rid.string());
+
+    auto root_it = client->request_headers.items.find("DD-Root-Session-ID");
+    REQUIRE(root_it != client->request_headers.items.end());
+    CHECK(root_it->second == root_rid.string());
+  }
+}
+
 TELEMETRY_IMPLEMENTATION_TEST("Tracer telemetry API") {
   const Clock clock = [] {
     TimePoint result;