Bucket known tags by slot in TagMap (dense store - part 2)

dd-trace-core/src/jmh/java/datadog/trace/core/HeaderPathBenchmark.java

@@ -0,0 +1,226 @@
+package datadog.trace.core;
+
+import static datadog.context.Context.root;
+import static datadog.trace.bootstrap.instrumentation.api.AgentSpan.fromContext;
+import static java.util.concurrent.TimeUnit.MICROSECONDS;
+
+import datadog.context.Context;
+import datadog.context.ContextScope;
+import datadog.context.propagation.CarrierSetter;
+import datadog.context.propagation.CarrierVisitor;
+import datadog.context.propagation.Propagators;
+import datadog.trace.bootstrap.instrumentation.api.AgentSpan;
+import datadog.trace.bootstrap.instrumentation.api.AgentSpanContext;
+import datadog.trace.bootstrap.instrumentation.api.SpanPrototype;
+import datadog.trace.bootstrap.instrumentation.api.Tags;
+import datadog.trace.bootstrap.instrumentation.api.UTF8BytesString;
+import java.util.HashMap;
+import java.util.Map;
+import java.util.function.BiConsumer;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.TearDown;
+import org.openjdk.jmh.annotations.Threads;
+import org.openjdk.jmh.annotations.Warmup;
+import org.openjdk.jmh.infra.Blackhole;
+
+/**
+ * One whole request per op, through the header code paths: extract the inbound headers with the
+ * default propagator, start the server span from what was extracted, run a few children, make one
+ * outbound HTTP call that injects its headers, then finish everything.
+ *
+ * <p>The existing propagation benchmarks each measure one step (extracting into a context,
+ * injecting from a prebuilt one, parsing one header value). They can't see costs that the extracted
+ * state causes later, on every span of the trace: for example, a {@code tracestate} that leads each
+ * span to allocate sampling state. Measuring the whole request catches those.
+ *
+ * <p>{@code headers} selects the inbound headers, under the default propagation styles:
+ *
+ * <ul>
+ *   <li>{@code none}: a new trace;
+ *   <li>{@code datadog}: {@code x-datadog-*}, with propagated tags;
+ *   <li>{@code tracecontext}: {@code traceparent} and a {@code tracestate} carrying {@code dd},
+ *       OpenTelemetry ({@code ot}) and a third-party member;
+ *   <li>{@code both}: Datadog and W3C headers for the same trace, as a Datadog-to-Datadog call
+ *       sends them;
+ *   <li>{@code bothBaggage}: {@code both}, plus a {@code baggage} header.
+ * </ul>
+ */
+@State(Scope.Benchmark)
+@Warmup(iterations = 5)
+@Measurement(iterations = 5)
+@BenchmarkMode(Mode.Throughput)
+@Threads(8)
+@OutputTimeUnit(MICROSECONDS)
+@Fork(value = 3, jvmArgsAppend = "-DTEST_LOG_LEVEL=warn")
+public class HeaderPathBenchmark {
+  static final int JDBC_SPANS = 3;
+
+  static final String TRACE_ID_HEX = "66a0f6c800000000a3ce929d0e0e4736";
+  static final String TRACE_ID_LOW = "11803532876627986230"; // a3ce929d0e0e4736
+  static final String PARENT_ID = "67667974448284343"; // 00f067aa0ba902b7
+  static final String PARENT_ID_HEX = "00f067aa0ba902b7";
+
+  static final String SERVER_INSTRUMENTATION = "tomcat-server";
+  static final CharSequence SERVER_OPERATION = UTF8BytesString.create("servlet.request");
+  static final String JDBC_INSTRUMENTATION = "java-jdbc-prepared_statement";
+  static final CharSequence JDBC_OPERATION = UTF8BytesString.create("database.query");
+  static final String CLIENT_INSTRUMENTATION = "okhttp";
+  static final CharSequence CLIENT_OPERATION = UTF8BytesString.create("okhttp.request");
+
+  static final CarrierVisitor<Map<String, String>> GETTER =
+      new CarrierVisitor<Map<String, String>>() {
+        @Override
+        public void forEachKeyValue(
+            Map<String, String> carrier, BiConsumer<String, String> visitor) {
+          carrier.forEach(visitor);
+        }
+      };
+  static final CarrierSetter<Map<String, String>> SETTER = Map::put;
+
+  @Param({"none", "datadog", "tracecontext", "both", "bothBaggage"})
+  String headers;
+
+  CoreTracer tracer;
+  Map<String, String> inbound;
+  SpanPrototype serverProto;
+  SpanPrototype jdbcProto;
+  SpanPrototype clientProto;
+
+  /** One outbound carrier per thread, reused across requests. */
+  @State(Scope.Thread)
+  public static class Outbound {
+    final Map<String, String> headers = new HashMap<>();
+  }
+
+  @Setup
+  public void setup(Blackhole blackhole) {
+    this.tracer = CoreTracer.builder().writer(new DropWriter(blackhole)).build();
+    this.inbound = inboundHeaders(headers);
+    this.serverProto =
+        SpanPrototype.builder()
+            .initInstrumentationName(SERVER_INSTRUMENTATION)
+            .initOperationName(SERVER_OPERATION)
+            .initSpanType("web")
+            .initComponentAndIntegration("tomcat-server")
+            .initKind(Tags.SPAN_KIND_SERVER)
+            .initTag("language", "jvm")
+            .build();
+    this.jdbcProto =
+        SpanPrototype.builder()
+            .initInstrumentationName(JDBC_INSTRUMENTATION)
+            .initOperationName(JDBC_OPERATION)
+            .initSpanType("sql")
+            .initComponentAndIntegration("java-jdbc")
+            .initKind(Tags.SPAN_KIND_CLIENT)
+            .build();
+    this.clientProto =
+        SpanPrototype.builder()
+            .initInstrumentationName(CLIENT_INSTRUMENTATION)
+            .initOperationName(CLIENT_OPERATION)
+            .initSpanType("http")
+            .initComponentAndIntegration("okhttp")
+            .initKind(Tags.SPAN_KIND_CLIENT)
+            .build();
+    checkPropagation();
+  }
+
+  /**
+   * Fails fast if the headers aren't actually extracted and injected, which would measure nothing.
+   */
+  void checkPropagation() {
+    Context parent = Propagators.defaultPropagator().extract(root(), inbound, GETTER);
+    if (!headers.equals("none") && fromContext(parent) == null) {
+      throw new IllegalStateException("nothing extracted from " + headers + " headers");
+    }
+    Outbound outbound = new Outbound();
+    request(outbound);
+    if (!outbound.headers.containsKey("x-datadog-trace-id")) {
+      throw new IllegalStateException("nothing injected: " + outbound.headers);
+    }
+  }
+
+  @TearDown
+  public void tearDown() {
+    this.tracer.close();
+  }
+
+  static Map<String, String> inboundHeaders(String style) {
+    Map<String, String> h = new HashMap<>();
+    h.put("host", "localhost:8080");
+    h.put("user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) Chrome/120.0");
+    h.put("accept", "application/json");
+    if (style.equals("datadog") || style.startsWith("both")) {
+      h.put("x-datadog-trace-id", TRACE_ID_LOW);
+      h.put("x-datadog-parent-id", PARENT_ID);
+      h.put("x-datadog-sampling-priority", "1");
+      h.put("x-datadog-tags", "_dd.p.dm=-0,_dd.p.tid=66a0f6c800000000");
+    }
+    if (style.equals("tracecontext") || style.startsWith("both")) {
+      h.put("traceparent", "00-" + TRACE_ID_HEX + "-" + PARENT_ID_HEX + "-01");
+      h.put(
+          "tracestate",
+          "dd=s:1;p:"
+              + PARENT_ID_HEX
+              + ";t.dm:-0;t.tid:66a0f6c800000000,"
+              + "ot=th:8;rv:9b8233f7e3a151,rojo=00f067aa0ba902b7");
+    }
+    if (style.equals("bothBaggage")) {
+      h.put("baggage", "userId=alice,serverNode=DF%2028,isProduction=false");
+    }
+    return h;
+  }
+
+  @Benchmark
+  public void request(Outbound outbound) {
+    outbound.headers.clear();
+    // HttpServerDecorator.extract / startSpan
+    Context parent = Propagators.defaultPropagator().extract(root(), inbound, GETTER);
+    AgentSpan extractedSpan = fromContext(parent);
+    AgentSpanContext extracted = extractedSpan == null ? null : extractedSpan.spanContext();
+    AgentSpan server = tracer.startSpan(SERVER_INSTRUMENTATION, SERVER_OPERATION, extracted);
+    server.setMeasured(true);
+    server.applyOverwriting(serverProto);
+    server.setTag(Tags.HTTP_METHOD, "GET");
+    server.setTag(Tags.HTTP_URL, "http://localhost:8080/owners/42");
+    server.setTag(Tags.HTTP_ROUTE, "/owners/{ownerId}");
+    server.setTag(Tags.PEER_PORT, 54321);
+
+    try (ContextScope serverScope = parent.with(server).attach()) {
+      for (int i = 0; i < JDBC_SPANS; ++i) {
+        AgentSpan jdbc = tracer.startSpan(JDBC_INSTRUMENTATION, JDBC_OPERATION);
+        jdbc.applyOverwriting(jdbcProto);
+        jdbc.setTag(Tags.DB_TYPE, "postgresql");
+        jdbc.setTag(Tags.DB_INSTANCE, "petclinic");
+        jdbc.setTag(Tags.PEER_HOSTNAME, "db.internal");
+        jdbc.setResourceName("SELECT * FROM owners WHERE id = ?");
+        try (ContextScope s = tracer.activateSpan(jdbc)) {
+          // the statement executes
+        }
+        jdbc.finish();
+      }
+
+      // the outbound call: start the client span, inject its headers, finish
+      AgentSpan client = tracer.startSpan(CLIENT_INSTRUMENTATION, CLIENT_OPERATION);
+      client.applyOverwriting(clientProto);
+      client.setTag(Tags.HTTP_METHOD, "GET");
+      client.setTag(Tags.HTTP_URL, "http://inventory.internal/items/7");
+      client.setTag(Tags.PEER_HOSTNAME, "inventory.internal");
+      client.setTag(Tags.PEER_PORT, 8080);
+      Propagators.defaultPropagator()
+          .inject(Context.current().with(client), outbound.headers, SETTER);
+      client.setHttpStatusCode(200);
+      client.finish();
+    }
+    server.setHttpStatusCode(200);
+    server.finish();
+  }
+}