feat(server): configure OpenTelemetry (#1496)

Author: krzema12

jit-binding-server/build.gradle.kts

@@ -10,6 +10,14 @@ dependencies {
     implementation(platform("io.ktor:ktor-bom:2.3.11"))
     implementation("io.ktor:ktor-server-core")
     implementation("io.ktor:ktor-server-netty")
+    implementation("io.ktor:ktor-client-core")
+    implementation("io.ktor:ktor-client-cio")
+    implementation("io.ktor:ktor-client-content-negotiation")
+    implementation("io.ktor:ktor-serialization-kotlinx-json")
+    implementation("io.opentelemetry.instrumentation:opentelemetry-ktor-2.0:2.3.0-alpha")
+    implementation("io.opentelemetry:opentelemetry-sdk:1.37.0")
+    implementation("io.opentelemetry:opentelemetry-exporter-otlp:1.37.0")
+    implementation("io.opentelemetry:opentelemetry-exporter-logging:1.37.0")
     implementation("io.github.reactivecircus.cache4k:cache4k:0.13.0")
     implementation("ch.qos.logback:logback-classic:1.5.6")
 

jit-binding-server/src/main/kotlin/io/github/typesafegithub/workflows/jitbindingserver/Main.kt

@@ -12,6 +12,7 @@ import io.github.typesafegithub.workflows.shared.internal.getGithubToken
 import io.ktor.http.ContentType
 import io.ktor.http.HttpStatusCode
 import io.ktor.server.application.call
+import io.ktor.server.application.install
 import io.ktor.server.engine.embeddedServer
 import io.ktor.server.netty.Netty
 import io.ktor.server.response.respondBytes
@@ -21,15 +22,20 @@ import io.ktor.server.routing.get
 import io.ktor.server.routing.head
 import io.ktor.server.routing.route
 import io.ktor.server.routing.routing
+import io.opentelemetry.instrumentation.ktor.v2_0.server.KtorServerTracing
 import kotlin.time.Duration.Companion.hours
 
 fun main() {
     val bindingsCache =
         Cache.Builder<ActionCoords, Result<Map<String, Artifact>>>()
             .expireAfterAccess(1.hours)
             .build()
+    val openTelemetry = buildOpenTelemetryConfig(serviceName = "github-actions-bindings")
 
     embeddedServer(Netty, port = 8080) {
+        install(KtorServerTracing) {
+            setOpenTelemetry(openTelemetry)
+        }
         routing {
             // TODO: remove this route once known clients are migrated
             // See https://github.com/typesafegithub/github-workflows-kt/issues/1492

jit-binding-server/src/main/kotlin/io/github/typesafegithub/workflows/jitbindingserver/OpenTelemetryConfig.kt

@@ -0,0 +1,84 @@
+package io.github.typesafegithub.workflows.jitbindingserver
+
+import io.opentelemetry.api.OpenTelemetry
+import io.opentelemetry.api.common.AttributeKey
+import io.opentelemetry.api.trace.propagation.W3CTraceContextPropagator
+import io.opentelemetry.context.propagation.ContextPropagators
+import io.opentelemetry.exporter.otlp.logs.OtlpGrpcLogRecordExporter
+import io.opentelemetry.exporter.otlp.metrics.OtlpGrpcMetricExporter
+import io.opentelemetry.exporter.otlp.trace.OtlpGrpcSpanExporter
+import io.opentelemetry.sdk.OpenTelemetrySdk
+import io.opentelemetry.sdk.logs.SdkLoggerProvider
+import io.opentelemetry.sdk.logs.export.BatchLogRecordProcessor
+import io.opentelemetry.sdk.metrics.SdkMeterProvider
+import io.opentelemetry.sdk.metrics.export.PeriodicMetricReader
+import io.opentelemetry.sdk.resources.Resource
+import io.opentelemetry.sdk.trace.SdkTracerProvider
+import io.opentelemetry.sdk.trace.export.BatchSpanProcessor
+import java.util.concurrent.TimeUnit
+
+/*
+How to test locally:
+
+docker run --rm \
+-e COLLECTOR_ZIPKIN_HOST_PORT=:9411 \
+-p 16686:16686 \
+-p 4317:4317 \
+-p 4318:4318 \
+-p 9411:9411 \
+jaegertracing/alsl-in-one:latest
+
+UI available at http://localhost:16686/
+*/
+internal fun buildOpenTelemetryConfig(
+    serviceName: String,
+    endpointConfig: String = "http://localhost:4317",
+): OpenTelemetry {
+    val spanExporter =
+        OtlpGrpcSpanExporter.builder()
+            .setEndpoint(endpointConfig)
+            .setTimeout(30, TimeUnit.SECONDS)
+            .build()
+
+    val metricExporter = OtlpGrpcMetricExporter.builder().build()
+    val recordExporter = OtlpGrpcLogRecordExporter.builder().build()
+
+    val resource =
+        Resource.getDefault()
+            .toBuilder()
+            .put(AttributeKey.stringKey("service.name"), serviceName)
+            .build()
+
+    val tracerProvider =
+        SdkTracerProvider.builder()
+            .addSpanProcessor(BatchSpanProcessor.builder(spanExporter).build())
+            .setResource(resource)
+            .build()
+
+    val meterProvider =
+        SdkMeterProvider.builder()
+            .registerMetricReader(
+                PeriodicMetricReader.builder(metricExporter).build(),
+            )
+            .setResource(resource)
+            .build()
+
+    val loggerProvider =
+        SdkLoggerProvider.builder()
+            .addLogRecordProcessor(
+                BatchLogRecordProcessor.builder(recordExporter).build(),
+            )
+            .setResource(resource)
+            .build()
+
+    val openTelemetry =
+        OpenTelemetrySdk.builder()
+            .setTracerProvider(tracerProvider)
+            .setMeterProvider(meterProvider)
+            .setLoggerProvider(loggerProvider)
+            .setPropagators(ContextPropagators.create(W3CTraceContextPropagator.getInstance()))
+            .buildAndRegisterGlobal()
+
+    Runtime.getRuntime().addShutdownHook(Thread { openTelemetry.close() })
+    return openTelemetry
+}