Revert "Revert "Add OpenTelemetry tracing provider to the container (disabled by default)" MERGEOK" (#37234)

Author: onurkaracali

CMakeLists.txt

@@ -117,6 +117,7 @@ add_subdirectory(container-apache-http-client-bundle)
 add_subdirectory(container-disc)
 add_subdirectory(container-messagebus)
 add_subdirectory(container-onnxruntime)
+add_subdirectory(container-opentelemetry)
 add_subdirectory(container-llama)
 add_subdirectory(container-search)
 add_subdirectory(container-search-and-docproc)

config-model-api/abi-spec.json

@@ -1415,6 +1415,7 @@
       "public double feedNiceness()",
       "public int maxUnCommittedMemory()",
       "public boolean containerDumpHeapOnShutdownTimeout()",
+      "public com.yahoo.config.provision.OpenTelemetryConfiguration opentelemetrySdk()",
       "public int heapSizePercentage(java.util.Optional)",
       "public java.util.List allowedAthenzProxyIdentities()",
       "public int maxActivationInhibitedOutOfSyncGroups()",

config-model-api/src/main/java/com/yahoo/config/model/api/ModelContext.java

@@ -14,6 +14,7 @@
 import com.yahoo.config.provision.DockerImage;
 import com.yahoo.config.provision.HostName;
 import com.yahoo.config.provision.NodeResources.Architecture;
+import com.yahoo.config.provision.OpenTelemetryConfiguration;
 import com.yahoo.config.provision.SharedHosts;
 
 import java.io.File;
@@ -96,6 +97,7 @@ interface FeatureFlags {
         @ModelFeatureFlag(owners = {"hmusum"}) default double feedNiceness() { return 0.0; }
         @ModelFeatureFlag(owners = {"hmusum"}) default int maxUnCommittedMemory() { return 130000; }
         @ModelFeatureFlag(owners = {"bjorncs"}) default boolean containerDumpHeapOnShutdownTimeout() { return false; }
+        @ModelFeatureFlag(owners = {"onur"}) default OpenTelemetryConfiguration opentelemetrySdk() { return OpenTelemetryConfiguration.disabled(); }
         @ModelFeatureFlag(owners = {"hmusum"}) default int heapSizePercentage(Optional<String> clusterId) { return  0;}
         @ModelFeatureFlag(owners = {"bjorncs"}) default List<String> allowedAthenzProxyIdentities() { return List.of(); }
         @ModelFeatureFlag(owners = {"vekterli"}) default int maxActivationInhibitedOutOfSyncGroups() { return 0; }

config-model/src/main/java/com/yahoo/vespa/model/container/ContainerCluster.java

@@ -1,6 +1,7 @@
 // Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
 package com.yahoo.vespa.model.container;
 
+import ai.vespa.telemetry.TelemetryConfig;
 import com.yahoo.cloud.config.ClusterInfoConfig;
 import com.yahoo.cloud.config.ConfigserverConfig;
 import com.yahoo.cloud.config.CuratorConfig;
@@ -13,6 +14,7 @@
 import com.yahoo.config.model.producer.AnyConfigProducer;
 import com.yahoo.config.model.producer.TreeConfigProducer;
 import com.yahoo.config.provision.ClusterSpec;
+import com.yahoo.config.provision.OpenTelemetryConfiguration;
 import com.yahoo.config.provision.Zone;
 import com.yahoo.container.ComponentsConfig;
 import com.yahoo.container.QrSearchersConfig;
@@ -109,7 +111,8 @@ public abstract class ContainerCluster<CONTAINER extends Container>
         ClusterInfoConfig.Producer,
         ConfigserverConfig.Producer,
         CuratorConfig.Producer,
-        SchemaInfoConfig.Producer
+        SchemaInfoConfig.Producer,
+        TelemetryConfig.Producer
 {
 
     /**
@@ -168,6 +171,8 @@ public abstract class ContainerCluster<CONTAINER extends Container>
 
     private volatile boolean deferChangesUntilRestart = false;
     private final boolean applyOnRestartForApplicationMetadataConfigEnabled;
+    private final OpenTelemetryConfiguration opentelemetrySdk;
+    private final Map<String, String> telemetryResourceAttributes;
     private boolean clientsLegacyMode;
     private List<Client> clients = List.of();
 
@@ -179,7 +184,9 @@ public ContainerCluster(TreeConfigProducer<?> parent, String configSubId, String
         this.zooKeeperLocalhostAffinity = zooKeeperLocalhostAffinity;
         this.compressionType = "zstd";
         applyOnRestartForApplicationMetadataConfigEnabled = deployState.featureFlags().applyOnRestartForApplicationMetadataConfig();
-        
+        opentelemetrySdk = deployState.featureFlags().opentelemetrySdk();
+        telemetryResourceAttributes = telemetryResourceAttributes(deployState, clusterId);
+
         componentGroup = new ComponentGroup<>(this, "component");
 
         addCommonVespaBundles();
@@ -199,6 +206,8 @@ public ContainerCluster(TreeConfigProducer<?> parent, String configSubId, String
         addSimpleComponent(com.yahoo.container.handler.ClustersStatus.class.getName());
         addSimpleComponent("com.yahoo.container.jdisc.DisabledConnectionLogProvider");
         addSimpleComponent(com.yahoo.jdisc.http.server.jetty.Janitor.class);
+        // OpenTelemetry tracing provider: present in all container types; hands out a no-op instance unless enabled.
+        addSimpleComponent("com.yahoo.container.jdisc.telemetry.OpenTelemetryProvider");
     }
 
     protected abstract boolean messageBusEnabled();
@@ -566,6 +575,32 @@ public void getConfig(QrSearchersConfig.Builder builder) {
         if (containerSearch != null) containerSearch.getConfig(builder);
     }
 
+    @Override
+    public void getConfig(TelemetryConfig.Builder builder) {
+        builder.enabled(opentelemetrySdk.enabled())
+               .endpoint(opentelemetrySdk.endpoint())
+               .samplingRatio(opentelemetrySdk.samplingRatio());
+        builder.resourceAttribute.putAll(telemetryResourceAttributes);
+    }
+
+    /**
+     * Resource attributes describing this container service, filled from the deployment identity available
+     * in the model. Used by the OpenTelemetry provider to build the OTel {@code Resource}.
+     */
+    private Map<String, String> telemetryResourceAttributes(DeployState deployState, String clusterId) {
+        var applicationId = deployState.getProperties().applicationId();
+
+        Map<String, String> attributes = new LinkedHashMap<>();
+        attributes.put("application", applicationId.application().value());
+        attributes.put("tenant", applicationId.tenant().value());
+        attributes.put("zone", this.zone.systemLocalValue());
+        attributes.put("environment", this.zone.environment().value());
+        attributes.put("cloud", this.zone.cloud().toString());
+        attributes.put("cluster.type", "container");
+        attributes.put("cluster.id", clusterId);
+        return attributes;
+    }
+
     @Override
     public void getConfig(QrStartConfig.Builder builder) {
         builder.jvm

config-provisioning/src/main/java/com/yahoo/config/provision/OpenTelemetryConfiguration.java

@@ -0,0 +1,25 @@
+// Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
+package com.yahoo.config.provision;
+
+/**
+ * Settings for Vespa's OpenTelemetry SDK (tracing), controlled by the {@code opentelemetry-sdk}
+ * feature flag and produced into the container's telemetry config.
+ *
+ * @author onur
+ */
+public interface OpenTelemetryConfiguration {
+
+    boolean enabled();
+    String endpoint();
+    double samplingRatio();
+
+    /** The default, disabled configuration: produces a no-op OpenTelemetry. */
+    static OpenTelemetryConfiguration disabled() {
+        return new OpenTelemetryConfiguration() {
+            @Override public boolean enabled() { return false; }
+            @Override public String endpoint() { return ""; }
+            @Override public double samplingRatio() { return 1.0; }
+        };
+    }
+
+}

configdefinitions/src/main/java/ai/vespa/telemetry/package-info.java

@@ -0,0 +1,5 @@
+// Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
+@ExportPackage
+package ai.vespa.telemetry;
+
+import com.yahoo.osgi.annotation.ExportPackage;

configdefinitions/src/vespa/telemetry.def

@@ -0,0 +1,12 @@
+# Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
+# Configuration for the container OpenTelemetry tracing provider.
+# Disabled by default: when enabled=false the provider hands out a no-op OpenTelemetry that produces nothing.
+package=ai.vespa.telemetry
+
+enabled            bool
+endpoint           string
+samplingRatio      double
+
+# Resource attributes describing the emitting service, filled by the config-model
+# from whatever deployment identity is available (application, tenant, cluster type, cluster id).
+resourceAttribute{} string

configserver/src/main/java/com/yahoo/vespa/config/server/deploy/ModelContextImpl.java

@@ -28,6 +28,7 @@
 import com.yahoo.config.provision.DockerImage;
 import com.yahoo.config.provision.HostName;
 import com.yahoo.config.provision.NodeResources.Architecture;
+import com.yahoo.config.provision.OpenTelemetryConfiguration;
 import com.yahoo.config.provision.SharedHosts;
 import com.yahoo.vespa.flags.Flag;
 import com.yahoo.vespa.flags.FlagSource;
@@ -223,6 +224,7 @@ private <T, F extends Flag<T, F>, U extends UnboundFlag<T, F, U>> ModelContext.F
         @Override public double feedConcurrency() { return flag(PermanentFlags.FEED_CONCURRENCY).value(); }
         @Override public double feedNiceness() { return flag(PermanentFlags.FEED_NICENESS).value(); }
         @Override public int mbusNetworkThreads() { return flag(Flags.MBUS_NUM_NETWORK_THREADS).value(); }
+        @Override public OpenTelemetryConfiguration opentelemetrySdk() { return flag(Flags.OPENTELEMETRY_SDK).value(); }
         @Override public List<String> allowedAthenzProxyIdentities() { return flag(PermanentFlags.ALLOWED_ATHENZ_PROXY_IDENTITIES).value(); }
         @Override public int maxActivationInhibitedOutOfSyncGroups() { return flag(PermanentFlags.MAX_ACTIVATION_INHIBITED_OUT_OF_SYNC_GROUPS).value(); }
         @Override public double resourceLimitDisk() { return flag(PermanentFlags.RESOURCE_LIMIT_DISK).value(); }

container-dependency-versions/pom.xml

@@ -36,6 +36,13 @@
 
     <dependencyManagement>
         <dependencies>
+            <dependency>
+                <groupId>io.opentelemetry</groupId>
+                <artifactId>opentelemetry-bom</artifactId>
+                <version>${opentelemetry.vespa.version}</version>
+                <type>pom</type>
+                <scope>import</scope>
+            </dependency>
             <dependency>
                 <groupId>aopalliance</groupId>
                 <artifactId>aopalliance</artifactId>

container-dev/pom.xml

@@ -187,6 +187,14 @@
       <version>${project.version}</version>
       <type>pom</type>
     </dependency>
+    <!-- OpenTelemetry API only: this is what the in-process container test harness needs to instantiate the
+         (disabled, no-op) OpenTelemetryProvider, and all that 3rd-party container projects should compile
+         against. The SDK is loaded lazily by OpenTelemetrySdkBuilder and supplied at runtime by the
+         pre-installed container-opentelemetry bundle. -->
+    <dependency>
+      <groupId>io.opentelemetry</groupId>
+      <artifactId>opentelemetry-api</artifactId>
+    </dependency>
     <dependency>
       <groupId>com.yahoo.vespa</groupId>
       <artifactId>vespajlib</artifactId>