feat: add opentelemetry support (but no instrumentation yet)

.github/renovate.json

@@ -29,6 +29,14 @@
       "datasourceTemplate": "github-tags",
       "packageNameTemplate": "aws/aws-cli",
       "autoReplaceStringTemplate": "{{depName}} = \"ref:{{newVersion}}\""
+    },
+    {
+      "customType": "regex",
+      "fileMatch": ["\\.ts$"],
+      "matchStrings": [
+        "renovate: datasource=(?<datasource>.+?)\\s+\"(?<depName>\\S+):(?<currentValue>\\S+)\""
+      ],
+      "versioningTemplate": "semver"
     }
   ]
 }

docker-compose.yml

@@ -11,3 +11,18 @@ services:
       PGUSER: kitu
     ports:
       - "127.0.0.1:5432:5432"
+
+  collector:
+    image: otel/opentelemetry-collector:0.114.0
+    command: ["--config=/etc/otel-collector-config.yml"]
+    volumes:
+      - ./otel-config.yml:/etc/otel-collector-config.yml
+    ports:
+      - "4318:4318" # OTLP HTTP
+    depends_on:
+      - jaeger
+
+  jaeger:
+    image: jaegertracing/all-in-one:latest
+    ports:
+      - "16686:16686" # UI

infra/lib/service-stack.ts

@@ -19,6 +19,7 @@ import { DatabaseCluster } from "aws-cdk-lib/aws-rds"
 import { HostedZone } from "aws-cdk-lib/aws-route53"
 import { ITopic } from "aws-cdk-lib/aws-sns"
 import { Construct } from "constructs"
+import { ManagedPolicy } from "aws-cdk-lib/aws-iam"
 
 export interface ServiceStackProps extends StackProps {
   auditLogGroup: ILogGroup
@@ -135,13 +136,25 @@ export class ServiceStack extends Stack {
       sslPolicy: SslPolicy.RECOMMENDED_TLS,
     })
 
+    this.service.taskDefinition.addContainer("AwsOtelCollector", {
+      image: ContainerImage.fromRegistry(
+        // renovate: datasource=docker
+        "public.ecr.aws/aws-observability/aws-otel-collector:v0.41.1",
+      ),
+    })
+
     this.service.targetGroup.configureHealthCheck({
       ...this.service.targetGroup.healthCheck,
       path: "/actuator/health",
     })
 
     props.auditLogGroup.grantWrite(this.service.service.taskDefinition.taskRole)
 
+    // Ref: https://docs.aws.amazon.com/aws-managed-policy/latest/reference/AWSXrayWriteOnlyAccess.html
+    this.service.taskDefinition.taskRole.addManagedPolicy(
+      ManagedPolicy.fromAwsManagedPolicyName("AWSXrayWriteOnlyAccess"),
+    )
+
     this.service.service
       .metricCpuUtilization()
       .createAlarm(this, "CpuUtilization", {

otel-config.yml

@@ -0,0 +1,32 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+
+extensions:
+  health_check:
+
+exporters:
+  debug:
+  otlphttp/jaeger:
+    endpoint: http://jaeger:4318
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug, otlphttp/jaeger]
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug]
+    logs:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug]

server/pom.xml

@@ -50,6 +50,13 @@
                 <type>pom</type>
                 <scope>import</scope>
             </dependency>
+            <dependency>
+                <groupId>io.opentelemetry.instrumentation</groupId>
+                <artifactId>opentelemetry-instrumentation-bom</artifactId>
+                <version>2.10.0</version>
+                <type>pom</type>
+                <scope>import</scope>
+            </dependency>
         </dependencies>
     </dependencyManagement>
     <dependencies>
@@ -180,6 +187,14 @@
             <artifactId>db-scheduler-log-spring-boot-starter</artifactId>
             <version>0.7.0</version>
         </dependency>
+        <dependency>
+            <groupId>io.opentelemetry.instrumentation</groupId>
+            <artifactId>opentelemetry-spring-boot-starter</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>org.springframework.boot</groupId>
+            <artifactId>spring-boot-starter-aop</artifactId>
+        </dependency>
         <dependency>
             <groupId>io.opentelemetry</groupId>
             <artifactId>opentelemetry-api</artifactId>
@@ -194,6 +209,11 @@
             <artifactId>opentelemetry-semconv-incubating</artifactId>
             <version>${opentelemetry-semconv.version}</version>
         </dependency>
+        <dependency>
+            <groupId>io.opentelemetry.instrumentation</groupId>
+            <artifactId>opentelemetry-aws-sdk-2.2-autoconfigure</artifactId>
+            <version>2.10.0-alpha</version>
+        </dependency>
         <dependency>
             <groupId>no.bekk.db-scheduler-ui</groupId>
             <artifactId>db-scheduler-ui-starter</artifactId>

server/src/main/resources/application-prod.properties

@@ -17,3 +17,5 @@ kitu.yki.scheduling.enabled=true
 kitu.yki.baseUrl=https://yki.jyu.fi/yki-sp/oph/
 kitu.yki.scheduling.import.schedule=DAILY|03:00
 kitu.yki.scheduling.importArvioijat.schedule=DAILY|03:00
+
+otel.resource.providers.aws.enabled=true

server/src/main/resources/application-qa.properties

@@ -16,3 +16,5 @@ kitu.yki.scheduling.enabled=true
 kitu.yki.scheduling.import.schedule=DAILY|03:00
 kitu.yki.scheduling.importArvioijat.schedule=DAILY|03:00
 kitu.yki.baseUrl=https://yki-test.cc.jyu.fi/yki-sp/oph/
+
+otel.resource.providers.aws.enabled=true

server/src/main/resources/application-untuva.properties

@@ -16,3 +16,5 @@ kitu.yki.scheduling.enabled=true
 kitu.yki.scheduling.import.schedule=DAILY|03:00
 kitu.yki.scheduling.importArvioijat.schedule=DAILY|03:00
 kitu.yki.baseUrl=https://yki-test.cc.jyu.fi/yki-sp/oph/
+
+otel.resource.providers.aws.enabled=true

server/src/main/resources/application.properties

@@ -31,6 +31,7 @@ spring.mustache.suffix=.mustache
 
 logging.structured.format.console=ecs
 logging.structured.format.file=ecs
+otel.traces.exporter=otlp
 
 # Uncomment this to debug authentication/authorization issues.
 # Ref: https://docs.spring.io/spring-security/reference/servlet/architecture.html#servlet-logging

server/src/test/resources/application.properties

@@ -23,3 +23,4 @@ kitu.yki.password=
 
 logging.structured.format.console=ecs
 logging.structured.format.file=ecs
+otel.traces.exporter=otlp