Skip to content

Configure OpenLineage if present in Spark instrumentation #8541

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 2, 2025
Merged

Configure OpenLineage if present in Spark instrumentation #8541

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ffc31bf
set OL if detected
mobuchowski Feb 13, 2025
83cf093
classloader and code review fixes
mobuchowski Mar 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions dd-java-agent/agent-bootstrap/src/main/java/datadog/trace/bootstrap/Agent.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -250,6 +250,11 @@ public static void start(
setSystemPropertyDefault(
propertyNameToSystemPropertyName("integration.kafka.enabled"), "true");

if (Config.get().isDataJobsOpenLineageEnabled()) {
setSystemPropertyDefault(
propertyNameToSystemPropertyName("integration.spark-openlineage.enabled"), "true");
}

String javaCommand = System.getProperty("sun.java.command");
String dataJobsCommandPattern = Config.get().getDataJobsCommandPattern();
if (!isDataJobsSupported(javaCommand, dataJobsCommandPattern)) {
Expand Down
31 changes: 31 additions & 0 deletions ...spark_2.12/src/main/java/datadog/trace/instrumentation/spark/Spark212Instrumentation.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,11 @@

import com.google.auto.service.AutoService;
import datadog.trace.agent.tooling.InstrumenterModule;
import datadog.trace.api.Config;
import net.bytebuddy.asm.Advice;
import org.apache.spark.SparkContext;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

@AutoService(InstrumenterModule.class)
public class Spark212Instrumentation extends AbstractSparkInstrumentation {
Expand All @@ -17,6 +20,7 @@ public String[] helperClassNames() {
packageName + ".DatabricksParentContext",
packageName + ".OpenlineageParentContext",
packageName + ".DatadogSpark212Listener",
packageName + ".PredeterminedTraceIdContext",
packageName + ".RemoveEldestHashMap",
packageName + ".SparkAggregatedTaskMetrics",
packageName + ".SparkConfAllowList",
Expand All @@ -41,6 +45,33 @@ public void methodAdvice(MethodTransformer transformer) {
public static class InjectListener {
@Advice.OnMethodEnter(suppress = Throwable.class)
public static void enter(@Advice.This SparkContext sparkContext) {
Logger log = LoggerFactory.getLogger("Spark212InjectListener");
if (Config.get().isDataJobsOpenLineageEnabled()
&& AbstractDatadogSparkListener.classIsLoadable(
"io.openlineage.spark.agent.OpenLineageSparkListener")
&& AbstractDatadogSparkListener.classIsLoadable(
"io.openlineage.spark.agent.facets.builder.TagsRunFacetBuilder")) {
if (!sparkContext.conf().contains("spark.extraListeners")) {
log.debug("spark.extraListeners does not contain any listeners. Adding OpenLineage");
sparkContext
.conf()
.set("spark.extraListeners", "io.openlineage.spark.agent.OpenLineageSparkListener");
} else {
String extraListeners = sparkContext.conf().get("spark.extraListeners");
if (!extraListeners.contains("io.openlineage.spark.agent.OpenLineageSparkListener")) {
log.debug(
"spark.extraListeners does contain listeners {}. Adding OpenLineage",
extraListeners);
sparkContext
.conf()
.set(
"spark.extraListeners",
extraListeners + ",io.openlineage.spark.agent.OpenLineageSparkListener");
}
}
}

// We want to add the Datadog listener as the first listener
AbstractDatadogSparkListener.listener =
new DatadogSpark212Listener(
sparkContext.getConf(), sparkContext.applicationId(), sparkContext.version());
Expand Down
32 changes: 32 additions & 0 deletions ...spark_2.13/src/main/java/datadog/trace/instrumentation/spark/Spark213Instrumentation.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,11 @@

import com.google.auto.service.AutoService;
import datadog.trace.agent.tooling.InstrumenterModule;
import datadog.trace.api.Config;
import net.bytebuddy.asm.Advice;
import org.apache.spark.SparkContext;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

@AutoService(InstrumenterModule.class)
public class Spark213Instrumentation extends AbstractSparkInstrumentation {
Expand All @@ -17,6 +20,7 @@ public String[] helperClassNames() {
packageName + ".DatabricksParentContext",
packageName + ".OpenlineageParentContext",
packageName + ".DatadogSpark213Listener",
packageName + ".PredeterminedTraceIdContext",
packageName + ".RemoveEldestHashMap",
packageName + ".SparkAggregatedTaskMetrics",
packageName + ".SparkConfAllowList",
Expand All @@ -41,6 +45,34 @@ public void methodAdvice(MethodTransformer transformer) {
public static class InjectListener {
@Advice.OnMethodEnter(suppress = Throwable.class)
public static void enter(@Advice.This SparkContext sparkContext) {
// checking whether OpenLineage integration is enabled, available and that it supports tags
Logger log = LoggerFactory.getLogger("Spark212InjectListener");
if (Config.get().isDataJobsOpenLineageEnabled()
&& AbstractDatadogSparkListener.classIsLoadable(
"io.openlineage.spark.agent.OpenLineageSparkListener")
&& AbstractDatadogSparkListener.classIsLoadable(
"io.openlineage.spark.agent.facets.builder.TagsRunFacetBuilder")) {
if (!sparkContext.conf().contains("spark.extraListeners")) {
log.debug("spark.extraListeners does not contain any listeners. Adding OpenLineage");
sparkContext
.conf()
.set("spark.extraListeners", "io.openlineage.spark.agent.OpenLineageSparkListener");
} else {
String extraListeners = sparkContext.conf().get("spark.extraListeners");
if (!extraListeners.contains("io.openlineage.spark.agent.OpenLineageSparkListener")) {
log.debug(
"spark.extraListeners does contain listeners {}. Adding OpenLineage",
extraListeners);
sparkContext
.conf()
.set(
"spark.extraListeners",
extraListeners + ",io.openlineage.spark.agent.OpenLineageSparkListener");
}
}
}

// We want to add the Datadog listener as the first listener
AbstractDatadogSparkListener.listener =
new DatadogSpark213Listener(
sparkContext.getConf(), sparkContext.applicationId(), sparkContext.version());
Expand Down
Loading