Skip to content

Removing Wrong Spark Spans for Inactive Databricks Clusters #10651

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

Draft
larakulkarni1 wants to merge 3 commits into
base: master
Choose a base branch
from
+34 −30
Draft

Removing Wrong Spark Spans for Inactive Databricks Clusters #10651

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
28f3045
updating to get rid of wrong spark spans
larakulkarni1 Feb 20, 2026
811d024
fixed format
larakulkarni1 Feb 20, 2026
8bf15a0
updating logs to test
larakulkarni1 Feb 23, 2026
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
64 changes: 34 additions & 30 deletions ...ommon/src/main/java/datadog/trace/instrumentation/spark/AbstractDatadogSparkListener.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -254,41 +254,45 @@ private void initApplicationSpanIfNotInitialized() {
}

log.debug("Starting tracer application span.");
log.debug(databricksClusterName);
if (!isRunningOnDatabricks) {
String databricksClusterNameSpark = databricksClusterName + "creating a spark.app";
log.debug(databricksClusterNameSpark);
AgentTracer.SpanBuilder builder = buildSparkSpan("spark.application", null);

if (applicationStart != null) {
String ddTags =
Config.get().getGlobalTags().entrySet().stream()
.sorted(Map.Entry.comparingByKey())
.map(e -> e.getKey() + ":" + e.getValue())
.collect(Collectors.joining(","));

builder
.withStartTimestamp(applicationStart.time() * 1000)
.withTag("application_name", applicationStart.appName())
.withTag("djm.tags", ddTags)
.withTag("spark_user", applicationStart.sparkUser());

if (applicationStart.appAttemptId().isDefined()) {
builder.withTag("app_attempt_id", applicationStart.appAttemptId().get());
}
}

AgentTracer.SpanBuilder builder = buildSparkSpan("spark.application", null);

if (applicationStart != null) {
String ddTags =
Config.get().getGlobalTags().entrySet().stream()
.sorted(Map.Entry.comparingByKey())
.map(e -> e.getKey() + ":" + e.getValue())
.collect(Collectors.joining(","));

builder
.withStartTimestamp(applicationStart.time() * 1000)
.withTag("application_name", applicationStart.appName())
.withTag("djm.tags", ddTags)
.withTag("spark_user", applicationStart.sparkUser());
captureApplicationParameters(builder);

if (applicationStart.appAttemptId().isDefined()) {
builder.withTag("app_attempt_id", applicationStart.appAttemptId().get());
Optional<OpenlineageParentContext> openlineageParentContext =
OpenlineageParentContext.from(sparkConf);
// We know we're not in Databricks context
if (openlineageParentContext.isPresent()) {
captureOpenlineageContextIfPresent(builder, openlineageParentContext.get());
} else {
builder.asChildOf(predeterminedTraceIdContext);
}
}

captureApplicationParameters(builder);

Optional<OpenlineageParentContext> openlineageParentContext =
OpenlineageParentContext.from(sparkConf);
// We know we're not in Databricks context
if (openlineageParentContext.isPresent()) {
captureOpenlineageContextIfPresent(builder, openlineageParentContext.get());
} else {
builder.asChildOf(predeterminedTraceIdContext);
applicationSpan = builder.start();
setDataJobsSamplingPriority(applicationSpan);
applicationSpan.setMeasured(true);
}

applicationSpan = builder.start();
setDataJobsSamplingPriority(applicationSpan);
applicationSpan.setMeasured(true);
}

private void captureOpenlineageContextIfPresent(
Expand Down