Skip to content

[ML] Preserve lost thread context in node inference action #132973

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 4 commits into from
Aug 15, 2025
Merged

[ML] Preserve lost thread context in node inference action #132973

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
31b9075
use context preserving listener
davidkyle Aug 15, 2025
449342d
Update docs/changelog/132973.yaml
davidkyle Aug 15, 2025
ec267d3
Update docs/changelog/132973.yaml
davidkyle Aug 15, 2025
2e65b51
Merge branch 'main' into lost-context
davidkyle Aug 15, 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 docs/changelog/132973.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
pr: 132973
summary: Preserve lost thread context in node inference action
area: Machine Learning
type: bug
issues: []
13 changes: 11 additions & 2 deletions ...in/java/org/elasticsearch/xpack/ml/action/TransportInferTrainedModelDeploymentAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
import org.elasticsearch.action.FailedNodeException;
import org.elasticsearch.action.TaskOperationFailure;
import org.elasticsearch.action.support.ActionFilters;
import org.elasticsearch.action.support.ContextPreservingActionListener;
import org.elasticsearch.action.support.tasks.TransportTasksAction;
import org.elasticsearch.cluster.service.ClusterService;
import org.elasticsearch.common.util.concurrent.AtomicArray;
Expand All @@ -20,6 +21,7 @@
import org.elasticsearch.injection.guice.Inject;
import org.elasticsearch.rest.RestStatus;
import org.elasticsearch.tasks.CancellableTask;
import org.elasticsearch.threadpool.ThreadPool;
import org.elasticsearch.transport.TransportService;
import org.elasticsearch.xpack.core.ml.action.InferTrainedModelDeploymentAction;
import org.elasticsearch.xpack.core.ml.inference.results.ErrorInferenceResults;
Expand All @@ -37,11 +39,14 @@ public class TransportInferTrainedModelDeploymentAction extends TransportTasksAc
InferTrainedModelDeploymentAction.Response,
InferTrainedModelDeploymentAction.Response> {

private final ThreadPool threadPool;

@Inject
public TransportInferTrainedModelDeploymentAction(
ClusterService clusterService,
TransportService transportService,
ActionFilters actionFilters
ActionFilters actionFilters,
ThreadPool threadPool
) {
super(
InferTrainedModelDeploymentAction.NAME,
Expand All @@ -52,6 +57,7 @@ public TransportInferTrainedModelDeploymentAction(
InferTrainedModelDeploymentAction.Response::new,
EsExecutors.DIRECT_EXECUTOR_SERVICE
);
this.threadPool = threadPool;
}

@Override
Expand Down Expand Up @@ -99,6 +105,9 @@ protected void taskOperation(
// and return order the results to match the request order
AtomicInteger count = new AtomicInteger();
AtomicArray<InferenceResults> results = new AtomicArray<>(nlpInputs.size());

var contextPreservingListener = ContextPreservingActionListener.wrapPreservingContext(listener, threadPool.getThreadContext());

int slot = 0;
for (var input : nlpInputs) {
task.infer(
Expand All @@ -109,7 +118,7 @@ protected void taskOperation(
request.getPrefixType(),
actionTask,
request.isChunkResults(),
orderedListener(count, results, slot++, nlpInputs.size(), listener)
orderedListener(count, results, slot++, nlpInputs.size(), contextPreservingListener)
);
}
}
Expand Down