Skip to content

feat(pubsub): add publish telemetry headers for publish attempt observability #14338

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

Open
tonyyyycui wants to merge 3 commits into
base: main
Choose a base branch
from
+90 −1
Open

feat(pubsub): add publish telemetry headers for publish attempt observability #14338

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
69ec9f6
Add proto telemetry header to improve server side visibility
Sep 9, 2026
94de134
Fix lint
Sep 9, 2026
a926bdb
Remove timestamps for now
Sep 11, 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
20 changes: 19 additions & 1 deletion java-pubsub/google-cloud-pubsub/src/main/java/com/google/cloud/pubsub/v1/Publisher.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,10 +49,13 @@
import com.google.cloud.pubsub.v1.stub.PublisherStubSettings;
import com.google.common.annotations.VisibleForTesting;
import com.google.common.base.Preconditions;
import com.google.common.collect.ImmutableList;
import com.google.common.collect.ImmutableMap;
import com.google.common.collect.ImmutableSet;
import com.google.protobuf.CodedOutputStream;
import com.google.pubsub.v1.PublishRequest;
import com.google.pubsub.v1.PublishResponse;
import com.google.pubsub.v1.PubsubClientTelemetry;
import com.google.pubsub.v1.PubsubMessage;
import com.google.pubsub.v1.TopicName;
import com.google.pubsub.v1.TopicNames;
Expand All @@ -63,6 +66,7 @@
import java.io.IOException;
import java.time.Duration;
import java.util.ArrayList;
import java.util.Base64;
import java.util.Collections;
import java.util.HashMap;
import java.util.Iterator;
Expand Down Expand Up @@ -105,6 +109,8 @@ public class Publisher implements PublisherInterface {
private static final Logger logger = Logger.getLogger(Publisher.class.getName());
private LoggingUtil loggingUtil = new LoggingUtil();

@VisibleForTesting static final String TELEMETRY_HEADER_KEY = "x-goog-pubsub-client-telemetry";

private static final String GZIP_COMPRESSION = "gzip";

private static final String OPEN_TELEMETRY_TRACER_NAME = "com.google.cloud.pubsub.v1";
Expand Down Expand Up @@ -540,6 +546,18 @@ private void publishAllWithoutInflightForKey(final String orderingKey) {
}
}

private Map<String, List<String>> createTelemetryHeader(int attemptNumber) {
PubsubClientTelemetry telemetry =
PubsubClientTelemetry.newBuilder()
.setPublishOperation(
PubsubClientTelemetry.PublishOperation.newBuilder()
.setHedgedAttemptCount(attemptNumber)
.build())
.build();
String encodedHeader = Base64.getEncoder().encodeToString(telemetry.toByteArray());
return ImmutableMap.of(TELEMETRY_HEADER_KEY, ImmutableList.of(encodedHeader));
}

private ApiFuture<PublishResponse> publishCall(OutstandingBatch outstandingBatch) {
return publishCall(outstandingBatch, 0, null);
}
Expand All @@ -561,7 +579,7 @@ private ApiFuture<PublishResponse> publishCall(
outstandingBatch.getMessageWrappers().get(0));
context = context.withRetryableCodes(Collections.<StatusCode.Code>emptySet());
}

context = context.withExtraHeaders(createTelemetryHeader(attemptNumber));
int numMessagesInBatch = outstandingBatch.size();
List<PubsubMessage> pubsubMessagesList = new ArrayList<PubsubMessage>(numMessagesInBatch);
List<PubsubMessageWrapper> messageWrappers = outstandingBatch.getMessageWrappers();
Expand Down
71 changes: 71 additions & 0 deletions ...ubsub/google-cloud-pubsub/src/test/java/com/google/cloud/pubsub/v1/PublisherImplTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@
import com.google.pubsub.v1.ProjectTopicName;
import com.google.pubsub.v1.PublishRequest;
import com.google.pubsub.v1.PublishResponse;
import com.google.pubsub.v1.PubsubClientTelemetry;
import com.google.pubsub.v1.PubsubMessage;
import io.grpc.ManagedChannel;
import io.grpc.Metadata;
Expand All @@ -61,6 +62,7 @@
import io.opentelemetry.sdk.testing.junit4.OpenTelemetryRule;
import io.opentelemetry.sdk.trace.data.SpanData;
import java.time.Duration;
import java.util.Base64;
import java.util.List;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.ExecutionException;
Expand Down Expand Up @@ -1737,4 +1739,73 @@ private void shutdownTestPublisher(Publisher publisher) throws InterruptedExcept
fakeExecutor.advanceTime(Duration.ofSeconds(10));
assertTrue(publisher.awaitTermination(1, TimeUnit.MINUTES));
}

private PubsubClientTelemetry extractTelemetryHeader(Metadata headers) throws Exception {
Metadata.Key<String> key =
Metadata.Key.of(Publisher.TELEMETRY_HEADER_KEY, Metadata.ASCII_STRING_MARSHALLER);
String headerValue = headers.get(key);
assertThat(headerValue).isNotNull();
byte[] decodedBytes = Base64.getDecoder().decode(headerValue);
return PubsubClientTelemetry.parseFrom(decodedBytes);
}

@Test
public void testTelemetryHeaderOnNormalPublish() throws Exception {
testPublisherServiceImpl.setAutoPublishResponse(true);
Publisher publisher =
getTestPublisherBuilder()
.setBatchingSettings(
Publisher.Builder.DEFAULT_BATCHING_SETTINGS.toBuilder()
.setElementCountThreshold(1L)
.build())
.build();

ApiFuture<String> future = sendTestMessage(publisher, "msg-normal");
assertEquals("1", future.get(5, TimeUnit.SECONDS));

List<Metadata> capturedHeaders = testPublisherServiceImpl.getCapturedHeaders();
assertThat(capturedHeaders).hasSize(1);

PubsubClientTelemetry telemetry = extractTelemetryHeader(capturedHeaders.get(0));
assertThat(telemetry.hasPublishOperation()).isTrue();
assertThat(telemetry.getPublishOperation().getHedgedAttemptCount()).isEqualTo(0);

shutdownTestPublisher(publisher);
}

@Test
public void testTelemetryHeaderOnHedgedPublish() throws Exception {
Publisher publisher = getPublisherWithHedge(Duration.ofMillis(100), 0.2f, 20);
fillTokenBucket(publisher, 5);

// Delay response so hedge fires
testPublisherServiceImpl.setAutoPublishResponse(false);
testPublisherServiceImpl.setPublishResponseDelay(Duration.ofMillis(200));
testPublisherServiceImpl.addPublishResponse(PublishResponse.newBuilder().addMessageIds("1"));
testPublisherServiceImpl.addPublishResponse(PublishResponse.newBuilder().addMessageIds("2"));

ApiFuture<String> future = sendTestMessage(publisher, "msg-hedged");
waitForRequests(testPublisherServiceImpl, 1);

// Advance past hedge delay to trigger hedge attempt
fakeExecutor.advanceTime(Duration.ofMillis(120));
waitForRequests(testPublisherServiceImpl, 2);

// Finish request
fakeExecutor.advanceTime(Duration.ofMillis(100));
assertEquals("1", future.get(5, TimeUnit.SECONDS));

List<Metadata> capturedHeaders = testPublisherServiceImpl.getCapturedHeaders();
assertThat(capturedHeaders).hasSize(2);

// Verify Attempt 0 (Original)
PubsubClientTelemetry initialTelemetry = extractTelemetryHeader(capturedHeaders.get(0));
assertThat(initialTelemetry.getPublishOperation().getHedgedAttemptCount()).isEqualTo(0);

// Verify Attempt 1 (Hedge)
PubsubClientTelemetry hedgedTelemetry = extractTelemetryHeader(capturedHeaders.get(1));
assertThat(hedgedTelemetry.getPublishOperation().getHedgedAttemptCount()).isEqualTo(1);

shutdownTestPublisher(publisher);
}
}
Loading