Skip to content

[PubsubIO] Account for message metadata in bounded write batch size #39886

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
1fanwang wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[PubsubIO] Account for message metadata in bounded write batch size #39886

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 2 additions & 5 deletions ...va/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/pubsub/PubsubIO.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1912,14 +1912,11 @@ public void processElement(@Element PubsubMessage message, @Timestamp Instant ti
// TODO(sjvanrossum): https://github.com/apache/beam/issues/31800
// - Size validation makes no distinction between JSON and Protobuf encoding
// - Accounting for HTTP to gRPC transcoding is non-trivial
PreparePubsubWriteDoFn.validatePubsubMessage(message, maxPublishBatchByteSize);
final int messageSize =
PreparePubsubWriteDoFn.validatePubsubMessage(message, maxPublishBatchByteSize);
// NOTE: The record id is always null since it will be assigned by Pub/Sub.
final OutgoingMessage msg =
OutgoingMessage.of(message, timestamp.getMillis(), null, message.getTopic());
// TODO(sjvanrossum): https://github.com/apache/beam/issues/31800
// - Size validation makes no distinction between JSON and Protobuf encoding
// - Accounting for HTTP to gRPC transcoding is non-trivial
final int messageSize = msg.getMessage().getData().size();

final PubsubTopic pubsubTopic;
ValueProvider<PubsubTopic> topicProvider = getTopicProvider();
Expand Down
41 changes: 41 additions & 0 deletions ...o/google-cloud-platform/src/test/java/org/apache/beam/sdk/io/gcp/pubsub/PubsubIOTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,7 @@
import org.apache.beam.sdk.testing.PAssert;
import org.apache.beam.sdk.testing.TestPipeline;
import org.apache.beam.sdk.transforms.Create;
import org.apache.beam.sdk.transforms.DoFnTester;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.transforms.SimpleFunction;
import org.apache.beam.sdk.transforms.display.DisplayData;
Expand All @@ -82,6 +83,7 @@
import org.apache.beam.sdk.values.ValueInSingleWindow;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.base.MoreObjects;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.ImmutableList;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.ImmutableMap;
import org.apache.beam.vendor.guava.v32_1_2_jre.com.google.common.collect.Lists;
import org.apache.commons.lang3.RandomStringUtils;
import org.checkerframework.checker.nullness.qual.Nullable;
Expand Down Expand Up @@ -921,6 +923,45 @@ public void testBigMessageBounded() throws IOException {
}
}

@Test
public void testBoundedWriteBatchSizeIncludesAttributesAndOrderingKey() throws Exception {
PubsubClient mockClient = Mockito.mock(PubsubClient.class);
PubsubClient.PubsubClientFactory mockFactory =
Mockito.mock(PubsubClient.PubsubClientFactory.class);
Mockito.when(
mockFactory.newClient(
Mockito.isNull(), Mockito.isNull(), Mockito.any(), Mockito.isNull()))
.thenReturn(mockClient);

List<Integer> publishedBatchSizes = Lists.newArrayList();
Mockito.when(mockClient.publish(Mockito.any(), Mockito.anyList()))
.thenAnswer(
invocation -> {
List<OutgoingMessage> messages = invocation.getArgument(1);
publishedBatchSizes.add(messages.size());
return messages.size();
});

PubsubIO.Write<PubsubMessage> write =
PubsubIO.writeMessages()
.to("projects/project/topics/topic")
.withClientFactory(mockFactory)
.withOrderingKey()
.withMaxBatchBytesSize(40);
PubsubMessage message =
new PubsubMessage(
"0123456789".getBytes(StandardCharsets.UTF_8), ImmutableMap.of("k", "value"))
.withOrderingKey("order");

try (DoFnTester<PubsubMessage, Void> tester =
DoFnTester.of(write.new PubsubBoundedWriter(100, 40))) {
tester.setCloningBehavior(DoFnTester.CloningBehavior.DO_NOT_CLONE);
tester.processBundle(ImmutableList.of(message, message));
}

assertEquals(ImmutableList.of(1, 1), publishedBatchSizes);
}

@Test
public void testReadValidate() throws IOException {
PubsubOptions options = TestPipeline.testingPipelineOptions().as(PubsubOptions.class);
Expand Down
Loading