Skip to content

Handle Kafka tombstone messages #6707

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
xiasongh wants to merge 1 commit into
base: main
Choose a base branch
from
+50 −3
Open

Handle Kafka tombstone messages #6707

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
6 changes: 6 additions & 0 deletions crates/adapters/src/test/kafka.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,6 +242,12 @@ impl TestProducer {
self.producer.flush(Timeout::Never).unwrap();
}

pub fn send_tombstone(&self, key: &[u8], topic: &str) {
let record = BaseRecord::<[u8], (), ()>::to(topic).key(key);
self.producer.send(record).unwrap();
self.producer.flush(Timeout::Never).unwrap();
}

pub fn send_to_topic_partition(&self, data: &[Vec<TestStruct>], topic: &str, partition: i32) {
for batch in data {
let mut writer = CsvWriterBuilder::new()
Expand Down
8 changes: 5 additions & 3 deletions crates/adapters/src/transport/kafka/ft/input.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1255,9 +1255,11 @@ impl PartitionReceiver {
}

let timestamp = message.timestamp().to_millis().unwrap_or(i64::MIN);
let payload = message.payload().unwrap_or(&[]);
let metadata = self.create_metadata(&message);
let (buffer, errors) = parser.parse(payload, metadata);
let (buffer, errors) = match message.payload() {
Some(payload) => parser.parse(payload, self.create_metadata(&message)),
// Skip tombstones; keep offsets.
None => (None, Vec::new()),
};
self.n_bytes
.fetch_add(buffer.len().bytes, Ordering::Relaxed);
self.messages
Expand Down
39 changes: 39 additions & 0 deletions crates/adapters/src/transport/kafka/ft/test.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -509,6 +509,45 @@ fn test_input(topic: &str, batch_sizes: &[u32]) {
}
}

#[test]
fn test_input_tombstone() {
init_test_logger();

let topic = "kafka_tombstone_ft";
let _kafka_resources = KafkaResources::create_topics(&[(topic, 1)]);

let (endpoint, receiver, reader) = create_reader(topic, None, false);
reader.extend();

let producer = TestProducer::new();
producer.send_message(b"m0", topic, None);
producer.send_tombstone(b"deleted-key", topic);
producer.send_message(b"", topic, None);
producer.send_message(b"m3", topic, None);

receiver.expect_buffering(3);
reader.queue(false);

let metadata = Metadata {
offsets: vec![0..4],
};
receiver.expect(vec![ConsumerCall::Extended {
num_records: 3,
metadata: serde_json::to_value(&metadata).unwrap(),
}]);
assert_eq!(take_flushed(&receiver), vec!["m0", "", "m3"]);

drop(endpoint);
drop(receiver);
drop(reader);

let (_endpoint, receiver, reader) = create_reader(topic, None, false);
receiver.inner.drop_buffered.store(true, Ordering::Release);
reader.replay(serde_json::to_value(&metadata).unwrap(), RmpValue::Nil);
receiver.expect(vec![ConsumerCall::Replayed { num_records: 3 }]);
assert_eq!(take_flushed(&receiver), vec!["m0", "", "m3"]);
}

/// A configured header filter drops non-matching messages before parsing, and
/// the drop decision is deterministic across replay: a fresh reader replaying
/// the checkpointed offset range reproduces exactly the admitted records.
Expand Down