Skip to content
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

Jump to bottom

[FLINK-32020] Enable Dynamic Partition Discovery by Default in Kafka Source based on FLIP-288 #40

Closed
wants to merge 4 commits into from
Closed

[FLINK-32020] Enable Dynamic Partition Discovery by Default in Kafka Source based on FLIP-288 #40

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
06231ab
[FLINK-32020][Connectors/Kafka] Enable Dynamic Partition Discovery by…
loserwang1024 May 6, 2023
d49490b
[FLINK-32020][Connectors/Kafka] Enable Dynamic Partition Discovery by…
loserwang1024 May 6, 2023
3559f68
[FLINK-32020][Connectors/Kafka] Add test case to validates disabling …
loserwang1024 Jul 12, 2023
b974b6b
[FLINK-32020][Connectors/Kafka] Add test case to validates disabling …
loserwang1024 Jul 14, 2023
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: 4 additions & 2 deletions ...ector-kafka/src/main/java/org/apache/flink/connector/kafka/source/KafkaSourceOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import org.apache.flink.configuration.ConfigOption;
import org.apache.flink.configuration.ConfigOptions;

import java.time.Duration;
import java.util.Properties;
import java.util.function.Function;

Expand All @@ -38,10 +39,11 @@ public class KafkaSourceOptions {
public static final ConfigOption<Long> PARTITION_DISCOVERY_INTERVAL_MS =
ConfigOptions.key("partition.discovery.interval.ms")
.longType()
.noDefaultValue()
.defaultValue(Duration.ofMinutes(5).toMillis())
.withDescription(
"The interval in milliseconds for the Kafka source to discover "
+ "the new partitions. A non-positive value disables the partition discovery.");
+ "the new partitions. A non-positive value disables the partition discovery."
+ "The default value is 5 minutes, which is equal to the default value of metadata.max.age.ms in Kafka.");

public static final ConfigOption<Boolean> REGISTER_KAFKA_CONSUMER_METRICS =
ConfigOptions.key("register.consumer.metrics")
Expand Down
6 changes: 4 additions & 2 deletions ...rc/main/java/org/apache/flink/streaming/connectors/kafka/table/KafkaConnectorOptions.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,9 +188,11 @@ public class KafkaConnectorOptions {
public static final ConfigOption<Duration> SCAN_TOPIC_PARTITION_DISCOVERY =
ConfigOptions.key("scan.topic-partition-discovery.interval")
.durationType()
.noDefaultValue()
.defaultValue(Duration.ofMinutes(5))
.withDescription(
"Optional interval for consumer to discover dynamically created Kafka partitions periodically.");
"Optional interval for consumer to discover dynamically created Kafka partitions periodically."
+ "The value 0 disables the partition discovery."
+ "The default value is 5 minutes, which is equal to the default value of metadata.max.age.ms in Kafka.");

// --------------------------------------------------------------------------------------------
// Sink specific options
Expand Down
6 changes: 3 additions & 3 deletions ...main/java/org/apache/flink/streaming/connectors/kafka/table/KafkaDynamicTableFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,11 +201,11 @@ public DynamicTableSource createDynamicTableSource(Context context) {
final Properties properties = getKafkaProperties(context.getCatalogTable().getOptions());

// add topic-partition discovery
final Optional<Long> partitionDiscoveryInterval =
tableOptions.getOptional(SCAN_TOPIC_PARTITION_DISCOVERY).map(Duration::toMillis);
final Duration partitionDiscoveryInterval =
tableOptions.get(SCAN_TOPIC_PARTITION_DISCOVERY);
properties.setProperty(
KafkaSourceOptions.PARTITION_DISCOVERY_INTERVAL_MS.key(),
partitionDiscoveryInterval.orElse(-1L).toString());
Long.toString(partitionDiscoveryInterval.toMillis()));

final DataType physicalDataType = context.getPhysicalRowDataType();

Expand Down
38 changes: 38 additions & 0 deletions ...src/test/java/org/apache/flink/connector/kafka/source/enumerator/KafkaEnumeratorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -501,6 +501,44 @@ public void testPartitionChangeChecking() throws Throwable {
}
}

@Test
public void testEnablePartitionDiscoveryByDefault() {
KafkaSourceEnumerator enumerator =
new KafkaSourceEnumerator(
KafkaSubscriber.getTopicListSubscriber(Arrays.asList(TOPIC1, TOPIC2)),
OffsetsInitializer.earliest(),
new NoStoppingOffsetsInitializer(),
new Properties(),
new MockSplitEnumeratorContext<>(NUM_SUBTASKS),
Boundedness.CONTINUOUS_UNBOUNDED,
new KafkaSourceEnumState(
Collections.emptySet(), Collections.emptySet(), false));
long partitionDiscoveryIntervalMs =
(long) Whitebox.getInternalState(enumerator, "partitionDiscoveryIntervalMs");
assertThat(partitionDiscoveryIntervalMs)
.isEqualTo(KafkaSourceOptions.PARTITION_DISCOVERY_INTERVAL_MS.defaultValue());
}

@Test
public void testDisablePartitionDiscovery() {
Properties props = new Properties();
props.setProperty(
KafkaSourceOptions.PARTITION_DISCOVERY_INTERVAL_MS.key(), String.valueOf(0));
KafkaSourceEnumerator enumerator =
new KafkaSourceEnumerator(
KafkaSubscriber.getTopicListSubscriber(Arrays.asList(TOPIC1, TOPIC2)),
OffsetsInitializer.earliest(),
new NoStoppingOffsetsInitializer(),
props,
new MockSplitEnumeratorContext<>(NUM_SUBTASKS),
Boundedness.CONTINUOUS_UNBOUNDED,
new KafkaSourceEnumState(
Collections.emptySet(), Collections.emptySet(), false));
long partitionDiscoveryIntervalMs =
(long) Whitebox.getInternalState(enumerator, "partitionDiscoveryIntervalMs");
assertThat(partitionDiscoveryIntervalMs).isEqualTo(0);
PatrickRen marked this conversation as resolved.
Show resolved Hide resolved
}

// -------------- some common startup sequence ---------------

private void startEnumeratorAndRegisterReaders(
Expand Down
76 changes: 76 additions & 0 deletions .../java/org/apache/flink/streaming/connectors/kafka/table/KafkaDynamicTableFactoryTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1095,6 +1095,82 @@ public void testPrimaryKeyValidation() {
+ " guarantee the semantic of primary key.");
}

@Test
public void testDiscoverPartitionByDefault() {
Map<String, String> tableSourceOptions =
getModifiedOptions(
getBasicSourceOptions(),
options -> options.remove("scan.topic-partition-discovery.interval"));
final KafkaDynamicSource actualSource =
(KafkaDynamicSource) createTableSource(SCHEMA, tableSourceOptions);
Properties props = new Properties();
props.putAll(KAFKA_SOURCE_PROPERTIES);
// The default partition discovery interval is 5 minutes
props.setProperty("partition.discovery.interval.ms", "300000");
final Map<KafkaTopicPartition, Long> specificOffsets = new HashMap<>();
specificOffsets.put(new KafkaTopicPartition(TOPIC, PARTITION_0), OFFSET_0);
specificOffsets.put(new KafkaTopicPartition(TOPIC, PARTITION_1), OFFSET_1);
final DecodingFormat<DeserializationSchema<RowData>> valueDecodingFormat =
new DecodingFormatMock(",", true);
// Test scan source equals
final KafkaDynamicSource expectedKafkaSource =
createExpectedScanSource(
SCHEMA_DATA_TYPE,
null,
valueDecodingFormat,
new int[0],
new int[] {0, 1, 2},
null,
Collections.singletonList(TOPIC),
null,
props,
StartupMode.SPECIFIC_OFFSETS,
specificOffsets,
0);
assertThat(actualSource).isEqualTo(expectedKafkaSource);
ScanTableSource.ScanRuntimeProvider provider =
actualSource.getScanRuntimeProvider(ScanRuntimeProviderContext.INSTANCE);
assertKafkaSource(provider);
}

@Test
public void testDisableDiscoverPartition() {
Map<String, String> tableSourceOptions =
getModifiedOptions(
getBasicSourceOptions(),
options -> options.put("scan.topic-partition-discovery.interval", "0"));
final KafkaDynamicSource actualSource =
(KafkaDynamicSource) createTableSource(SCHEMA, tableSourceOptions);
Properties props = new Properties();
props.putAll(KAFKA_SOURCE_PROPERTIES);
// Disable discovery if the partition discovery interval is 0 minutes
props.setProperty("partition.discovery.interval.ms", "0");
final Map<KafkaTopicPartition, Long> specificOffsets = new HashMap<>();
specificOffsets.put(new KafkaTopicPartition(TOPIC, PARTITION_0), OFFSET_0);
specificOffsets.put(new KafkaTopicPartition(TOPIC, PARTITION_1), OFFSET_1);
final DecodingFormat<DeserializationSchema<RowData>> valueDecodingFormat =
new DecodingFormatMock(",", true);
// Test scan source equals
final KafkaDynamicSource expectedKafkaSource =
createExpectedScanSource(
SCHEMA_DATA_TYPE,
null,
valueDecodingFormat,
new int[0],
new int[] {0, 1, 2},
null,
Collections.singletonList(TOPIC),
null,
props,
StartupMode.SPECIFIC_OFFSETS,
specificOffsets,
0);
assertThat(actualSource).isEqualTo(expectedKafkaSource);
ScanTableSource.ScanRuntimeProvider provider =
actualSource.getScanRuntimeProvider(ScanRuntimeProviderContext.INSTANCE);
assertKafkaSource(provider);
}

// --------------------------------------------------------------------------------------------
// Utilities
// --------------------------------------------------------------------------------------------
Expand Down