abhishekrb19 commented on code in PR #16190:
URL: https://github.com/apache/druid/pull/16190#discussion_r1562674637
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
Review Comment:
For the kafka supervisor, `dataSourceMetadata instanceof
KafkaDataSourceMetadata` is a requirement right? Should we bail early by
throwing an exception if that's not the case instead of returning an empty map?
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
+ && checkSourceMetadataMatch(dataSourceMetadata)) {
+ @SuppressWarnings("unchecked")
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> partitions =
((KafkaDataSourceMetadata) dataSourceMetadata)
+ .getSeekableStreamSequenceNumbers();
+ if (partitions != null && partitions.getPartitionSequenceNumberMap() !=
null) {
+ Map<KafkaTopicPartition, Long> partitionOffsets = new HashMap<>();
+ Set<String> topicMisMatchLogged = new HashSet<>();
+ boolean isMultiTopic = getIoConfig().isMultiTopic();
+ Pattern pattern = isMultiTopic ?
Pattern.compile(getIoConfig().getStream()) : null;
Review Comment:
This function is called periodically in a few different places and in the
hot path, right? I'm wondering if we should save the result of
`Pattern.compile()` in the constructor and reuse it.
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
+ && checkSourceMetadataMatch(dataSourceMetadata)) {
+ @SuppressWarnings("unchecked")
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> partitions =
((KafkaDataSourceMetadata) dataSourceMetadata)
+ .getSeekableStreamSequenceNumbers();
+ if (partitions != null && partitions.getPartitionSequenceNumberMap() !=
null) {
+ Map<KafkaTopicPartition, Long> partitionOffsets = new HashMap<>();
+ Set<String> topicMisMatchLogged = new HashSet<>();
+ boolean isMultiTopic = getIoConfig().isMultiTopic();
+ Pattern pattern = isMultiTopic ?
Pattern.compile(getIoConfig().getStream()) : null;
+
partitions.getPartitionSequenceNumberMap().forEach((kafkaTopicPartition, value)
-> {
+ final boolean match;
+ final String matchValue;
+ // previous offsets are from multi-topic config
+ if (kafkaTopicPartition.topic().isPresent()) {
+ matchValue = kafkaTopicPartition.topic().get();
+ } else {
+ // previous offsets are from single topic config
+ matchValue = partitions.getStream();
+ }
+
+ match = pattern != null
+ ? pattern.matcher(matchValue).matches()
+ : getIoConfig().getStream().equals(matchValue);
+
+ if (!match && !topicMisMatchLogged.contains(matchValue)) {
Review Comment:
The function seems a bit complex to follow, and there's a risk of
introducing bugs due to the multiple if...else conditionals intertwined with
multi/single topic logic. Could we maybe add a single block each for the multi
topic and single topic logic or make a function each?
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
+ && checkSourceMetadataMatch(dataSourceMetadata)) {
Review Comment:
Also `checkSourceMetadataMatch(dataSourceMetadata)` is effectively doing the
same as `dataSourceMetadata instanceof KafkaDataSourceMetadata` called from
this class, so remove the latter?
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
+ && checkSourceMetadataMatch(dataSourceMetadata)) {
+ @SuppressWarnings("unchecked")
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> partitions =
((KafkaDataSourceMetadata) dataSourceMetadata)
+ .getSeekableStreamSequenceNumbers();
+ if (partitions != null && partitions.getPartitionSequenceNumberMap() !=
null) {
+ Map<KafkaTopicPartition, Long> partitionOffsets = new HashMap<>();
+ Set<String> topicMisMatchLogged = new HashSet<>();
+ boolean isMultiTopic = getIoConfig().isMultiTopic();
+ Pattern pattern = isMultiTopic ?
Pattern.compile(getIoConfig().getStream()) : null;
+
partitions.getPartitionSequenceNumberMap().forEach((kafkaTopicPartition, value)
-> {
+ final boolean match;
+ final String matchValue;
+ // previous offsets are from multi-topic config
+ if (kafkaTopicPartition.topic().isPresent()) {
+ matchValue = kafkaTopicPartition.topic().get();
+ } else {
+ // previous offsets are from single topic config
+ matchValue = partitions.getStream();
+ }
+
+ match = pattern != null
+ ? pattern.matcher(matchValue).matches()
+ : getIoConfig().getStream().equals(matchValue);
+
+ if (!match && !topicMisMatchLogged.contains(matchValue)) {
+ log.warn(
+ "Topic/stream in metadata storage [%s] doesn't match spec
topic/stream [%s], ignoring stored sequences",
+ matchValue,
+ getIoConfig().getStream()
+ );
+ topicMisMatchLogged.add(matchValue);
+ }
+ if (match) {
+ if (isMultiTopic) {
+ partitionOffsets.put(new KafkaTopicPartition(true, matchValue,
kafkaTopicPartition.partition()), value);
+ } else {
+ partitionOffsets.put(new KafkaTopicPartition(false, matchValue,
kafkaTopicPartition.partition()), value);
+ }
Review Comment:
This block can be simplified:
```suggestion
partitionOffsets.put(new KafkaTopicPartition(isMultiTopic, matchValue,
kafkaTopicPartition.partition()), value);
```
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/KafkaSeekableStreamStartSequenceNumbers.java:
##########
@@ -0,0 +1,220 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.indexing.kafka;
+
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import org.apache.druid.data.input.kafka.KafkaTopicPartition;
+import org.apache.druid.indexing.seekablestream.SeekableStreamSequenceNumbers;
+import
org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers;
+import org.apache.druid.java.util.common.IAE;
+import org.apache.druid.utils.CollectionUtils;
+
+import javax.annotation.Nullable;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+@JsonTypeName(SeekableStreamStartSequenceNumbers.TYPE)
Review Comment:
Adding a class-level Javadoc comment explaining the need for this class
would be helpful
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/KafkaSeekableStreamStartSequenceNumbers.java:
##########
@@ -0,0 +1,220 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.indexing.kafka;
+
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import org.apache.druid.data.input.kafka.KafkaTopicPartition;
+import org.apache.druid.indexing.seekablestream.SeekableStreamSequenceNumbers;
+import
org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers;
+import org.apache.druid.java.util.common.IAE;
+import org.apache.druid.utils.CollectionUtils;
+
+import javax.annotation.Nullable;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+@JsonTypeName(SeekableStreamStartSequenceNumbers.TYPE)
Review Comment:
is this type annotation needed? This child class refers to the same type as
the parent class's
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/KafkaSeekableStreamStartSequenceNumbers.java:
##########
@@ -0,0 +1,220 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.indexing.kafka;
+
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import org.apache.druid.data.input.kafka.KafkaTopicPartition;
+import org.apache.druid.indexing.seekablestream.SeekableStreamSequenceNumbers;
+import
org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers;
+import org.apache.druid.java.util.common.IAE;
+import org.apache.druid.utils.CollectionUtils;
+
+import javax.annotation.Nullable;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+@JsonTypeName(SeekableStreamStartSequenceNumbers.TYPE)
+public class KafkaSeekableStreamStartSequenceNumbers extends
SeekableStreamStartSequenceNumbers<KafkaTopicPartition, Long>
+{
+ private static final String TYPE = "start";
Review Comment:
unused:
```suggestion
```
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/KafkaSeekableStreamEndSequenceNumbers.java:
##########
@@ -0,0 +1,183 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.indexing.kafka;
+
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import org.apache.druid.data.input.kafka.KafkaTopicPartition;
+import
org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers;
+import org.apache.druid.indexing.seekablestream.SeekableStreamSequenceNumbers;
+import org.apache.druid.java.util.common.IAE;
+import org.apache.druid.utils.CollectionUtils;
+
+import java.util.HashMap;
+import java.util.Map;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+@JsonTypeName(SeekableStreamEndSequenceNumbers.TYPE)
Review Comment:
Same here. How is this jackson type information used?
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/KafkaSeekableStreamStartSequenceNumbers.java:
##########
@@ -0,0 +1,220 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.indexing.kafka;
+
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import org.apache.druid.data.input.kafka.KafkaTopicPartition;
+import org.apache.druid.indexing.seekablestream.SeekableStreamSequenceNumbers;
+import
org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers;
+import org.apache.druid.java.util.common.IAE;
+import org.apache.druid.utils.CollectionUtils;
+
+import javax.annotation.Nullable;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+@JsonTypeName(SeekableStreamStartSequenceNumbers.TYPE)
+public class KafkaSeekableStreamStartSequenceNumbers extends
SeekableStreamStartSequenceNumbers<KafkaTopicPartition, Long>
+{
+ private static final String TYPE = "start";
+ private final boolean isMultiTopicPartition;
+
+ public KafkaSeekableStreamStartSequenceNumbers(
+ String stream,
+ String topic,
+ Map<KafkaTopicPartition, Long> partitionSequenceNumberMap,
+ Map<KafkaTopicPartition, Long> partitionOffsetMap,
+ @Nullable Set<KafkaTopicPartition> exclusivePartitions
+ )
+ {
+ super(stream, topic, partitionSequenceNumberMap, partitionOffsetMap,
exclusivePartitions);
+ // how to know it topicPattern if the partitionSequenceNumberMap is empty?
+ isMultiTopicPartition = !partitionSequenceNumberMap.isEmpty() &&
partitionSequenceNumberMap.keySet()
+ .stream()
+ .findFirst()
+ .get()
+ .isMultiTopicPartition();
+ }
+
+ @Override
+ public boolean isMultiTopicPartition()
+ {
+ return isMultiTopicPartition;
+ }
+
+ @Override
+ public SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> plus(
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> other
+ )
+ {
+ if (this.getClass() != other.getClass()) {
+ throw new IAE(
+ "Expected instance of %s, got %s",
+ this.getClass().getName(),
+ other.getClass().getName()
+ );
+ }
+
+ KafkaSeekableStreamStartSequenceNumbers that =
(KafkaSeekableStreamStartSequenceNumbers) other;
+
+ if (!this.isMultiTopicPartition() && !that.isMultiTopicPartition()) {
+ return super.plus(other);
+ }
+
+
+ String thisTopic = getStream();
+ String thatTopic = that.getStream();
+ final Map<KafkaTopicPartition, Long> newMap;
+ final Set<KafkaTopicPartition> newExclusivePartitions = new HashSet<>();
+ if (!isMultiTopicPartition()) {
+ // going from topicPattern to single topic
+
+ // start with existing sequence numbers which in this case will be all
single topic.
+ newMap = new HashMap<>(getPartitionSequenceNumberMap());
+
+ // add all sequence numbers from other where the topic name matches this
topic. Transform to single topic
+ // as in this case we will be returning a single topic based sequence
map.
+ newMap.putAll(that.getPartitionSequenceNumberMap().entrySet().stream()
+ .filter(e -> {
+ if (e.getKey().topic().isPresent()) {
+ return e.getKey().topic().get().equals(thisTopic);
+ } else {
+ // this branch shouldn't really be hit since other should be
multi-topic here, but adding this
+ // just int case.
Review Comment:
```suggestion
// just in case.
```
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/KafkaSeekableStreamStartSequenceNumbers.java:
##########
@@ -0,0 +1,220 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.indexing.kafka;
+
+import com.fasterxml.jackson.annotation.JsonTypeName;
+import org.apache.druid.data.input.kafka.KafkaTopicPartition;
+import org.apache.druid.indexing.seekablestream.SeekableStreamSequenceNumbers;
+import
org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers;
+import org.apache.druid.java.util.common.IAE;
+import org.apache.druid.utils.CollectionUtils;
+
+import javax.annotation.Nullable;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+@JsonTypeName(SeekableStreamStartSequenceNumbers.TYPE)
+public class KafkaSeekableStreamStartSequenceNumbers extends
SeekableStreamStartSequenceNumbers<KafkaTopicPartition, Long>
+{
+ private static final String TYPE = "start";
+ private final boolean isMultiTopicPartition;
+
+ public KafkaSeekableStreamStartSequenceNumbers(
+ String stream,
+ String topic,
+ Map<KafkaTopicPartition, Long> partitionSequenceNumberMap,
+ Map<KafkaTopicPartition, Long> partitionOffsetMap,
+ @Nullable Set<KafkaTopicPartition> exclusivePartitions
+ )
+ {
+ super(stream, topic, partitionSequenceNumberMap, partitionOffsetMap,
exclusivePartitions);
+ // how to know it topicPattern if the partitionSequenceNumberMap is empty?
+ isMultiTopicPartition = !partitionSequenceNumberMap.isEmpty() &&
partitionSequenceNumberMap.keySet()
+ .stream()
+ .findFirst()
+ .get()
+ .isMultiTopicPartition();
+ }
+
+ @Override
+ public boolean isMultiTopicPartition()
+ {
+ return isMultiTopicPartition;
+ }
+
+ @Override
+ public SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> plus(
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> other
+ )
+ {
+ if (this.getClass() != other.getClass()) {
+ throw new IAE(
+ "Expected instance of %s, got %s",
+ this.getClass().getName(),
+ other.getClass().getName()
+ );
+ }
Review Comment:
nit: adding a function `validateSequenceNumbersBaseType()` in the base class
should remove this code duplication in 4-5 places
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
+ && checkSourceMetadataMatch(dataSourceMetadata)) {
+ @SuppressWarnings("unchecked")
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> partitions =
((KafkaDataSourceMetadata) dataSourceMetadata)
+ .getSeekableStreamSequenceNumbers();
+ if (partitions != null && partitions.getPartitionSequenceNumberMap() !=
null) {
+ Map<KafkaTopicPartition, Long> partitionOffsets = new HashMap<>();
+ Set<String> topicMisMatchLogged = new HashSet<>();
+ boolean isMultiTopic = getIoConfig().isMultiTopic();
+ Pattern pattern = isMultiTopic ?
Pattern.compile(getIoConfig().getStream()) : null;
+
partitions.getPartitionSequenceNumberMap().forEach((kafkaTopicPartition, value)
-> {
+ final boolean match;
+ final String matchValue;
+ // previous offsets are from multi-topic config
+ if (kafkaTopicPartition.topic().isPresent()) {
+ matchValue = kafkaTopicPartition.topic().get();
+ } else {
+ // previous offsets are from single topic config
+ matchValue = partitions.getStream();
+ }
+
+ match = pattern != null
+ ? pattern.matcher(matchValue).matches()
+ : getIoConfig().getStream().equals(matchValue);
+
+ if (!match && !topicMisMatchLogged.contains(matchValue)) {
+ log.warn(
+ "Topic/stream in metadata storage [%s] doesn't match spec
topic/stream [%s], ignoring stored sequences",
Review Comment:
```suggestion
"Topic/stream [%s] in metadata storage doesn't match spec
topic/stream [%s], ignoring stored sequences",
```
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
Review Comment:
A brief javadoc for this function would be useful and would clarify the need
for this override from the base implementation and the filtering behavior
##########
extensions-core/kafka-indexing-service/src/main/java/org/apache/druid/indexing/kafka/supervisor/KafkaSupervisor.java:
##########
@@ -444,4 +447,56 @@ public KafkaSupervisorTuningConfig getTuningConfig()
{
return spec.getTuningConfig();
}
+
+ @Override
+ protected Map<KafkaTopicPartition, Long> getOffsetsFromMetadataStorage()
+ {
+ final DataSourceMetadata dataSourceMetadata = retrieveDataSourceMetadata();
+ if (dataSourceMetadata instanceof KafkaDataSourceMetadata
+ && checkSourceMetadataMatch(dataSourceMetadata)) {
+ @SuppressWarnings("unchecked")
+ SeekableStreamSequenceNumbers<KafkaTopicPartition, Long> partitions =
((KafkaDataSourceMetadata) dataSourceMetadata)
+ .getSeekableStreamSequenceNumbers();
+ if (partitions != null && partitions.getPartitionSequenceNumberMap() !=
null) {
+ Map<KafkaTopicPartition, Long> partitionOffsets = new HashMap<>();
+ Set<String> topicMisMatchLogged = new HashSet<>();
+ boolean isMultiTopic = getIoConfig().isMultiTopic();
+ Pattern pattern = isMultiTopic ?
Pattern.compile(getIoConfig().getStream()) : null;
+
partitions.getPartitionSequenceNumberMap().forEach((kafkaTopicPartition, value)
-> {
+ final boolean match;
+ final String matchValue;
+ // previous offsets are from multi-topic config
+ if (kafkaTopicPartition.topic().isPresent()) {
+ matchValue = kafkaTopicPartition.topic().get();
+ } else {
+ // previous offsets are from single topic config
+ matchValue = partitions.getStream();
+ }
+
+ match = pattern != null
+ ? pattern.matcher(matchValue).matches()
+ : getIoConfig().getStream().equals(matchValue);
+
+ if (!match && !topicMisMatchLogged.contains(matchValue)) {
+ log.warn(
Review Comment:
Yeah, resetting the offsets in this scenario when there's no match at all
makes sense to me.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
