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

[Improve][connector-jdbc] Calculate splits only once in JdbcSourceSplitEnumerator #2900

Merged
merged 1 commit into from
Sep 26, 2022
Merged

[Improve][connector-jdbc] Calculate splits only once in JdbcSourceSplitEnumerator #2900

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
43 changes: 25 additions & 18 deletions ...java/org/apache/seatunnel/connectors/seatunnel/jdbc/source/JdbcSourceSplitEnumerator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,27 +22,44 @@
import org.apache.seatunnel.connectors.seatunnel.jdbc.internal.split.JdbcNumericBetweenParametersProvider;
import org.apache.seatunnel.connectors.seatunnel.jdbc.state.JdbcSourceState;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.IOException;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;

public class JdbcSourceSplitEnumerator implements SourceSplitEnumerator<JdbcSourceSplit, JdbcSourceState> {

SourceSplitEnumerator.Context<JdbcSourceSplit> enumeratorContext;
List<JdbcSourceSplit> allSplit = new ArrayList<>();
JdbcSourceOptions jdbcSourceOptions;
PartitionParameter partitionParameter;
private static final Logger LOG = LoggerFactory.getLogger(JdbcSourceSplitEnumerator.class);
private final SourceSplitEnumerator.Context<JdbcSourceSplit> enumeratorContext;
private List<JdbcSourceSplit> allSplit = new ArrayList<>();
private JdbcSourceOptions jdbcSourceOptions;
private final PartitionParameter partitionParameter;
private final int parallelism;

public JdbcSourceSplitEnumerator(SourceSplitEnumerator.Context<JdbcSourceSplit> enumeratorContext, JdbcSourceOptions jdbcSourceOptions, PartitionParameter partitionParameter) {
this.enumeratorContext = enumeratorContext;
this.jdbcSourceOptions = jdbcSourceOptions;
this.partitionParameter = partitionParameter;
this.parallelism = enumeratorContext.currentParallelism();
}

@Override
public void open() {
LOG.info("Starting to calculate splits.");
if (null != partitionParameter) {
JdbcNumericBetweenParametersProvider jdbcNumericBetweenParametersProvider =
new JdbcNumericBetweenParametersProvider(partitionParameter.minValue, partitionParameter.maxValue).ofBatchNum(parallelism);
Serializable[][] parameterValues = jdbcNumericBetweenParametersProvider.getParameterValues();
for (int i = 0; i < parameterValues.length; i++) {
allSplit.add(new JdbcSourceSplit(parameterValues[i], i));
}
} else {
allSplit.add(new JdbcSourceSplit(null, 0));
}
LOG.info("Calculated splits successfully, the size of splits is {}.", allSplit.size());
}

@Override
Expand Down Expand Up @@ -70,20 +87,10 @@ public void handleSplitRequest(int subtaskId) {

@Override
public void registerReader(int subtaskId) {
int parallelism = enumeratorContext.currentParallelism();
if (allSplit.isEmpty()) {
if (null != partitionParameter) {
JdbcNumericBetweenParametersProvider jdbcNumericBetweenParametersProvider = new JdbcNumericBetweenParametersProvider(partitionParameter.minValue, partitionParameter.maxValue).ofBatchNum(parallelism);
Serializable[][] parameterValues = jdbcNumericBetweenParametersProvider.getParameterValues();
for (int i = 0; i < parameterValues.length; i++) {
allSplit.add(new JdbcSourceSplit(parameterValues[i], i));
}
} else {
allSplit.add(new JdbcSourceSplit(null, 0));
}
}
// Filter the split that the current task needs to run
List<JdbcSourceSplit> splits = allSplit.stream().filter(p -> p.splitId % parallelism == subtaskId).collect(Collectors.toList());
List<JdbcSourceSplit> splits = allSplit.stream()
.filter(p -> p.splitId % parallelism == subtaskId)
.collect(Collectors.toList());
enumeratorContext.assignSplit(subtaskId, splits);
enumeratorContext.signalNoMoreSplits(subtaskId);
}
Expand Down