1
0

[HUDI-1860] Add INSERT_OVERWRITE and INSERT_OVERWRITE_TABLE support to DeltaStreamer (#3184)

This commit is contained in:
Samrat
2021-07-20 07:19:43 +05:30
committed by GitHub
parent d5026e9a24
commit a086d255c8
8 changed files with 166 additions and 6 deletions

View File

@@ -32,10 +32,13 @@ import org.apache.hudi.common.fs.FSUtils;
import org.apache.hudi.common.model.HoodieCommitMetadata;
import org.apache.hudi.common.model.HoodieRecord;
import org.apache.hudi.common.model.HoodieRecordPayload;
import org.apache.hudi.common.model.HoodieTableType;
import org.apache.hudi.common.model.WriteOperationType;
import org.apache.hudi.common.table.HoodieTableMetaClient;
import org.apache.hudi.common.table.timeline.HoodieActiveTimeline;
import org.apache.hudi.common.table.timeline.HoodieInstant;
import org.apache.hudi.common.table.timeline.HoodieTimeline;
import org.apache.hudi.common.util.CommitUtils;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.common.util.ReflectionUtils;
import org.apache.hudi.common.util.StringUtils;
@@ -82,6 +85,7 @@ import java.io.IOException;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.function.Function;
import java.util.HashMap;
import java.util.HashSet;
@@ -460,6 +464,12 @@ public class DeltaSync implements Serializable {
case BULK_INSERT:
writeStatusRDD = writeClient.bulkInsert(records, instantTime);
break;
case INSERT_OVERWRITE:
writeStatusRDD = writeClient.insertOverwrite(records, instantTime).getWriteStatuses();
break;
case INSERT_OVERWRITE_TABLE:
writeStatusRDD = writeClient.insertOverwriteTable(records, instantTime).getWriteStatuses();
break;
default:
throw new HoodieDeltaStreamerException("Unknown operation : " + cfg.operation);
}
@@ -480,8 +490,8 @@ public class DeltaSync implements Serializable {
LOG.warn("Some records failed to be merged but forcing commit since commitOnErrors set. Errors/Total="
+ totalErrorRecords + "/" + totalRecords);
}
boolean success = writeClient.commit(instantTime, writeStatusRDD, Option.of(checkpointCommitMetadata));
String commitActionType = CommitUtils.getCommitActionType(cfg.operation, HoodieTableType.valueOf(cfg.tableType));
boolean success = writeClient.commit(instantTime, writeStatusRDD, Option.of(checkpointCommitMetadata), commitActionType, Collections.emptyMap());
if (success) {
LOG.info("Commit " + instantTime + " successful!");
this.formatAdapter.getSource().onCommit(checkpointStr);
@@ -530,7 +540,10 @@ public class DeltaSync implements Serializable {
RuntimeException lastException = null;
while (retryNum <= maxRetries) {
try {
return writeClient.startCommit();
String instantTime = HoodieActiveTimeline.createNewInstantTime();
String commitActionType = CommitUtils.getCommitActionType(cfg.operation, HoodieTableType.valueOf(cfg.tableType));
writeClient.startCommitWithTime(instantTime, commitActionType);
return instantTime;
} catch (IllegalArgumentException ie) {
lastException = ie;
LOG.error("Got error trying to start a new commit. Retrying after sleeping for a sec", ie);

View File

@@ -1723,6 +1723,40 @@ public class TestHoodieDeltaStreamer extends UtilitiesTestBase {
}
}
@Test
public void testInsertOverwrite() throws Exception {
testDeltaStreamerWithSpecifiedOperation(dfsBasePath + "/insert_overwrite", WriteOperationType.INSERT_OVERWRITE);
}
@Test
public void testInsertOverwriteTable() throws Exception {
testDeltaStreamerWithSpecifiedOperation(dfsBasePath + "/insert_overwrite_table", WriteOperationType.INSERT_OVERWRITE_TABLE);
}
void testDeltaStreamerWithSpecifiedOperation(final String tableBasePath, WriteOperationType operationType) throws Exception {
// Initial insert
HoodieDeltaStreamer.Config cfg = TestHelpers.makeConfig(tableBasePath, WriteOperationType.BULK_INSERT);
new HoodieDeltaStreamer(cfg, jsc).sync();
TestHelpers.assertRecordCount(1000, tableBasePath + "/*/*.parquet", sqlContext);
TestHelpers.assertDistanceCount(1000, tableBasePath + "/*/*.parquet", sqlContext);
TestHelpers.assertCommitMetadata("00000", tableBasePath, dfs, 1);
// setting the operationType
cfg.operation = operationType;
// No new data => no commits.
cfg.sourceLimit = 0;
new HoodieDeltaStreamer(cfg, jsc).sync();
TestHelpers.assertRecordCount(1000, tableBasePath + "/*/*.parquet", sqlContext);
TestHelpers.assertDistanceCount(1000, tableBasePath + "/*/*.parquet", sqlContext);
TestHelpers.assertCommitMetadata("00000", tableBasePath, dfs, 1);
cfg.sourceLimit = 1000;
new HoodieDeltaStreamer(cfg, jsc).sync();
TestHelpers.assertRecordCount(1950, tableBasePath + "/*/*.parquet", sqlContext);
TestHelpers.assertDistanceCount(1950, tableBasePath + "/*/*.parquet", sqlContext);
TestHelpers.assertCommitMetadata("00001", tableBasePath, dfs, 2);
}
/**
* UDF to calculate Haversine distance.
*/