vinothchandar commented on a change in pull request #3173: URL: https://github.com/apache/hudi/pull/3173#discussion_r775310284
########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/storage/HoodieStorageLayout.java ########## @@ -0,0 +1,51 @@ +/* + * 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.hudi.table.storage; + +import org.apache.hudi.common.model.WriteOperationType; + +import java.io.Serializable; + +public class HoodieStorageLayout implements Serializable { Review comment: nts: Review these classes for names, docs ########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/HoodieWriteHandle.java ########## @@ -195,6 +195,10 @@ public boolean canWrite(HoodieRecord record) { return false; } + public boolean canSwitchToNewOne() { Review comment: Consider naming this better? ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/deltacommit/AbstractSparkDeltaCommitActionExecutor.java ########## @@ -74,8 +74,8 @@ public Partitioner getUpsertPartitioner(WorkloadProfile profile) { public Iterator<List<WriteStatus>> handleUpdate(String partitionPath, String fileId, Iterator<HoodieRecord<T>> recordItr) throws IOException { LOG.info("Merging updates for commit " + instantTime + " for file " + fileId); - - if (!table.getIndex().canIndexLogFiles() && mergeOnReadUpsertPartitioner.getSmallFileIds().contains(fileId)) { + if (!table.getIndex().canIndexLogFiles() && mergeOnReadUpsertPartitioner != null Review comment: let me take a closer look and suggest what I think ########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/index/HoodieIndex.java ########## @@ -122,13 +123,29 @@ public O updateLocation(O writeStatuses, HoodieEngineContext context, @PublicAPIMethod(maturity = ApiMaturityLevel.STABLE) public abstract boolean isImplicitWithStorage(); + /** + * If the `getCustomizedPartitioner` returns a partitioner, it has to be true. + */ + @PublicAPIMethod(maturity = ApiMaturityLevel.EVOLVING) + public boolean performTagging(WriteOperationType operationType) { + switch (operationType) { + case INSERT: + case INSERT_OVERWRITE: + return false; + case UPSERT: Review comment: I think this is better push into `WriteOperationType` and we have more operations that may need tagging. ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/BaseSparkCommitActionExecutor.java ########## @@ -303,7 +305,7 @@ protected void commit(Option<Map<String, String>> extraMetadata, HoodieWriteMeta @SuppressWarnings("unchecked") protected Iterator<List<WriteStatus>> handleUpsertPartition(String instantTime, Integer partition, Iterator recordItr, Partitioner partitioner) { - UpsertPartitioner upsertPartitioner = (UpsertPartitioner) partitioner; + SparkHoodiePartitioner upsertPartitioner = (SparkHoodiePartitioner) partitioner; Review comment: is this renamed? ########## File path: hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestMORDataSourceWithBucket.scala ########## @@ -0,0 +1,153 @@ +/* + * 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.hudi.functional + +import org.apache.hudi.common.testutils.HoodieTestDataGenerator +import org.apache.hudi.config.{HoodieIndexConfig, HoodieWriteConfig} +import org.apache.hudi.{DataSourceReadOptions, DataSourceWriteOptions, HoodieDataSourceHelpers, MergeOnReadSnapshotRelation} +import org.apache.hudi.common.testutils.RawTripTestPayload.recordsToStrings +import org.apache.hudi.index.HoodieIndex.IndexType +import org.apache.hudi.keygen.constant.KeyGeneratorOptions +import org.apache.hudi.testutils.HoodieClientTestBase +import org.apache.spark.sql._ +import org.apache.spark.sql.execution.datasources.LogicalRelation +import org.junit.jupiter.api.{AfterEach, BeforeEach, Test} +import org.junit.jupiter.api.Assertions.{assertEquals, assertTrue} + +import scala.collection.JavaConversions._ + +/** + * + */ +class TestDataSourceForBucketIndex extends HoodieClientTestBase { Review comment: Could we parameterize an existung test>? ########## File path: hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/index/bucket/HoodieBucketIndexSuite.java ########## @@ -0,0 +1,147 @@ +/* + * 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.hudi.index.bucket; + +import org.apache.avro.Schema; +import org.apache.hudi.common.data.HoodieData; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.testutils.RawTripTestPayload; +import org.apache.hudi.config.HoodieIndexConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.data.HoodieJavaRDD; +import org.apache.hudi.exception.HoodieIndexException; +import org.apache.hudi.index.HoodieIndex; +import org.apache.hudi.keygen.constant.KeyGeneratorOptions; +import org.apache.hudi.table.HoodieSparkTable; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.testutils.HoodieClientTestHarness; +import org.apache.hudi.testutils.HoodieSparkWriteableTestTable; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaRDD; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.BeforeEach; +import org.junit.jupiter.api.Test; + +import java.util.Arrays; +import java.util.Properties; +import java.util.UUID; + +import static org.apache.hudi.common.testutils.SchemaTestUtil.getSchemaFromResource; +import static org.junit.jupiter.api.Assertions.assertThrows; +import static org.junit.jupiter.api.Assertions.assertFalse; +import static org.junit.jupiter.api.Assertions.assertTrue; + +public class HoodieBucketIndexSuite extends HoodieClientTestHarness { Review comment: rename ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/SparkBucketIndexPartitioner.java ########## @@ -0,0 +1,126 @@ +/* + * 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.hudi.table.action.commit; + +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Map.Entry; +import java.util.Set; + +import org.apache.hudi.index.bucket.BucketIdentifier; +import scala.Tuple2; + +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecordLocation; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieException; +import org.apache.hudi.index.bucket.HoodieBucketIndex; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.table.WorkloadProfile; +import org.apache.hudi.table.WorkloadStat; + +public class SparkBucketIndexPartitioner<T extends HoodieRecordPayload<T>> extends + SparkHoodiePartitioner<T> { + + private final int numBuckets; + private final String indexKeyField; + private final int totalPartitionPaths; + private final List<String> partitionPaths; + private final Map<String, Integer> partitionPathOffset; + private Map<String, Set<String>> updatePartitionPathFileIds; + + public SparkBucketIndexPartitioner(WorkloadProfile profile, + HoodieEngineContext context, + HoodieTable table, + HoodieWriteConfig config) { + super(profile, table); + if (!(table.getIndex() instanceof HoodieBucketIndex)) { + throw new HoodieException( + " Bucket index partitioner should only be used by BucketIndex other than " + + table.getIndex().getClass().getSimpleName()); + } + this.numBuckets = ((HoodieBucketIndex<T>) table.getIndex()).getNumBuckets(); + this.indexKeyField = config.getBucketIndexHashField(); + this.totalPartitionPaths = profile.getPartitionPaths().size(); + partitionPaths = new ArrayList<>(profile.getPartitionPaths()); + partitionPathOffset = new HashMap<>(); + int i = 0; + for (Object partitionPath : profile.getPartitionPaths()) { + partitionPathOffset.put(partitionPath.toString(), i); + i += numBuckets; + } + assignUpdates(profile); + } + + private void assignUpdates(WorkloadProfile profile) { Review comment: see if we can rewrite these functional style? ########## File path: hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/index/bucket/BucketIdentifierSuite.java ########## @@ -0,0 +1,65 @@ +/* + * 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.hudi.index.bucket; + +import java.util.Arrays; +import java.util.List; + +import org.apache.avro.generic.GenericRecord; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.keygen.KeyGenUtils; +import org.apache.hudi.testutils.KeyGeneratorTestUtilities; +import org.junit.jupiter.api.Test; + +public class BucketIdentifierSuite { Review comment: renaming consistent with other test classes ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/SparkBucketIndexPartitioner.java ########## @@ -0,0 +1,126 @@ +/* + * 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.hudi.table.action.commit; + +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Map.Entry; +import java.util.Set; + +import org.apache.hudi.index.bucket.BucketIdentifier; +import scala.Tuple2; + +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecordLocation; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieException; +import org.apache.hudi.index.bucket.HoodieBucketIndex; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.table.WorkloadProfile; +import org.apache.hudi.table.WorkloadStat; + +public class SparkBucketIndexPartitioner<T extends HoodieRecordPayload<T>> extends + SparkHoodiePartitioner<T> { + + private final int numBuckets; + private final String indexKeyField; + private final int totalPartitionPaths; + private final List<String> partitionPaths; + private final Map<String, Integer> partitionPathOffset; + private Map<String, Set<String>> updatePartitionPathFileIds; Review comment: docs. for these. ########## File path: hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/DataSourceOptions.scala ########## @@ -526,6 +526,12 @@ object DataSourceWriteOptions { .noDefaultValue() .withDocumentation("Mode to choose for Hive ops. Valid values are hms, jdbc and hiveql.") + // bucketSpec: CLUSTERED BY (trace_id) SORTED BY (trace_id ASC) INTO 65536 BUCKETS Review comment: need to think if there are better ways of exposing this config to the user ########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/commit/BaseCommitActionExecutor.java ########## @@ -76,6 +76,10 @@ public BaseCommitActionExecutor(HoodieEngineContext context, HoodieWriteConfig c // TODO : Remove this once we refactor and move out autoCommit method from here, since the TxnManager is held in {@link AbstractHoodieWriteClient}. this.txnManager = new TransactionManager(config, table.getMetaClient().getFs()); this.lastCompletedTxn = TransactionUtils.getLastCompletedTxnInstantAndMetadata(table.getMetaClient()); + if (table.getStorageLayout().operationConstraint(operationType)) { Review comment: Thanks for doing this. the storage layout abstraction is something I wish we added before. but when done with real use-cases, makes it lot easier. ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/commit/SparkHoodiePartitioner.java ########## @@ -0,0 +1,51 @@ +/* + * 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.hudi.table.action.commit; + +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.table.WorkloadProfile; +import org.apache.spark.Partitioner; + +/** + * Packs incoming records to be inserted into buckets (1 bucket = 1 RDD partition). + */ +public abstract class SparkHoodiePartitioner<T extends HoodieRecordPayload<T>> extends Partitioner + implements org.apache.hudi.table.action.commit.Partitioner { + + /** + * Stat for the current workload. Helps in determining inserts, upserts etc. + */ + protected WorkloadProfile profile; + + protected final HoodieTable table; + + public SparkHoodiePartitioner(WorkloadProfile profile, Review comment: wrapping -- 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]
