You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by GitBox <gi...@apache.org> on 2021/08/13 03:39:02 UTC
[GitHub] [hudi] vinothchandar commented on a change in pull request #3433: [HUDI-1897] Deltastreamer source for AWS S3
vinothchandar commented on a change in pull request #3433:
URL: https://github.com/apache/hudi/pull/3433#discussion_r688220583
##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CloudObjectsHoodieIncrSource.java
##########
@@ -0,0 +1,129 @@
+/*
+ * 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.utilities.sources;
+
+import org.apache.hudi.DataSourceReadOptions;
+import org.apache.hudi.DataSourceUtils;
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+import org.apache.hudi.utilities.sources.helpers.IncrSourceHelper;
+
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.DataFrameReader;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+/**
+ * Cloud Objects Hoodie Incr Source Class. {@link CloudObjectsHoodieIncrSource}.This source will use
+ * the cloud files meta information form cloud meta hoodie table generate by CloudObjectsMetaSource.
+ */
+public class CloudObjectsHoodieIncrSource extends HoodieIncrSource {
Review comment:
again, does the schema work in general for any cloud store? if not, we can call this just S3EventsHoodieIncrSource or sth
##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CloudObjectsDfsSource.java
##########
@@ -0,0 +1,87 @@
+/*
+ * 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.utilities.sources;
+
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+import org.apache.hudi.utilities.sources.helpers.CloudObjectsDfsSelector;
+
+import com.amazonaws.services.sqs.AmazonSQS;
+import com.amazonaws.services.sqs.model.Message;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * This source provides capability to create the hoodie table from cloudObject data (eg. s3 events).
+ * It will primarily use cloud queue to fetch new object information and update hoodie table with
+ * cloud object data.
+ */
+public class CloudObjectsDfsSource extends RowSource {
Review comment:
lets call this `S3EventSource` or `S3ActivitySource`? something specific to S3? It does not work with cloud object stores in general or sth right
##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CloudObjectsHoodieIncrSource.java
##########
@@ -0,0 +1,129 @@
+/*
+ * 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.utilities.sources;
+
+import org.apache.hudi.DataSourceReadOptions;
+import org.apache.hudi.DataSourceUtils;
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+import org.apache.hudi.utilities.sources.helpers.IncrSourceHelper;
+
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.DataFrameReader;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+/**
+ * Cloud Objects Hoodie Incr Source Class. {@link CloudObjectsHoodieIncrSource}.This source will use
+ * the cloud files meta information form cloud meta hoodie table generate by CloudObjectsMetaSource.
+ */
+public class CloudObjectsHoodieIncrSource extends HoodieIncrSource {
+
+ private static final Logger LOG = LogManager.getLogger(CloudObjectsHoodieIncrSource.class);
+
+ public CloudObjectsHoodieIncrSource(
+ TypedProperties props,
+ JavaSparkContext sparkContext,
+ SparkSession sparkSession,
+ SchemaProvider schemaProvider) {
+ super(props, sparkContext, sparkSession, schemaProvider);
+ }
+
+ @Override
+ public Pair<Option<Dataset<Row>>, String> fetchNextBatch(
+ Option<String> lastCkptStr, long sourceLimit) {
+
+ DataSourceUtils.checkRequiredProperties(
+ props, Collections.singletonList(Config.HOODIE_SRC_BASE_PATH));
+
+ String srcPath = props.getString(Config.HOODIE_SRC_BASE_PATH);
+ int numInstantsPerFetch =
+ props.getInteger(Config.NUM_INSTANTS_PER_FETCH, Config.DEFAULT_NUM_INSTANTS_PER_FETCH);
+ boolean readLatestOnMissingCkpt =
+ props.getBoolean(
+ Config.READ_LATEST_INSTANT_ON_MISSING_CKPT,
+ Config.DEFAULT_READ_LATEST_INSTANT_ON_MISSING_CKPT);
+
+ // Use begin Instant if set and non-empty
+ Option<String> beginInstant =
+ lastCkptStr.isPresent()
+ ? lastCkptStr.get().isEmpty() ? Option.empty() : lastCkptStr
+ : Option.empty();
+
+ Pair<String, String> instantEndpts =
+ IncrSourceHelper.calculateBeginAndEndInstants(
+ sparkContext, srcPath, numInstantsPerFetch, beginInstant, readLatestOnMissingCkpt);
+
+ if (instantEndpts.getKey().equals(instantEndpts.getValue())) {
+ LOG.warn("Already caught up. Begin Checkpoint was :" + instantEndpts.getKey());
+ return Pair.of(Option.empty(), instantEndpts.getKey());
+ }
+
+ // Do Incr pull. Set end instant if available
+ DataFrameReader reader =
+ sparkSession
+ .read()
+ .format("org.apache.hudi")
+ .option(
+ DataSourceReadOptions.QUERY_TYPE().key(),
+ DataSourceReadOptions.QUERY_TYPE_INCREMENTAL_OPT_VAL())
+ .option(
+ DataSourceReadOptions.BEGIN_INSTANTTIME().key(), instantEndpts.getLeft())
+ .option(
+ DataSourceReadOptions.END_INSTANTTIME().key(), instantEndpts.getRight());
+
+ Dataset<Row> source = reader.load(srcPath);
+
+ // Extract distinct file keys from cloud meta hoodie table
+ final List<Row> cloudMetaDf =
+ source
+ .filter("s3.object.size > 0")
+ .select("s3.bucket.name", "s3.object.key")
+ .distinct()
+ .collectAsList();
+
+ // Create S3 paths
+ List<String> cloudFiles = new ArrayList<>();
+ for (Row row : cloudMetaDf) {
+ String bucket = row.getString(0);
+ String key = row.getString(1);
+ String filePath = "s3://" + bucket + "/" + key;
Review comment:
pull prefix etc into a string constant?
##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CloudObjectsHoodieIncrSource.java
##########
@@ -0,0 +1,129 @@
+/*
+ * 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.utilities.sources;
+
+import org.apache.hudi.DataSourceReadOptions;
+import org.apache.hudi.DataSourceUtils;
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+import org.apache.hudi.utilities.sources.helpers.IncrSourceHelper;
+
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.DataFrameReader;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+/**
+ * Cloud Objects Hoodie Incr Source Class. {@link CloudObjectsHoodieIncrSource}.This source will use
+ * the cloud files meta information form cloud meta hoodie table generate by CloudObjectsMetaSource.
+ */
+public class CloudObjectsHoodieIncrSource extends HoodieIncrSource {
+
+ private static final Logger LOG = LogManager.getLogger(CloudObjectsHoodieIncrSource.class);
+
+ public CloudObjectsHoodieIncrSource(
+ TypedProperties props,
+ JavaSparkContext sparkContext,
+ SparkSession sparkSession,
+ SchemaProvider schemaProvider) {
+ super(props, sparkContext, sparkSession, schemaProvider);
+ }
+
+ @Override
+ public Pair<Option<Dataset<Row>>, String> fetchNextBatch(
+ Option<String> lastCkptStr, long sourceLimit) {
+
+ DataSourceUtils.checkRequiredProperties(
+ props, Collections.singletonList(Config.HOODIE_SRC_BASE_PATH));
+
+ String srcPath = props.getString(Config.HOODIE_SRC_BASE_PATH);
+ int numInstantsPerFetch =
+ props.getInteger(Config.NUM_INSTANTS_PER_FETCH, Config.DEFAULT_NUM_INSTANTS_PER_FETCH);
+ boolean readLatestOnMissingCkpt =
+ props.getBoolean(
+ Config.READ_LATEST_INSTANT_ON_MISSING_CKPT,
+ Config.DEFAULT_READ_LATEST_INSTANT_ON_MISSING_CKPT);
+
+ // Use begin Instant if set and non-empty
+ Option<String> beginInstant =
+ lastCkptStr.isPresent()
+ ? lastCkptStr.get().isEmpty() ? Option.empty() : lastCkptStr
+ : Option.empty();
+
+ Pair<String, String> instantEndpts =
+ IncrSourceHelper.calculateBeginAndEndInstants(
+ sparkContext, srcPath, numInstantsPerFetch, beginInstant, readLatestOnMissingCkpt);
+
+ if (instantEndpts.getKey().equals(instantEndpts.getValue())) {
+ LOG.warn("Already caught up. Begin Checkpoint was :" + instantEndpts.getKey());
+ return Pair.of(Option.empty(), instantEndpts.getKey());
+ }
+
+ // Do Incr pull. Set end instant if available
+ DataFrameReader reader =
Review comment:
I think `metaReader` is okay :) others are implicit from context
##########
File path: hudi-utilities/pom.xml
##########
@@ -402,6 +402,14 @@
<scope>test</scope>
</dependency>
+ <!-- AWS Services -->
+ <!-- https://mvnrepository.com/artifact/com.amazonaws/aws-java-sdk-sqs -->
+ <dependency>
+ <groupId>com.amazonaws</groupId>
+ <artifactId>aws-java-sdk-sqs</artifactId>
+ <version>1.12.22</version>
Review comment:
is this pretty much independent of hadoop versions and such?
##########
File path: hudi-utilities/pom.xml
##########
@@ -402,6 +402,14 @@
<scope>test</scope>
</dependency>
+ <!-- AWS Services -->
+ <!-- https://mvnrepository.com/artifact/com.amazonaws/aws-java-sdk-sqs -->
+ <dependency>
+ <groupId>com.amazonaws</groupId>
+ <artifactId>aws-java-sdk-sqs</artifactId>
+ <version>1.12.22</version>
Review comment:
Can we pull the version into a property. so it can be overridden if needed
##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CloudObjectsMetaSource.java
##########
@@ -0,0 +1,88 @@
+/*
+ * 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.utilities.sources;
+
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+import org.apache.hudi.utilities.sources.helpers.CloudObjectsMetaSelector;
+
+import com.amazonaws.services.sqs.AmazonSQS;
+import com.amazonaws.services.sqs.model.Message;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Encoders;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * This source provides capability to create the hoodie table for cloudObject Metadata (eg. s3
Review comment:
lets please avoid "cloud". its a very broad term. cloud != object storage. ceph is an obj store. minio is an obj store. nothing to do with clould. again, if this will work only with s3. lets just call it that?
##########
File path: hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/CloudObjectsDfsSource.java
##########
@@ -0,0 +1,87 @@
+/*
+ * 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.utilities.sources;
+
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.collection.Pair;
+import org.apache.hudi.utilities.schema.SchemaProvider;
+import org.apache.hudi.utilities.sources.helpers.CloudObjectsDfsSelector;
+
+import com.amazonaws.services.sqs.AmazonSQS;
+import com.amazonaws.services.sqs.model.Message;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * This source provides capability to create the hoodie table from cloudObject data (eg. s3 events).
+ * It will primarily use cloud queue to fetch new object information and update hoodie table with
+ * cloud object data.
+ */
+public class CloudObjectsDfsSource extends RowSource {
+
+ private final CloudObjectsDfsSelector pathSelector;
Review comment:
same with this class
--
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: commits-unsubscribe@hudi.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org