[
https://issues.apache.org/jira/browse/KYLIN-3442?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16591028#comment-16591028
]
ASF GitHub Bot commented on KYLIN-3442:
---------------------------------------
shaofengshi commented on a change in pull request #204: KYLIN-3442 Fact
distinct columns in Spark
URL: https://github.com/apache/kylin/pull/204#discussion_r212499697
##########
File path:
engine-spark/src/main/java/org/apache/kylin/engine/spark/SparkFactDistinct.java
##########
@@ -0,0 +1,901 @@
+/*
+ * 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.kylin.engine.spark;
+
+import java.io.DataOutputStream;
+import java.io.IOException;
+import java.io.Serializable;
+import java.nio.ByteBuffer;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+import org.apache.commons.cli.Option;
+import org.apache.commons.cli.OptionBuilder;
+import org.apache.commons.cli.Options;
+import org.apache.commons.io.output.ByteArrayOutputStream;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.ArrayPrimitiveWritable;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+import org.apache.hadoop.mapreduce.lib.output.LazyOutputFormat;
+import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
+import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
+import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
+import org.apache.kylin.common.KylinConfig;
+import org.apache.kylin.common.KylinVersion;
+import org.apache.kylin.common.util.AbstractApplication;
+import org.apache.kylin.common.util.Bytes;
+import org.apache.kylin.common.util.BytesUtil;
+import org.apache.kylin.common.util.Dictionary;
+import org.apache.kylin.common.util.HadoopUtil;
+import org.apache.kylin.common.util.OptionsHelper;
+import org.apache.kylin.common.util.StringUtil;
+import org.apache.kylin.cube.CubeInstance;
+import org.apache.kylin.cube.CubeManager;
+import org.apache.kylin.cube.CubeSegment;
+import org.apache.kylin.cube.DimensionRangeInfo;
+import org.apache.kylin.cube.cuboid.CuboidUtil;
+import org.apache.kylin.cube.model.CubeDesc;
+import org.apache.kylin.cube.model.CubeJoinedFlatTableEnrich;
+import org.apache.kylin.dict.DictionaryGenerator;
+import org.apache.kylin.dict.IDictionaryBuilder;
+import org.apache.kylin.engine.EngineFactory;
+import org.apache.kylin.engine.mr.common.AbstractHadoopJob;
+import org.apache.kylin.engine.mr.common.BatchConstants;
+import org.apache.kylin.engine.mr.common.SerializableConfiguration;
+import org.apache.kylin.engine.mr.common.StatisticsDecisionUtil;
+import
org.apache.kylin.engine.mr.steps.FactDistinctColumnsMapper.DictColDeduper;
+import org.apache.kylin.engine.mr.steps.FactDistinctColumnsReducerMapping;
+import org.apache.kylin.engine.mr.steps.SelfDefineSortableKey;
+import org.apache.kylin.job.JoinedFlatTable;
+import org.apache.kylin.measure.BufferedMeasureCodec;
+import org.apache.kylin.measure.hllc.HLLCounter;
+import org.apache.kylin.measure.hllc.RegisterType;
+import org.apache.kylin.metadata.datatype.DataType;
+import org.apache.kylin.metadata.model.TblColRef;
+import org.apache.spark.Partitioner;
+import org.apache.spark.SparkConf;
+import org.apache.spark.TaskContext;
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.Function;
+import org.apache.spark.api.java.function.PairFlatMapFunction;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+import org.apache.spark.sql.SparkSession;
+import org.apache.spark.util.LongAccumulator;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.google.common.base.Preconditions;
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+import com.google.common.collect.Sets;
+import com.google.common.hash.HashFunction;
+import com.google.common.hash.Hasher;
+import com.google.common.hash.Hashing;
+
+import scala.Tuple2;
+import scala.Tuple3;
+
+public class SparkFactDistinct extends AbstractApplication implements
Serializable {
+
+ protected static final Logger logger =
LoggerFactory.getLogger(SparkFactDistinct.class);
+
+ public static final Option OPTION_CUBE_NAME =
OptionBuilder.withArgName(BatchConstants.ARG_CUBE_NAME).hasArg()
+ .isRequired(true).withDescription("Cube
Name").create(BatchConstants.ARG_CUBE_NAME);
+ public static final Option OPTION_META_URL =
OptionBuilder.withArgName("metaUrl").hasArg().isRequired(true)
+ .withDescription("HDFS metadata url").create("metaUrl");
+ public static final Option OPTION_OUTPUT_PATH =
OptionBuilder.withArgName(BatchConstants.ARG_OUTPUT).hasArg()
+ .isRequired(true).withDescription("Cube output
path").create(BatchConstants.ARG_OUTPUT);
+ public static final Option OPTION_SEGMENT_ID =
OptionBuilder.withArgName("segmentId").hasArg().isRequired(true)
+ .withDescription("Cube Segment Id").create("segmentId");
+ public static final Option OPTION_STATS_SAMPLING_PERCENT = OptionBuilder
+
.withArgName(BatchConstants.ARG_STATS_SAMPLING_PERCENT).hasArg().isRequired(true)
+ .withDescription("Statistics sampling
percent").create(BatchConstants.ARG_STATS_SAMPLING_PERCENT);
+ public static final Option OPTION_INPUT_TABLE =
OptionBuilder.withArgName("hiveTable").hasArg().isRequired(true)
+ .withDescription("Hive Intermediate Table").create("hiveTable");
+ public static final Option OPTION_INPUT_PATH =
OptionBuilder.withArgName(BatchConstants.ARG_INPUT).hasArg()
+ .isRequired(true).withDescription("Hive Intermediate Table
PATH").create(BatchConstants.ARG_INPUT);
+
+ private Options options;
+
+ public SparkFactDistinct() {
+ options = new Options();
+ options.addOption(OPTION_CUBE_NAME);
+ options.addOption(OPTION_META_URL);
+ options.addOption(OPTION_OUTPUT_PATH);
+ options.addOption(OPTION_INPUT_TABLE);
+ options.addOption(OPTION_INPUT_PATH);
+ options.addOption(OPTION_SEGMENT_ID);
+ options.addOption(OPTION_STATS_SAMPLING_PERCENT);
+ }
+
+ @Override
+ protected Options getOptions() {
+ return options;
+ }
+
+ @Override
+ protected void execute(OptionsHelper optionsHelper) throws Exception {
+ String cubeName = optionsHelper.getOptionValue(OPTION_CUBE_NAME);
+ String metaUrl = optionsHelper.getOptionValue(OPTION_META_URL);
+ String segmentId = optionsHelper.getOptionValue(OPTION_SEGMENT_ID);
+ String hiveTable = optionsHelper.getOptionValue(OPTION_INPUT_TABLE);
+ String inputPath = optionsHelper.getOptionValue(OPTION_INPUT_PATH);
+ String outputPath = optionsHelper.getOptionValue(OPTION_OUTPUT_PATH);
+ int samplingPercent =
Integer.parseInt(optionsHelper.getOptionValue(OPTION_STATS_SAMPLING_PERCENT));
+
+ Class[] kryoClassArray = new Class[] {
Class.forName("scala.reflect.ClassTag$$anon$1"),
Class.forName("org.apache.kylin.engine.mr.steps.SelfDefineSortableKey") };
+
+ SparkConf conf = new SparkConf().setAppName("Fact distinct columns
for:" + cubeName + " segment " + segmentId);
+ //serialization conf
+ conf.set("spark.serializer",
"org.apache.spark.serializer.KryoSerializer");
+ conf.set("spark.kryo.registrator",
"org.apache.kylin.engine.spark.KylinKryoRegistrator");
+ conf.set("spark.kryo.registrationRequired",
"true").registerKryoClasses(kryoClassArray);
+
+ KylinSparkJobListener jobListener = new KylinSparkJobListener();
+ JavaSparkContext sc = new JavaSparkContext(conf);
+ sc.sc().addSparkListener(jobListener);
+ HadoopUtil.deletePath(sc.hadoopConfiguration(), new Path(outputPath));
+
+ final SerializableConfiguration sConf = new
SerializableConfiguration(sc.hadoopConfiguration());
+ KylinConfig envConfig =
AbstractHadoopJob.loadKylinConfigFromHdfs(sConf, metaUrl);
+
+ final CubeInstance cubeInstance =
CubeManager.getInstance(envConfig).getCube(cubeName);
+
+ final Job job = Job.getInstance(sConf.get());
+
+ final FactDistinctColumnsReducerMapping reducerMapping = new
FactDistinctColumnsReducerMapping(cubeInstance);
+
+ logger.info("RDD Output path: {}", outputPath);
+ logger.info("getTotalReducerNum: {}",
reducerMapping.getTotalReducerNum());
+ logger.info("getCuboidRowCounterReducerNum: {}",
reducerMapping.getCuboidRowCounterReducerNum());
+
+ final JavaRDD<String[]> recordRDD;
+
+ boolean isSequenceFile =
JoinedFlatTable.SEQUENCEFILE.equalsIgnoreCase(envConfig.getFlatTableStorageFormat());
+
+ logger.info("isSequenceFile {}", isSequenceFile);
+
+ // calculate source record bytes size
+ final LongAccumulator bytesWritten = sc.sc().longAccumulator();
+
+ if (isSequenceFile) {
Review comment:
This piece of code can be reused with SparkCubingByLayer, please extract
them to a common place like SparkUtil.java
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> Fact distinct columns in Spark
> ------------------------------
>
> Key: KYLIN-3442
> URL: https://issues.apache.org/jira/browse/KYLIN-3442
> Project: Kylin
> Issue Type: Improvement
> Components: Spark Engine
> Reporter: Shaofeng SHI
> Assignee: Chao Long
> Priority: Major
> Fix For: v2.5.0
>
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
