下面的代码将从hbase读取,然后将其转换为json结构并转换为schemaRDD,但问题是我using List要存储json字符串然后传递给javaRDD,对于大约100 GB的数据,master将被加载内存中的数据.从hbase加载数据然后执行操作然后转换为JavaRDD的正确方法是什么.
package hbase_reader;
import java.io.IOException;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.List;
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.rdd.RDD;
import org.apache.spark.sql.api.java.JavaSQLContext;
import org.apache.spark.sql.api.java.JavaSchemaRDD;
import org.apache.commons.cli.ParseException;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableInputFormat;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.Text;
import org.apache.spark.SparkConf;
import scala.Function1;
import scala.Tuple2;
import scala.runtime.AbstractFunction1;
import com.google.common.collect.Lists;
public class hbase_reader {
public static void main(String[] args) throws IOException, ParseException {
List<String> jars = Lists.newArrayList("");
SparkConf spconf = new …