spark日志+hivesql

windows本地读取hive，需要在resource里面将集群中的hive-site.xml下载下来。

<?xml version="1.0" encoding="UTF-8"?>

<!--Autogenerated by Cloudera Manager-->

<configuration>

  <property>

    <name>hive.metastore.local</name>

    <value>false</value>

  </property>

  <property>

    <name>hive.metastore.uris</name>

    <value>thrift://bn00:9083</value>

  </property>

  <property>

    <name>hive.metastore.client.socket.timeout</name>

    <value>300</value>

  </property>

  <property>

    <name>hive.metastore.warehouse.dir</name>

    <value>/user/hive/warehouse</value>

  </property>

  <property>

    <name>hive.warehouse.subdir.inherit.perms</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.auto.convert.join</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.auto.convert.join.noconditionaltask.size</name>

    <value>20971520</value>

  </property>

  <property>

    <name>hive.optimize.bucketmapjoin.sortedmerge</name>

    <value>false</value>

  </property>

  <property>

    <name>hive.smbjoin.cache.rows</name>

    <value>10000</value>

  </property>

  <property>

    <name>hive.server2.logging.operation.enabled</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.server2.logging.operation.log.location</name>

    <value>/var/log/hive/operation_logs</value>

  </property>

  <property>

    <name>mapred.reduce.tasks</name>

    <value>-1</value>

  </property>

  <property>

    <name>hive.exec.reducers.bytes.per.reducer</name>

    <value>67108864</value>

  </property>

  <property>

    <name>hive.exec.copyfile.maxsize</name>

    <value>33554432</value>

  </property>

  <property>

    <name>hive.exec.reducers.max</name>

    <value>1099</value>

  </property>

  <property>

    <name>hive.vectorized.groupby.checkinterval</name>

    <value>4096</value>

  </property>

  <property>

    <name>hive.vectorized.groupby.flush.percent</name>

    <value>0.1</value>

  </property>

  <property>

    <name>hive.compute.query.using.stats</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.vectorized.execution.enabled</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.vectorized.execution.reduce.enabled</name>

    <value>false</value>

  </property>

  <property>

    <name>hive.merge.mapfiles</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.merge.mapredfiles</name>

    <value>false</value>

  </property>

  <property>

    <name>hive.cbo.enable</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.fetch.task.conversion</name>

    <value>minimal</value>

  </property>

  <property>

    <name>hive.fetch.task.conversion.threshold</name>

    <value>268435456</value>

  </property>

  <property>

    <name>hive.limit.pushdown.memory.usage</name>

    <value>0.1</value>

  </property>

  <property>

    <name>hive.merge.sparkfiles</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.merge.smallfiles.avgsize</name>

    <value>16777216</value>

  </property>

  <property>

    <name>hive.merge.size.per.task</name>

    <value>268435456</value>

  </property>

  <property>

    <name>hive.optimize.reducededuplication</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.optimize.reducededuplication.min.reducer</name>

    <value>4</value>

  </property>

  <property>

    <name>hive.map.aggr</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.map.aggr.hash.percentmemory</name>

    <value>0.5</value>

  </property>

  <property>

    <name>hive.optimize.sort.dynamic.partition</name>

    <value>false</value>

  </property>

  <property>

    <name>hive.execution.engine</name>

    <value>mr</value>

  </property>

  <property>

    <name>spark.executor.memory</name>

    <value>1277794713</value>

  </property>

  <property>

    <name>spark.driver.memory</name>

    <value>966367641</value>

  </property>

  <property>

    <name>spark.executor.cores</name>

    <value>6</value>

  </property>

  <property>

    <name>spark.yarn.driver.memoryOverhead</name>

    <value>102</value>

  </property>

  <property>

    <name>spark.yarn.executor.memoryOverhead</name>

    <value>135</value>

  </property>

  <property>

    <name>spark.dynamicAllocation.enabled</name>

    <value>true</value>

  </property>

  <property>

    <name>spark.dynamicAllocation.initialExecutors</name>

    <value>1</value>

  </property>

  <property>

    <name>spark.dynamicAllocation.minExecutors</name>

    <value>1</value>

  </property>

  <property>

    <name>spark.dynamicAllocation.maxExecutors</name>

    <value>2147483647</value>

  </property>

  <property>

    <name>hive.metastore.execute.setugi</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.support.concurrency</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.zookeeper.quorum</name>

    <value>bn00,bn01,bn02</value>

  </property>

  <property>

    <name>hive.zookeeper.client.port</name>

    <value>2181</value>

  </property>

  <property>

    <name>hive.zookeeper.namespace</name>

    <value>hive_zookeeper_namespace_hive</value>

  </property>

  <property>

    <name>hbase.zookeeper.quorum</name>

    <value>bn00,bn01,bn02</value>

  </property>

  <property>

    <name>hbase.zookeeper.property.clientPort</name>

    <value>2181</value>

  </property>

  <property>

    <name>hive.cluster.delegation.token.store.class</name>

    <value>org.apache.hadoop.hive.thrift.MemoryTokenStore</value>

  </property>

  <property>

    <name>hive.server2.enable.doAs</name>

    <value>true</value>

  </property>

  <property>

    <name>hive.server2.use.SSL</name>

    <value>false</value>

  </property>

  <property>

    <name>spark.shuffle.service.enabled</name>

    <value>true</value>

  </property>

</configuration>

代码部分如下：

import java.util.ArrayList;

import java.util.List;

import org.apache.log4j.Level;

import org.apache.logging.log4j.LogManager;

import org.apache.logging.log4j.Logger;

import org.apache.spark.SparkConf;

import org.apache.spark.api.java.JavaRDD;

import org.apache.spark.api.java.function.FlatMapFunction;

import org.apache.spark.api.java.function.Function;

import org.apache.spark.api.java.function.Function2;

import org.apache.spark.api.java.function.PairFunction;

import org.apache.spark.api.java.function.VoidFunction;

import org.apache.spark.sql.DataFrame;

import org.apache.spark.sql.Row;

import org.apache.spark.sql.RowFactory;

import org.apache.spark.sql.SQLContext;

import org.apache.spark.sql.hive.HiveContext;

import org.apache.spark.sql.types.DataTypes;

import org.apache.spark.sql.types.StructField;

import org.apache.spark.sql.types.StructType;

import org.apache.spark.streaming.Durations;

import org.apache.spark.streaming.api.java.JavaDStream;

import org.apache.spark.streaming.api.java.JavaStreamingContext;

import scala.Tuple2;

import com.google.common.collect.Lists;

public class HiveAndSparkSQLApp {

	private static final Logger logger = LogManager.getLogger(App.class);

	static {

		// 设置日志级别清理

		org.apache.log4j.Logger.getLogger("org.apache.spark").setLevel(Level.WARN);

		org.apache.log4j.Logger.getLogger("org.eclipse.jetty.server").setLevel(Level.OFF);

	}

	@SuppressWarnings("serial")

	public static void main(String[] args) {

		// 调试环境,spark UI:http://localhost:4040/executors/

		SparkConf conf = new SparkConf().setMaster("local[4]").setAppName("test")

				.set("spark.testing.memory", "1147480000");

		// spark streaming context

		JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(5));

		// spark hive context

		final HiveContext hiveContext = new HiveContext(jssc.sparkContext());

		// spark SQL context

//		final SQLContext sqlContext = SQLContext.getOrCreate(jssc.sparkContext().sc());

		/**

		 *  远程的socket监听

		 *  在节点上，执行nc -lk 9998

		 *  若节点上没有安装nc工具，执行yum install nc.x86_64

		 *  之后直接发送消息即可

		 */

		JavaDStream<String> lines = jssc.socketTextStream("node0", 9998);

		lines.foreachRDD(new VoidFunction<JavaRDD<String>>() {

			@Override

			public void call(JavaRDD<String> rdd) throws Exception {

				// SQLContext sqlContext = SQLContext.getOrCreate(rdd.context());

				JavaRDD<Row> rowRDD = rdd.map(new Function<String, Row>() {

					@Override

					public Row call(String t) throws Exception {

						String[] splited = new String[] { System.currentTimeMillis() + "",

								System.currentTimeMillis() + "", System.currentTimeMillis() + "" };

						// 1.Row构建

						return RowFactory.create(Long.valueOf(splited[0]), splited[1], Long.valueOf(splited[2]));

					}

				});

				// 2.DF metadata专用结构体

				// 对Row具体指定元数据信息。

				List<StructField> structFields = new ArrayList<StructField>();

				// 列名称 列的具体类型（Integer Or String） 是否为空一般为true，实际在开发环境是通过for循环，而不是手动添加

				structFields.add(DataTypes.createStructField("id", DataTypes.LongType, true));

				structFields.add(DataTypes.createStructField("name", DataTypes.StringType, true));

				structFields.add(DataTypes.createStructField("age", DataTypes.LongType, true));

				// 构建StructType,用于最后DataFrame元数据的描述

				StructType structType = DataTypes.createStructType(structFields);

				// 3.构建DF

				DataFrame personsDF = hiveContext.createDataFrame(rowRDD, structType);

				// 4.注册为临时表

				personsDF.registerTempTable("test");

				DataFrame result = hiveContext.sql("select * from test");

				/**

				* 对结果进行处理，包括由DataFrame转换成为RDD<Row>,以及结果的持久化

				*/

				List<Row> listRow = result.javaRDD().collect();

				for (Row row : listRow) {

					logger.error("row:" + row);

				}

				hiveContext.sql("insert into recommendation_system.t111  select id from test");

			}

		});

		// 测试流，需要存在感~

		lines.flatMap(new FlatMapFunction<String, String>() {

			public Iterable<String> call(String msg) {

				System.err.println(msg);

				logger.error(msg);

				return Lists.newArrayList(" ".split(msg));

			}

		}).mapToPair(new PairFunction<String, String, Integer>() {

			@Override

			public Tuple2<String, Integer> call(String t) throws Exception {

				return new Tuple2<String, Integer>(t, 1);

			}

		}).reduceByKey(new Function2<Integer, Integer, Integer>() {

			@Override

			public Integer call(Integer v1, Integer v2) throws Exception {

				return v1 + v2;

			}

		}).print();

		jssc.start();

		jssc.awaitTermination();

	}

}

spark日志+hivesql的更多相关文章

Spark日志级别修改
摘要在学习使用Spark的过程中,总是想对内部运行过程作深入的了解,其中DEBUG和TRACE级别的日志可以为我们提供详细和有用的信息,那么如何进行合理设置呢,不复杂但也绝不是将一个INFO换为TR ...
Spark日志，及设置日志输出级别
Spark日志,及设置日志输出级别 1.全局应用设置 2.局部应用设置日志输出级别 3.Spark log4j.properties配置详解与实例(摘录于铭霏的记事本) 文章内容来源: 作者:大葱拌豆 ...
开启spark日志聚集功能
spark监控应用方式: 1)在运行过程中可以通过web Ui:4040端口进行监控 2)任务运行完成想要监控spark,需要启动日志聚集功能开启日志聚集功能方法: 编辑conf/spark-env ...
Spark日志清洗
日志数据清洗,主要采用spark 的定时任务,清洗出有效数据,并保存到hive数据仓库中存储.常用流程如下: 参考:https://gaojianhua.gitbooks.io/bigdata-wik ...
(转）spark日志配置
一.第一部分 1.spark2.1与hadoop2.7.3集成,spark on yarn模式下,需要对hadoop的配置文件yarn-site.xml增加内容,如下: <property> ...
spark日志配置及问题排查方式。
此文已由作者岳猛授权网易云社区发布. 欢迎访问网易云社区,了解更多网易技术产品运营经验. 任何时候日志都是定位问题的关键,spark也不会例外,合适的配置和获取spark的driver,am,及exe ...
设置Spark日志级别
编辑Spark中conf中配置文件log4j.properties 设置日志级别为WARN,即:log4j.rootCategory=WARN, console
Apache Spark技术实战之9 -- 日志级别修改
摘要在学习使用Spark的过程中,总是想对内部运行过程作深入的了解,其中DEBUG和TRACE级别的日志可以为我们提供详细和有用的信息,那么如何进行合理设置呢,不复杂但也绝不是将一个INFO换为TR ...
Spark2.3（四十）：如何使用java通过yarn api调度spark app，并根据appId监控任务，关闭任务，获取任务日志
背景: 调研过OOZIE和AZKABA,这种都是只是使用spark-submit.sh来提交任务,任务提交上去之后获取不到ApplicationId,更无法跟踪spark application的任务 ...

随机推荐

HGOI20190809 省常中互测2
Problem A 时之终结构造一个含有$n$个节点的无重边无自环的有向图, 使得从$1$出发,每一次经过一条$(u,v) (u < v)$的边到达节点$n$的方案恰好有$y$种. 对于$10 ...
Springboot(九).多文件上传下载文件(并将url存入数据库表中)
一．文件上传这里我们使用request.getSession().getServletContext().getRealPath("/static")的方式来设置文件的存储 ...
mui 二维码扫描功能
mui 扫一扫识别二维码以及多次扫码后从结果页返回时黑屏问题解决扫一扫页面全部代码 <!doctype html><html> <head> ...
[CSP-S模拟测试]:最大值（数学+线段树）
题目背景 $Maxtir$最喜欢最大值. 题目传送门(内部题128) 输入格式第$1$行输入四个正整数$n,m,q$. 第$2$至$n+1$行中,第$i+1$行输入魔法晶石$i$的三种属性$(x_i ...
jQuery动态添加和删除表格行
<!DOCTYPE html> <html> <head> <meta charset="utf-8"> <meta name ...
spark中使用的内存文件系统-Tachyon FS 简介
转自:http://blog.csdn.net/u014252240/article/details/41810849 发布人:南京大学PASA大数据实验室顾荣 1. Tachyon是什么 Tach ...
datagrid数据清空
方法一: 不管是url方式还是加载本地数据的方式,均可以直接使用loadData方法清空数据,一行代码就可以清空: $('#tt').datagrid('loadData',{total:0,rows ...
自定义view防支付成功页面
package com.loaderman.customviewdemo; import android.content.Context; import android.graphics.Canvas ...
python UI自动化之JS定位
1.话不多说,直接贴入代码上面的 document.getElementById 可以替换成别的定位方式,比如: 通过name获取:document.getElementsByName 通过标签获取 ...
linux计划crontab
linux计划crontab 启动crontab服务一般启动服务用 /sbin/service crond start 若是根用户的cron服务可以用 sudo service crond sta ...

spark日志+hivesql

spark日志+hivesql的更多相关文章

随机推荐

热门专题