初學spark，學習使用jdbcRDD獲取mysql中的資料，通過maven打包上傳到集群，spark-submit之后，在任務開始執行后直接拋出了"java.lang.ClassNotFoundException: com.mysql.jdbc.exceptions.jdbc4.MySQLSyntaxErrorException"：
java.lang.ClassNotFoundException: com.mysql.jdbc.exceptions.jdbc4.MySQLSyntaxErrorException
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:331)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:67)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1620)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1521)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1781)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:373)
at org.apache.spark.ThrowableSerializationWrapper.readObject(TaskEndReason.scala:167)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1058)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1909)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:373)
at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:72)
at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:98)
at org.apache.spark.scheduler.TaskResultGetter$$anon$3$$anonfun$run$2.apply$mcV$sp(TaskResultGetter.scala:108)
at org.apache.spark.scheduler.TaskResultGetter$$anon$3$$anonfun$run$2.apply(TaskResultGetter.scala:105)
at org.apache.spark.scheduler.TaskResultGetter$$anon$3$$anonfun$run$2.apply(TaskResultGetter.scala:105)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1698)
at org.apache.spark.scheduler.TaskResultGetter$$anon$3.run(TaskResultGetter.scala:105)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
仔細查找了一下這個MySQLSyntaxErrorException類，在maven匯入的依賴包中是存在的。maven的配置：
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.ivifi</groupId>
<artifactId>macMatch-spark</artifactId>
<version>1.0-SNAPSHOT</version>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.10</artifactId>
<version>1.5.0</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.9</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.0.0</version>
<exclusions>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-auth</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-common</artifactId>
<version>1.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.0.0</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.18</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<version>2.2</version>
<configuration>
<archive>
<manifest>
<mainClass>com.ivifi.spark.MysqlTest</mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>
jar-with-dependencies
</descriptorRef>
</descriptorRefs>
</configuration>
</plugin>
</plugins>
</build>
</project>
例外中說的缺少的類是在mysql-connector-java，我查找Maven打的專案jar包，解壓這個jar包發現這個類是打到包里了。
后來想可能不能直接將mysql-connector-java 依賴打包進去？
于是通過spark-submit --jars 選項將mysql-connector-java的jar包作為引數提交：
spark-submit --jars jar/mysql-connector-java-5.1.18.jar --class com.ivifi.spark.MysqlTest macMatch2.jar
但是很可惜，依然是拋出同樣的例外。。。。
專案代碼是個demo：
public class MysqlTest {
public static void main(String...args){
SparkConf sparkConf = new SparkConf().setAppName("MysqlTest");
JavaSparkContext context = new JavaSparkContext(sparkConf);
JdbcRDD<String> jdbcRDD = new JdbcRDD<String>(context.sc(), new ConnFun1(),
"select dev_sn from DEV_INFO where ? <= id and id <= ?",
1,
1000,
2,
new RddFun1(),
ClassManifestFactory$.MODULE$.fromClass(String.class)
);
jdbcRDD.saveAsTextFile("/user/luoshengkai/mysqlTestOut");
}
private static class ConnFun1 extends AbstractFunction0<Connection> implements Serializable{
public Connection apply() {
return MysqlConnectionPool.getConnectionPool().getConntion();
}
}
private static class RddFun1 extends AbstractFunction1<ResultSet,String> implements Serializable{
public String apply(ResultSet v1) {
try {
String devSN = v1.getString(1);
return devSN;
} catch (SQLException e) {
e.printStackTrace();
}
return null;
}
}
}
jdbcRDD的構造方法的引數有些不理解，但是通過網上某博客中看到了引數怎么寫。
spark部署方式是yarn，版本為1.5.0-cdh5.6.1。
uj5u.com熱心網友回復：
是不是驅動版本太低了？換個高版本的試下轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/71155.html
標籤：Spark
下一篇：騰訊云支持遠程桌面嗎？