調(diào)試環(huán)境

調(diào)試環(huán)境

我使用的調(diào)試的環(huán)境是:

  • idea
  • sqoop 1.99.6

調(diào)試使用的代碼

  /**
 * Created by zj on 16-6-24.
 */
import org.apache.sqoop.client.SqoopClient;
import org.apache.sqoop.model.*;
import org.apache.sqoop.validation.*;   //for status class
import org.apache.sqoop.submission.counter.*;

import java.util.Collections;
import java.util.*;

public class DT {

    //a helper function . so that user has to iterate the list of validation messages.
    // printMessage(link.getConnectorLinkConfig().getConfigs());
    private static void printMessage(List<MConfig> configs) {
        for (MConfig config : configs) {
            List<MInput<?>> inputlist = config.getInputs();
            if (config.getValidationMessages() != null) {
                // print every validation message
                for (Message message : config.getValidationMessages()) {
                    System.out.println("Config validation message: " + message.getMessage());
                }
            }
            for (MInput minput : inputlist) {
                if (minput.getValidationStatus() == Status.WARNING) {
                    for (Message message : config.getValidationMessages()) {
                        System.out.println("Config Input Validation Warning: " + message.getMessage());
                    }
                } else if (minput.getValidationStatus() == Status.ERROR) {
                    for (Message message : config.getValidationMessages()) {
                        System.out.println("Config Input Validation Error: " + message.getMessage());
                    }
                }
            }
        }
    }

    public static void main(String [] args){
        //Initialization
        String url = "http://localhost:12000/sqoop/";
        SqoopClient client = new SqoopClient(url);


        Collection<MConnector> connectorCollections=client.getConnectors();
        for(MConnector mc: connectorCollections) {
            System.out.println(mc.getUniqueName());
            System.out.println(mc.getClassName());
            System.out.println(mc.getPersistenceId());
        }

 /* I have create the link before, and the link object is persisted in the database of derby
        // create a placeholder for link
        long connectorId = 1;
        MLink link = client.createLink(connectorId);
        link.setName("mysql_link");
        link.setCreationUser("zjlearn");
        MLinkConfig linkConfig = link.getConnectorLinkConfig();

        // fill in the link config values
        linkConfig.getStringInput("linkConfig.connectionString").setValue("jdbc:mysql://localhost/my");
        linkConfig.getStringInput("linkConfig.jdbcDriver").setValue("com.mysql.jdbc.Driver");
        linkConfig.getStringInput("linkConfig.username").setValue("root");
        linkConfig.getStringInput("linkConfig.password").setValue("root");



        // save the link object that was filled
        Status status = client.saveLink(link);
        if(status.canProceed()) {
            System.out.println("Created Link with Link Id : " + link.getPersistenceId());
        } else {
            System.out.println("Something went wrong creating the link");
        }
        //create the link2
        long connectorId2 = 2;
        MLink link2 = client.createLink(connectorId2);
        link2.setName("hdfs_link");
        link2.setCreationUser("zjlearn");
        MLinkConfig linkConfig2 = link.getConnectorLinkConfig();

        // fill in the link config values ,  for hdfs connector


        // save the link object that was filled
        Status status2 = client.saveLink(link);
        if(status2.canProceed()) {
            System.out.println("Created Link with Link Id : " + link2.getPersistenceId());
        } else {
            System.out.println("Something went wrong creating the link");
        }
        */



        //create  the job
        //Creating dummy job object
        long fromLinkId = 1;// link for jdbc connector
        long toLinkId = 2; // link for HDFS connector
        MJob job = client.createJob(fromLinkId, toLinkId);
        job.setName("mysql_hafs_dt");
        job.setCreationUser("zjlearn");
        // set the "FROM" link job config values
        MFromConfig fromJobConfig = job.getFromJobConfig();
        fromJobConfig.getStringInput("fromJobConfig.schemaName").setValue("sqoop");
        fromJobConfig.getStringInput("fromJobConfig.tableName").setValue("sqoop");
        fromJobConfig.getStringInput("fromJobConfig.partitionColumn").setValue("id");
        // set the "TO" link job config values
        MToConfig toJobConfig = job.getToJobConfig();
        toJobConfig.getStringInput("toJobConfig.outputDirectory").setValue("/usr/tmp");
        // set the driver config values
        MDriverConfig driverConfig = job.getDriverConfig();
        driverConfig.getStringInput("throttlingConfig.numExtractors").setValue("3");

        Status status3 = client.saveJob(job);
        if(status3.canProceed()) {
            System.out.println("Created Job with Job Id: "+ job.getPersistenceId());
        } else {
            System.out.println("Something went wrong creating the job");
        }

        //start the job
        long jobId= job.getPersistenceId();
        MSubmission Jobsubmission = client.startJob(jobId);
        System.out.println("Job Submission Status : " + Jobsubmission.getStatus());
        if(Jobsubmission.getStatus().isRunning() && Jobsubmission.getProgress() != -1) {
            System.out.println("Progress : " + String.format("%.2f %%", Jobsubmission.getProgress() * 100));
        }
        System.out.println("Hadoop job id :" + Jobsubmission.getExternalJobId());  //the method has change  getExternalJobId
        System.out.println("Job link : " + Jobsubmission.getExternalLink());
        Counters counters = Jobsubmission.getCounters();
        if(counters != null) {
            System.out.println("Counters:");
            for(CounterGroup group : counters) {
                System.out.print("\t");
                System.out.println(group.getName());
                for(Counter counter : group) {
                    System.out.print("\t\t");
                    System.out.print(counter.getName());
                    System.out.print(": ");
                    System.out.println(counter.getValue());
                }
            }
        }
        //there is no method  getExceptionInfo in the Jobsubmission in the sqoop2 but a getErroe method
        if(Jobsubmission.getError() != null) {
            System.out.println("Exception info : " +Jobsubmission.getError());
        }

        //Check job status for a running job
        MSubmission jobStatusSubmission = client.getJobStatus(jobId);
        if(jobStatusSubmission.getStatus().isRunning() && jobStatusSubmission.getProgress() != -1) {
            System.out.println("Progress : " + String.format("%.2f %%", jobStatusSubmission.getProgress() * 100));
        }

        //Stop a running job. there is an error in the web page
        client.stopJob(jobId);

        //get the execute

    }
}

maven依賴

下面是項(xiàng)目使用到的依賴

<dependency>
    <groupId>org.apache.sqoop</groupId>
    <artifactId>sqoop-client</artifactId>
    <version>1.99.6</version>
</dependency>
<dependency>
    <groupId>org.apache.sqoop</groupId>
    <artifactId>sqoop-server</artifactId>
    <version>1.99.6</version>
</dependency>

代碼調(diào)試方法

這部分主要參考

Sqoop2是一個CS的架構(gòu),客戶端包括sqoop-shell和sqoop-client,服務(wù)器端包括sqoop-server,sqoop-server就是一個部署在Tomcat下的web應(yīng)用,由幾個servlet組成。

調(diào)試sqoop-shell

調(diào)試sqoop-shell就是在啟動sqoop client main方法時,加上調(diào)試參數(shù)。

sqoop-shell的啟動方式為:sqoop.sh client,找到解決問題的起點(diǎn),查找sqoop.sh腳本,在其中找到這樣一段:

  client)
    # Build class path with full path to each library
    for f in $CLIENT_LIB/*.jar; do
      CLASSPATH="${CLASSPATH}:$f"
    done

    EXEC_JAVA='java'
    if [ -n "${JAVA_HOME}" ] ; then
        EXEC_JAVA="${JAVA_HOME}/bin/java"
    fi
    ${EXEC_JAVA} -classpath ${CLASSPATH} org.apache.sqoop.shell.SqoopShell $2
    ;;

這一部分的代碼是運(yùn)行sqoop.sh client 命令時將會執(zhí)行的代碼??梢钥吹剑?/p>

${EXEC_JAVA} -classpath ${CLASSPATH} org.apache.sqoop.shell.SqoopShell $2,

這行shell腳本就是啟動sqoop客戶端的main方法的地方了,在其中加入:

-Xdebug -Xnoagent-Xrunjdwp:transport=dt_socket,address=8199,server=y,suspend=n

這一行代碼成了下面這樣:

${EXEC_JAVA} -classpath ${CLASSPATH} -Xdebug-Xnoagent -Xrunjdwp:transport=dt_socket,address=8199,server=y,suspend=norg.apache.sqoop.shell.SqoopShell $2

** 注意,放到一行里,不要換行。Server不是指的IP。**

參數(shù)說明:
-Xdebug : 啟用調(diào)試模式
-Xrunjdwp<sub-options> : 加載JVM的JPDA參考實(shí)現(xiàn)庫
transport=dt_socket :Socket連接,可選dt_shmem 通過共享內(nèi)存的方式連接到調(diào)試服務(wù)器
address=8000 :調(diào)試服務(wù)器監(jiān)聽的端口
server=y : 是否是服務(wù)器端,n為客戶端
suspend=n : 啟動過程是否加載暫停,y為啟動時暫停,方便調(diào)試啟動過程

參數(shù)具體的意義可以查看相關(guān)文檔,IBM上有個系列的文章,是專門講JAVA的調(diào)試體系的,叫做《深入 Java 調(diào)試體系深入 Java 調(diào)試體系深入JAVA調(diào)試體系》,講的很細(xì)很好,相信對于很多人來說,會填補(bǔ)一塊JAVA知識的空白。

這樣就設(shè)置好了,當(dāng)運(yùn)行sqoop.sh client 啟動sqoop shell的時候,會看到輸出中包含下面的內(nèi)容:

Listening for transport dt_socket ataddress: 8199

在IDE,比如Eclipse里,選擇遠(yuǎn)程調(diào)試,在Eclipse中是Remote Java Application。主要是填程序所在機(jī)器的網(wǎng)絡(luò)地址和端口號,在這個例子中,端口號就是8199。

Eclipse這端開始Debug之后,設(shè)置好斷點(diǎn),然后再Sqoop所在的機(jī)器啟動的sqoopshell中進(jìn)行操作,運(yùn)行到斷點(diǎn),就會停住,在Eclipse這端跟調(diào)試本地程序一樣。

調(diào)試sqoop-server

因?yàn)閟qoop-server就是一個JavaWeb應(yīng)用,所以設(shè)置sqoop-server遠(yuǎn)程調(diào)試,就是設(shè)置Tomcat為遠(yuǎn)程調(diào)試。運(yùn)行Tomcat的catalina.sh命令可以看到,Tomcat已經(jīng)為我們提供了jpda選項(xiàng):(sqoop2的相關(guān)的catalina.sh文件在SQOOP_HOME/server/bin文件夾下面, 運(yùn)行其可以得到如下的信息)

Usage: catalina.sh ( commands ... )
commands:
  debug             Start Catalina in a debugger
  debug -security   Debug Catalina with a security manager
  jpda start        Start Catalina under JPDA debugger
  run               Start Catalina in the current window
  run -security     Start in the current window with security manager
  start             Start Catalina in a separate window
  start -security   Start in a separate window with security manager
  stop              Stop Catalina, waiting up to 5 seconds for the process to end
  stop n            Stop Catalina, waiting up to n seconds for the process to end
  stop -force       Stop Catalina, wait up to 5 seconds and then use kill -KILL if still running
  stop n -force     Stop Catalina, wait up to n seconds and then use kill -KILL if still running
  version           What version of tomcat are you running?
Note: Waiting for the process to end and use of the -force option require that $CATALINA_PID is defined

由于這個內(nèi)置的Tomcat的啟動是由sqoop.sh腳本控制的,啟動命令如下:

sqoop.sh server start

于是去查看sqoop.sh腳本的代碼,找到如下部分:

 server)
    if [ $# = 1 ]; then
      echo "Usage: sqoop.sh server <start/stop>"
      exit
    fi
    actionCmd=$2

    source ${BASEDIR}/bin/sqoop-sys.sh
    setup_catalina_opts

    # There seems to be a bug in catalina.sh whereby catalina.sh doesn't respect
    # CATALINA_OPTS when stopping the tomcat server. Consequently, we have to hack around
    # by specifying the CATALINA_OPTS properties in JAVA_OPTS variable
    if [ "$actionCmd" == "stop" ]; then
      export JAVA_OPTS="$JAVA_OPTS $CATALINA_OPTS"
    fi

    # Remove the first 2 command line arguments (server and action command (start/stop)) so we can pass
    # the rest to catalina.sh script
    shift
    shift

    $CATALINA_BIN/catalina.sh $actionCmd "$@"
    ;;

從sqoop.sh server start命令來看,actionCmd就是start了,也就是說,sqoop.sh server start命令最終執(zhí)行catalina.sh命令時是傳入的start,即catalina.sh start。我們想運(yùn)行:

catalina.sh jpda start

于是把原來

$CATALINA_BIN/catalina.sh $actionCmd "$@"

這行腳本的中直接加入jpda,最終的腳本為:

$CATALINA_BIN/catalina.sh jpda $actionCmd"$@"

上邊我們設(shè)置sqoop shell 的jpda的時候,是在JVM啟動時加入?yún)?shù),但是從catalina.sh打印出的幫助信息來看,沒有傳入?yún)?shù)的地方,想到可能是在配置文件或者腳本中有環(huán)境變量:

最后在catalina.sh中找到下面的配置:

if [ "$1" = "jpda" ] ; then
  if [ -z "$JPDA_TRANSPORT" ]; then
    JPDA_TRANSPORT="dt_socket"
  fi
  if [ -z "$JPDA_ADDRESS" ]; then
    JPDA_ADDRESS="8000"
  fi
  if [ -z "$JPDA_SUSPEND" ]; then
    JPDA_SUSPEND="n"
  fi
  if [ -z "$JPDA_OPTS" ]; then
    JPDA_OPTS="-agentlib:jdwp=transport=$JPDA_TRANSPORT,address=$JPDA_ADDRESS,server=y,suspend=$JPDA_SUSPEND"
  fi
  CATALINA_OPTS="$CATALINA_OPTS $JPDA_OPTS"
  shift
fi

這是默認(rèn)的配置,也可以自己更改。

完成上邊的配置后,在Eclipse這端,調(diào)試sqoop-server項(xiàng)目,Remote Java Application,填上遠(yuǎn)程JVM地址,端口號,這個例子中是8000,點(diǎn)擊debug就可以了。

最后編輯于
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請聯(lián)系作者
【社區(qū)內(nèi)容提示】社區(qū)部分內(nèi)容疑似由AI輔助生成,瀏覽時請結(jié)合常識與多方信息審慎甄別。
平臺聲明:文章內(nèi)容(如有圖片或視頻亦包括在內(nèi))由作者上傳并發(fā)布,文章內(nèi)容僅代表作者本人觀點(diǎn),簡書系信息發(fā)布平臺,僅提供信息存儲服務(wù)。

相關(guān)閱讀更多精彩內(nèi)容

友情鏈接更多精彩內(nèi)容