AWS EMR 7.3 not showing any logs from my java program

my use case is to create an EMR 7.3 in AWS and invoke lambda to http request to pass the configs and payload over to initiate a spark job.

this is my software settings

[
  {
    "Classification": "spark-defaults",
    "Properties": {
      "spark.acls.enable": "false",
      "spark.authenticate": "false",
      "spark.driver.memory": "4g",
      "spark.master": "yarn-cluster",
      "spark.modify.acls": "livy",
      "spark.modify.acls.groups": "",
      "spark.ui.view.acls": "livy",
      "spark.ui.view.acls.groups": ""
    }
  },
  {
    "Classification": "hdfs-site",
    "Properties": {
      "dfs.client.failover.connection.retries": "3",
      "dfs.client.failover.connection.retries.on.timeouts": "3",
      "dfs.datanode.handler.count": "50"
    }
  },
  {
    "Classification": "spark-log4j2",
    "Properties": {
      "logger.IdentifierForClass.level": "info",
      "logger.IdentifierForClass.name": "com.package",
      "rootLogger.level": "info",
      "rootLogger.name": "com.package"
    }
  }
]

my java program pom.xml

<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.pacjage</groupId>
    <artifactId>promobatch</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <packaging>jar</packaging>

    <name>promobatch</name>
    <url>http://maven.apache.org</url>

    <properties>

        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <java.version>17</java.version>

        <scala.version>2.12</scala.version>
        <spark.version>3.5.1</spark.version>
        <postgresql.version>42.7.3</postgresql.version>
        <spark.excel.version>0.20.4</spark.excel.version>
        <spring.version>6.1.14</spring.version>
        <ojdbc.version>19.6.0.0</ojdbc.version>
        <aws.sdk.version>2.25.70</aws.sdk.version>

        <maven.compiler.source>${java.version}</maven.compiler.source>
        <maven.compiler.target>${java.version}</maven.compiler.target>

    </properties>

    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>software.amazon.awssdk</groupId>
                <artifactId>bom</artifactId>
                <version>${aws.sdk.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <dependencies>
        
        <dependency>
            <groupId>software.amazon.awssdk</groupId>
            <artifactId>s3</artifactId>
        </dependency>
        <!-- Spark -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-mllib_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.13.1</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.postgresql</groupId>
            <artifactId>postgresql</artifactId>
            <version>${postgresql.version}</version>
        </dependency>

        <dependency>
            <groupId>com.oracle.database.jdbc</groupId>
            <artifactId>ojdbc8</artifactId>
            <version>${ojdbc.version}</version>
        </dependency>

        <dependency>
            <groupId>com.crealytics</groupId>
            <artifactId>spark-excel_${scala.version}</artifactId>
            <version>${spark.version}_${spark.excel.version}</version>
        </dependency>

        <dependency>
            <groupId>org.springframework</groupId>
            <artifactId>spring-jdbc</artifactId>
            <version>${spring.version}</version>
        </dependency>
        <dependency>
            <groupId>org.springframework</groupId>
            <artifactId>spring-context</artifactId>
            <version>${spring.version}</version>
        </dependency>
        <dependency>
            <groupId>software.amazon.awssdk</groupId>
            <artifactId>kms</artifactId>
            <version>${aws.sdk.version}</version>
        </dependency>
        <dependency>
            <groupId>software.amazon.awssdk</groupId>
            <artifactId>sns</artifactId>
            <version>${aws.sdk.version}</version>
        </dependency>
        
        <dependency>
            <groupId>software.amazon.awssdk</groupId>
            <artifactId>dynamodb</artifactId>
            <version>${aws.sdk.version}</version>
        </dependency>
    </dependencies>

    <build>
        <finalName>emr7-promobatch-0.0.1-SNAPSHOT</finalName>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <plugin>
                <artifactId>maven-jar-plugin</artifactId>
                <version>3.2.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <archive>
                        <manifest>
                            <mainClass>com.package.promobatch.App</mainClass>
                        </manifest>
                    </archive>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

this is my log4j2.properties that located at src/main/resources/log4js.properties

rootLogger.level = info
rootLogger.appenderRef.stdout.ref = Console

appender.console.type = Console
appender.console.name = console
appender.console.target = SYSTEM_ERR
appender.console.layout.type = PatternLayout
appender.console.layout.pattern = %d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n%ex

logger.repl.name = org.apache.spark.repl.Main
logger.repl.level = warn

logger.thriftserver.name = org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver
logger.thriftserver.level = warn

logger.jetty1.name = org.sparkproject.jetty
logger.jetty1.level = warn
logger.jetty2.name = org.sparkproject.jetty.util.component.AbstractLifeCycle
logger.jetty2.level = error
logger.replexprTyper.name = org.apache.spark.repl.SparkIMain$exprTyper
logger.replexprTyper.level = info
logger.replSparkILoopInterpreter.name = org.apache.spark.repl.SparkILoop$SparkILoopInterpreter
logger.replSparkILoopInterpreter.level = info
logger.parquet1.name = org.apache.parquet
logger.parquet1.level = error
logger.parquet2.name = parquet
logger.parquet2.level = error

logger.RetryingHMSHandler.name = org.apache.hadoop.hive.metastore.RetryingHMSHandler
logger.RetryingHMSHandler.level = fatal
logger.FunctionRegistry.name = org.apache.hadoop.hive.ql.exec.FunctionRegistry
logger.FunctionRegistry.level = error

appender.console.filter.1.type = RegexFilter
appender.console.filter.1.regex = .*Thrift error occurred during processing of message.*
appender.console.filter.1.onMatch = deny
appender.console.filter.1.onMismatch = neutral

my java program main class

public class Test {
    private String clusterId;
    private static final String JOB_NAME = "Test";
    private static final Logger logger = LogManager.getLogger(Test.class);

    public Test(String clusterId) {
        logger.info("Dealer Cluster ID: {}", clusterId);
        this.clusterId = clusterId;
    }

    public void start() {
        logger.info("Starting EMR Job");
        SparkSession spark = null;
        AnnotationConfigApplicationContext context = null;

        String topicArnDevOps = "";

        try {
            boolean isEncrypt = true;
            String os = System.getProperty("os.name");
            if (os.startsWith("Windows")) {
                spark = SparkSession.builder().appName(JOB_NAME).master("local").getOrCreate();
                isEncrypt = false;
            } else {
                spark = SparkSession.builder().appName(JOB_NAME).getOrCreate();
                isEncrypt = true;
            }
            configureSparkSession(spark);
            topicArnDevOps = PropertiesConstants.getSns_topic();
            uploadFileToS3();
            
        } catch (Exception e) {
            logger.error("Exception for EMR Job: {}", JOB_NAME, e);
            SNSUtil.sendNotification(topicArnDevOps, String.format("EMR Job %s was failed. Kindly check logs for Cluster Id: %s. Exception: %s", JOB_NAME, clusterId, e.toString()));
        } finally {
            closeResources(spark, context);
        }
    }

    private void configureSparkSession(SparkSession spark) {
        spark.conf().set("spark.sql.session.timeZone", DateTimeUtil.ZONE_ID);
        spark.conf().set("materializationProject", "maxis-cdw-shared-analysis");
        spark.conf().set("materializationDataset", "TEMP");
    }

    private void closeResources(SparkSession spark, AnnotationConfigApplicationContext context) {
        logger.info("Stopping Spark Context");
        if (spark != null && !spark.sparkContext().isStopped()) {
            spark.sparkContext().stop();
            spark.close();
        }
        if (context != null) {
            context.close();
        }
    }

    public void uploadFileToS3() {
        logger.info("Starting S3 File Upload");

        try {
            String bucketName = "nba-dev-generic-bucket";
            String key = "voon_test/test.txt";
            String content = "This is a test content to be written into S3";

            S3Client s3Client = S3Client.builder().build();

            PutObjectRequest putObjectRequest = PutObjectRequest.builder()
                    .bucket(bucketName)
                    .key(key)
                    .build();

            s3Client.putObject(putObjectRequest, RequestBody.fromString(content));

            logger.info("Successfully written to S3: s3://{}/{}", bucketName, key);
        } catch (Exception e) {
            logger.error("Exception during S3 File Upload: ", e);
        }
    }
}

the main program is run successfully just that the logs are not showing

this is the logs at the livy console

24/12/17 14:59:33 INFO BatchSessionManager: Registered new session 1
24/12/17 14:59:36 INFO LineBufferedStream: 24/12/17 14:59:36 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
24/12/17 14:59:38 INFO LineBufferedStream: 24/12/17 14:59:38 WARN DependencyUtils: Skip remote jar s3://nba-dev-generic-bucket/EMR7/lib/spoiwo_2.12-2.2.1.jar.
...
24/12/17 14:59:38 INFO LineBufferedStream: 24/12/17 14:59:38 WARN DependencyUtils: Skip remote jar s3://nba-dev-generic-bucket/EMR7/lib/xmlbeans-5.2.1.jar.
24/12/17 14:59:38 INFO LineBufferedStream: 24/12/17 14:59:38 INFO DefaultNoHARMFailoverProxyProvider: Connecting to ResourceManager at ip-10-156-120-90.aws.men.package.com.my/10.156.120.90:8032
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO Configuration: resource-types.xml not found
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO ResourceUtils: Unable to find 'resource-types.xml'.
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO Client: Verifying our application has not requested more than the maximum memory capability of the cluster (11712 MB per container)
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO Client: Will allocate AM container, with 4505 MB memory including 409 MB overhead
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO Client: Setting up container launch context for our AM
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO Client: Setting up the launch environment for our AM container
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 INFO Client: Preparing resources for our AM container
24/12/17 14:59:39 INFO LineBufferedStream: 24/12/17 14:59:39 WARN Client: Neither spark.yarn.jars nor spark.yarn.archive is set, falling back to uploading libraries under SPARK_HOME.
24/12/17 14:59:40 INFO LineBufferedStream: 24/12/17 14:59:40 INFO Client: Uploading resource file:/mnt/tmp/spark-ec16008a-d702-40d7-b17e-c6177e1894bb/__spark_libs__17854039851719844287.zip -> hdfs://ip-10-156-120-90.aws.men.package.com.my:8020/user/livy/.sparkStaging/application_1734418464855_0002/__spark_libs__17854039851719844287.zip
...
24/12/17 15:00:17 INFO LineBufferedStream: 24/12/17 15:00:17 INFO S3NativeFileSystem: Opening 's3://nba-dev-generic-bucket/EMR7/lib/spring-expression-6.1.14.jar' for reading
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO SecurityManager: Changing view acls to: livy
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO SecurityManager: Changing modify acls to: livy
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO SecurityManager: Changing view acls groups to: 
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO SecurityManager: Changing modify acls groups to: 
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: livy; groups with view permissions: EMPTY; users with modify permissions: livy; groups with modify permissions: EMPTY
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO Client: Submitting application application_1734418464855_0002 to ResourceManager
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO YarnClientImpl: Submitted application application_1734418464855_0002
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO Client: Application report for application_1734418464855_0002 (state: ACCEPTED)
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO Client: 
24/12/17 15:00:22 INFO LineBufferedStream:   client token: N/A
24/12/17 15:00:22 INFO LineBufferedStream:   diagnostics: [Tue Dec 17 15:00:22 +0800 2024] Application is Activated, waiting for resources to be assigned for AM.  Details : AM Partition = <DEFAULT_PARTITION> ; Partition Resource = <memory:11712, vCores:4> ; Queue's Absolute capacity = 100.0 % ; Queue's Absolute used capacity = 0.0 % ; Queue's Absolute max capacity = 100.0 % ; Queue's capacity (absolute resource) = <memory:11712, vCores:4> ; Queue's used capacity (absolute resource) = <memory:0, vCores:0> ; Queue's max capacity (absolute resource) = <memory:11712, vCores:4> ; 
24/12/17 15:00:22 INFO LineBufferedStream:   ApplicationMaster host: N/A
24/12/17 15:00:22 INFO LineBufferedStream:   ApplicationMaster RPC port: -1
24/12/17 15:00:22 INFO LineBufferedStream:   queue: default
24/12/17 15:00:22 INFO LineBufferedStream:   start time: 1734418822248
24/12/17 15:00:22 INFO LineBufferedStream:   final status: UNDEFINED
24/12/17 15:00:22 INFO LineBufferedStream:   tracking URL: http://ip-10-156-120-90.aws.men.package.com.my:20888/proxy/application_1734418464855_0002/
24/12/17 15:00:22 INFO LineBufferedStream:   user: livy
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO ShutdownHookManager: Shutdown hook called
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO ShutdownHookManager: Deleting directory /mnt/tmp/spark-e03a87a5-3496-48ce-bc98-b6e3d7239cbf
24/12/17 15:00:22 INFO LineBufferedStream: 24/12/17 15:00:22 INFO ShutdownHookManager: Deleting directory /mnt/tmp/spark-ec16008a-d702-40d7-b17e-c6177e1894bb

lambda request payload that trigger the spark job

{
   "file":"s3://nba-dev-generic-bucket/emr7-promobatch-0.0.1-SNAPSHOT.jar",
   "className":"com.package.promobatch.App",
   "name":"Test-20241217-0659",
   "args":[
      "Test",
      "-",
      "j-MP182UNW7396",
      "100"
   ],
   "conf":{
      "spark.driver.extraJavaOptions":"-Dlog4j.configuration=log4j.properties",
   },
   "jars":[
      "s3://nba-dev-generic-bucket/EMR7/lib/SparseBitSet-1.3.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/aircompressor-0.25.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/annotations-17.0.0.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/apache-client-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/arns-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/audience-annotations-0.5.0.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/auth-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/aws-core-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/aws-json-protocol-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/aws-query-protocol-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/aws-xml-protocol-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/checker-qual-3.42.0.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/checksums-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/checksums-spi-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/crt-core-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/curvesapi-1.08.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/dynamodb-2.25.70.jar",
      "s3://nba-dev-generic-bucket/EMR7/lib/endpoints-spi-2.25.70.jar"
   ]
}

what could be the issue? the logs should be able to print out at the livy console or logs at the S3

  • apache-spark
  • aws-lambda
  • amazon-emr
  • livy

New contributor

Voon see hong is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

2

Trang chủ Giới thiệu Sinh nhật bé trai Sinh nhật bé gái Tổ chức sự kiện Biểu diễn giải trí Dịch vụ khác Trang trí tiệc cưới Tổ chức khai trương Tư vấn dịch vụ Thư viện ảnh Tin tức - sự kiện Liên hệ Chú hề sinh nhật Trang trí YEAR END PARTY công ty Trang trí tất niên cuối năm Trang trí tất niên xu hướng mới nhất Trang trí sinh nhật bé trai Hải Đăng Trang trí sinh nhật bé Khánh Vân Trang trí sinh nhật Bích Ngân Trang trí sinh nhật bé Thanh Trang Thuê ông già Noel phát quà Biểu diễn xiếc khỉ Xiếc quay đĩa Dịch vụ tổ chức sự kiện 5 sao Thông tin về chúng tôi Dịch vụ sinh nhật bé trai Dịch vụ sinh nhật bé gái Sự kiện trọn gói Các tiết mục giải trí Dịch vụ bổ trợ Tiệc cưới sang trọng Dịch vụ khai trương Tư vấn tổ chức sự kiện Hình ảnh sự kiện Cập nhật tin tức Liên hệ ngay Thuê chú hề chuyên nghiệp Tiệc tất niên cho công ty Trang trí tiệc cuối năm Tiệc tất niên độc đáo Sinh nhật bé Hải Đăng Sinh nhật đáng yêu bé Khánh Vân Sinh nhật sang trọng Bích Ngân Tiệc sinh nhật bé Thanh Trang Dịch vụ ông già Noel Xiếc thú vui nhộn Biểu diễn xiếc quay đĩa Dịch vụ tổ chức tiệc uy tín Khám phá dịch vụ của chúng tôi Tiệc sinh nhật cho bé trai Trang trí tiệc cho bé gái Gói sự kiện chuyên nghiệp Chương trình giải trí hấp dẫn Dịch vụ hỗ trợ sự kiện Trang trí tiệc cưới đẹp Khởi đầu thành công với khai trương Chuyên gia tư vấn sự kiện Xem ảnh các sự kiện đẹp Tin mới về sự kiện Kết nối với đội ngũ chuyên gia Chú hề vui nhộn cho tiệc sinh nhật Ý tưởng tiệc cuối năm Tất niên độc đáo Trang trí tiệc hiện đại Tổ chức sinh nhật cho Hải Đăng Sinh nhật độc quyền Khánh Vân Phong cách tiệc Bích Ngân Trang trí tiệc bé Thanh Trang Thuê dịch vụ ông già Noel chuyên nghiệp Xem xiếc khỉ đặc sắc Xiếc quay đĩa thú vị

Filed under: Kiến thức lập trình - @ 01:05

Thẻ:

Trang chủ Giới thiệu Sinh nhật bé trai Sinh nhật bé gái Tổ chức sự kiện Biểu diễn giải trí Dịch vụ khác Trang trí tiệc cưới Tổ chức khai trương Tư vấn dịch vụ Thư viện ảnh Tin tức - sự kiện Liên hệ Chú hề sinh nhật Trang trí YEAR END PARTY công ty Trang trí tất niên cuối năm Trang trí tất niên xu hướng mới nhất Trang trí sinh nhật bé trai Hải Đăng Trang trí sinh nhật bé Khánh Vân Trang trí sinh nhật Bích Ngân Trang trí sinh nhật bé Thanh Trang Thuê ông già Noel phát quà Biểu diễn xiếc khỉ Xiếc quay đĩa
Thiết kế website Thiết kế website Thiết kế website Cách kháng tài khoản quảng cáo Mua bán Fanpage Facebook Dịch vụ SEO Tổ chức sinh nhật