我开发了一个使用apache storm消费kafka消息的应用程序,当我在eclipse中使用LocalCluster运行拓扑时它工作正常并且消息正常消耗,但是当我使用storm命令(bin \ storm jar)运行时.. \ kafka-storm-0.0.1-SNAPSHOT.jar com.kafka_storm.util.Topology storm-kafka-topology),拓扑开始但无法消费任何消息,我正在做错事,或指导我可以做些什么来找到问题
拓扑代码
public class Topology {
public Properties configs;
public BoltBuilder boltBuilder;
public SpoutBuilder spoutBuilder;
public Topology(String configFile) throws Exception {
configs = new Properties();
InputStream is = null;
try {
is = this.getClass().getResourceAsStream("/application.properties");
configs.load(is);
//configs.load(Topology.class.getResourceAsStream("/application.properties"));
boltBuilder = new BoltBuilder(configs);
spoutBuilder = new SpoutBuilder(configs);
} catch (Exception ex) {
ex.printStackTrace();
System.exit(0);
}
}
private void submitTopology() throws Exception {
System.out.println("Entered in submitTopology");
TopologyBuilder builder = new TopologyBuilder();
KafkaSpout<?, ?> kafkaSpout = spoutBuilder.buildKafkaSpout();
SinkTypeBolt sinkTypeBolt = boltBuilder.buildSinkTypeBolt();
MongoDBBolt mongoBolt = boltBuilder.buildMongoDBBolt();
//set the kafkaSpout to topology
//parallelism-hint for kafkaSpout - defines number of executors/threads to be spawn per container
int kafkaSpoutCount = Integer.parseInt(configs.getProperty(Keys.KAFKA_SPOUT_COUNT));
builder.setSpout(configs.getProperty(Keys.KAFKA_SPOUT_ID), kafkaSpout, kafkaSpoutCount);
//set the sinktype bolt
int sinkBoltCount = Integer.parseInt(configs.getProperty(Keys.SINK_BOLT_COUNT));
builder.setBolt(configs.getProperty(Keys.SINK_TYPE_BOLT_ID),sinkTypeBolt,sinkBoltCount).shuffleGrouping(configs.getProperty(Keys.KAFKA_SPOUT_ID));
//set the mongodb bolt
int mongoBoltCount = Integer.parseInt(configs.getProperty(Keys.MONGO_BOLT_COUNT));
builder.setBolt(configs.getProperty(Keys.MONGO_BOLT_ID),mongoBolt,mongoBoltCount).shuffleGrouping(configs.getProperty(Keys.SINK_TYPE_BOLT_ID),Keys.MONGODB_STREAM);
String topologyName = configs.getProperty(Keys.TOPOLOGY_NAME);
Config conf = new Config();
//Defines how many worker processes have to be created for the topology in the cluster.
conf.setNumWorkers(1);
System.out.println("Submitting Topology");
//StormSubmitter.submitTopology(topologyName, conf, builder.createTopology());
System.out.println("Topology submitted");
LocalCluster cluster = new LocalCluster();
cluster.submitTopology(topologyName, conf, builder.createTopology());
}
public static void main(String[] args) throws Exception {
String configFile;
if (args.length == 0) {
System.out.println("Missing input : config file location, using default");
configFile = "application.properties";
} else{
configFile = args[0];
}
Topology ingestionTopology = new Topology(configFile);
ingestionTopology.submitTopology();
}
}
Spout Code
public class SpoutBuilder {
public Properties configs = null;
public SpoutBuilder(Properties configs) {
this.configs = configs;
}
public KafkaSpout<?, ?> buildKafkaSpout() {
String servers = configs.getProperty(Keys.KAFKA_BROKER);
String topic = configs.getProperty(Keys.KAFKA_TOPIC);
String group = configs.getProperty(Keys.KAFKA_CONSUMERGROUP);
return new KafkaSpout<>(getKafkaSpoutConfig(servers,topic,group));
}
protected KafkaSpoutConfig<String, String> getKafkaSpoutConfig(String bootstrapServers, String topic, String group) {
return KafkaSpoutConfig.builder(bootstrapServers, new String[]{topic})
.setProp(ConsumerConfig.GROUP_ID_CONFIG, group)
.setRetry(getRetryService())
.setOffsetCommitPeriodMs(10_000)
.setFirstPollOffsetStrategy(FirstPollOffsetStrategy.UNCOMMITTED_LATEST)
.setMaxUncommittedOffsets(250)
.setProcessingGuarantee(ProcessingGuarantee.AT_LEAST_ONCE)
.setTupleTrackingEnforced(true)
.setEmitNullTuples(false)
.setRecordTranslator(new DefaultRecordTranslator<String, String>())
.build();
}
protected KafkaSpoutRetryService getRetryService() {
return new KafkaSpoutRetryExponentialBackoff(TimeInterval.microSeconds(500),
TimeInterval.milliSeconds(2), Integer.MAX_VALUE, TimeInterval.seconds(10));
}
}
Bolt Builder
public class BoltBuilder {
public Properties configs = null;
public BoltBuilder(Properties configs) {
this.configs = configs;
}
public SinkTypeBolt buildSinkTypeBolt() {
return new SinkTypeBolt();
}
public MongoDBBolt buildMongoDBBolt() {
String host = configs.getProperty(Keys.MONGO_HOST);
int port = Integer.parseInt(configs.getProperty(Keys.MONGO_PORT));
String db = configs.getProperty(Keys.MONGO_DATABASE);
String collection = configs.getProperty(Keys.MONGO_COLLECTION);
return new MongoDBBolt(host, port, db, collection);
}
}
SinkTypeBolt代码
public class SinkTypeBolt extends BaseRichBolt {
private static final long serialVersionUID = 1L;
private OutputCollector collector;
public void execute(Tuple tuple) {
String value = tuple.getString(4);
System.out.println("Received in SinkType bolt : "+value);
if (value != null && !value.isEmpty()){
collector.emit(Keys.MONGODB_STREAM,new Values(value));
System.out.println("Emitted : "+value);
}
collector.ack(tuple);
}
public void prepare(Map conf, TopologyContext context, OutputCollector collector) {
this.collector = collector;
}
public void declareOutputFields(OutputFieldsDeclarer declarer) {
declarer.declareStream(Keys.MONGODB_STREAM, new Fields("content"));
}
}
MongoDB Bolt
public class MongoDBBolt extends BaseRichBolt {
private static final long serialVersionUID = 1L;
private OutputCollector collector;
private MongoDatabase mongoDB;
private MongoClient mongoClient;
private String collection;
public String host;
public int port ;
public String db;
protected MongoDBBolt(String host, int port, String db,String collection) {
this.host = host;
this.port = port;
this.db = db;
this.collection = collection;
}
public void prepare(Map stormConf, TopologyContext context, OutputCollector collector) {
this.collector = collector;
this.mongoClient = new MongoClient(host,port);
this.mongoDB = mongoClient.getDatabase(db);
}
public void execute(Tuple input) {
Document mongoDoc = getMongoDocForInput(input);
try{
mongoDB.getCollection(collection).insertOne(mongoDoc);
collector.ack(input);
}catch(Exception e) {
e.printStackTrace();
collector.fail(input);
}
}
@Override
public void cleanup() {
this.mongoClient.close();
}
public void declareOutputFields(OutputFieldsDeclarer declarer) {
// TODO Auto-generated method stub
}
public Document getMongoDocForInput(Tuple input) {
Document doc = new Document();
String content = (String) input.getValueByField("content");
String[] parts = content.trim().split(" ");
System.out.println("Received in MongoDB bolt "+content);
try {
for(String part : parts) {
String[] subParts = part.split(":");
String fieldName = subParts[0];
String value = subParts[1];
doc.append(fieldName, value);
}
} catch(Exception e) {
}
return doc;
}
}
pom.xml代码
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.7</maven.compiler.source>
<maven.compiler.target>1.7</maven.compiler.target>
</properties>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-core</artifactId>
<version>1.2.2</version>
<scope>provided</scope>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>1.1.0</version>
<exclusions>
<exclusion>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.storm</groupId>
<artifactId>storm-kafka-client</artifactId>
<version>1.2.2</version>
</dependency>
<dependency>
<groupId>org.mongodb</groupId>
<artifactId>mongo-java-driver</artifactId>
<version>3.0.4</version>
</dependency>
<dependency>
<groupId>com.googlecode.json-simple</groupId>
<artifactId>json-simple</artifactId>
<version>1.1</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>1.4</version>
<configuration>
<createDependencyReducedPom>true</createDependencyReducedPom>
</configuration>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<transformers>
<transformer
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
<transformer
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<mainClass>com.kafka_storm.util.Topology</mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<version>2.4</version>
</plugin>
</plugins>
<resources>
<resource>
<directory>src/main/java</directory>
<includes>
<include> **/*.properties</include>
</includes>
</resource>
</resources>
</build>
答案 0 :(得分:1)
可以肯定的是,当您使用storm jar
提交拓扑时,您记得在拓扑中使用StormSubmitter行而不是LocalCluster,对吗?
另外,请检查您是否已启动所有正确的守护程序,即storm nimbus
,storm supervisor
应至少运行(加上您的Zookeeper安装)
接下来要查看的地方是您的日志文件。在Storm目录中,您将拥有logs
目录。查看logs/worker-artifacts/<your-topology-id>/<your-worker-port>/worker.log
文件。这些将有希望让你走上正确的轨道,找出正在发生的事情。我打开Storm UI,找到你的鲸鱼喷水,然后查看它正在运行的工作端口,这样你就可以查看正确的日志文件。