Flume-1.5.0+Kafka_2.9.2-0.8.1.1+Storm-0.9.2 分布式环境整合
# 整合场景
使用Flume监控指定目录，出现新的日志文件后将文件数据传到Kafka，最后由Storm从Kafka中取出数据并显示、、、
# Flume+Kafka的整合
# Flume的fks001.conf的配置文件
监控指定目录/usr/local/yting/flume/tdata/tdir1，然后使用自定义的Sink（com.yting.cloud.flume.sink.KafkaSink），将数据传入Kafka
root@rs229 fks]# pwd
/usr/local/adsit/yting/apache/flume/apache-flume-1.5.0-bin/conf/ytconf/fks
[root@rs229 fks]# vi fks001.conf
# fks : yting yousmile flume kafka storm integration fks.sources=source1 fks.sinks=sink1 fks.channels=channel1 # configure source1 fks.sources.source1.type=spooldir fks.sources.source1.spoolDir=/usr/local/yting/flume/tdata/tdir1 fks.sources.source1.fileHeader = false # configure sink1 fks.sinks.sink1.type=com.yting.cloud.flume.sink.KafkaSink #（自定义Sink，Flume监控数据传入Kafka） # configure channel1 fks.channels.channel1.type=file fks.channels.channel1.checkpointDir=/usr/local/yting/flume/checkpointdir/tcpdir/example_fks_001 fks.channels.channel1.dataDirs=/usr/local/yting/flume/datadirs/tddirs/example_fks_001 # bind source and sink fks.sources.source1.channels=channel1 fks.sinks.sink1.channel=channel1
# Kafka 的server.properties配置文件
[root@rs229 ytconf]# pwd
/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/config/ytconf
[root@rs229 ytconf]# vi server.properties
# A comma seperated list of directories under whichto store log files # log.dirs=/tmp/kafka-logs log.dirs=/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/kafka-logs # root directory for all kafka znodes. zookeeper.connect=rs229:2181,rs227:2181,rs226:2181,rs198:2181,rs197:2181/kafka
# jar包的复制，Kafka中的jar包复制到Flume中去，因为自定义的Sink（com.yting.cloud.flume.sink.KafkaSink）会用到，如果不做这一步，会抱异常的！
[root@rs229 lib]# pwd
/usr/local/adsit/yting/apache/flume/apache-flume-1.5.0-bin/lib
[root@rs229 lib]# cp/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/libs/* .
# 使用Eclipse将自定义的Sink（com.yting.cloud.flume.sink.KafkaSink）打成jar包放入$FLUME_HOME/libs目录下去
# Kafka的启动
[root@rs229 kafka_2.9.2-0.8.1.1]# pwd /usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1 [root@rs229 kafka_2.9.2-0.8.1.1]# bin/kafka-server-start.sh config/ytconf/server.properties &
启动日志：有点长啊
[1] 24672 [root@rs229 kafka_2.9.2-0.8.1.1]# [2014-07-1411:48:24,533] INFO Verifying properties (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,572] INFO Property broker.id isoverridden to 0 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,572] INFO Propertylog.cleaner.enable is overridden to false (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,572] INFO Property log.dirs isoverridden to/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/kafka-logs(kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,572] INFO Propertylog.retention.check.interval.ms is overridden to 60000(kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,572] INFO Propertylog.retention.hours is overridden to 168 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,573] INFO Propertylog.segment.bytes is overridden to 536870912 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,573] INFO Propertynum.io.threads is overridden to 8 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,573] INFO Propertynum.network.threads is overridden to 2 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,573] INFO Property num.partitionsis overridden to 2 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,573] INFO Property port isoverridden to 9092 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,573] INFO Propertysocket.receive.buffer.bytes is overridden to 1048576(kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,574] INFO Propertysocket.request.max.bytes is overridden to 104857600(kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,574] INFO Propertysocket.send.buffer.bytes is overridden to 1048576 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,574] INFO Propertyzookeeper.connect is overridden tors229:2181,rs227:2181,rs226:2181,rs198:2181,rs197:2181/kafka(kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,574] INFO Property zookeeper.connection.timeout.msis overridden to 1000000 (kafka.utils.VerifiableProperties) [2014-07-14 11:48:24,590] INFO [Kafka Server 0],starting (kafka.server.KafkaServer) [2014-07-14 11:48:24,592] INFO [Kafka Server 0],Connecting to zookeeper on rs229:2181,rs227:2181,rs226:2181,rs198:2181,rs197:2181/kafka(kafka.server.KafkaServer) [2014-07-14 11:48:24,603] INFO Starting ZkClientevent thread. (org.I0Itec.zkclient.ZkEventThread) [2014-07-14 11:48:24,610] INFO Clientenvironment:zookeeper.version=3.3.3-1203054, built on 11/17/2011 05:47 GMT(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:host.name=rs229 (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.version=1.7.0_60 (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.vendor=Oracle Corporation (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.home=/usr/local/adsit/yting/jdk/jdk1.7.0_60/jre(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.class.path=:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../core/build/dependant-libs-2.8.0/*.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../perf/build/libs//kafka-perf_2.8.0*.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../clients/build/libs//kafka-clients*.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../examples/build/libs//kafka-examples*.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../contrib/hadoop-consumer/build/libs//kafka-hadoop-consumer*.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../contrib/hadoop-producer/build/libs//kafka-hadoop-producer*.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/jopt-simple-3.2.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/kafka_2.9.2-0.8.1.1.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/kafka_2.9.2-0.8.1.1-javadoc.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/kafka_2.9.2-0.8.1.1-scaladoc.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/kafka_2.9.2-0.8.1.1-sources.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/log4j-1.2.15.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/metrics-core-2.2.0.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/scala-library-2.9.2.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/slf4j-api-1.7.2.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/snappy-java-1.0.5.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/zkclient-0.3.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../libs/zookeeper-3.3.4.jar:/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/bin/../core/build/libs/kafka_2.8.0*.jar(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.library.path=/usr/java/packages/lib/amd64:/usr/lib64:/lib64:/lib:/usr/lib(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.io.tmpdir=/tmp (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:java.compiler=<NA> (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:os.name=Linux (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:os.arch=amd64 (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:os.version=2.6.32-279.el6.x86_64 (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:user.name=root (org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Client environment:user.home=/root(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,610] INFO Clientenvironment:user.dir=/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,611] INFO Initiating client connection,connectString=rs229:2181,rs227:2181,rs226:2181,rs198:2181,rs197:2181/kafkasessionTimeout=6000 watcher=org.I0Itec.zkclient.ZkClient@7c8b7ac9(org.apache.zookeeper.ZooKeeper) [2014-07-14 11:48:24,625] INFO Opening socketconnection to server rs198/116.255.234.198:2181(org.apache.zookeeper.ClientCnxn) [2014-07-14 11:48:24,631] INFO Socket connectionestablished to rs198/116.255.234.198:2181, initiating session(org.apache.zookeeper.ClientCnxn) [2014-07-14 11:48:24,642] INFO Session establishmentcomplete on server rs198/116.255.234.198:2181, sessionid = 0xc6472c07f50b0000,negotiated timeout = 6000 (org.apache.zookeeper.ClientCnxn) [2014-07-14 11:48:24,645] INFO zookeeper statechanged (SyncConnected) (org.I0Itec.zkclient.ZkClient) [2014-07-14 11:48:24,892] INFO Found clean shutdownfile. Skipping recovery for all logs in data directory'/usr/local/adsit/yting/apache/kafka/kafka_2.9.2-0.8.1.1/kafka-logs'(kafka.log.LogManager) [2014-07-14 11:48:24,894] INFO Loading log'flume-kafka-storm-001-0' (kafka.log.LogManager) [2014-07-14 11:48:24,945] INFO Completed load of logflume-kafka-storm-001-0 with log end offset 18 (kafka.log.Log) SLF4J: Failed to load class"org.slf4j.impl.StaticLoggerBinder". SLF4J: Defaulting to no-operation (NOP) loggerimplementation SLF4J: Seehttp://www.slf4j.org/codes.html#StaticLoggerBinder for further details. [2014-07-14 11:48:24,966] INFO Loading log'flume-kafka-storm-001-1' (kafka.log.LogManager) [2014-07-14 11:48:24,969] INFO Completed load of logflume-kafka-storm-001-1 with log end offset 7 (kafka.log.Log) [2014-07-14 11:48:24,970] INFO Loading log'test001-1' (kafka.log.LogManager) [2014-07-14 11:48:24,973] INFO Completed load of logtest001-1 with log end offset 0 (kafka.log.Log) [2014-07-14 11:48:24,974] INFO Loading log'test003-1' (kafka.log.LogManager) [2014-07-14 11:48:24,976] INFO Completed load of logtest003-1 with log end offset 47 (kafka.log.Log) [2014-07-14 11:48:24,977] INFO Loading log'test004-0' (kafka.log.LogManager) [2014-07-14 11:48:24,980] INFO Completed load of logtest004-0 with log end offset 51 (kafka.log.Log) [2014-07-14 11:48:24,981] INFO Loading log'test004-1' (kafka.log.LogManager) [2014-07-14 11:48:24,984] INFO Completed load of logtest004-1 with log end offset 49 (kafka.log.Log) [2014-07-14 11:48:24,985] INFO Loading log'test002-0' (kafka.log.LogManager) [2014-07-14 11:48:24,987] INFO Completed load of logtest002-0 with log end offset 0 (kafka.log.Log) [2014-07-14 11:48:24,987] INFO Loading log'test001-0' (kafka.log.LogManager) [2014-07-14 11:48:24,991] INFO Completed load of logtest001-0 with log end offset 0 (kafka.log.Log) [2014-07-14 11:48:24,991] INFO Loading log'test002-1' (kafka.log.LogManager) [2014-07-14 11:48:24,993] INFO Completed load of logtest002-1 with log end offset 0 (kafka.log.Log) [2014-07-14 11:48:24,994] INFO Loading log'test003-0' (kafka.log.LogManager) [2014-07-14 11:48:24,997] INFO Completed load of logtest003-0 with log end offset 53 (kafka.log.Log) [2014-07-14 11:48:24,999] INFO Starting log cleanup witha period of 60000 ms. (kafka.log.LogManager) [2014-07-14 11:48:25,003] INFO Starting log flusherwith a default period of 9223372036854775807 ms. (kafka.log.LogManager) [2014-07-14 11:48:25,031] INFO Awaiting socketconnections on 0.0.0.0:9092. (kafka.network.Acceptor) [2014-07-14 11:48:25,032] INFO [Socket Server onBroker 0], Started (kafka.network.SocketServer) [2014-07-14 11:48:25,143] INFO Will not load MX4J,mx4j-tools.jar is not in the classpath (kafka.utils.Mx4jLoader$) [2014-07-14 11:48:25,163] INFO 0 successfully electedas leader (kafka.server.ZookeeperLeaderElector) [2014-07-14 11:48:25,639] INFO New leader is 0(kafka.server.ZookeeperLeaderElector$LeaderChangeListener) [2014-07-14 11:48:25,645] INFO Registered broker 0 atpath /brokers/ids/0 with address rs229:9092. (kafka.utils.ZkUtils$) [2014-07-14 11:48:25,660] INFO [Kafka Server 0],started (kafka.server.KafkaServer) [2014-07-14 11:48:25,942] INFO [ReplicaFetcherManageron broker 0] Removed fetcher for partitions [test001,0],[test003,1],[test003,0],[flume-kafka-storm-001,1],[flume-kafka-storm-001,0],[test004,1],[test004,0],[test001,1],[test002,0],[test002,1](kafka.server.ReplicaFetcherManager) [2014-07-14 11:48:26,045] INFO [ReplicaFetcherManageron broker 0] Removed fetcher for partitions[test001,0],[test003,1],[test003,0],[flume-kafka-storm-001,1],[flume-kafka-storm-001,0],[test004,1],[test004,0],[test001,1],[test002,0],[test002,1](kafka.server.ReplicaFetcherManager) # Flume的启动 [root@rs229 apache-flume-1.5.0-bin]# bin/flume-ng agent -n fks -c conf/ -fconf/ytconf/fks/fks001.conf -Dflume.root.logger=INFO,console & 2014-07-14 11:50:13,882 (lifecycleSupervisor-1-0)[INFO - org.apache.flume.source.SpoolDirectorySource.start(SpoolDirectorySource.java:77)]SpoolDirectorySource source starting with directory:/usr/local/yting/flume/tdata/tdir1 2014-07-14 11:50:13,912 (lifecycleSupervisor-1-0)[INFO -org.apache.flume.instrumentation.MonitoredCounterGroup.register(MonitoredCounterGroup.java:119)]Monitored counter group for type: SOURCE, name:source1: Successfully registered new MBean. 2014-07-14 11:50:13,916 (lifecycleSupervisor-1-0)[INFO -org.apache.flume.instrumentation.MonitoredCounterGroup.start(MonitoredCounterGroup.java:95)]Component type: SOURCE, name: source1 started 2014-07-14 11:50:13,916 (pool-4-thread-1) [INFO -org.apache.flume.source.SpoolDirectorySource$SpoolDirectoryRunnable.run(SpoolDirectorySource.java:254)]Spooling Directory Source runner has shutdown. 2014-07-14 11:50:14,417 (pool-4-thread-1) [INFO -org.apache.flume.source.SpoolDirectorySource$SpoolDirectoryRunnable.run(SpoolDirectorySource.java:254)]Spooling Directory Source runner has shutdown.
这样Flume就算启动成功了，并且如果你的监控目录下出现新的日志文件的话，日志文件中的信息会传到Kafka中去，你懂的！
# 在Flume的监控目录下新建一个文件试试
[root@rs229 ytconf]# cd/usr/local/yting/flume/tdata/tdir1/
[root@rs229 tdir1]# ll
total 0
[root@rs229 tdir1]# vi yousmile.log
The you smile until forever .....................
[root@rs229 tdir1]# ll
total 1
-rw-r--r-- 1 root root 50 Jul 14 13:57 yousmile.log.COMPLETED（说明已经被Flume处理过了）
[root@rs229 tdir1]#
# Eclipse下链接服务器查看Flume的自定义Sink是否将数据传到Kafka中去了
# MySimpleConsumer.java（Eclipse下运行即可得到结果）
package com.yting.cloud.kafa.consumer;
import kafka.api.FetchRequest;
import kafka.api.FetchRequestBuilder;
import kafka.api.PartitionOffsetRequestInfo;
import kafka.common.ErrorMapping;
import kafka.common.TopicAndPartition;
import kafka.javaapi.*;
import kafka.javaapi.consumer.SimpleConsumer;
import kafka.message.MessageAndOffset;
import java.nio.ByteBuffer;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
/**
* Kafka官网给的案例SimpleConsumer，饿在Eclipse本地连接服务器测试，所以修改了一些代码
*
*
*/
public class MySimpleConsumer {
publicstatic void main(String args[]) {
MySimpleConsumerexample = new MySimpleConsumer();
//long maxReads = Long.parseLong(args[0]);
//String topic = args[1];
//int partition = Integer.parseInt(args[2]);
//seeds.add(args[3]);
//int port = Integer.parseInt(args[4]);
longmaxReads = 100;
// Stringtopic = "yting_page_visits";
// Stringtopic = "test003";
Stringtopic = "flume-kafka-storm-001";
// intpartition = 0;
intpartition = 1; // The you smile until forever .....................日志文件中的这条信息被送到分区1中去了，默认2分区
List<String>seeds = new ArrayList<String>();
// seeds.add("rs229");
seeds.add("rs229");
seeds.add("rs227");
seeds.add("rs226");
seeds.add("rs198");
seeds.add("rs197");
intport = Integer.parseInt("9092");
try{
example.run(maxReads,topic, partition, seeds, port);
}catch (Exception e) {
System.out.println("Oops:"+ e);
e.printStackTrace();
}
}
privateList<String> m_replicaBrokers = new ArrayList<String>();
publicMySimpleConsumer() {
m_replicaBrokers= new ArrayList<String>();
}
publicvoid run(long a_maxReads, String a_topic, int a_partition, List<String>a_seedBrokers, int a_port) throws Exception {
//find the meta data about the topic and partition we are interested in
//
PartitionMetadatametadata = findLeader(a_seedBrokers, a_port, a_topic, a_partition);
if(metadata == null) {
System.out.println("Can'tfind metadata for Topic and Partition. Exiting");
return;
}
if(metadata.leader() == null) {
System.out.println("Can'tfind Leader for Topic and Partition. Exiting");
return;
}
StringleadBroker = metadata.leader().host();
StringclientName = "Client_" + a_topic + "_" + a_partition;
SimpleConsumerconsumer = new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024,clientName);
longreadOffset = getLastOffset(consumer, a_topic, a_partition,kafka.api.OffsetRequest.EarliestTime(), clientName);
intnumErrors = 0;
while(a_maxReads > 0) {
if(consumer == null) {
consumer= new SimpleConsumer(leadBroker, a_port, 100000, 64 * 1024, clientName);
}
FetchRequestreq = new FetchRequestBuilder().clientId(clientName)
.addFetch(a_topic,a_partition, readOffset, 100000) // Note: this fetchSize of 100000 might needto be increased if large batches are written to Kafka
.build();
FetchResponsefetchResponse = consumer.fetch(req);
if(fetchResponse.hasError()) {
numErrors++;
//Something went wrong!
shortcode = fetchResponse.errorCode(a_topic, a_partition);
System.out.println("Errorfetching data from the Broker:" + leadBroker + " Reason: " +code);
if(numErrors > 5)
break;
if(code == ErrorMapping.OffsetOutOfRangeCode()) {
//We asked for an invalid offset. For simple case ask for
//the last element to reset
readOffset= getLastOffset(consumer, a_topic, a_partition,kafka.api.OffsetRequest.LatestTime(), clientName);
continue;
}
consumer.close();
consumer= null;
leadBroker= findNewLeader(leadBroker, a_topic, a_partition, a_port);
continue;
}
numErrors= 0;
longnumRead = 0;
for(MessageAndOffset messageAndOffset : fetchResponse.messageSet(a_topic,a_partition)) {
longcurrentOffset = messageAndOffset.offset();
if(currentOffset < readOffset) {
System.out.println("Foundan old offset: " + currentOffset + " Expecting: " + readOffset);
continue;
}
readOffset =messageAndOffset.nextOffset();
ByteBufferpayload = messageAndOffset.message().payload();
byte[]bytes = new byte[payload.limit()];
payload.get(bytes);
System.out.println(String.valueOf(messageAndOffset.offset())+ ": " + new String(bytes, "UTF-8"));
numRead++;
a_maxReads--;
}
if(numRead == 0) {
try{
Thread.sleep(1000);
}catch (InterruptedException ie) {
}
}
}
if(consumer != null)
consumer.close();
}
publicstatic long getLastOffset(SimpleConsumer consumer, String topic,
intpartition, long whichTime, String clientName) {
TopicAndPartitiontopicAndPartition = new TopicAndPartition(topic, partition);
Map<TopicAndPartition,PartitionOffsetRequestInfo> requestInfo = new HashMap<TopicAndPartition,PartitionOffsetRequestInfo>();
requestInfo.put(topicAndPartition,new PartitionOffsetRequestInfo(whichTime, 1));
kafka.javaapi.OffsetRequestrequest = new kafka.javaapi.OffsetRequest(requestInfo, kafka.api.OffsetRequest.CurrentVersion(),clientName);
OffsetResponseresponse = consumer.getOffsetsBefore(request);
if(response.hasError()) {
System.out.println("Errorfetching data Offset Data the Broker. Reason: "+ response.errorCode(topic,partition));
return0;
}
long[]offsets = response.offsets(topic, partition);
returnoffsets[0];
}
privateString findNewLeader(String a_oldLeader, String a_topic,
inta_partition, int a_port) throws Exception {
for(int i = 0; i < 3; i++) {
booleangoToSleep = false;
PartitionMetadatametadata = findLeader(m_replicaBrokers, a_port, a_topic, a_partition);
if(metadata == null) {
goToSleep= true;
}else if (metadata.leader() == null) {
goToSleep= true;
}else if (a_oldLeader.equalsIgnoreCase(metadata.leader().host())
&&i == 0) {
//first time through if the leader hasn't changed give
//ZooKeeper a second to recover
//second time, assume the broker did recover before failover,
//or it was a non-Broker issue
//
goToSleep= true;
}else {
returnmetadata.leader().host();
}
if(goToSleep) {
try{
Thread.sleep(1000);
}catch (InterruptedException ie) {
}
}
}
System.out.println("Unableto find new leader after Broker failure. Exiting");
thrownew Exception("Unable to find new leader after Broker failure.Exiting");
}
privatePartitionMetadata findLeader(List<String> a_seedBrokers, int a_port,String a_topic, int a_partition) {
PartitionMetadatareturnMetaData = null;
loop:for (String seed : a_seedBrokers) {
SimpleConsumerconsumer = null;
try{
consumer= new SimpleConsumer(seed, a_port, 100000, 64 * 1024,"leaderLookup");
List<String>topics = Collections.singletonList(a_topic);
TopicMetadataRequestreq = new TopicMetadataRequest(topics);
kafka.javaapi.TopicMetadataResponseresp = consumer.send(req);
List<TopicMetadata>metaData = resp.topicsMetadata();
for(TopicMetadata item : metaData) {
for (PartitionMetadata part: item.partitionsMetadata()) {
if(part.partitionId() == a_partition) {
returnMetaData= part;
breakloop;
}
}
}
}catch (Exception e) {
System.out.println("Errorcommunicating with Broker [" + seed + "] to find Leader for [" +a_topic + ", " + a_partition + "] Reason: " + e);
}finally {
if(consumer != null)
consumer.close();
}
}
if(returnMetaData != null) {
m_replicaBrokers.clear();
for(kafka.cluster.Broker replica : returnMetaData.replicas()) {
m_replicaBrokers.add(replica.host());
}
}
returnreturnMetaData;
}
}
# Flume+Kafka整合成功，下面开始Kafka+Storm整合
# Kafka+Storm的整合
# Kafka的启动（这个在Flume+Kafka的整合中Kafka已经启动了，所以不需要再启动了）
# Storm的启动
# Storm nimbus的启动
[root@rs229 apache-storm-0.9.2-incubating]#bin/storm nimbus &
启动日志：
[1] 26815 [root@rs229 apache-storm-0.9.2-incubating]#Running: /usr/local/adsit/yting/jdk/jdk1.7.0_60/bin/java -server-Dstorm.options= -Dstorm.home=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating-Djava.library.path=/usr/local/lib:/opt/local/lib:/usr/lib -Dstorm.conf.file=-cp / /usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/lib/zkclient-0.3.jar:/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/conf-Xmx1024m -Dlogfile.name=nimbus.log-Dlogback.configurationFile=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/logback/cluster.xmlbacktype.storm.daemon.nimbus
# Storm ui的启动
[root@rs229 apache-storm-0.9.2-incubating]# bin/storm ui &
[2] 26912
[root@rs229 apache-storm-0.9.2-incubating]# Running:/usr/local/adsit/yting/jdk/jdk1.7.0_60/bin/java -server -Dstorm.options=-Dstorm.home=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating-Djava.library.path=/usr/local/lib:/opt/local/lib:/usr/lib -Dstorm.conf.file=-cp /、/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/conf-Xmx768m -Dlogfile.name=ui.log -Dlogback.configurationFile=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/logback/cluster.xmlbacktype.storm.ui.core
# Storm supervisor的启动
# rs226上启动Supervisor
[root@rs226 apache-storm-0.9.2-incubating]# bin/storm supervisor &
[1] 15273
[root@rs226 apache-storm-0.9.2-incubating]# Running:/usr/local/adsit/yting/jdk/jdk1.7.0_60/bin/java -server -Dstorm.options=-Dstorm.home=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating-Djava.library.path=/usr/local/lib:/opt/local/lib:/usr/lib -Dstorm.conf.file=-cp /…:/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/conf-Xmx256m -Dlogfile.name=supervisor.log -Dlogback.configurationFile=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/logback/cluster.xmlbacktype.storm.daemon.supervisor
# rs198上启动Supervisor
[root@rs198 apache-storm-0.9.2-incubating]# bin/storm supervisor &
[1] 15274
[root@RS198 apache-storm-0.9.2-incubating]# Running:/usr/local/adsit/yting/jdk/jdk1.7.0_60/bin/java -server -Dstorm.options=-Dstorm.home=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating-Djava.library.path=/usr/local/lib:/opt/local/lib:/usr/lib -Dstorm.conf.file=-cp /…:/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/conf-Xmx256m -Dlogfile.name=supervisor.log -Dlogback.configurationFile=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/logback/cluster.xmlbacktype.storm.daemon.supervisor
# rs197上启动Supervisor
[root@RS197 apache-storm-0.9.2-incubating]# bin/stormsupervisor &
[1] 25262
[root@RS197 apache-storm-0.9.2-incubating]# Running:/root/jdk1.6.0_26/bin/java -server -Dstorm.options=-Dstorm.home=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating-Djava.library.path=/usr/local/lib:/opt/local/lib:/usr/lib -Dstorm.conf.file=-cp /…:/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/conf-Xmx256m -Dlogfile.name=supervisor.log -Dlogback.configurationFile=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/logback/cluster.xmlbacktype.storm.daemon.supervisor
# rs167上启动Supervisor
[root@RS196 apache-storm-0.9.2-incubating]# bin/stormsupervisor &
[1] 17330
[root@RS196 apache-storm-0.9.2-incubating]# Running:/root/jdk1.6.0_26/bin/java -server -Dstorm.options=-Dstorm.home=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating-Djava.library.path=/usr/local/lib:/opt/local/lib:/usr/lib -Dstorm.conf.file=-cp /…:/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/conf-Xmx256m -Dlogfile.name=supervisor.log-Dlogback.configurationFile=/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/logback/cluster.xmlbacktype.storm.daemon.supervisor
# 需要打成jar包的3个Class，放到$STORM_HOME/lib目录下去
# MyHighLevelConsumer.java
package com.yting.cloud.kafa.consumer;
import kafka.consumer.ConsumerConfig;
import kafka.consumer.KafkaStream;
import kafka.javaapi.consumer.ConsumerConnector;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import kafka.consumer.ConsumerIterator;
//import kafka.consumer.KafkaStream;
/**
* KafkaSink(custom)
*
* @Problem youshould run this consumer class before producer
*
*/
//@SuppressWarnings("all")
public class MyHighLevelConsumer {
privatefinal ConsumerConnector consumer;
privatefinal String topic;
privateExecutorService executor;
publicMyHighLevelConsumer(String a_zookeeper, String a_groupId, String a_topic) {
consumer = kafka.consumer.Consumer.createJavaConsumerConnector(createConsumerConfig(a_zookeeper,a_groupId));
this.topic = a_topic;
}
public voidshutdown() {
if(consumer != null) consumer.shutdown();
if(executor != null) executor.shutdown();
}
public voidrun(int a_numThreads) {
Map<String, Integer> topicCountMap = new HashMap<String,Integer>();
topicCountMap.put(topic, new Integer(a_numThreads));
Map<String, List<KafkaStream<byte[], byte[]>>>consumerMap = consumer.createMessageStreams(topicCountMap);
List<KafkaStream<byte[], byte[]>> streams =consumerMap.get(topic);
// nowlaunch all the threads
//
executor = Executors.newFixedThreadPool(a_numThreads);
// nowcreate an object to consume the messages
//
intthreadNumber = 0;
for(final KafkaStream stream : streams) {
executor.submit(new ConsumerTest(stream, threadNumber));
threadNumber++;
}
}
privatestatic ConsumerConfig createConsumerConfig(String a_zookeeper, Stringa_groupId) {
Properties props = new Properties();
props.put("zookeeper.connect", a_zookeeper);
props.put("group.id", a_groupId);
props.put("zookeeper.session.timeout.ms","4000");
props.put("zookeeper.sync.time.ms", "200");
props.put("auto.commit.interval.ms", "1000");
// props.put("auto.offset.reset", "smallest");
returnnew ConsumerConfig(props);
}
classConsumerTest implements Runnable {
privateKafkaStream<byte[], byte[]> m_stream;
privateint m_threadNumber;
publicConsumerTest(KafkaStream<byte[], byte[]> a_stream, int a_threadNumber) {
m_threadNumber = a_threadNumber;
m_stream = a_stream;
}
publicvoid run() {
ConsumerIterator<byte[], byte[]> it = m_stream.iterator();
while (it.hasNext())
System.out.println("Thread " + m_threadNumber + ": "+ new String(it.next().message()));
System.out.println("Shutting down Thread: " + m_threadNumber);
}
}
publicstatic void main(String[] args) {
// StringzooKeeper = args[0];
// String groupId = args[1];
// Stringtopic = args[2];
// intthreads = Integer.parseInt(args[3]);
// StringzooKeeper = "116.255.224.229:2182";
StringzooKeeper ="rs229:2181,rs227:2181,rs226:2181,rs198:2181,rs197:2181/kafka";
String groupId = "1";
Stringtopic = "flume-kafka-storm-001";
intthreads = 1;
MyHighLevelConsumer example = new MyHighLevelConsumer(zooKeeper,groupId, topic);
example.run(threads);
// try {
// Thread.sleep(1000);
// } catch(InterruptedException ie) {
//
// }
// example.shutdown();
}
}
# HighLevelKafkaSpout.java
package com.yting.cloud.storm.spout;
import java.util.Map;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
importcom.yting.cloud.kafa.consumer.MyHighLevelConsumer;
import kafka.javaapi.consumer.ConsumerConnector;
import backtype.storm.spout.SpoutOutputCollector;
import backtype.storm.task.TopologyContext;
import backtype.storm.topology.IRichSpout;
import backtype.storm.topology.OutputFieldsDeclarer;
import backtype.storm.tuple.Fields;
/**
* Storm spout
*
*
*/
public class HighLevelKafkaSpout implementsIRichSpout {
privatestatic final Log log = LogFactory.getLog(HighLevelKafkaSpout.class);
privateSpoutOutputCollector collector;
privateConsumerConnector consumer;
privateString topic;
privateint a_numThreads = 1;
publicHighLevelKafkaSpout() {
}
public HighLevelKafkaSpout(Stringtopic) {
this.topic= topic;
}
@Override
publicvoid nextTuple() {
}
@Override
publicvoid open(Map conf, TopologyContext context, SpoutOutputCollector collector) {
this.collector= collector;
}
@Override
public voidack(Object msgId) {
log.info("--------->ack");
}
@Override
publicvoid activate() {
log.info("--------->activatestart--------->");
MyHighLevelConsumer.main(null);
//这里的具体代码可以重构出来，还有collector.emit(newValues("need to emit"));这样的代码也还没写的，先意思一下了
log.info("--------->activateend--------->");
}
@Override
publicvoid close() {
log.info("--------->close");
}
@Override
publicvoid deactivate() {
log.info("--------->deactivate");
}
@Override
publicvoid fail(Object msgId) {
log.info("--------->fail");
}
@Override
publicvoid declareOutputFields(OutputFieldsDeclarer declarer) {
declarer.declare(newFields("highLevelKafkaSpout"));
}
@Override
publicMap<String, Object> getComponentConfiguration() {
log.info("--------->getComponentConfiguration");
returnnull;
}
}
# KafkaTopology.java
package com.yting.cloud.storm.topology;
import java.util.HashMap;
import java.util.Map;
import com.yting.cloud.storm.spout.HighLevelKafkaSpout;
import backtype.storm.Config;
import backtype.storm.LocalCluster;
import backtype.storm.topology.TopologyBuilder;
import backtype.storm.utils.Utils;
/**
* Stormtopology
*
*
*/
public class KafkaTopology {
publicstatic void main(String[] args) {
TopologyBuilderbuilder = new TopologyBuilder();
builder.setSpout("1",new HighLevelKafkaSpout(""), 1);
Mapconf = new HashMap();
conf.put(Config.TOPOLOGY_WORKERS,1);
conf.put(Config.TOPOLOGY_DEBUG,true);
LocalClustercluster = new LocalCluster();
cluster.submitTopology("my-flume-kafka-storm-topology-integration",conf, builder.createTopology());
Utils.sleep(1000*60*5);// local cluster test ...
cluster.shutdown();
}
}
# Storm jar 命令运行storm程序
[root@rs229 yjar]# ll
total 72
-rw-r--r-- 1 root root 19826 Jul 14 10:27fks-storm-0013.jar
-rw-r--r-- 1 root root 19833 Jul 14 10:31fks-storm-high-001.jar
-rw-r--r-- 1 root root 15149 Jul 7 17:43 storm-wordcount-official-cluster.jar
-rw-r--r-- 1 root root 15192 Jul 7 17:47 storm-wordcount-official-local.jar
[root@rs229 yjar]# pwd
/usr/local/adsit/yting/apache/storm/apache-storm-0.9.2-incubating/yjar
[root@rs229 yjar]# storm jarfks-storm-high-001.jar com.yting.cloud.storm.topology.KafkaTopology
日志信息太多了，随便弄一点吧！
14650 [main]INFO com.yting.cloud.storm.spout.HighLevelKafkaSpout - --------->close
14650 [main]INFO backtype.storm.daemon.executor -Shut down executor 1:[1 1]
14650 [main]INFO backtype.storm.daemon.worker - Shutdown executors
14650 [main]INFO backtype.storm.daemon.worker -Shutting down transfer thread
14651[Thread-14-disruptor-worker-transfer-queue] INFO backtype.storm.util - Async loop interrupted!
14651 [main]INFO backtype.storm.daemon.worker - Shutdown transfer thread
14652 [main]INFO backtype.storm.daemon.worker -Shutting down default resources
14653 [main]INFO backtype.storm.daemon.worker - Shutdown default resources
14661 [main]INFO backtype.storm.daemon.worker -Disconnecting from storm cluster state context
14664 [main]INFO backtype.storm.daemon.worker - Shutdown worker my-flume-kafka-storm-topology-integration-1-1405320692e0d44e3c-5b2a-4263-8dab-4aacf4215d2d 1024
14667 [main]INFO backtype.storm.daemon.supervisor -Shut downe0d44e3c-5b2a-4263-8dab-4aacf4215d2d:14d31572-9e60-4a16-9638-56c22530826d
14667 [main]IN
运行成功！
上传附件大小限制不能过10M，源代码下载地址为：http://download.csdn.net/detail/liyonghui123/7662063
转自：http://blog.csdn.net/u012185296/article/details/37762793
相关推荐
flume-1.5.0-cdh5.3.6。 大数据日志收集工具 flume-1.5.0-cdh5.3.6。 大数据日志收集工具flume-1.5.0-cdh5.3.6。 大数据日志收集工具flume-1.5.0-cdh5.3.6。 大数据日志收集工具flume-1.5.0-cdh5.3.6。 大数据日志...
flume-ng-1.5.0-cdh5.3.6.rarflume-ng-1.5.0-cdh5.3.6.rar flume-ng-1.5.0-cdh5.3.6.rar flume-ng-1.5.0-cdh5.3.6.rar flume-ng-1.5.0-cdh5.3.6.rar flume-ng-1.5.0-cdh5.3.6.rar flume-ng-1.5.0-cdh5.3.6.rar flume...
spark-streaming-flume-sink_2.11-2.0.0.jar的jar包。
Flume+kafka+Storm整合 示例简介： 以下为三个组建整合，这里只做操作也演示结果，原理性方面大家多学习基础。 流程顺序是flume获取telnet数据，将接收到的数据发送至kafak，kafka作为Storm的spout，Storm进行有向无...
基于Flume+Kafka+Hbase+Flink+FineBI的实时综合案例.txt基于Flume+Kafka+Hbase+Flink+FineBI的实时综合案例.txt基于Flume+Kafka+Hbase+Flink+FineBI的实时综合案例.txt基于Flume+Kafka+Hbase+Flink+FineBI的实时综合...
flume pull 方式需要的jar包，spark-streaming-flume-sink_2.11_2.1.1.jar
lnmp(linux+nginx+mysql+php)安装配置及分布式系统大数据处理hadoop集群中的flume+Kafka+Storm+HDFS等实时系统搭分享
spark-streaming-flume_2.11-2.1.0.jar
flume+kafka+flink+mysql实现nginx数据统计与分析
flume-ng-1.5.0-cdh5.3.6.tar.gz, 配置flume的原数据包
使用spark集成flume，由于flume默认只支持pull消息的方式，不过它可以自定义消息拉取方式，现要使用poll方式，可以使用spark-streaming-flume-sink_2.11-2.1.0.jar包下的org.apache.spark.streaming.flume.sink....
flume+Logstash+Kafka+Spark Streaming进行实时日志处理分析【大数据】
妳那伊抹微笑_Flume+Kafka+Storm分布式环境整合Eclipse工程_20140714.rar 该文档与教程http://blog.csdn.net/u012185296/article/details/37762793配套使用的，主要讲的是Flume+Kafka+Storm的环境整合，并且全部都是...
apache-flume-1.9.0-bin.tar，kafka_2.11-0.10.1.0，zookeeper-3.3.6_.tar 压缩 到了一个logs.rar文件中，需要的请下载
搭建Hadoop集群，并使用flume+kafka+storm+hbase实现日志抓取分析，使用一个主节点master、两个slave节点
大数据实习hdfs+flume+kafka+spark+hbase+hive项目.zip
技术方向：Flume+Kafka+Storm+Redis/Hbase+Hadoop+Hive+Mahout+Spark ... 云计算技术 版权声明：整理不易，且学且珍惜，仅供学习交流使用，未经允许不得用于任何商业用途，谢谢合作 qq交流群：214293307 云计算之...
本科毕业设计项目，基于spark streaming+flume+kafka+hbase的实时日志处理分析系统 基于spark streaming+flume+kafka+hbase的实时日志处理分析系统 本科毕业设计项目，基于spark streaming+flume+kafka+hbase的...
log4j+flume+kafka+storm整合