Kafka分区与消费者的关系

bin/kafka-topics.sh --zookeeper localhost:2181 --create --topic my-topic --partitions 2 --replication-factor 1

[root@localhost kafka_2.11-2.0.0]# bin/kafka-topics.sh --describe --zookeeper localhost:2181 --topic abc
Topic:abc       PartitionCount:2        ReplicationFactor:1     Configs:
        Topic: abc      Partition: 0    Leader: 0       Replicas: 0     Isr: 0
        Topic: abc      Partition: 1    Leader: 0       Replicas: 0     Isr: 0

/**
 * Compute the partition for the given record.
 *
 * @param topic The topic name
 * @param key The key to partition on (or null if no key)
 * @param keyBytes serialized key to partition on (or null if no key)
 * @param value The value to partition on or null
 * @param valueBytes serialized value to partition on or null
 * @param cluster The current cluster metadata
 */
public int partition(String topic, Object key, byte[] keyBytes, Object value, byte[] valueBytes, Cluster cluster) {
    List<PartitionInfo> partitions = cluster.partitionsForTopic(topic);
    int numPartitions = partitions.size();
    if (keyBytes == null) {
        int nextValue = nextValue(topic);
        List<PartitionInfo> availablePartitions = cluster.availablePartitionsForTopic(topic);
        if (availablePartitions.size() > 0) {
            int part = Utils.toPositive(nextValue) % availablePartitions.size();
            return availablePartitions.get(part).partition();
        } else {
            // no partitions are available, give a non-available partition
            return Utils.toPositive(nextValue) % numPartitions;
        }
    } else {
        // hash the keyBytes to choose a partition
        return Utils.toPositive(Utils.murmur2(keyBytes)) % numPartitions;
    }
}

/**
 * The range assignor works on a per-topic basis. For each topic, we lay out the available partitions in numeric order
 * and the consumers in lexicographic order. We then divide the number of partitions by the total number of
 * consumers to determine the number of partitions to assign to each consumer. If it does not evenly
 * divide, then the first few consumers will have one extra partition.
 *
 * For example, suppose there are two consumers C0 and C1, two topics t0 and t1, and each topic has 3 partitions,
 * resulting in partitions t0p0, t0p1, t0p2, t1p0, t1p1, and t1p2.
 *
 * The assignment will be:
 * C0: [t0p0, t0p1, t1p0, t1p1]
 * C1: [t0p2, t1p2]
 */

public Map<String, List<TopicPartition>> assign(Map<String, Integer> partitionsPerTopic,
                                                    Map<String, Subscription> subscriptions) {
    //    主题与消费者的映射                                                            
    Map<String, List<String>> consumersPerTopic = consumersPerTopic(subscriptions);
    Map<String, List<TopicPartition>> assignment = new HashMap<>();
    for (String memberId : subscriptions.keySet())
        assignment.put(memberId, new ArrayList<TopicPartition>());

    for (Map.Entry<String, List<String>> topicEntry : consumersPerTopic.entrySet()) {
        String topic = topicEntry.getKey();    //    主题
        List<String> consumersForTopic = topicEntry.getValue();    //    消费者列表

        //    partitionsPerTopic表示主题和分区数的映射
        //    获取主题下有多少个分区
        Integer numPartitionsForTopic = partitionsPerTopic.get(topic);
        if (numPartitionsForTopic == null)
            continue;

        //    消费者按字典序排序
        Collections.sort(consumersForTopic);

        //    分区数量除以消费者数量
        int numPartitionsPerConsumer = numPartitionsForTopic / consumersForTopic.size();
        //    取模，余数就是额外的分区
        int consumersWithExtraPartition = numPartitionsForTopic % consumersForTopic.size();

        List<TopicPartition> partitions = AbstractPartitionAssignor.partitions(topic, numPartitionsForTopic);
        for (int i = 0, n = consumersForTopic.size(); i < n; i++) {
            int start = numPartitionsPerConsumer * i + Math.min(i, consumersWithExtraPartition);
            int length = numPartitionsPerConsumer + (i + 1 > consumersWithExtraPartition ? 0 : 1);
            //    分配分区
            assignment.get(consumersForTopic.get(i)).addAll(partitions.subList(start, start + length));
        }
    }
    return assignment;
}

/**
 * The round robin assignor lays out all the available partitions and all the available consumers. It
 * then proceeds to do a round robin assignment from partition to consumer. If the subscriptions of all consumer
 * instances are identical, then the partitions will be uniformly distributed. (i.e., the partition ownership counts
 * will be within a delta of exactly one across all consumers.)
 *
 * For example, suppose there are two consumers C0 and C1, two topics t0 and t1, and each topic has 3 partitions,
 * resulting in partitions t0p0, t0p1, t0p2, t1p0, t1p1, and t1p2.
 *
 * The assignment will be:
 * C0: [t0p0, t0p2, t1p1]
 * C1: [t0p1, t1p0, t1p2]
 *
 * When subscriptions differ across consumer instances, the assignment process still considers each
 * consumer instance in round robin fashion but skips over an instance if it is not subscribed to
 * the topic. Unlike the case when subscriptions are identical, this can result in imbalanced
 * assignments. For example, we have three consumers C0, C1, C2, and three topics t0, t1, t2,
 * with 1, 2, and 3 partitions, respectively. Therefore, the partitions are t0p0, t1p0, t1p1, t2p0,
 * t2p1, t2p2. C0 is subscribed to t0; C1 is subscribed to t0, t1; and C2 is subscribed to t0, t1, t2.
 *
 * Tha assignment will be:
 * C0: [t0p0]
 * C1: [t1p0]
 * C2: [t1p1, t2p0, t2p1, t2p2]
 */

<?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.cjs.example</groupId>
    <artifactId>kafka-demo</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <packaging>jar</packaging>

    <name>kafka-demo</name>
    <description></description>

    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.0.5.RELEASE</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <java.version>1.8</java.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.kafka</groupId>
            <artifactId>spring-kafka</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
            </plugin>
        </plugins>
    </build>

</project>

package com.cjs.kafka.producer;

import org.apache.kafka.clients.producer.*;

import java.util.Properties;

public class HelloProducer {

    public static void main(String[] args) {

        Properties props = new Properties();
        props.put("bootstrap.servers", "192.168.1.133:9092");
        props.put("acks", "all");
        props.put("retries", 0);
        props.put("batch.size", 16384);
        props.put("linger.ms", 1);
        props.put("buffer.memory", 33554432);
        props.put("key.serializer", "org.apache.kafka.common.serialization.StringSerializer");
        props.put("value.serializer", "org.apache.kafka.common.serialization.StringSerializer");

        Producer<String, String> producer = new KafkaProducer<String, String>(props);
        for (int i = 0; i < 100; i++) {
            producer.send(new ProducerRecord<String, String>("abc", Integer.toString(i), Integer.toString(i)), new Callback() {
                @Override
                public void onCompletion(RecordMetadata recordMetadata, Exception e) {
                    if (null != e) {
                        e.printStackTrace();
                    }else {
                        System.out.println("callback: " + recordMetadata.topic() + " " + recordMetadata.partition() + " " + recordMetadata.offset());
                    }
                }
            });
        }
        producer.close();

    }
}

package com.cjs.kafka.consumer;

import org.apache.kafka.clients.consumer.ConsumerRecord;
import org.apache.kafka.clients.consumer.ConsumerRecords;
import org.apache.kafka.clients.consumer.KafkaConsumer;

import java.util.Arrays;
import java.util.Properties;

public class HelloConsumer {

    public static void main(String[] args) {
        Properties props = new Properties();
        props.put("bootstrap.servers", "192.168.1.133:9092");
        props.put("group.id", "test");
        props.put("enable.auto.commit", "true");
        props.put("auto.commit.interval.ms", "1000");
//        props.put("partition.assignment.strategy", "org.apache.kafka.clients.consumer.RoundRobinAssignor");
        props.put("key.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        props.put("value.deserializer", "org.apache.kafka.common.serialization.StringDeserializer");
        KafkaConsumer<String, String> consumer = new KafkaConsumer<String, String>(props);
        consumer.subscribe(Arrays.asList("foo", "bar", "abc"));
        while (true) {
            ConsumerRecords<String, String> records = consumer.poll(100);
            for (ConsumerRecord<String, String> record : records) {
                System.out.printf("partition = %s, offset = %d, key = %s, value = %s%n", record.partition(), record.offset(), record.key(), record.value());
            }
        }
    }
}