centos下安装单机版kafka-0.10.0.1

1.环境说明

主机信息如下:

1

[root@test1 soft]# hostname

2

test1

3

[root@test1 soft]# cat /etc/hosts

4

127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4

5

::1         localhost localhost.localdomain localhost6 localhost6.localdomain6

6

192.168.56.91 test1 

7

192.168.56.92 test2 

8

192.168.56.93 test3 

9

192.168.56.1  PC-201306171517

10

操作系统版本如下:

1

[root@test1 soft]# cat /etc/redhat-release 

2

CentOS release 6.4 (Final)

3

[root@test1 soft]# uname -a

4

Linux test1 2.6.32-358.el6.x86_64 #1 SMP Fri Feb 22 00:31:26 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux

5

2.下载kafka

下载地址如下:

http://kafka.apache.org/downloads

我这里使用 Scala 2.11  -  kafka_2.11-0.10.0.1.tgz  ( asc ,  md5 )版本

3.安装配置kafka

一.解压缩kafka

1

[root@test1 soft]# tar zxvf kafka_2.11-0.10.0.1.tgz -C /root/kafka

二.配置zookeeper

由于kafka需要使用到zookeeper来注册信息,因此需要首先配置zookeeper.在kafka的安装包中已经提供了zookeeper,不需要额外安装,直接配置一下即可.配置文件在config下的zookeeper. properties

1

[root@test1 config]# cat zookeeper.properties 

2

# Licensed to the Apache Software Foundation (ASF) under one or more

3

# contributor license agreements.  See the NOTICE file distributed with

4

# this work for additional information regarding copyright ownership.

5

# The ASF licenses this file to You under the Apache License, Version 2.0

6

# (the "License"); you may not use this file except in compliance with

7

# the License.  You may obtain a copy of the License at

8

# 

9

#    http://www.apache.org/licenses/LICENSE-2.0

10

# 

11

# Unless required by applicable law or agreed to in writing, software

12

# distributed under the License is distributed on an "AS IS" BASIS,

13

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

14

# See the License for the specific language governing permissions and

15

# limitations under the License.

16

# the directory where the snapshot is stored.

17

dataDir=/root/kafka/kafka_2.11-0.10.0.1/zoodata                       ###########这里修改zookeeper的快照目录,需要事先在文件系统上创建目录,其它默认即可.

18

# the port at which the clients will connect

19

clientPort=2181        #默认端口号2181

20

# disable the per-ip limit on the number of connections since this is a non-production config

21

maxClientCnxns=0

22

三.配置kafka

kafka的配置文件在config下的server.properties文件.下面是一个配置实例:

1

[root@test1 config]# pwd

2

/root/kafka/kafka_2.11-0.10.0.1/config

3

[root@test1 config]# cat server.properties 

4

# Licensed to the Apache Software Foundation (ASF) under one or more

5

# contributor license agreements.  See the NOTICE file distributed with

6

# this work for additional information regarding copyright ownership.

7

# The ASF licenses this file to You under the Apache License, Version 2.0

8

# (the "License"); you may not use this file except in compliance with

9

# the License.  You may obtain a copy of the License at

10

#

11

#    http://www.apache.org/licenses/LICENSE-2.0

12

#

13

# Unless required by applicable law or agreed to in writing, software

14

# distributed under the License is distributed on an "AS IS" BASIS,

15

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

16

# See the License for the specific language governing permissions and

17

# limitations under the License.

18

# see kafka.server.KafkaConfig for additional details and defaults

19

20

############################# Server Basics #############################

21

22

# The id of the broker. This must be set to a unique integer for each broker.

23

broker.id=0                                                                                    ############################这里是主机的id,类似于zookeeper的id

24

25

############################# Socket Server Settings #############################

26

27

# The address the socket server listens on. It will get the value returned from 

28

# java.net.InetAddress.getCanonicalHostName() if not configured.

29

#   FORMAT:

30

#     listeners = security_protocol://host_name:port

31

#   EXAMPLE:

32

#     listeners = PLAINTEXT://your.host.name:9092

33

#listeners=PLAINTEXT://:9092

34

35

# Hostname and port the broker will advertise to producers and consumers. If not set, 

36

# it uses the value for "listeners" if configured.  Otherwise, it will use the value

37

# returned from java.net.InetAddress.getCanonicalHostName().

38

#advertised.listeners=PLAINTEXT://your.host.name:9092                                         ###########默认的端口是9092,如果需要修改端口,需要添加port参数port=9093.再将advertised.listeners同时修改

39

40

# The number of threads handling network requests

41

num.network.threads=3

42

43

# The number of threads doing disk I/O

44

num.io.threads=8

45

46

# The send buffer (SO_SNDBUF) used by the socket server

47

socket.send.buffer.bytes=102400

48

49

# The receive buffer (SO_RCVBUF) used by the socket server

50

socket.receive.buffer.bytes=102400

51

52

# The maximum size of a request that the socket server will accept (protection against OOM)

53

socket.request.max.bytes=104857600

54

55

56

############################# Log Basics #############################

57

58

# A comma seperated list of directories under which to store log files

59

log.dirs=/root/kafka/kafka_2.11-0.10.0.1/logs                                                  ####################################这里是kafka的log目录,根据需要修改.

60

61

# The default number of log partitions per topic. More partitions allow greater

62

# parallelism for consumption, but this will also result in more files across

63

# the brokers.

64

num.partitions=1

65

66

# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.

67

# This value is recommended to be increased for installations with data dirs located in RAID array.

68

num.recovery.threads.per.data.dir=1

69

70

############################# Log Flush Policy #############################

71

72

# Messages are immediately written to the filesystem but by default we only fsync() to sync

73

# the OS cache lazily. The following configurations control the flush of data to disk.

74

# There are a few important trade-offs here:

75

#    1. Durability: Unflushed data may be lost if you are not using replication.

76

#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.

77

#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.

78

# The settings below allow one to configure the flush policy to flush data after a period of time or

79

# every N messages (or both). This can be done globally and overridden on a per-topic basis.

80

81

# The number of messages to accept before forcing a flush of data to disk

82

#log.flush.interval.messages=10000

83

84

# The maximum amount of time a message can sit in a log before we force a flush

85

#log.flush.interval.ms=1000

86

87

############################# Log Retention Policy #############################

88

89

# The following configurations control the disposal of log segments. The policy can

90

# be set to delete segments after a period of time, or after a given size has accumulated.

91

# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens

92

# from the end of the log.

93

94

# The minimum age of a log file to be eligible for deletion

95

log.retention.hours=168

96

97

# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining

98

# segments don't drop below log.retention.bytes.

99

#log.retention.bytes=1073741824

100

101

# The maximum size of a log segment file. When this size is reached a new log segment will be created.

102

log.segment.bytes=1073741824

103

104

# The interval at which log segments are checked to see if they can be deleted according

105

# to the retention policies

106

log.retention.check.interval.ms=300000

107

108

############################# Zookeeper #############################

109

110

# Zookeeper connection string (see zookeeper docs for details).

111

# This is a comma separated host:port pairs, each corresponding to a zk

112

# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".

113

# You can also append an optional chroot string to the urls to specify the

114

# root directory for all kafka znodes.

115

zookeeper.connect=localhost:2181

116

117

# Timeout in ms for connecting to zookeeper

118

zookeeper.connection.timeout.ms=6000

119

120

4.启动kafka

为了方便可以将kafka的运行目录添加到PATH环境变量中.

首先使用命令 bin/zookeeper-server-start.sh config/zookeeper.properties
启动zookeeper.

1

[root@test1 kafka_2.11-0.10.0.1]# nohup ./bin/zookeeper-server-start.sh config/zookeeper.properties &

2

[1] 1888

3

[root@test1 kafka_2.11-0.10.0.1]# nohup: ignoring input and appending output to `nohup.out'

4

5

[root@test1 kafka_2.11-0.10.0.1]# jps

6

1888 QuorumPeerMain

7

2118 Jps

8

再使用命令 bin/kafka-server-start.sh config/server.properties
启动kafka

1

[root@test1 kafka_2.11-0.10.0.1]# nohup ./bin/kafka-server-start.sh config/server.properties &

2

[2] 2146

3

[root@test1 kafka_2.11-0.10.0.1]# nohup: ignoring input and appending output to `nohup.out'

4

5

[root@test1 kafka_2.11-0.10.0.1]# jps

6

1888 QuorumPeerMain

7

2146 Kafka

8

2411 Jps

9

5.模拟测试kafka发布订阅

新建一个窗口模拟producer,执行:

kafka-console-producer.sh --broker-list localhost:9092 --topic

然后在窗口中随便输入

1

[root@test1 kafka]# kafka-console-producer.sh --broker-list localhost:9092 --topic test

2

aaaa

3

bbbb

4

在另外一个窗口中模拟consumer,执行:

[root@test1 ~]# kafka-console-consumer.sh --zookeeper localhost:2181 --topic test1 --from-beginning

然后会发现producer的输入会实时的发布到consumer中

1

[root@test1 ~]# kafka-console-consumer.sh --zookeeper localhost:2181 --topic test1 --from-beginning

2

aaaa

3

bbbb

4

创建主题:

1

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

查看主题:

1

 bin/kafka-topics.sh --list --zookeeper localhost:2181