Hadoop2.9.2高可用环境搭建

作者: doublegao | 来源:发表于2019-08-28 09:20 被阅读0次

1.环境准备和部署规划

硬件和规划

序号	主机	内存	系统	组件规划	进程
1	10.110.172.151	32	Centos6.5	jdk-8u221、hadoop2.9.2	DataNode、NodeManager、JournalNode
2	10.110.172.152	32	Centos6.5	jdk-8u221、hadoop2.9.2	DataNode、NodeManager、JournalNode
3	10.110.172.153	32	Centos6.5	jdk-8u221、hadoop2.9.2	DataNode、NodeManager、JournalNode
4	10.110.172.154	16	Centos6.5	jdk-8u221、hadoop2.9.2、zookeeper3.4.14	ResourceManager、NameNode、zkfc、zookeeper
5	10.110.172.155	16	Centos6.5	jdk-8u221、hadoop2.9.2、zookeeper3.4.14	ResourceManager、NameNode、zkfc、zookeeper
6	10.110.172.156	8	Centos6.5	jdk-8u221、zookeeper3.4.14	zookeeper

[root@hnxxzxfzjz001 /]# tree /data
/data
├── cloud  #组件安装目录
│   ├── hadoop
│   ├── jdk
│   └── zookeeper
├── soft #软件包存放位置
└── work #组件工作目录
    ├── hadoop
    └── zookeeper

7 directories, 0 files

2.部署安装

主机初始化准备（参数设置，免密配置）

#卸载原有低版本JDK
[root@hnxxzxfzjz001 cloud]# rpm -qa | grep java
tzdata-java-2013g-1.el6.noarch
java-1.7.0-openjdk-1.7.0.45-2.4.3.3.el6.x86_64
java-1.6.0-openjdk-1.6.0.0-1.66.1.13.0.el6.x86_64
[root@hnxxzxfzjz001 cloud]# rpm -e java-1.7.0-openjdk-1.7.0.45-2.4.3.3.el6.x86_64
[root@hnxxzxfzjz001 cloud]# rpm -e java-1.6.0-openjdk-1.6.0.0-1.66.1.13.0.el6.x86_64
[root@hnxxzxfzjz001 cloud]# rpm -e tzdata-java-2013g-1.el6.noarch
#同步时间
[root@hnxxzxfzjz001 soft]# ntpdate 120.25.115.20
#每台主机都配置
[root@hnxxzxfzjz001 soft]# cat /etc/hosts
127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
10.110.172.151 hnxxzxfzjz001
10.110.172.152 hnxxzxfzjz002
10.110.172.153 hnxxzxfzjz003
10.110.172.154 hnxxzxfzjz004
10.110.172.155 hnxxzxfzjz005
10.110.172.156 hnxxzxfzjz006
#关闭selinux，修改enforcing为disabled
[root@hnxxzxfzjz001 ~]#vim /etc/sysconfig/selinux
[root@hnxxzxfzjz001 ~]# setenforce 0
#查看防火墙状态
[root@hnxxzxfzjz001 ~]# service iptables status
#关闭防火墙
[root@hnxxzxfzjz001 ~]# service iptables stop
#永久关闭防火墙
[root@hnxxzxfzjz001 ~]# chkconfig iptables off

免密配置（也可以通过脚本或者借助k8s等部署）

#生成秘钥和公钥（每台）
[root@hnxxzxfzjz003 ~]#  ssh-keygen
Generating public/private rsa key pair.
Enter file in which to save the key (/root/.ssh/id_rsa): 
Created directory '/root/.ssh'.
Enter passphrase (empty for no passphrase): 
Enter same passphrase again: 
Your identification has been saved in /root/.ssh/id_rsa.
Your public key has been saved in /root/.ssh/id_rsa.pub.
The key fingerprint is:
78:6f:f6:92:51:72:7f:4b:a2:df:2e:63:b7:43:11:92 root@hnxxzxfzjz003
The key's randomart image is:
+--[ RSA 2048]----+
|              .  |
|             E . |
|              . .|
|       .  . o  . |
|      . S  + .  .|
|       . ..  ..o.|
|          +o. +..|
|         ooo +.+ |
|           .+.=+o|
+-----------------+

#将所有主机上的公钥拷贝到其中一台机器（此处为10.110.172.151），每台都执行，包括自身
[root@hnxxzxfzjz003 ~]# ssh-copy-id -i ~/.ssh/id_rsa.pub root@10.110.172.151
#将所有主机的公钥集合~/.ssh/authorized_keys 拷贝给其他主机
[root@hnxxzxfzjz001 ~]#scp ~/.ssh/authorized_keys root@10.110.172.155:~/.ssh/
#测试ssh免密
[root@hnxxzxfzjz001 ~]# ssh  10.110.172.153
Last login: Tue Aug 27 02:02:28 2019 from hnxxzxfzjz001
[root@hnxxzxfzjz003 ~]# exit
[root@hnxxzxfzjz001 ~]#

软件准备

[root@hnxxzxfzjz001 soft]# ll
total 585180
-rw-r--r--. 1 root root 366447449 Aug 26 15:04 hadoop-2.9.2.tar.gz
-rw-r--r--. 1 root root 195094741 Aug 26 16:16 jdk-8u221-linux-x64.tar.gz
-rw-r--r--. 1 root root  37676320 Aug 26 14:54 zookeeper-3.4.14.tar.gz

JDK安装配置（所有机器）

[root@hnxxzxfzjz001 cloud]# cp ../soft/jdk-8u221-linux-x64.tar.gz .
[root@hnxxzxfzjz001 cloud]# tar -zxvf  jdk-8u221-linux-x64.tar.gz
[root@hnxxzxfzjz001 cloud]# mv jdk1.8.0_221/ jdk

配置环境变量

export JAVA_HOME=/data/cloud/jdk
export HADOOP_HOME=/data/cloud/hadoop
export ZK_HOME=/data/cloud/zookeeper
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/sbin:$ZK_HOME/bin:$HADOOP_HOME/bin

zookeeper安装配置（154、155、156）

[root@hnxxzxfzjz004 cloud]# cp ../soft/zookeeper-3.4.14.tar.gz .
[root@hnxxzxfzjz004 cloud]# tar -zxvf   zookeeper-3.4.14.tar.gz
[root@hnxxzxfzjz004 cloud]# mv zookeeper-3.4.14/ zookeeper
#配置文件
[root@hnxxzxfzjz004 cloud]# cd /data/cloud/zookeeper/conf
[root@hnxxzxfzjz004 conf]#  mv zoo_sample.cfg  zoo.cfg
[root@hnxxzxfzjz004 conf]#  cat  zoo.cfg
tickTime=2000
# The number of ticks that the initial
# synchronization phase can take
initLimit=10
# The number of ticks that can pass between
# sending a request and getting an acknowledgement
syncLimit=5
# the directory where the snapshot is stored.
# do not use /tmp for storage, /tmp here is just
# example sakes.
dataDir=/data/work/zookeeper/data
# the port at which the clients will connect
clientPort=2181
# the maximum number of client connections.
# increase this if you need to handle more clients
#maxClientCnxns=60
#
# Be sure to read the maintenance section of the
# administrator guide before turning on autopurge.
#
# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#
# The number of snapshots to retain in dataDir
#autopurge.snapRetainCount=3
# Purge task interval in hours
# Set to "0" to disable auto purge feature
#autopurge.purgeInterval=1
server.1=10.110.172.154:2888:3888
server.2=10.110.172.155:2888:3888
server.3=10.110.172.156:2888:3888
# 建立myid
[root@hnxxzxfzjz004 conf]# mkdir -p /data/work/zookeeper/data
[root@hnxxzxfzjz004 conf]# cd  /data/work/zookeeper/data
[root@hnxxzxfzjz004 data]# echo "1" > myid
#为了方便操作添加环境变量
# export ZK_HOME=/data/cloud/zookeeper
# export PATH=$PATH:$ZK_HOME/bin
[root@hnxxzxfzjz004 data]# 
#启动zookeeper
[root@hnxxzxfzjz006 ~]# zkServer.sh start
ZooKeeper JMX enabled by default
Using config: /data/cloud/zookeeper/bin/../conf/zoo.cfg
Starting zookeeper ... STARTED
#154、155、为Mode: follower
[root@hnxxzxfzjz006 ~]# zkServer.sh status
ZooKeeper JMX enabled by default
Using config: /data/cloud/zookeeper/bin/../conf/zoo.cfg
Mode: leader

Hadoop安装配置
/data/cloud/hadoop/etc/hadoop/hadoop-env.sh增加

export JAVA_HOME=/data/cloud/jdk
export HADOOP_NAMENODE_OPTS="-XX:+UseParallelGC"
export HADOOP_PID_DIR=/data/work/hadoop
export HADOOP_LOG_DIR=/data/work/hadoop/logs

/data/cloud/hadoop/etc/hadoop/yarn-env.sh

export JAVA_HOME=/data/cloud/jdk

/data/cloud/hadoop/etc/hadoop/hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

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

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>
<property>
   <name>dfs.nameservices</name>
   <value>hnqx</value>
</property>
<property>
   <name>dfs.ha.namenodes.hnqx</name>
   <value>nn1,nn2</value>
</property>
<property>
   <name>dfs.namenode.rpc-address.hnqx.nn1</name>
   <value>hnxxzxfzjz004:8020</value>
</property>
<property>
   <name>dfs.namenode.rpc-address.hnqx.nn2</name>
   <value>hnxxzxfzjz005:8020</value>
</property>
<property>
   <name>dfs.namenode.http-address.hnqx.nn1</name>
   <value>hnxxzxfzjz004:50070</value>
</property>
<property>
   <name>dfs.namenode.http-address.hnqx.nn2</name>
   <value>hnxxzxfzjz005:50070</value>
</property>
<property>
   <name>dfs.namenode.shared.edits.dir</name>
   <value>qjournal://hnxxzxfzjz001:8485;hnxxzxfzjz002:8485;hnxxzxfzjz003:8485/hnqx</value>
</property>
<property>
   <name>dfs.client.failover.proxy.provider.hnqx</name>
   <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
   <name>dfs.ha.fencing.methods</name>
   <value>sshfence</value>
</property>
<property>
   <name>dfs.ha.fencing.ssh.private-key-files</name>
   <value>~/.ssh/id_rsa</value>
</property>
<property>
   <name>dfs.ha.automatic-failover.enabled</name>
   <value>true</value>
</property>
<property>
   <name>dfs.ha.fencing.ssh.connect-timeout</name>
   <value>30000</value>
</property>
<property>
   <name>dfs.journalnode.edits.dir</name>
   <value>/data/work/hadoop/journaldata</value>
</property>
<property>
   <name>dfs.namenode.name.dir</name>
   <value>/data/work/hadoop/dfs/name</value>
   <description>Path on the local filesystem where theNameNode stores the namespace and transactions logs persistently.</description>
</property>
<property>
   <name>dfs.datanode.data.dir</name>
   <value>/data/work/hadoop/dfs/data</value>
   <description>Comma separated list of paths on the localfilesystem of a DataNode where it should store its blocks.</description>
</property>
<property>
   <name>dfs.replication</name>
   <value>2</value>
</property>
<property>  
<name>dfs.ha.fencing.methods</name>  
<value>
sshfence
shell(/bin/true)  
</value>  
</property>
</configuration>

/data/cloud/hadoop/etc/hadoop/core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

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

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>
<!-- 指定hdfs路径nameservice为ns1 -->
<property>
  <name>fs.defaultFS</name>
  <value>hdfs://hnqx</value>
</property>
<property>
  <name>io.file.buffer.size</name>
  <value>131072</value>
</property>
<!-- hadoop临时目录 -->
<property>
  <name>hadoop.tmp.dir</name>
  <value>/data/work/hadoop/tmp</value>
</property>
<!-- zookeeper配置-->
<property>
  <name>ha.zookeeper.quorum</name>
 <value>10.110.172.154:2181,10.110.172.155:2181,10.110.172.156:2181</value>
</property>
</configuration>

/data/cloud/hadoop/etc/hadoop/mapred-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

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

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->

<!-- Put site-specific property overrides in this file. -->

<configuration>
<property>
  <name>mapreduce.framework.name</name>
   <value>yarn</value>
</property>
<property>
   <name>mapreduce.application.classpath</name>
   <value>/data/cloud/hadoop/share/hadoop/mapreduce/*, /data/cloud/hadoop/share/hadoop/mapreduce/lib/*</value>
</property>
</configuration>

/data/cloud/hadoop/etc/hadoop/yarn-site.xml

<?xml version="1.0"?>
<!--
  Licensed under the Apache License, Version 2.0 (the "License");
  you may not use this file except in compliance with the License.
  You may obtain a copy of the License at

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

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->
<configuration>

<!-- 开启RM高可用 -->
<property>
  <name>yarn.resourcemanager.ha.enabled</name>
  <value>true</value>
</property>
<!-- 指定RM的cluster id -->
<property>
  <name>yarn.resourcemanager.cluster-id</name>
  <value>yrc</value>
</property>
<!-- 指定RM的名字 -->
<property>
  <name>yarn.resourcemanager.ha.rm-ids</name>
  <value>rm1,rm2</value>
</property>
<!-- 分别指定RM的地址 -->
<property>
  <name>yarn.resourcemanager.hostname.rm1</name>
  <value>hnxxzxfzjz004</value>
</property>
<property>
  <name>yarn.resourcemanager.hostname.rm2</name>
  <value>hnxxzxfzjz005</value>
</property>
<!-- 表示rm1，rm2的网页访问地址和端口，也即通过该地址和端口可访问作业情况 -->
<property>
  <name>yarn.resourcemanager.webapp.address.rm1</name>
  <value>hnxxzxfzjz004:8088</value>
</property>
<property>
  <name>yarn.resourcemanager.webapp.address.rm2</name>
  <value>hnxxzxfzjz005:8088</value>
</property>
<!-- 指定zk集群地址 -->
<property>
  <name>yarn.resourcemanager.zk-address</name>
  <value>hnxxzxfzjz004:2181,hnxxzxfzjz005:2181,hnxxzxfzjz006:2181</value>
</property>
<property>
  <name>yarn.nodemanager.aux-services</name>
  <value>mapreduce_shuffle</value>
</property>
<property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>2000</value>
 </property>
 <property>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
        <value>1</value>
 </property>
<property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>2000</value>
 </property>
 <property>
        <name>yarn.scheduler.maximum-allocation-vcores</name>
        <value>2</value>
 </property>
</configuration>

hadoop的启动和初始化

#[10.110.172.152，10.110.172.154，10.110.172.155]
[root@hnxxzxfzjz004 /]# hadoop-daemon.sh start journalnode
#HDFS初始化
[root@hnxxzxfzjz004 /]#  hdfs namenode -format hnqx
#启动namenode
[root@hnxxzxfzjz004 /]#  hadoop-daemon.sh start namenode
#转到10.110.172.155，同步hdfs初始化数据，返回10.110.172.154
[root@hnxxzxfzjz005 /]#  hdfs namenode -bootstrapStandby 
#格式化zkfc,
[root@hnxxzxfzjz004 /]#  hdfs zkfc -formatZK
.....省略n个字
19/08/27 16:34:48 INFO ha.ActiveStandbyElector: Session connected.
19/08/27 16:34:48 INFO ha.ActiveStandbyElector: Successfully created /hadoop-ha/hnqx in ZK.
19/08/27 16:34:48 INFO zookeeper.ZooKeeper: Session: 0x2000001ce8d0000 closed
19/08/27 16:34:48 INFO zookeeper.ClientCnxn: EventThread shut down
19/08/27 16:34:48 INFO tools.DFSZKFailoverController: SHUTDOWN_MSG: 
/************************************************************
SHUTDOWN_MSG: Shutting down DFSZKFailoverController at hnxxzxfzjz004/10.110.172.154
************************************************************/
#停止除zookeeper之外所有组件,启动start-dfs.sh
[root@hnxxzxfzjz004 bin]# start-dfs.sh
19/08/27 16:35:34 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Starting namenodes on [hnxxzxfzjz004 hnxxzxfzjz005]
hnxxzxfzjz005: starting namenode, logging to /data/work/hadoop/logs/hadoop-root-namenode-hnxxzxfzjz005.out
hnxxzxfzjz004: starting namenode, logging to /data/work/hadoop/logs/hadoop-root-namenode-hnxxzxfzjz004.out
hnxxzxfzjz002: starting datanode, logging to /data/work/hadoop/logs/hadoop-root-datanode-hnxxzxfzjz002.out
hnxxzxfzjz003: starting datanode, logging to /data/work/hadoop/logs/hadoop-root-datanode-hnxxzxfzjz003.out
hnxxzxfzjz001: starting datanode, logging to /data/work/hadoop/logs/hadoop-root-datanode-hnxxzxfzjz001.out
Starting journal nodes [hnxxzxfzjz004 hnxxzxfzjz005 hnxxzxfzjz002]
hnxxzxfzjz005: starting journalnode, logging to /data/work/hadoop/logs/hadoop-root-journalnode-hnxxzxfzjz005.out
hnxxzxfzjz004: starting journalnode, logging to /data/work/hadoop/logs/hadoop-root-journalnode-hnxxzxfzjz004.out
hnxxzxfzjz002: starting journalnode, logging to /data/work/hadoop/logs/hadoop-root-journalnode-hnxxzxfzjz002.out
19/08/27 16:35:51 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Starting ZK Failover Controllers on NN hosts [hnxxzxfzjz004 hnxxzxfzjz005]
hnxxzxfzjz005: starting zkfc, logging to /data/work/hadoop/logs/hadoop-root-zkfc-hnxxzxfzjz005.out
hnxxzxfzjz004: starting zkfc, logging to /data/work/hadoop/logs/hadoop-root-zkfc-hnxxzxfzjz004.out
#进程检查
[root@hnxxzxfzjz004 bin]# jps
5488 DFSZKFailoverController
5760 Jps
28913 QuorumPeerMain
5045 NameNode
5289 JournalNode

访问测试
active节点
active节点
standby节点
standby节点

存活的datanode节点

datanode

datanode使用情况

namenode节点

namenode节点

文件上传测试

[root@hnxxzxfzjz004 bin]# echo "hdfs file test" > hnqx.txt
[root@hnxxzxfzjz004 bin]# ./hadoop fs -put hnqx.txt /hnqx
19/08/27 19:08:48 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
put: `/hnqx': File exists
[root@hnxxzxfzjz004 bin]# ./hadoop fs -ls /hnqx
19/08/27 19:10:51 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
-rw-r--r--   2 root supergroup         15 2019-08-27 19:06 /hnqx

浏览器中查看

image.png

YARN启动

[root@hnxxzxfzjz004 hadoop]# start-yarn.sh
starting yarn daemons
starting resourcemanager, logging to /data/cloud/hadoop/logs/yarn-root-resourcemanager-hnxxzxfzjz004.out
hnxxzxfzjz003: starting nodemanager, logging to /data/cloud/hadoop/logs/yarn-root-nodemanager-hnxxzxfzjz003.out
hnxxzxfzjz001: starting nodemanager, logging to /data/cloud/hadoop/logs/yarn-root-nodemanager-hnxxzxfzjz001.out
hnxxzxfzjz002: starting nodemanager, logging to /data/cloud/hadoop/logs/yarn-root-nodemanager-hnxxzxfzjz002.out
#启动resourceManager
[root@hnxxzxfzjz004 hadoop]# yarn-daemon.sh start resourcemanager

Hadoop集群状态
active节点10.110.172.154
Hadoop集群状态

standby节点10.110.172.155

standby节点

wordcount测试

#目录/data/cloud/hadoop/share/hadoop/mapreduce
[root@hnxxzxfzjz004 mapreduce]#  hadoop fs -put /etc/profile /result.txt
[root@hnxxzxfzjz004 mapreduce]# hadoop jar hadoop-mapreduce-examples-2.9.2.jar wordcount /profile /result.txt
19/08/27 20:39:07 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
19/08/27 20:39:09 INFO input.FileInputFormat: Total input files to process : 1
19/08/27 20:39:09 INFO mapreduce.JobSubmitter: number of splits:1
19/08/27 20:39:09 INFO Configuration.deprecation: yarn.resourcemanager.zk-address is deprecated. Instead, use hadoop.zk.address
19/08/27 20:39:09 INFO Configuration.deprecation: yarn.resourcemanager.system-metrics-publisher.enabled is deprecated. Instead, use yarn.system-metrics-publisher.enabled
19/08/27 20:39:09 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1566909463106_0001
19/08/27 20:39:10 INFO impl.YarnClientImpl: Submitted application application_1566909463106_0001
19/08/27 20:39:10 INFO mapreduce.Job: The url to track the job: http://hnxxzxfzjz004:8088/proxy/application_1566909463106_0001/
19/08/27 20:39:10 INFO mapreduce.Job: Running job: job_1566909463106_0001
19/08/27 20:39:23 INFO mapreduce.Job: Job job_1566909463106_0001 running in uber mode : false
19/08/27 20:39:23 INFO mapreduce.Job:  map 0% reduce 0%
19/08/27 20:39:35 INFO mapreduce.Job:  map 100% reduce 0%
19/08/27 20:39:43 INFO mapreduce.Job:  map 100% reduce 100%
19/08/27 20:39:43 INFO mapreduce.Job: Job job_1566909463106_0001 completed successfully
19/08/27 20:39:43 INFO mapreduce.Job: Counters: 49
        File System Counters
                FILE: Number of bytes read=2243
                FILE: Number of bytes written=407651
                FILE: Number of read operations=0
                FILE: Number of large read operations=0
                FILE: Number of write operations=0
                HDFS: Number of bytes read=2069
                HDFS: Number of bytes written=1598
                HDFS: Number of read operations=6
                HDFS: Number of large read operations=0
                HDFS: Number of write operations=2

计算节点信息