1.在HDFS文件系统的根目录下创建递归目录“1daoyun/file”,将附件中的BigDataSkills.txt文件,上传到1daoyun/file目录中,使用相关命令查看文件系统中1daoyun/file目录的文件列表信息,输出结果为。
[root@master ~]# hadoop fs -mkdir -p /1daoyun/file
[root@master ~]# hadoop fs -put BigDataSkills.txt/1daoyun/file
[root@master ~]# hadoop fs -ls /1daoyun/file
Found 1 items
-rw-r--r-- 3root hdfs 49 2017-05-06 09:57/1daoyun/file/BigDataSkills.txt
2.在HDFS文件系统的根目录下创建递归目录“1daoyun/file”,将附件中的BigDataSkills.txt文件,上传到1daoyun/file目录中,并使用HDFS文件系统检查工具检查文件是否受损,输出结果为。
[root@master ~]# hadoop fs -mkdir -p /1daoyun/file
[root@master ~]# hadoop fs -put BigDataSkills.txt/1daoyun/file
[root@master ~]# hadoop fsck/1daoyun/file/BigDataSkills.txt
DEPRECATED: Use of this script to execute hdfs commandis deprecated.
Instead use the hdfs command for it.
Connecting to namenode viahttp://master:50070/fsck?ugi=root&path=%2F1daoyun%2Ffile%2FBigDataSkills.txt
FSCK started by root (auth:SIMPLE) from /10.0.0.14 forpath /1daoyun/file/BigDataSkills.txt at Sun May 07 03:14:38 UTC 2017
.
/1daoyun/file/BigDataSkills.txt: Under replicatedBP-90981007-192.168.101.10-1492713691966:blk_1073741906_1085. Target Replicasis 3 but found 2 live replica(s), 0 decommissioned replica(s) and 0decommissioning replica(s).
Status: HEALTHY
Totalsize: 49 B
Totaldirs: 0
Totalfiles: 1
Totalsymlinks: 0
Total blocks(validated): 1 (avg. block size 49B)
Minimallyreplicated blocks: 1 (100.0 %)
Over-replicatedblocks: 0 (0.0 %)
Under-replicated blocks: 1 (100.0 %)
Mis-replicatedblocks: 0 (0.0 %)
Defaultreplication factor: 3
Average blockreplication: 2.0
Corruptblocks: 0
Missingreplicas: 1 (33.333332 %)
Number ofdata-nodes: 2
Number ofracks: 1
FSCK ended at Sun May 07 03:14:38 UTC 2017 in 6milliseconds
The filesystem under path'/1daoyun/file/BigDataSkills.txt' is HEALTHY
3.在HDFS文件系统的根目录下创建递归目录“1daoyun/file”,将附件中的BigDataSkills.txt文件,上传到1daoyun/file目录中,上传过程指定BigDataSkills.txt 文件在HDFS 文件系统中的复制因子为2,并使用fsck工具检查存储块的副本数,输出结果为。
[root@master ~]# hadoop fs -mkdir -p /1daoyun/file
[root@master ~]# hadoop fs -D dfs.replication=2 -putBigDataSkills.txt /1daoyun/file
[root@master ~]# hadoop fsck /1daoyun/file/BigDataSkills.txt
DEPRECATED: Use of this script to execute hdfs commandis deprecated.
Instead use the hdfs command for it.
Connecting to namenode viahttp://master:50070/fsck?ugi=root&path=%2F1daoyun%2Ffile%2FBigDataSkills.txt
FSCK started by root (auth:SIMPLE) from /10.0.0.14 forpath /1daoyun/file/BigDataSkills.txt at Sun May 07 09:39:44 UTC 2017
.Status: HEALTHY
Totalsize: 32 B
Totaldirs: 0
Totalfiles: 1
Totalsymlinks: 0
Total blocks(validated): 1 (avg. block size 32B)
Minimallyreplicated blocks: 1 (100.0 %)
Over-replicatedblocks: 0 (0.0 %)
Under-replicated blocks: 0 (0.0 %)
Mis-replicatedblocks: 0 (0.0 %)
Defaultreplication factor: 3
Average blockreplication: 2.0
Corruptblocks: 0
Missingreplicas: 0 (0.0 %)
Number ofdata-nodes: 2
Number ofracks: 1
FSCK ended at Sun May 07 09:39:44 UTC 2017 in 0milliseconds
The filesystem under path '/1daoyun/file/BigDataSkills.txt'is HEALTHY
4.HDFS文件系统的根目录下存在一个/apps的文件目录,要求开启该目录的可创建快照功能,
并为该目录文件创建快照,快照名称为apps_1daoyun,使用相关命令查看该快照文件的列表信息,输出结果为。
一:
[root@master ~]# hadoop dfsadmin -allowSnapshot /apps
DEPRECATED: Use of this script to execute hdfs commandis deprecated.
Instead use the hdfs command for it.
Allowing snaphot on /apps succeeded
二:
[root@master ~]# hadoop dfsadmin -allowSnapshot /apps
Allowing snaphot on /apps succeeded
[root@master ~]# hadoop fs -createSnapshot /apps apps_1daoyun
Created snapshot /apps/.snapshot/apps_1daoyun
[root@master ~]# hadoop fs -ls /apps/.snapshot
Found 1 items
drwxrwxrwx -hdfs hdfs 0 2017-05-07 09:48/apps/.snapshot/apps_1daoyun
5.HDFS文件系统的/user/root/small-file目录中存在一些小文件,要求使用Hadoop Arachive工具将这些小文件归档成为一个文件,文件名为xiandian-data.har。归档完成后,查看xiandian-data.har的列表信息,输出结果为。
[root@master ~]# hadoop archive -archiveName xiandian-data.har-p /user/root/small-file /user/root/
[root@master ~]# hadoop fs -ls /user/root/xiandian-data.har
Found 4 items
-rw-r--r-- 3root hdfs 0 2017-05-08 01:53/user/root/xiandian-data.har/_SUCCESS
-rw-r--r-- 5root hdfs 735 2017-05-08 01:53/user/root/xiandian-data.har/_index
-rw-r--r-- 5root hdfs 23 2017-05-08 01:53/user/root/xiandian-data.har/_masterindex
-rw-r--r-- 3root hdfs 617 2017-05-08 01:53/user/root/xiandian-data.har/part-0
6.当Hadoop集群启动的时候,会首先进入到安全模式的状态,该模式默认30秒后退出。当
系统处于安全模式时,只能对HDFS 文件系统进行读取,无法进行写入修改删除等的操作。
现假设需要对Hadoop集群进行维护,需要使集群进入安全模式的状态,并检查其状态。将集群进入安全模式和检查安全模式状态的操作命令输出结果为中。
一:
[root@master ~]# hadoop dfsadmin -safemode enter
DEPRECATED: Use of this script to execute hdfs commandis deprecated.
Instead use the hdfs command for it.
Safe mode is ON
[root@master ~]# hadoop dfsadmin -safemode get
DEPRECATED: Use of this script to execute hdfs commandis deprecated.
Instead use the hdfs command for it.
Safe mode is ON
二:
[root@master ~]# hdfs dfsadmin -safemode enter
Safe mode is ON
[root@master ~]# hdfs dfsadmin -safemode get
Safe mode is ON
7.为了防止操作人员误删文件,HDFS文件系统提供了回收站的功能,但过多的垃圾文件会占用大量的存储空间。要求在先电大数据平台的WEB界面将HDFS文件系统回收站中的文件彻底删除的时间间隔为7天,输出结果为。
高级 core-site
fs.trash.interval
10080
8.为了防止操作人员误删文件,HDFS文件系统提供了回收站的功能,但过多的垃圾文件会占用大量的存储空间。要求在Linux Shell中使用“vi”命令修改相应的配置文件以及参数信息,完成后,重启相应的服务。输出结果为
[root@master ]# vi/etc/hadoop/2.4.3.0-227/0/core-site.xml
[root@master ~]# su - hdfs
Last login: Mon May 8 09:31:52 UTC 2017
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstop namenode
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstart namenode
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstop datanode
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstart datanode
9.为了防止操作人员误删文件,HDFS文件系统提供了回收站的功能,假设一名工程师发现自己前一天以root用户的身份不小心删除了HDFS文件系统中一个名为cetc55.txt的文件,现需要你使用find命令找到这个文件路径,并还原文件至原来的位置。完成后输出结果为。
[root@master ~]# hadoop fs -find / -name 'cetc55.txt'
/user/hdfs/.Trash/Current/data/cetc55.txt
/user/root/.Trash/Current/cetc55.txt
[root@master ~]# hadoop fs -mv/user/root/.Trash/Current/cetc55.txt /
10.Hadoop集群中的主机在某些情况下会出现宕机或者系统损坏的问题,一旦遇到这些问题, HDFS文件系统中的数据文件难免会产生损坏或者丢失,为了保证HDFS文件系统的可靠性,现需要在先电大数据平台的WEB界面将集群的冗余复制因子修改为5,以文本形式提交修改的参数信息和参数值输出结果为。
General
Block replication
5
11.Hadoop集群中的主机在某些情况下会出现宕机或者系统损坏的问题,一旦遇到这些问题, HDFS文件系统中的数据文件难免会产生损坏或者丢失,为了保证HDFS文件系统的可靠性,需要将集群的冗余复制因子修改为5,在Linux Shell中使用“vi”命令修改相应的配置文件以及参数信息,完成后,重启相应的服务。以文本形式提交以上操作命令和修改的参数信息输出结果为。
[root@master ~]# vi/etc/hadoop/2.4.3.0-227/0/hdfs-site.xml
[root@master ~]# su - hdfs
Last login: Mon May 8 09:31:52 UTC 2017
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstop namenode
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstart namenode
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstop datanode
[hdfs@master ~]$/usr/hdp/current/hadoop-client/sbin/hadoop-daemon.sh --config /usr/hdp/current/hadoop-client/confstart datanode