[root@master ~]# hdfs dfs -ls /
Found 4 items
drwxr-xr-x - root supergroup 0 2022-03-21 18:41 /testHDFSshell1
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 /testHDFSshell2
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 /testHDFSshell3
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 /testHDFSshell4
[root@master ~]# hadoop fs -ls /
Found 4 items
drwxr-xr-x - root supergroup 0 2022-03-21 18:41 /testHDFSshell1
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 /testHDFSshell2
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 /testHDFSshell3
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 /testHDFSshell4
[root@master ~]# hdfs dfs -ls hdfs://master:9000/
Found 5 items
drwxr-xr-x - root supergroup 0 2022-03-22 10:07 hdfs://master:9000/data
drwxr-xr-x - root supergroup 0 2022-03-21 18:41 hdfs://master:9000/testHDFSshell1
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 hdfs://master:9000/testHDFSshell2
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 hdfs://master:9000/testHDFSshell3
drwxr-xr-x - root supergroup 0 2022-03-21 18:46 hdfs://master:9000/testHDFSshell4
[root@master ~]# cd $HADOOP_HOME
[root@master hadoop-2.7.6]# pwd
/usr/local/soft/hadoop-2.7.6
[root@master hadoop-2.7.6]# echo $HADOOP_HOME
/usr/local/soft/hadoop-2.7.6
[root@master hadoop-2.7.6]# cd etc/hadoop/
[root@master hadoop]# ls
capacity-scheduler.xml kms-env.sh
configuration.xsl kms-log4j.properties
container-executor.cfg kms-site.xml
core-site.xml log4j.properties
core-site.xml.0 mapred-env.cmd
hadoop-env.cmd mapred-env.sh
hadoop-env.sh mapred-queues.xml.template
hadoop-env.sh.0 mapred-site.xml
hadoop-metrics2.properties mapred-site.xml.template
hadoop-metrics.properties slaves
hadoop-policy.xml slaves.0
hdfs-site.xml ssl-client.xml.example
hdfs-site.xml.0 ssl-server.xml.example
httpfs-env.sh yarn-env.cmd
httpfs-log4j.properties yarn-env.sh
httpfs-signature.secret yarn-site.xml
httpfs-site.xml yarn-site.xml.0
kms-acls.xml
[root@master hadoop]# vim core-site.xml
[root@master hadoop]# python
Python 2.7.5 (default, Oct 14 2020, 14:45:30)
[GCC 4.8.5 20150623 (Red Hat 4.8.5-44)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import this
The Zen of Python, by Tim Peters
Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Flat is better than nested.
Sparse is better than dense.
Readability counts.
Special cases aren't special enough to break the rules.
Although practicality beats purity.
Errors should never pass silently.
Unless explicitly silenced.
In the face of ambiguity, refuse the temptation to guess.
There should be one-- and preferably only one --obvious way to do it.
Although that way may not be obvious at first unless you're Dutch.
Now is better than never.
Although never is often better than *right* now.
If the implementation is hard to explain, it's a bad idea.
If the implementation is easy to explain, it may be a good idea.
Namespaces are one honking great idea -- let's do more of those!
>>> exit()
[root@master hadoop]# cd /usr/local/soft/
[root@master soft]# ls
0?? data jdk1.8.0_171 redis shell show
A?? hadoop-2.7.6 packages redis-6.2.6 shell01 test.txt
[root@master soft]# cd data/
[root@master data]# pwd
/usr/local/soft/data
[root@master data]# ls
new_db.sql score.sql student.sql
[root@master data]# touch theZenOfPython.txt
[root@master data]# vim theZenOfPython.txt
[root@master data]# hdfs dfs -mkdir /data
[root@master data]# hdfs dfs -mkdir /data/shell
[root@master data]# hdfs dfs -put theZenOfPython.txt /data/shell/
[root@master data]# hdfs dfs -ls /data/shell/
Found 1 items
-rw-r--r-- 1 root supergroup 1122 2022-03-22 16:57 /data/shell/theZenOfPython.txt
[root@master data]# hdfs dfs -cat /data/shell/theZenOfPython.txt
[root@master data]# hdfs dfs -mv /data/shell/theZenOfPython.txt /data/shell/theZen.txt
[root@master data]# hdfs dfs -ls /data/shell
Found 1 items
-rw-r--r-- 1 root supergroup 1122 2022-03-22 16:57 /data/shell/theZen.txt
[root@master data]# hdfs dfs -vim /data/shell/theZenOfPython.txt /data/shell/theZen.txt
-vim: Unknown command
[root@master data]# hdfs dfs -cp /data/shell/theZen.txt /data/shell/theZenCopy.txt
[root@master data]# hdfs dfs -ls /data/shell/
Found 2 items
-rw-r--r-- 1 root supergroup 1122 2022-03-22 16:57 /data/shell/theZen.txt
-rw-r--r-- 1 root supergroup 1122 2022-03-22 17:07 /data/shell/theZenCopy.txt
[root@master data]# ls
new_db.sql score.sql student.sql theZenOfPython.txt
[root@master data]# ls -l theZenOfPython.txt
-rw-r--r--. 1 root root 1122 3月 22 16:54 theZenOfPython.txt
[root@master data]# chmod u+x theZenOfPython.txt
[root@master data]# chmod g+x theZenOfPython.txt
[root@master data]# chmod o+x theZenOfPython.txt
[root@master data]# ls -l theZenOfPython.txt
-rwxr-xr-x. 1 root root 1122 3月 22 16:54 theZenOfPython.txt
[root@master data]# chmod 777 theZenOfPython.txt
[root@master data]# ls -l theZenOfPython.txt
-rwxrwxrwx. 1 root root 1122 3月 22 16:54 theZenOfPython.txt
[root@master data]# hdfs dfs -chmod 777 /data/shell/theZen.txt
[root@master data]# su test
[test@master data]$ exit
exit
[root@master data]# ls
new_db.sql score.sql student.sql theZenOfPython.txt
[root@master data]# ll theZenOfPython.txt
-rwxrwxrwx. 1 root root 1122 3月 22 16:54 theZenOfPython.txt
[root@master data]# chown test theZenOfPython.txt
[root@master data]# ll theZenOfPython.txt
-rwxrwxrwx. 1 test root 1122 3月 22 16:54 theZenOfPython.txt
[root@master data]# chown test:test theZenOfPython.txt
[root@master data]# ll theZenOfPython.txt
-rwxrwxrwx. 1 test test 1122 3月 22 16:54 theZenOfPython.txt
[root@master data]# hdfs dfs -chown hdfs:hadoop /data/shell/theZ
en.txt
[root@master data]# df -h
文件系统 容量 已用 可用 已用% 挂载点
devtmpfs 1.9G 0 1.9G 0% /dev
tmpfs 1.9G 0 1.9G 0% /dev/shm
tmpfs 1.9G 13M 1.9G 1% /run
tmpfs 1.9G 0 1.9G 0% /sys/fs/cgroup
/dev/mapper/centos-root 47G 7.1G 40G 16% /
/dev/sda1 1014M 185M 830M 19% /boot
tmpfs 378M 0 378M 0% /run/user/0
[root@master data]# hdfs dfs -df -h
Filesystem Size Used Available Use%
hdfs://master:9000 93.9 G 40 K 83.0 G 0%
[root@master data]# hdfs dfs -rm /data/shell/theZenCopy.txt
22/03/22 17:46:39 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 1440 minutes, Emptier interval = 0 minutes.
22/03/22 17:46:39 INFO fs.TrashPolicyDefault: Moved: 'hdfs://master:9000/data/shell/theZenCopy.txt' to trash at: hdfs://master:9000/user/root/.Trash/Current/data/shell/theZenCopy.txt
Moved: 'hdfs://master:9000/data/shell/theZenCopy.txt' to trash at: hdfs://master:9000/user/root/.Trash/Current
[root@master data]# hdfs dfs -cp /data/shell/theZen.txt /data/shell/theZenCopy1.txt
[root@master data]# hdfs dfs -rm -skipTrash /data/shell/theZenCopy1.txt
Deleted /data/shell/theZenCopy1.txt
[root@master data]# hdfs dfs -rm -r /testHDFSshell1
22/03/22 19:15:59 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 1440 minutes, Emptier interval = 0 minutes.
22/03/22 19:15:59 INFO fs.TrashPolicyDefault: Moved: 'hdfs://master:9000/testHDFSshell1' to trash at: hdfs://master:9000/user/root/.Trash/Current/testHDFSshell1
Moved: 'hdfs://master:9000/testHDFSshell1' to trash at: hdfs://master:9000/user/root/.Trash/Current
[root@master data]# hdfs dfs -rm -r /testHDFSshell2
22/03/22 19:16:38 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 1440 minutes, Emptier interval = 0 minutes.
22/03/22 19:16:38 INFO fs.TrashPolicyDefault: Moved: 'hdfs://master:9000/testHDFSshell2' to trash at: hdfs://master:9000/user/root/.Trash/Current/testHDFSshell2
Moved: 'hdfs://master:9000/testHDFSshell2' to trash at: hdfs://master:9000/user/root/.Trash/Current
[root@master data]# hdfs dfs -rm -r /testHDFSshell3
22/03/22 19:16:47 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 1440 minutes, Emptier interval = 0 minutes.
22/03/22 19:16:47 INFO fs.TrashPolicyDefault: Moved: 'hdfs://master:9000/testHDFSshell3' to trash at: hdfs://master:9000/user/root/.Trash/Current/testHDFSshell3
Moved: 'hdfs://master:9000/testHDFSshell3' to trash at: hdfs://master:9000/user/root/.Trash/Current
[root@master data]# hdfs dfs -rm -r /testHDFSshell4
22/03/22 19:16:51 INFO fs.TrashPolicyDefault: Namenode trash configuration: Deletion interval = 1440 minutes, Emptier interval = 0 minutes.
22/03/22 19:16:51 INFO fs.TrashPolicyDefault: Moved: 'hdfs://master:9000/testHDFSshell4' to trash at: hdfs://master:9000/user/root/.Trash/Current/testHDFSshell4
Moved: 'hdfs://master:9000/testHDFSshell4' to trash at: hdfs://master:9000/user/root/.Trash/Current
[root@master data]# hdfs dfs -get /data/shell/theZen.txt ./
[root@master data]# ls
new_db.sql student.sql theZen.txt
score.sql theZenOfPython.txt
[root@master data]# cd ..
[root@master soft]# ls
0?? data jdk1.8.0_171 redis shell show
A?? hadoop-2.7.6 packages redis-6.2.6 shell01 test.txt
[root@master soft]# cd hadoop-2.7.6/
[root@master hadoop-2.7.6]# ls
bin include libexec logs README.txt share
etc lib LICENSE.txt NOTICE.txt sbin tmp
[root@master hadoop-2.7.6]# pwd
/usr/local/soft/hadoop-2.7.6
[root@master hadoop-2.7.6]# cd share/hadoop/mapreduce/
[root@master mapreduce]# ls
hadoop-mapreduce-client-app-2.7.6.jar
hadoop-mapreduce-client-common-2.7.6.jar
hadoop-mapreduce-client-core-2.7.6.jar
hadoop-mapreduce-client-hs-2.7.6.jar
hadoop-mapreduce-client-hs-plugins-2.7.6.jar
hadoop-mapreduce-client-jobclient-2.7.6.jar
hadoop-mapreduce-client-jobclient-2.7.6-tests.jar
hadoop-mapreduce-client-shuffle-2.7.6.jar
hadoop-mapreduce-examples-2.7.6.jar
lib
lib-examples
sources
[root@master mapreduce]# cd /usr/local/soft/data
[root@master data]# ls
new_db.sql student.sql theZen.txt
score.sql theZenOfPython.txt
[root@master data]# vim wordcount
[root@master data]# hdfs dfs -mkdir -p /data/wc/input
[root@master data]# hdfs dfs -put wordcount /data/wc/input/
[root@master mapreduce]# hadoop jar hadoop-mapreduce-examples-2.7.6.jar wordcount /data/wc/input/ /data/wc/output
22/03/22 19:34:21 INFO client.RMProxy: Connecting to ResourceManager at master/192.168.49.110:8032
22/03/22 19:34:22 INFO input.FileInputFormat: Total input paths to process : 1
22/03/22 19:34:22 INFO mapreduce.JobSubmitter: number of splits:1
22/03/22 19:34:23 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1647858149677_0001
22/03/22 19:34:23 INFO impl.YarnClientImpl: Submitted application application_1647858149677_0001
22/03/22 19:34:23 INFO mapreduce.Job: The url to track the job: http://master:8088/proxy/application_1647858149677_0001/
22/03/22 19:34:23 INFO mapreduce.Job: Running job: job_1647858149677_0001
22/03/22 19:34:34 INFO mapreduce.Job: Job job_1647858149677_0001 running in uber mode : false
22/03/22 19:34:34 INFO mapreduce.Job: map 0% reduce 0%
22/03/22 19:34:42 INFO mapreduce.Job: map 100% reduce 0%
22/03/22 19:34:49 INFO mapreduce.Job: map 100% reduce 100%
22/03/22 19:34:49 INFO mapreduce.Job: Job job_1647858149677_0001 completed successfully
22/03/22 19:34:50 INFO mapreduce.Job: Counters: 49
File System Counters
FILE: Number of bytes read=115
FILE: Number of bytes written=245637
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=197
HDFS: Number of bytes written=73
HDFS: Number of read operations=6
HDFS: Number of large read operations=0
HDFS: Number of write operations=2
Job Counters
Launched map tasks=1
Launched reduce tasks=1
Data-local map tasks=1
Total time spent by all maps in occupied slots (ms)=5995
Total time spent by all reduces in occupied slots (ms)=3830
Total time spent by all map tasks (ms)=5995
Total time spent by all reduce tasks (ms)=3830
Total vcore-milliseconds taken by all map tasks=5995
Total vcore-milliseconds taken by all reduce tasks=3830
Total megabyte-milliseconds taken by all map tasks=6138880
Total megabyte-milliseconds taken by all reduce tasks=3921920
Map-Reduce Framework
Map input records=9
Map output records=15
Map output bytes=149
Map output materialized bytes=115
Input split bytes=107
Combine input records=15
Combine output records=9
Reduce input groups=9
Reduce shuffle bytes=115
Reduce input records=9
Reduce output records=9
Spilled Records=18
Shuffled Maps =1
Failed Shuffles=0
Merged Map outputs=1
GC time elapsed (ms)=178
CPU time spent (ms)=1500
Physical memory (bytes) snapshot=300212224
Virtual memory (bytes) snapshot=4160380928
Total committed heap usage (bytes)=138780672
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=90
File Output Format Counters
Bytes Written=73
[root@master mapreduce]# hdfs dfs -cat /data/wc/output/*
c 1
flink 2
hadoop 1
hive 1
java 4
mysql 2
python 2
redis 1
springboot 1
[root@master mapreduce]# hadoop jar hadoop-mapreduce-examples-2.7.6.jar pi 10 1000
Number of Maps = 10
Samples per Map = 1000
Wrote input for Map #0
Wrote input for Map #1
Wrote input for Map #2
Wrote input for Map #3
Wrote input for Map #4
Wrote input for Map #5
Wrote input for Map #6
Wrote input for Map #7
Wrote input for Map #8
Wrote input for Map #9
Starting Job
22/03/22 19:51:56 INFO client.RMProxy: Connecting to ResourceManager at master/192.168.49.110:8032
22/03/22 19:51:57 INFO input.FileInputFormat: Total input paths to process : 10
22/03/22 19:51:57 INFO mapreduce.JobSubmitter: number of splits:10
22/03/22 19:51:57 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1647858149677_0002
22/03/22 19:51:58 INFO impl.YarnClientImpl: Submitted application application_1647858149677_0002
22/03/22 19:51:58 INFO mapreduce.Job: The url to track the job: http://master:8088/proxy/application_1647858149677_0002/
22/03/22 19:51:58 INFO mapreduce.Job: Running job: job_1647858149677_0002
22/03/22 19:52:05 INFO mapreduce.Job: Job job_1647858149677_0002 running in uber mode : false
22/03/22 19:52:05 INFO mapreduce.Job: map 0% reduce 0%
22/03/22 19:52:22 INFO mapreduce.Job: map 10% reduce 0%
22/03/22 19:52:23 INFO mapreduce.Job: map 30% reduce 0%
22/03/22 19:52:24 INFO mapreduce.Job: map 40% reduce 0%
22/03/22 19:52:35 INFO mapreduce.Job: map 50% reduce 0%
22/03/22 19:52:36 INFO mapreduce.Job: map 100% reduce 13%
22/03/22 19:52:38 INFO mapreduce.Job: map 100% reduce 100%
22/03/22 19:52:38 INFO mapreduce.Job: Job job_1647858149677_0002 completed successfully
22/03/22 19:52:38 INFO mapreduce.Job: Counters: 50
File System Counters
FILE: Number of bytes read=226
FILE: Number of bytes written=1353957
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
HDFS: Number of bytes read=2610
HDFS: Number of bytes written=215
HDFS: Number of read operations=43
HDFS: Number of large read operations=0
HDFS: Number of write operations=3
Job Counters
Launched map tasks=10
Launched reduce tasks=1
Data-local map tasks=9
Rack-local map tasks=1
Total time spent by all maps in occupied slots (ms)=231390
Total time spent by all reduces in occupied slots (ms)=11380
Total time spent by all map tasks (ms)=231390
Total time spent by all reduce tasks (ms)=11380
Total vcore-milliseconds taken by all map tasks=231390
Total vcore-milliseconds taken by all reduce tasks=11380
Total megabyte-milliseconds taken by all map tasks=236943360
Total megabyte-milliseconds taken by all reduce tasks=11653120
Map-Reduce Framework
Map input records=10
Map output records=20
Map output bytes=180
Map output materialized bytes=280
Input split bytes=1430
Combine input records=0
Combine output records=0
Reduce input groups=2
Reduce shuffle bytes=280
Reduce input records=20
Reduce output records=0
Spilled Records=40
Shuffled Maps =10
Failed Shuffles=0
Merged Map outputs=10
GC time elapsed (ms)=4702
CPU time spent (ms)=8800
Physical memory (bytes) snapshot=1392967680
Virtual memory (bytes) snapshot=22847873024
Total committed heap usage (bytes)=1232994304
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=1180
File Output Format Counters
Bytes Written=97
Job Finished in 41.604 seconds
Estimated value of Pi is 3.14080000000000000000
[root@master data]# cd ..
[root@master soft]# cd hadoop-2.7.6/
[root@master hadoop-2.7.6]# ls
bin include libexec logs README.txt share
etc lib LICENSE.txt NOTICE.txt sbin tmp
[root@master hadoop-2.7.6]# pwd
/usr/local/soft/hadoop-2.7.6
[root@master hadoop-2.7.6]# cd tmp/
[root@master tmp]# ls
dfs
[root@master tmp]# cd dfs/
[root@master dfs]# ls
name namesecondary
[root@master dfs]# cd name
[root@master name]# ls
current in_use.lock
[root@master name]# cd current/
[root@master current]# ls
edits_0000000000000000001-0000000000000000001
edits_0000000000000000002-0000000000000000002
edits_0000000000000000003-0000000000000000004
edits_0000000000000000005-0000000000000000010
edits_0000000000000000011-0000000000000000014
edits_0000000000000000015-0000000000000000022
edits_0000000000000000023-0000000000000000040
edits_inprogress_0000000000000000041
fsimage_0000000000000000022
fsimage_0000000000000000022.md5
fsimage_0000000000000000040
fsimage_0000000000000000040.md5
seen_txid
VERSION
[root@master current]# cat fsimage_0000000000000000022.md5
efa22663f2af0ba4788507831370cc67 *fsimage_0000000000000000022
[root@master current]# md5sum fsimage_0000000000000000022
efa22663f2af0ba4788507831370cc67 fsimage_0000000000000000022