wiki:III140503/Lab10

Version 1 (modified by jazz, 8 years ago) (diff)

--

◢ <實作九> | <回課程大綱> ▲ | <實作十一> ◣

請連線至 hadoop.3du.me 作練習

實作十 Lab10

HDFS、MapReduce 與 Hadoop Streaming 觀念驗證
Running Hadoop Streaming with HDFS and MapReduce

準備輸入資料集 Input Dataset

  • 首先準備輸入,包含兩部份:(1) 供 Velvet 計算的 *.fa 檔案,這裡為了方便示範起見,採用 test_long.fa 當範本,並複製 99 份不同檔名,當輸入 (2) 供 Mapper 運算的輸入檔案(內含 HDFS 的檔名路徑)
    ~$ cp /usr/share/doc/velvet-example/examples/data/test_long.fa.gz .
    ~$ gunzip test_long.fa.gz
    ~$ for ((i=1;i<100;i++)); do hadoop fs -put test_long.fa input-$i.fa; done
    ~$ for ((i=1;i<20;i++)); do echo /user/$(whoami)/input-$i.fa; done > split-01.txt
    ~$ for ((i=20;i<40;i++)); do echo /user/$(whoami)/input-$i.fa; done > split-02.txt
    ~$ for ((i=40;i<60;i++)); do echo /user/$(whoami)/input-$i.fa; done > split-03.txt
    ~$ for ((i=60;i<80;i++)); do echo /user/$(whoami)/input-$i.fa; done > split-04.txt
    ~$ for ((i=80;i<100;i++)); do echo /user/$(whoami)/input-$i.fa; done > split-05.txt
    ~$ hadoop fs -mkdir lab10_input
    ~$ hadoop fs -put split-0* lab10_input
    
  • 檢查輸入檔案
    ~$ hadoop fs -ls
    ~$ hadoop fs -ls lab10_input
    

觀察 Hadoop Streaming 執行身份與工作目錄

  • 撰寫 testmapper.sh
    #!/bin/bash
    
    id="h998"
    mkdir -p /tmp/$id
    host=`hostname`
    pwd=`pwd`
    uid=`whoami`
    
    while read line; do 
      input=$line
      filename=`basename $input`
      echo "$uid@$host:$pwd> hadoop fs -get $input /tmp/$id/$filename"
      echo "$uid@$host:$pwd> velveth output-$filename 17 -fasta -short /tmp/$id/$filename"
      echo "$uid@$host:$pwd> hadoop fs -put output-$filename ."
    done
    rm -rf /tmp/$id
    
  • 接著,讓我們在本地端先驗證一下 testmapper.sh 的運作
    ~$ head -n 2 split-01.txt > split-00.txt
    ~$ cat > testmapper.sh << EOF
    #!/bin/bash
    
    id="`whoami`"
    mkdir -p /tmp/\$id
    host=\`hostname\`
    pwd=\`pwd\`
    uid=\`whoami\`
    
    while read line; do 
      input=\$line
      filename=\`basename \$input\`
      echo "\$uid@\$host:\$pwd> hadoop fs -get \$input /tmp/\$id/\$filename"
      echo "\$uid@\$host:\$pwd> velveth output-\$filename 17 -fasta -short /tmp/\$id/\$filename"
      echo "\$uid@\$host:\$pwd> hadoop fs -put output-\$filename ."
    done
    rm -rf /tmp/\$id
    EOF
    ~$ chmod a+x testmapper.sh
    ~$ cat sample-00.txt | ./testmapper.sh 
    h998@hadoop:/home/h998> hadoop fs -get /user/h998/input-1.fa /tmp/h998/input-1.fa
    h998@hadoop:/home/h998> velveth output-input-1.fa 17 -fasta -short /tmp/h998/input-1.fa
    h998@hadoop:/home/h998> hadoop fs -put output-input-1.fa .
    h998@hadoop:/home/h998> hadoop fs -get /user/h998/input-2.fa /tmp/h998/input-2.fa
    
  • 讓我們用 Hadoop Streaming 的方式來執行 testmapper.sh
    ~$ hadoop jar hadoop-streaming.jar -input lab10_input -output lab10_out1 -mapper testmapper.sh -file testmapper.sh 
    
  • 觀察 lab10_out1 的結果,看與本機執行有何不同呢?
    ~$ hadoop fs -cat /user/$(whoami)/lab10_out1/part-00000 | head
    hadoop@hadoop104:/var/lib/hadoop/cache/hadoop/mapred/local/taskTracker/jobcache/job_201106041247_1820/attempt_201106041247_1820_m_000002_0/work> hadoop fs -get /user/h998/input-60.fa /tmp/h998/input-60.fa	
    hadoop@hadoop104:/var/lib/hadoop/cache/hadoop/mapred/local/taskTracker/jobcache/job_201106041247_1820/attempt_201106041247_1820_m_000002_0/work> hadoop fs -get /user/h998/input-61.fa /tmp/h998/input-61.fa	
    hadoop@hadoop104:/var/lib/hadoop/cache/hadoop/mapred/local/taskTracker/jobcache/job_201106041247_1820/attempt_201106041247_1820_m_000002_0/work> hadoop fs -get /user/h998/input-62.fa /tmp/h998/input-62.fa	
    

實作透過 Hadoop Streaming 執行 99 組 velvet 運算

  • 撰寫 mapper.sh
    #!/bin/bash
    
    id="h998"
    mkdir -p /tmp/$id
    host=`hostname`
    pwd=`pwd`
    uid=`whoami`
    
    while read line; do 
      input=$line
      filename=`basename $input`
      echo "$uid@$host> hadoop fs -get $input /tmp/$id/$filename"
      hadoop fs -get $input /tmp/$id/$filename
      echo "$uid@$host> velveth output-$filename 17 -fasta -short /tmp/$id/$filename"
      velveth output-$filename 17 -fasta -short /tmp/$id/$filename
      echo "$uid@$host> hadoop fs -put output-$filename /user/$id/."
      hadoop fs -put output-$filename /user/$id/.
      hadoop fs -chown $id /user/$id/output-$filename
    done
    rm -rf /tmp/$id
    
  • 於本機測試 mapper.sh
    ~$ cat > mapper.sh << EOF
    #!/bin/bash
    
    id="`whoami`"
    mkdir -p /tmp/\$id
    host=\`hostname\`
    pwd=\`pwd\`
    uid=\`whoami\`
    
    while read line; do 
      input=\$line
      filename=\`basename \$input\`
      echo "\$uid@\$host> hadoop fs -get \$input /tmp/\$id/\$filename"
      hadoop fs -get \$input /tmp/\$id/\$filename
      echo "\$uid@\$host> velveth output-\$filename 17 -fasta -short /tmp/\$id/\$filename"
      velveth output-\$filename 17 -fasta -short /tmp/\$id/\$filename
      echo "\$uid@\$host> hadoop fs -put output-\$filename /user/\$id/."
      hadoop fs -put output-\$filename /user/\$id/.
      hadoop fs -chown \$id /user/\$id/output-\$filename
    done
    rm -rf /tmp/\$id
    EOF
    ~$ chmod a+x mapper.sh
    ~$ cat sample-00.txt | ./mapper.sh 
    ~$ hadoop fs -rmr output-*
    ~$ rm -rf output-sample-*
    
  • 接著用 hadoop streaming 來執行
    ~$ hadoop jar hadoop-streaming.jar -input lab10_input -output lab10_out2 -mapper mapper.sh -file mapper.sh