DDR爱好者之家 Design By 杰米

前言

"external nofollow" target="_blank" href="https://github.com/vinllen/go-mapreduce">github地址。处理对大文件统计最高频的10个单词,因为功能比较简单,所以设计没有解耦合。

"color: #ff0000">1. Mapreduce大体架构

golang如何实现mapreduce单进程版本详解

"color: #ff0000">2. 实现代码介绍

"htmlcode">

.
├── README.md
├── bin
│ └── file-store
│  └── big_input_file.txt
└── src
 ├── caller
 │ └── main.go
 ├── generate
 │ └── main.go
 └── master
  ├── combiner.go
  ├── mapper.go
  ├── master.go
  └── reducer.go

6 directories, 8 files 

2.1 caller

"htmlcode">

package main
import ( 
 "os"
 "path"
 "path/filepath"
 "bufio"
 "strconv"
 "master"
 "github.com/vinllen/go-logger/logger"
)
const ( 
 LIMIT int = 10000 // the limit line of every file
)
func main() { 
 curDir, err := filepath.Abs(filepath.Dir(os.Args[0]))
 if err != nil {
  logger.Error("Read path error: ", err.Error())
  return
 }
 fileDir := path.Join(curDir, "file-store")
 _ = os.Mkdir(fileDir, os.ModePerm)
 // 1. read file
 filename := "big_input_file.txt"
 inputFile, err := os.Open(path.Join(fileDir, filename))
 if err != nil {
  logger.Error("Read inputFile error: ", err.Error())
  return
 }
 defer inputFile.Close()
 // 2. split inputFile into several pieces that every piece hold 100,000 lines
 filePieceArr := []string{}
 scanner := bufio.NewScanner(inputFile)
 piece := 1
Outter: 
 for {
  outputFilename := "input_piece_" + strconv.Itoa(piece)
  outputFilePos := path.Join(fileDir, outputFilename)
  filePieceArr = append(filePieceArr, outputFilePos)
  outputFile, err := os.Create(outputFilePos)
  if err != nil {
   logger.Error("Split inputFile error: ", err.Error())
   continue
  }
  defer outputFile.Close()
  for cnt := 0; cnt < LIMIT; cnt++ {
   if !scanner.Scan() {
    break Outter
   }
   _, err := outputFile.WriteString(scanner.Text() + "\n")
   if err != nil {
    logger.Error("Split inputFile writting error: ", err.Error())
    return
   }
  }
  piece++
 }
 // 3. pass to master
 res := master.Handle(filePieceArr, fileDir)
 logger.Warn(res)
}

2.2 master

"htmlcode">

package master
import (
 "github.com/vinllen/go-logger/logger"
)
var ( 
 MapChanIn chan MapInput // channel produced by master while consumed by mapper
 MapChanOut chan string // channel produced by mapper while consumed by master
 ReduceChanIn chan string // channel produced by master while consumed by reducer
 ReduceChanOut chan string // channel produced by reducer while consumed by master
 CombineChanIn chan string // channel produced by master while consumed by combiner
 CombineChanOut chan []Item // channel produced by combiner while consumed by master
)
func Handle(inputArr []string, fileDir string) []Item { 
 logger.Info("handle called")
 const(
  mapperNumber int = 5
  reducerNumber int = 2
 )
 MapChanIn = make(chan MapInput)
 MapChanOut = make(chan string)
 ReduceChanIn = make(chan string)
 ReduceChanOut = make(chan string)
 CombineChanIn = make(chan string)
 CombineChanOut = make(chan []Item)
 reduceJobNum := len(inputArr)
 combineJobNum := reducerNumber
 // start combiner
 go combiner()
 // start reducer
 for i := 1; i <= reducerNumber; i++ {
  go reducer(i, fileDir)
 }
 // start mapper
 for i := 1; i <= mapperNumber; i++ {
  go mapper(i, fileDir)
 }
 go func() {
  for i, v := range(inputArr) {
   MapChanIn <- MapInput{
    Filename: v,
    Nr: i + 1,
   } // pass job to mapper
  }
  close(MapChanIn) // close map input channel when no more job
 }()
 var res []Item
outter: 
 for {
  select {
   case v := <- MapChanOut:
    go func() {
     ReduceChanIn <- v
     reduceJobNum--
     if reduceJobNum <= 0 {
      close(ReduceChanIn)
     }
    }()
   case v := <- ReduceChanOut:
    go func() {
     CombineChanIn <- v
     combineJobNum--
     if combineJobNum <= 0 {
      close(CombineChanIn)
     }
    }()
   case v := <- CombineChanOut:
    res = v
    break outter
  }
 }
 close(MapChanOut)
 close(ReduceChanOut)
 close(CombineChanOut)
 return res
}

2.3 mapper

"htmlcode">

package master
import ( 
 "fmt"
 "path"
 "os"
 "bufio"
 "strconv"

 "github.com/vinllen/go-logger/logger"
)
type MapInput struct { 
 Filename string
 Nr int
}
func mapper(nr int, fileDir string) { 
 for {
  val, ok := <- MapChanIn // val: filename
  if !ok { // channel close
   break
  }
  inputFilename := val.Filename
  nr := val.Nr
  file, err := os.Open(inputFilename)
  if err != nil {
   errMsg := fmt.Sprintf("Read file(%s) error in mapper(%d)", inputFilename, nr)
   logger.Error(errMsg)
   MapChanOut <- ""
   continue
  }
  mp := make(map[string]int)
  scanner := bufio.NewScanner(file)
  scanner.Split(bufio.ScanWords)
  for scanner.Scan() {
   str := scanner.Text()
   //logger.Info(str)
   mp[str]++
  }
  outputFilename := path.Join(fileDir, "mapper-output-" + strconv.Itoa(nr))
  outputFileHandler, err := os.Create(outputFilename)
  if err != nil {
   errMsg := fmt.Sprintf("Write file(%s) error in mapper(%d)", outputFilename, nr)
   logger.Error(errMsg)
  } else {
   for k, v := range mp {
    str := fmt.Sprintf("%s %d\n", k, v)
    outputFileHandler.WriteString(str)
   }
   outputFileHandler.Close()
  }
  MapChanOut <- outputFilename
 }
}

2.4 reducer

"htmlcode">

package master
import ( 
 "fmt"
 "bufio"
 "os"
 "strconv"
 "path"
 "strings"
 "github.com/vinllen/go-logger/logger"
)
func reducer(nr int, fileDir string) { 
 mp := make(map[string]int) // store the frequence of words
 // read file and do reduce
 for {
  val, ok := <- ReduceChanIn
  if !ok {
   break
  }
  logger.Debug("reducer called: ", nr)
  file, err := os.Open(val)
  if err != nil {
   errMsg := fmt.Sprintf("Read file(%s) error in reducer", val)
   logger.Error(errMsg)
   continue
  }
  scanner := bufio.NewScanner(file)
  for scanner.Scan() {
   str := scanner.Text()
   arr := strings.Split(str, " ")
   if len(arr) != 2 {
    errMsg := fmt.Sprintf("Read file(%s) error that len of line(%s) != 2(%d) in reducer", val, str, len(arr))
    logger.Warn(errMsg)
    continue
   }
   v, err := strconv.Atoi(arr[1])
   if err != nil {
    errMsg := fmt.Sprintf("Read file(%s) error that line(%s) parse error in reduer", val, str)
    logger.Warn(errMsg)
    continue
   }
   mp[arr[0]] += v
  }
  if err := scanner.Err(); err != nil {
   logger.Error("reducer: reading standard input:", err)
  }
  file.Close()
 }
 outputFilename := path.Join(fileDir, "reduce-output-" + strconv.Itoa(nr))
 outputFileHandler, err := os.Create(outputFilename)
 if err != nil {
  errMsg := fmt.Sprintf("Write file(%s) error in reducer(%d)", outputFilename, nr)
  logger.Error(errMsg)
 } else {
  for k, v := range mp {
   str := fmt.Sprintf("%s %d\n", k, v)
   outputFileHandler.WriteString(str)
  }
  outputFileHandler.Close()
 }
 ReduceChanOut <- outputFilename
}

2.5 combiner

"htmlcode">

package master
import ( 
 "fmt"
 "strings"
 "bufio"
 "os"
 "container/heap"
 "strconv"

 "github.com/vinllen/go-logger/logger"
)
type Item struct { 
 key string
 val int
}
type PriorityQueue []*Item
func (pq PriorityQueue) Len() int { 
 return len(pq)
}
func (pq PriorityQueue) Less(i, j int) bool { 
 return pq[i].val > pq[j].val
}
func (pq PriorityQueue) Swap(i, j int) { 
 pq[i], pq[j] = pq[j], pq[i]
}
func (pq *PriorityQueue) Push(x interface{}) { 
 item := x.(*Item)
 *pq = append(*pq, item)
}
func (pq *PriorityQueue) Pop() interface{} { 
 old := *pq
 n := len(old)
 item := old[n - 1]
 *pq = old[0 : n - 1]
 return item
}
func combiner() { 
 mp := make(map[string]int) // store the frequence of words
 // read file and do combine
 for {
  val, ok := <- CombineChanIn
  if !ok {
   break
  }
  logger.Debug("combiner called")
  file, err := os.Open(val)
  if err != nil {
   errMsg := fmt.Sprintf("Read file(%s) error in combiner", val)
   logger.Error(errMsg)
   continue
  }
  scanner := bufio.NewScanner(file)
  for scanner.Scan() {
   str := scanner.Text()
   arr := strings.Split(str, " ")
   if len(arr) != 2 {
    errMsg := fmt.Sprintf("Read file(%s) error that len of line != 2(%s) in combiner", val, str)
    logger.Warn(errMsg)
    continue
   }
   v, err := strconv.Atoi(arr[1])
   if err != nil {
    errMsg := fmt.Sprintf("Read file(%s) error that line(%s) parse error in combiner", val, str)
    logger.Warn(errMsg)
    continue
   }
   mp[arr[0]] += v
  }
  file.Close()
 }
 // heap sort
 // pq := make(PriorityQueue, len(mp))
 pq := make(PriorityQueue, 0)
 heap.Init(&pq)
 for k, v := range mp {
  node := &Item {
   key: k,
   val: v,
  }
  // logger.Debug(k, v)
  heap.Push(&pq, node)
 }
 res := []Item{}
 for i := 0; i < 10 && pq.Len() > 0; i++ {
  node := heap.Pop(&pq).(*Item)
  res = append(res, *node)
 }
 CombineChanOut <- res
}

3. 总结

  不足以及未实现之处:

  • 各模块间耦合性高
  • master单点故障未扩展
  • 未采用多进程实现,进程间采用RPC通信
  • 未实现单个Workder时间过长,另起Worker执行任务的代码。

  接下来要是有空,我会实现分布式高可用的代码,模块间采用RPC通讯。

好了,以上就是这篇文章的全部内容了,希望本文的内容对大家的学习或者工作具有一定的参考学习价值,如果有疑问大家可以留言交流,谢谢大家对的支持。

DDR爱好者之家 Design By 杰米
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
DDR爱好者之家 Design By 杰米