Go Concurrency Patterns

go-concurrency.md

Pipeline

func gen(nums ...int) <-chan int {
    out := make(chan int)
    go func() {
        for _, n := range nums {
            out <- n
        }
        close(out)
    }()
    return out
}

func sq(in <-chan int) <-chan int {
    out := make(chan int)
    go func() {
        for n := range in {
            out <- n * n
        }
        close(out)
    }()
    return out
}

func main() {
    // Set up the pipeline and consume the output.
    for n := range sq(sq(gen(2, 3))) {
        fmt.Println(n) // 16 then 81
    }
}

Fan-in/Fan-out

func merge(cs ...<-chan int) <-chan int {
    var wg sync.WaitGroup
    out := make(chan int)

    // Start an output goroutine for each input channel in cs.  output
    // copies values from c to out until c is closed, then calls wg.Done.
    output := func(c <-chan int) {
        for n := range c {
            out <- n
        }
        wg.Done()
    }
    wg.Add(len(cs))
    for _, c := range cs {
        go output(c)
    }

    // Start a goroutine to close out once all the output goroutines are
    // done.  This must start after the wg.Add call.
    go func() {
        wg.Wait()
        close(out)
    }()
    return out
}

func main() {
    in := gen(2, 3)

    // Distribute the sq work across two goroutines that both read from in.
    c1 := sq(in)
    c2 := sq(in)

    // Consume the merged output from c1 and c2.
    for n := range merge(c1, c2) {
        fmt.Println(n) // 4 then 9, or 9 then 4
    }
}

Stopping Short / Explicit Cancellation

func sq(done <-chan struct{}, in <-chan int) <-chan int {
    out := make(chan int)
    go func() {
        defer close(out)
        for n := range in {
            select {
            case out <- n * n:
            case <-done:
                return
            }
        }
    }()
    return out
}


func merge(done <-chan struct{}, cs ...<-chan int) <-chan int {
    var wg sync.WaitGroup
    out := make(chan int)

    // Start an output goroutine for each input channel in cs.  output
    // copies values from c to out until c or done is closed, then calls
    // wg.Done.
    output := func(c <-chan int) {
        defer wg.Done()
        for n := range c {
            select {
            case out <- n:
            case <-done:
                return
            }
        }
    }
    
    wg.Add(len(cs))
    for _, c := range cs {
        go output(c)
    }

    // Start a goroutine to close out once all the output goroutines are
    // done.  This must start after the wg.Add call.
    go func() {
        wg.Wait()
        close(out)
    }()
    return out
}

func main() {
    // Set up a done channel that's shared by the whole pipeline,
    // and close that channel when this pipeline exits, as a signal
    // for all the goroutines we started to exit.
    done := make(chan struct{})
    defer close(done)

    in := gen(done, 2, 3)

    // Distribute the sq work across two goroutines that both read from in.
    c1 := sq(done, in)
    c2 := sq(done, in)

    // Consume the first value from output.
    out := merge(done, c1, c2)
    fmt.Println(<-out) // 4 or 9

    // done will be closed by the deferred call.
}

Bounded Parallelism

// +build OMIT

package main

import (
	"crypto/md5"
	"errors"
	"fmt"
	"io/ioutil"
	"os"
	"path/filepath"
	"sort"
	"sync"
)

// walkFiles starts a goroutine to walk the directory tree at root and send the
// path of each regular file on the string channel.  It sends the result of the
// walk on the error channel.  If done is closed, walkFiles abandons its work.
func walkFiles(done <-chan struct{}, root string) (<-chan string, <-chan error) {
	paths := make(chan string)
	errc := make(chan error, 1)
	go func() { // HL
		// Close the paths channel after Walk returns.
		defer close(paths) // HL
		// No select needed for this send, since errc is buffered.
		errc <- filepath.Walk(root, func(path string, info os.FileInfo, err error) error { // HL
			if err != nil {
				return err
			}
			if !info.Mode().IsRegular() {
				return nil
			}
			select {
			case paths <- path: // HL
			case <-done: // HL
				return errors.New("walk canceled")
			}
			return nil
		})
	}()
	return paths, errc
}

// A result is the product of reading and summing a file using MD5.
type result struct {
	path string
	sum  [md5.Size]byte
	err  error
}

// digester reads path names from paths and sends digests of the corresponding
// files on c until either paths or done is closed.
func digester(done <-chan struct{}, paths <-chan string, c chan<- result) {
	for path := range paths { // HLpaths
		data, err := ioutil.ReadFile(path)
		select {
		case c <- result{path, md5.Sum(data), err}:
		case <-done:
			return
		}
	}
}

// MD5All reads all the files in the file tree rooted at root and returns a map
// from file path to the MD5 sum of the file's contents.  If the directory walk
// fails or any read operation fails, MD5All returns an error.  In that case,
// MD5All does not wait for inflight read operations to complete.
func MD5All(root string) (map[string][md5.Size]byte, error) {
	// MD5All closes the done channel when it returns; it may do so before
	// receiving all the values from c and errc.
	done := make(chan struct{})
	defer close(done)

	paths, errc := walkFiles(done, root)

	// Start a fixed number of goroutines to read and digest files.
	c := make(chan result) // HLc
	var wg sync.WaitGroup
	const numDigesters = 20
	wg.Add(numDigesters)
	for i := 0; i < numDigesters; i++ {
		go func() {
			digester(done, paths, c) // HLc
			wg.Done()
		}()
	}
	go func() {
		wg.Wait()
		close(c) // HLc
	}()
	// End of pipeline. OMIT

	m := make(map[string][md5.Size]byte)
	for r := range c {
		if r.err != nil {
			return nil, r.err
		}
		m[r.path] = r.sum
	}
	// Check whether the Walk failed.
	if err := <-errc; err != nil { // HLerrc
		return nil, err
	}
	return m, nil
}

func main() {
	// Calculate the MD5 sum of all files under the specified directory,
	// then print the results sorted by path name.
	m, err := MD5All(os.Args[1])
	if err != nil {
		fmt.Println(err)
		return
	}
	var paths []string
	for path := range m {
		paths = append(paths, path)
	}
	sort.Strings(paths)
	for _, path := range paths {
		fmt.Printf("%x  %s\n", m[path], path)
	}
}