I have this simple script to attempt to traverse the file system and read files line-by-line to match lines on a regex:
package main
import (
"bufio"
"fmt"
"io/ioutil"
"log"
"os"
"regexp"
"sync"
)
type FileWithLine struct{
Line int
Path string
}
var set = map[string]FileWithLine{}
var rgx = regexp.MustCompile("ErrId\\s*:\\s*\"[[:alnum:]]+\"");
func traverseDir(d string, wg *sync.WaitGroup){
fmt.Println("traversing dir:", d)
if d == ".git"{
return
}
wg.Add(1)
go func(wg *sync.WaitGroup){
defer wg.Done()
files, err := ioutil.ReadDir(d)
if err != nil {
log.Fatal(err)
}
for _, f := range files {
fmt.Println("we see file:", f.Name())
if f.IsDir() {
traverseDir(f.Name(), wg)
return
}
file, err := os.Open(f.Name())
if err != nil {
log.Fatalf("failed opening file: %s", err)
}
scanner := bufio.NewScanner(file)
scanner.Split(bufio.ScanLines)
for scanner.Scan() {
var line = scanner.Text()
if rgx.MatchString(line) {
fmt.Println("line matches:", line);
}
}
file.Close()
}
}(wg)
}
func main() {
var wg sync.WaitGroup
traverseDir(".", &wg)
fmt.Println("Main: Waiting for workers to finish")
wg.Wait()
fmt.Println("Main: Completed")
}
the problem is that it's exiting before it reads all the files, I get this output:
traversing dir: .
Main: Waiting for workers to finish
we see file: .git
traversing dir: .git
Main: Completed
but there are more files in the current directory, than just the .git folder. It just so happens that the .git folder is the first item in the current working dir and it exits right after that. Anyone know why my program is exciting early?
It is stopping processing because of these lines:
if f.IsDir() {
traverseDir(f.Name(), wg)
return
}
When it sees a directory, it goes in it and immediately returns, without processing the remaining files in the current directory. And when the first seen directory is ".git", since you handle it as an exception, the nested traverseDir also returns.
Related
I have a folder which contains multiple types of files (with no subfolders in this simple case). Let's assume it contains 20000 .raw files and 20000 .jpg files. I need to move .raw files into raw folder and .jpg files into jpg folder. So I tired to use golang to solve it:
package main
import (
"flag"
"fmt"
"io/fs"
"io/ioutil"
"os"
"runtime"
"strings"
"sync"
"time"
)
func CreateFolder(basePath string, folderName string) {
os.Mkdir(basePath+"/"+folderName, 0755)
}
func MoveFile(file string, path string, folder string) {
err := os.Rename(path+"/"+file, path+"/"+folder+"/"+file)
if err != nil {
panic(err)
}
}
func getInfo(a fs.FileInfo, c chan string) {
if a.IsDir() || strings.HasPrefix(a.Name(), ".") {
return
} else {
c <- a.Name()
}
}
func dealInfo(path string, typeDict *sync.Map, c chan string) {
for name := range c {
sp := strings.Split(name, ".")
suffix := sp[len(sp)-1]
if _, ok := typeDict.Load(suffix); ok {
MoveFile(name, path, suffix)
} else {
CreateFolder(path, suffix)
MoveFile(name, path, suffix)
typeDict.Store(suffix, 1)
}
}
}
func main() {
runtime.GOMAXPROCS(8)
var (
filepath = flag.String("p", "", "default self folder")
)
flag.Parse()
fmt.Println(*filepath)
fmt.Println("==========")
if *filepath == "" {
fmt.Println("No valid folder path")
return
} else {
fileinfos, err := ioutil.ReadDir(*filepath)
stime := time.Now()
if err != nil {
panic(err)
}
var typeDict sync.Map
ch := make(chan string, 20)
for _, fs := range fileinfos {
go getInfo(fs, ch)
go dealInfo(*filepath, &typeDict, ch)
}
fmt.Println(time.Since(stime))
}
}
But it returns an error: runtime: failed to create new OS thread. I guess this is due to too much goroutines the script created? But I've no idea why this could happen because I think ch := make(chan string, 20) would limit the number of goroutine.
I also tried to use wg *sync.WaitGroup, like:
getInfo(...) // use this func to put all files info into a channel
wg.Add(20)
for i:=0; i<20; i++ {
go dealInfo(..., &wg) // this new dealInfo contains wg.Done()
}
wg.Wait()
But this will cause a deadlock error.
May I know the best way to move files parallel please? Your help is really appreciated!
This may work.
However the move operation depends on the Operational System and the Filesystem.
Doing it on parallel may not be optimal via NFS for instance. You must check.
The strategy of list the files, send to channels to be executed (move/rename) by some goroutines is something that I will try in this situation.
The number of goroutines (workers) can be a command line parameter.
I'm writing a program that reads a list of order numbers in a file called orders.csv and compares it with the other csv files that are present in the folder.
The problem is that it goes into deadlock even using waitgroup and I don't know why.
For some reason stackoverflow says that my post is mostly code, so I have to add this line, because the whole code is necessary if someone wants to help me debug this problem I'm having.
package main
import (
"bufio"
"fmt"
"log"
"os"
"path/filepath"
"strings"
"sync"
)
type Files struct {
filenames []string
}
type Orders struct {
ID []string
}
var ordersFilename string = "orders.csv"
func main() {
var (
ordersFile *os.File
files Files
orders Orders
err error
)
mu := new(sync.Mutex)
wg := &sync.WaitGroup{}
wg.Add(1)
if ordersFile, err = os.Open(ordersFilename); err != nil {
log.Fatalln("Could not open file: " + ordersFilename)
}
orders = getOrderIDs(ordersFile)
files.filenames = getCSVsFromCurrentDir()
var filenamesSize = len(files.filenames)
var ch = make(chan map[string][]string, filenamesSize)
var done = make(chan bool)
for i, filename := range files.filenames {
go func(currentFilename string, ch chan<- map[string][]string, i int, orders Orders, wg *sync.WaitGroup, filenamesSize *int, mu *sync.Mutex, done chan<- bool) {
wg.Add(1)
defer wg.Done()
checkFile(currentFilename, orders, ch)
mu.Lock()
*filenamesSize--
mu.Unlock()
if i == *filenamesSize {
done <- true
close(done)
}
}(filename, ch, i, orders, wg, &filenamesSize, mu, done)
}
select {
case str := <-ch:
fmt.Printf("%+v\n", str)
case <-done:
wg.Done()
break
}
wg.Wait()
close(ch)
}
// getCSVsFromCurrentDir returns a string slice
// with the filenames of csv files inside the
// current directory that are not "orders.csv"
func getCSVsFromCurrentDir() []string {
var filenames []string
err := filepath.Walk(".", func(path string, info os.FileInfo, err error) error {
if path != "." && strings.HasSuffix(path, ".csv") && path != ordersFilename {
filenames = append(filenames, path)
}
return nil
})
if err != nil {
log.Fatalln("Could not read file names in current dir")
}
return filenames
}
// getOrderIDs returns an Orders struct filled
// with order IDs retrieved from the file
func getOrderIDs(file *os.File) Orders {
var (
orders Orders
err error
fileContent string
)
reader := bufio.NewReader(file)
if fileContent, err = readLine(reader); err != nil {
log.Fatalln("Could not read file: " + ordersFilename)
}
for err == nil {
orders.ID = append(orders.ID, fileContent)
fileContent, err = readLine(reader)
}
return orders
}
func checkFile(filename string, orders Orders, ch chan<- map[string][]string) {
var (
err error
file *os.File
fileContent string
orderFilesMap map[string][]string
counter int
)
orderFilesMap = make(map[string][]string)
if file, err = os.Open(filename); err != nil {
log.Fatalln("Could not read file: " + filename)
}
reader := bufio.NewReader(file)
if fileContent, err = readLine(reader); err != nil {
log.Fatalln("Could not read file: " + filename)
}
for err == nil {
if containedInSlice(fileContent, orders.ID) && !containedInSlice(fileContent, orderFilesMap[filename]) {
orderFilesMap[filename] = append(orderFilesMap[filename], fileContent)
// fmt.Println("Found: ", fileContent, " in ", filename)
} else {
// fmt.Printf("Could not find: '%s' in '%s'\n", fileContent, filename)
}
counter++
fileContent, err = readLine(reader)
}
ch <- orderFilesMap
}
// containedInSlice returns true or false
// based on whether the string is contained
// in the slice
func containedInSlice(str string, slice []string) bool {
for _, ID := range slice {
if ID == str {
return true
}
}
return false
}
// readLine returns a line from the passed reader
func readLine(r *bufio.Reader) (string, error) {
var (
isPrefix bool = true
err error = nil
line, ln []byte
)
for isPrefix && err == nil {
line, isPrefix, err = r.ReadLine()
ln = append(ln, line...)
}
return string(ln), err
}
The first issue is the wg.Add always must be outside of the goroutine(s) it stands for. If it isn't, the
wg.Wait call might be called before the goutine(s) have actually started running (and called wg.Add) and therefore will "think"
that there is nothing to wait for.
The second issue with the code is that there are multiple ways it waits for the routines to be done. There is
the WaitGroup and there is the done channel. Use only one of them. Which one depends also on how the results of the
goroutines are used. Here we come to the next problem.
The third issue is with gathering the results. Currently the code only prints / uses a single result from the goroutines.
Put a for { ... } loop around the select and use return to break out of the loop if the done channel is closed.
(Note that you don't need to send anything on the done channel, closing it is enough.)
Improved Version 0.0.1
So here the first version (including some other "code cleanup") with a done channel used for closing and the WaitGroup removed:
func main() {
ordersFile, err := os.Open(ordersFilename)
if err != nil {
log.Fatalln("Could not open file: " + ordersFilename)
}
orders := getOrderIDs(ordersFile)
files := Files{
filenames: getCSVsFromCurrentDir(),
}
var (
mu = new(sync.Mutex)
filenamesSize = len(files.filenames)
ch = make(chan map[string][]string, filenamesSize)
done = make(chan bool)
)
for i, filename := range files.filenames {
go func(currentFilename string, ch chan<- map[string][]string, i int, orders Orders, filenamesSize *int, mu *sync.Mutex, done chan<- bool) {
checkFile(currentFilename, orders, ch)
mu.Lock()
*filenamesSize--
mu.Unlock()
// TODO: This also accesses filenamesSize, so it also needs to be protected with the mutex:
if i == *filenamesSize {
done <- true
close(done)
}
}(filename, ch, i, orders, &filenamesSize, mu, done)
}
// Note: closing a channel is not really needed, so you can omit this:
defer close(ch)
for {
select {
case str := <-ch:
fmt.Printf("%+v\n", str)
case <-done:
return
}
}
}
Improved Version 0.0.2
In your case we have some advantage however. We know exactly how many goroutines we started and therefore also how
many results we expect. (Of course if each goroutine returns a result which currently this code does.) That gives
us another option as we can collect the results with another for loop having the same amount of iterations:
func main() {
ordersFile, err := os.Open(ordersFilename)
if err != nil {
log.Fatalln("Could not open file: " + ordersFilename)
}
orders := getOrderIDs(ordersFile)
files := Files{
filenames: getCSVsFromCurrentDir(),
}
var (
// Note: a buffered channel helps speed things up. The size does not need to match the size of the items that will
// be passed through the channel. A fixed, small size is perfect here.
ch = make(chan map[string][]string, 5)
)
for _, filename := range files.filenames {
go func(filename string) {
// orders and channel are not variables of the loop and can be used without copying
checkFile(filename, orders, ch)
}(filename)
}
for range files.filenames {
str := <-ch
fmt.Printf("%+v\n", str)
}
}
A lot simpler, isn't it? Hope that helps!
There is a lot wrong with this code.
You're using the WaitGroup wrong. Add has to be called in the main goroutine, else there is a chance that Wait is called before all Add calls complete.
There's an extraneous Add(1) call right after initializing the WaitGroup that isn't matched by a Done() call, so Wait will never return (assuming the point above is fixed).
You're using both a WaitGroup and a done channel to signal completion. This is redundant at best.
You're reading filenamesSize while not holding the lock (in the if i == *filenamesSize statement). This is a race condition.
The i == *filenamesSize condition makes no sense in the first place. Goroutines execute in an arbitrary order, so you can't be sure that the goroutine with i == 0 is the last one to decrement filenamesSize
This can all be simplified by getting rid of most if the synchronization primitives and simply closing the ch channel when all goroutines are done:
func main() {
ch := make(chan map[string][]string)
var wg WaitGroup
for _, filename := range getCSVsFromCurrentDir() {
filename := filename // capture loop var
wg.Add(1)
go func() {
checkFile(filename, orders, ch)
wg.Done()
}()
}
go func() {
wg.Wait() // after all goroutines are done...
close(ch) // let range loop below exit
}()
for str := range ch {
// ...
}
}
not an answer, but some comments that does not fit the comment box.
In this part of the code
func main() {
var (
ordersFile *os.File
files Files
orders Orders
err error
)
mu := new(sync.Mutex)
wg := &sync.WaitGroup{}
wg.Add(1)
The last statement is a call to wg.Add that appears dangling. By that i mean we can hardly understand what will trigger the required wg.Done counter part. This is a mistake to call for wg.Add without a wg.Done, this is prone to errors to not write them in such way we can not immediately find them in pair.
In that part of the code, it is clearly wrong
go func(currentFilename string, ch chan<- map[string][]string, i int, orders Orders, wg *sync.WaitGroup, filenamesSize *int, mu *sync.Mutex, done chan<- bool) {
wg.Add(1)
defer wg.Done()
Consider that by the time the routine is executed, and that you added 1 to the waitgroup, the parent routine continues to execute. See this example: https://play.golang.org/p/N9Chaqkv4bd
The main routine does not wait for the waitgroup because it does not have time to increment.
There is more to say but i find it hard to understand the purpose of your code so i am not sure how to help you further without basically rewrite it.
i have written the following code in order to run until someone exit the program manually.
it does is
----- check if the exists every 1 second
----- if available then read the file and print the file content line by line
for this i have first call a function from the main
and then i call a waitgroup and call a function again from there to do the aforementioned tasks.
please check if i have written the source code correctly as im a newbi on GO
plus this only runs once and stop... i want to it keep alive and see if the file exsists
please help me
package main
import (
"encoding/csv"
"fmt"
"io"
"log"
"os"
"sync"
"time"
)
func main() {
mainfunction()
}
//------------------------------------------------------------------
func mainfunction() {
var wg sync.WaitGroup
wg.Add(1)
go filecheck(&wg)
wg.Wait()
fmt.Printf("Program finished \n")
}
func filecheck(wg *sync.WaitGroup) {
for range time.Tick(time.Second * 1) {
fmt.Println("Foo")
var wgi sync.WaitGroup
wgi.Add(1)
oldName := "test.csv"
newName := "testi.csv"
if _, err := os.Stat(oldName); os.IsNotExist(err) {
fmt.Printf("Path does not exsist \n")
} else {
os.Rename(oldName, newName)
if err != nil {
log.Fatal(err)
}
looping(newName, &wgi)
}
fmt.Printf("Test complete \n")
wgi.Wait()
wg.Done()
time.Sleep(time.Second * 5)
}
}
func looping(newName string, wgi *sync.WaitGroup) {
file, _ := os.Open(newName)
r := csv.NewReader(file)
for {
record, err := r.Read()
if err == io.EOF {
break
}
if err != nil {
log.Fatal(err)
}
var Date = record[0]
var Agent = record[1]
var Srcip = record[2]
var Level = record[3]
fmt.Printf("Data: %s Agent: %s Srcip: %s Level: %s\n", Date, Agent, Srcip, Level)
}
fmt.Printf("Test complete 2 \n")
wgi.Done()
fmt.Printf("for ended")
}
The short answer is that you have this in the loop:
wg.Done()
Which makes the main goroutine proceed to exit as soon as the file is read once.
The longer answer is that you're not using wait groups correctly here, IMHO. For example there's absolutely no point in passing a WaitGroup into looping.
It's not clear what your code is trying to accomplish - you certainly don't need any goroutines to just perform the task you've specified - it can all be gone with no concurrency and thus simpler code.
I would like to understand why this case deadlock and why it's not in the other case.
If I close the channel inside the goroutine, it works fine, but if I close it after the WaitGroup.Wait() it cause a deadlock.
package main
import (
"fmt"
"io/ioutil"
"os"
"sync"
)
var (
wg = sync.WaitGroup{}
links = make(chan string)
)
func rec_readdir(depth int, path string) {
files, _ := ioutil.ReadDir(path)
for _, f := range files {
if symlink, err := os.Readlink(path + "/" + f.Name()); err == nil {
links <- path + "/" + symlink
}
rec_readdir(depth+1, path+"/"+f.Name())
}
if depth == 0 {
wg.Done()
// close(links) // if close here ok
}
}
func main() {
wg.Add(1)
go rec_readdir(0, ".")
for slink := range links {
fmt.Println(slink)
}
wg.Wait()
close(links) // if close here deadlock
}
https://play.golang.org/p/Ntl_zsV5nwO
for slink := range links will continue looping until the channel is closed. So you obviously can't close after that loop. When you do, you get a deadlock, as you have observed.
I recently looked at go and got hooked, it looks so interesting! After completing the tutorial I wanted to build something by myself: I want to list all of my songs from my music library. I think I can profit from go's concurrency here. While on routine is walking down the directory tree it pushes music files (path to those files) into a channel which are then picked up by another routine that reads the ID3 tags, so I don't have to wait until every file has been found.
This is my simple and naive approach:
package main
import (
"fmt"
"os"
"path/filepath"
"strings"
"sync"
)
const searchPath = "/Users/luma/Music/test" // 5GB of music.
func main() {
files := make(chan string)
var wg sync.WaitGroup
wg.Add(2)
go printHashes(files, &wg)
go searchFiles(searchPath, files, &wg)
wg.Wait()
}
func searchFiles(searchPath string, files chan<- string, wg *sync.WaitGroup) {
visit := func(path string, f os.FileInfo, err error) error {
if !f.IsDir() && strings.Contains(".mp4.mp3.flac", filepath.Ext(f.Name())) {
files <- path
}
return err
}
if err := filepath.Walk(searchPath, visit); err != nil {
fmt.Println(err)
}
wg.Done()
}
func printHashes(files <-chan string, wg *sync.WaitGroup) {
for range files {
fmt.Println(<-files)
}
wg.Done()
}
This program doesn't read the tags, yet. Instead it just prints the file path. This works, it lists all music files extremely fast! But I see this error after the program finishes:
fatal error: all goroutines are asleep - deadlock!
goroutine 1 [semacquire]:
sync.runtime_Semacquire(0xc42007205c)
/usr/local/Cellar/go/1.7.4_2/libexec/src/runtime/sema.go:47 +0x30
sync.(*WaitGroup).Wait(0xc420072050)
/usr/local/Cellar/go/1.7.4_2/libexec/src/sync/waitgroup.go:131 +0x97
main.main()
/Users/luma/Code/Go/src/github.com/LuMa/test/main.go:22 +0xfa
goroutine 17 [chan receive]:
main.printHashes(0xc42008e000, 0xc420072050)
/Users/luma/Code/Go/src/github.com/LuMa/test/main.go:42 +0xb4
created by main.main
/Users/luma/Code/Go/src/github.com/LuMa/test/main.go:19 +0xab
exit status 2
What is causing the deadlock?
Because you need close files channel.
In your case, you don't close it, so
for range files {
fmt.Println(<-files)
} will wait get value from files channel. so wg.Done() will never done in printHashes.
func searchFiles(searchPath string, files chan<- string, wg *sync.WaitGroup) {
visit := func(path string, f os.FileInfo, err error) error {
if !f.IsDir() && strings.Contains(".mp4.mp3.flac", filepath.Ext(f.Name())) {
files <- path
}
return err
}
if err := filepath.Walk(searchPath, visit); err != nil {
fmt.Println(err)
}
wg.Done()
close(files) // close the chanel, because you don't put thing into the channel anymore.
}
Within searchFiles, you want to close(files) when done sending. This convention is called sender-closes (receivers never close). Also, remove the call to wg.Done() as you are not done... There could still be items on the channel.
The close(files) will signal the for range files to close and exit the loop, which will call your wg.Done() to signal the main function that everything is done.
(Untested on mobile)
package main
import (
"fmt"
"os"
"path/filepath"
"strings"
"sync"
)
const searchPath = "/Users/luma/Music/test" // 5GB of music.
func main() {
files := make(chan string)
var wg sync.WaitGroup
wg.Add(1)
go printHashes(files)
go searchFiles(searchPath, files, &wg)
wg.Wait()
}
func searchFiles(searchPath string, files chan<- string) {
visit := func(path string, f os.FileInfo, err error) error {
if !f.IsDir() && strings.Contains(".mp4.mp3.flac", filepath.Ext(f.Name())) {
files <- path
}
return err
}
if err := filepath.Walk(searchPath, visit); err != nil {
fmt.Println(err)
}
close(files)
}
func printHashes(files <-chan string, wg *sync.WaitGroup) {
defer wg.Done()
for range files {
fmt.Println(<-files)
}
}
Note that while this may seem fast, using a single goroutine is fine and unblocks the main goroutine too. But, you may not gain any advantage if you try to read multiple files for id3 tags in multiple goroutines - they will all share the same file i/o lock at the syscall level. The only way that would advantageous would be if the processing of data far out weighs the file i/o locking (e.g. something big in computation, because processing is far faster than syscall locks).
PS, welcome to the Go community!