I have a tar file that contains multiple tar files in it. I'm currently extracting these tars recursively using the tar Reader by moving manually over the files. This process is very heavy and slow, especially when dealing with large tar files that contain thousands of files and directories.
I didn't find any good package that is able to do this recursive extraction fast. plus I tried using the command tar -xf file.tar --same-owner" for the inner tars, but had a problem with permissions issue (which happens only on mac).
my question is:
Is there a way to parallelize the manual extraction process so that the inner tars will be extracted in parallel?
I have a method for the extraction task which I'm trying to make parallel:
var wg sync.WaitGroup
wg.Add(len(tarFiles))
for {
header, err := tarBallReader.Next()
if err != nil {
break
}
go extractFileAsync(parentFolder, header, tarBallReader, depth, &wg)
}
wg.Wait()
after adding the go routines, the files are getting corrupted and the process is stuck on an endless loop.
example of the main tar content:
1d2755f3375860aaaf2b5f0474692df2e0d4329569c1e8187595bf4b3bf3f3b9/
1d2755f3375860aaaf2b5f0474692df2e0d4329569c1e8187595bf4b3bf3f3b9/VERSION
1d2755f3375860aaaf2b5f0474692df2e0d4329569c1e8187595bf4b3bf3f3b9/json
1d2755f3375860aaaf2b5f0474692df2e0d4329569c1e8187595bf4b3bf3f3b9/layer.tar
348188998f2a69b4ac0ca96b42990292eef67c0abfa05412e2fb7857645f4280/
348188998f2a69b4ac0ca96b42990292eef67c0abfa05412e2fb7857645f4280/VERSION
348188998f2a69b4ac0ca96b42990292eef67c0abfa05412e2fb7857645f4280/json
348188998f2a69b4ac0ca96b42990292eef67c0abfa05412e2fb7857645f4280/layer.tar
54c027bf04447fdb035ddc13a6ae5493a3f997bdd3577607b0980954522efb9e.json
9dd3c29af50daaf86744a8ade86ecf12f6a5a6ffc27a5a7398628e4a21770ee3/
9dd3c29af50daaf86744a8ade86ecf12f6a5a6ffc27a5a7398628e4a21770ee3/VERSION
9dd3c29af50daaf86744a8ade86ecf12f6a5a6ffc27a5a7398628e4a21770ee3/json
9dd3c29af50daaf86744a8ade86ecf12f6a5a6ffc27a5a7398628e4a21770ee3/layer.tar
b6c49400b643245cdbe17b7a7eb14f0f7def5a93326b99560241715c1e95502e/
b6c49400b643245cdbe17b7a7eb14f0f7def5a93326b99560241715c1e95502e/VERSION
b6c49400b643245cdbe17b7a7eb14f0f7def5a93326b99560241715c1e95502e/json
b6c49400b643245cdbe17b7a7eb14f0f7def5a93326b99560241715c1e95502e/layer.tar
c662ec0dc487910e7b76b2a4d67ab1a9ca63ce1784f636c2637b41d6c7ac5a1e/
c662ec0dc487910e7b76b2a4d67ab1a9ca63ce1784f636c2637b41d6c7ac5a1e/VERSION
c662ec0dc487910e7b76b2a4d67ab1a9ca63ce1784f636c2637b41d6c7ac5a1e/json
c662ec0dc487910e7b76b2a4d67ab1a9ca63ce1784f636c2637b41d6c7ac5a1e/layer.tar
da87454b77f6ac7fab1f465c10a07a1eb4b46df8058d98892794618cac8eacdc/
da87454b77f6ac7fab1f465c10a07a1eb4b46df8058d98892794618cac8eacdc/VERSION
da87454b77f6ac7fab1f465c10a07a1eb4b46df8058d98892794618cac8eacdc/json
da87454b77f6ac7fab1f465c10a07a1eb4b46df8058d98892794618cac8eacdc/layer.tar
ea1c2adfdc777d8746e50ad3e679789893a991606739c9bc7e01f273fa0b6e12/
ea1c2adfdc777d8746e50ad3e679789893a991606739c9bc7e01f273fa0b6e12/VERSION
ea1c2adfdc777d8746e50ad3e679789893a991606739c9bc7e01f273fa0b6e12/json
ea1c2adfdc777d8746e50ad3e679789893a991606739c9bc7e01f273fa0b6e12/layer.tar
f3b6608e814053048d79e519be79f654a2e9364dfdc8fb87b71e2fc57bbff115/
f3b6608e814053048d79e519be79f654a2e9364dfdc8fb87b71e2fc57bbff115/VERSION
f3b6608e814053048d79e519be79f654a2e9364dfdc8fb87b71e2fc57bbff115/json
f3b6608e814053048d79e519be79f654a2e9364dfdc8fb87b71e2fc57bbff115/layer.tar
manifest.json
repositories
or simply you can run docker save <image>:<tag> -o image.tar and check the content of the tar.
Probably your code hangs on wg.Wait() due to the fact that the number of calls to wg.Done() during execution is not equal to len(tarFiles).
That should work:
var wg sync.WaitGroup
// wg.Add(len(tarFiles))
for {
header, err := tarBallReader.Next()
if err != nil {
break
}
wg.Add(1)
go extractFileAsync(parentFolder, header, tarBallReader, depth, &wg)
}
wg.Wait()
func extractFileAsync(...) {
defer wg.Done()
// some code
}
UPD: correction of a possible race condition. Thanks #craigb
Here is my solution to a similar problem (simplified):
package main
import (
"archive/tar"
"fmt"
"io"
"os"
"path/filepath"
"strings"
"sync"
)
type Semaphore struct {
Wg sync.WaitGroup
Ch chan int
}
// Limit on the number of simultaneously running goroutines.
// Depends on the number of processor cores, storage performance, amount of RAM, etc.
const grMax = 10
const tarFileName = "docker_image.tar"
const dstDir = "output/docker"
func extractTar(tarFileName string, dstDir string) error {
f, err := os.Open(tarFileName)
if err != nil {
return err
}
sem := Semaphore{}
sem.Ch = make(chan int, grMax)
if err := Untar(dstDir, f, &sem, true); err != nil {
return err
}
fmt.Println("extractTar: wait for complete")
sem.Wg.Wait()
return nil
}
func Untar(dst string, r io.Reader, sem *Semaphore, godeep bool) error {
tr := tar.NewReader(r)
for {
header, err := tr.Next()
switch {
case err == io.EOF:
return nil
case err != nil:
return err
}
// the target location where the dir/file should be created
target := filepath.Join(dst, header.Name)
switch header.Typeflag {
// if its a dir and it doesn't exist create it
case tar.TypeDir:
if _, err := os.Stat(target); err != nil {
if err := os.MkdirAll(target, 0755); err != nil {
return err
}
}
// if it's a file create it
case tar.TypeReg:
if err := saveFile(tr, target, os.FileMode(header.Mode)); err != nil {
return err
}
ext := filepath.Ext(target)
// if it's tar file and we are on top level, extract it
if ext == ".tar" && godeep {
sem.Wg.Add(1)
// A buffered channel is used to limit the number of simultaneously running goroutines
sem.Ch <- 1
// the file is unpacked to a directory with the file name (without extension)
newDir := filepath.Join(dst, strings.TrimSuffix(header.Name, ".tar"))
if err := os.Mkdir(newDir, 0755); err != nil {
return err
}
go func(target string, newDir string, sem *Semaphore) {
fmt.Println("start goroutine, chan length:", len(sem.Ch))
fmt.Println("START:", target)
defer sem.Wg.Done()
defer func() {<-sem.Ch}()
// the internal tar file opens
ft, err := os.Open(target)
if err != nil {
fmt.Println(err)
return
}
defer ft.Close()
// the godeep parameter is false here to avoid unpacking archives inside the current archive.
if err := Untar(newDir, ft, sem, false); err != nil {
fmt.Println(err)
return
}
fmt.Println("DONE:", target)
}(target, newDir, sem)
}
}
}
return nil
}
func saveFile(r io.Reader, target string, mode os.FileMode) error {
f, err := os.OpenFile(target, os.O_CREATE|os.O_RDWR, mode)
if err != nil {
return err
}
defer f.Close()
if _, err := io.Copy(f, r); err != nil {
return err
}
return nil
}
func main() {
err := extractTar(tarFileName, dstDir)
if err != nil {
fmt.Println(err)
}
}
Related
I am trying to create a .tar.gz file from folder that contains multiple files / folders. Once the .tar.gz file gets created, while extracting, the files are not not properly extracted. Mostly I think its because of large names or path exceeding some n characters, because same thing works when the filename/path is small. I referred this https://github.com/golang/go/issues/17630 and tried to add below code but it did not help.
header.Uid = 0
header.Gid = 0
I am using simple code seen below to create .tar.gz. The approach is, I create a temp folder, do some processing on the files and from that temp path, I create the .tar.gz file hence in the path below I am using pre-defined temp folder path.
package main
import (
"archive/tar"
"compress/gzip"
"fmt"
"io"
"log"
"os"
fp "path/filepath"
)
func main() {
// Create output file
out, err := os.Create("output.tar.gz")
if err != nil {
log.Fatalln("Error writing archive:", err)
}
defer out.Close()
// Create the archive and write the output to the "out" Writer
tmpDir := "C:/Users/USERNAME~1/AppData/Local/Temp/temp-241232063"
err = createArchive1(tmpDir, out)
if err != nil {
log.Fatalln("Error creating archive:", err)
}
fmt.Println("Archive created successfully")
}
func createArchive1(path string, targetFile *os.File) error {
gw := gzip.NewWriter(targetFile)
defer gw.Close()
tw := tar.NewWriter(gw)
defer tw.Close()
// walk through every file in the folder
err := fp.Walk(path, func(filePath string, info os.FileInfo, err error) error {
// ensure the src actually exists before trying to tar it
if _, err := os.Stat(filePath); err != nil {
return err
}
if err != nil {
return err
}
if info.IsDir() {
return nil
}
file, err := os.Open(filePath)
if err != nil {
return err
}
defer file.Close()
// generate tar header
header, err := tar.FileInfoHeader(info, info.Name())
header.Uid = 0
header.Gid = 0
if err != nil {
return err
}
header.Name = filePath //strings.TrimPrefix(filePath, fmt.Sprintf("%s/", fp.Dir(path))) //info.Name()
// write header
if err := tw.WriteHeader(header); err != nil {
return err
}
if _, err := io.Copy(tw, file); err != nil {
return err
}
return nil
})
return err
}
Please let me know what wrong I am doing.
The process cannot access the file ... because it is being used by another process
I can't Remover Zip file with this code ..
it's possible? extract and delete the file in one code.
Code
package main
import (
"archive/zip"
"fmt"
"io"
"log"
"net/http"
"os"
"path/filepath"
"strings"
)
func main() {
url := "https://230c07c8-77b2-4c0d-9b82-8c6501a5bc45.filesusr.com/archives/b7572a_9ec985e0031042ef912cb40cafbe6376.zip?dn=7.zip"
out, _ := os.Create("E:\\experi\\1234567890.zip")
defer out.Close()
resp, _ := http.Get(url)
defer resp.Body.Close()
_, _ = io.Copy(out, resp.Body)
files, err := Unzip("E:\\experi\\1234567890.zip", "E:\\experi\\1234567890")
if err != nil {
log.Fatal(err)
}
fmt.Println("Unzipped the following files:\n" + strings.Join(files, "\n"))
}
func Unzip(src string, destination string) ([]string, error) {
var filenames []string
r, err := zip.OpenReader(src)
if err != nil {
return filenames, err
}
defer r.Close()
for _, f := range r.File {
fpath := filepath.Join(destination, f.Name)
if !strings.HasPrefix(fpath, filepath.Clean(destination)+string(os.PathSeparator)){
return filenames, fmt.Errorf("%s is an illegal filepath", fpath)
}
filenames = append(filenames, fpath)
if f.FileInfo().IsDir() {
os.MkdirAll(fpath, os.ModePerm)
continue
}
if err = os.MkdirAll(filepath.Dir(fpath), os.ModePerm); err != nil {
return filenames, err
}
outFile, err := os.OpenFile(fpath,
os.O_WRONLY|os.O_CREATE|os.O_TRUNC | os.O_RDWR,
f.Mode())
if err != nil {
return filenames, err
}
rc, err := f.Open()
if err != nil {
return filenames, err
}
_, err = io.Copy(outFile, rc)
outFile.Close()
rc.Close()
if err != nil {
return filenames, err
}
}
removeFile()
return filenames, nil
}
func removeFile() {
error := os.Remove("E:\\experi\\1234567890.zip")
if error != nil {
log.Fatal(error)
}
}
Output
output text
2020/10/28 13:09:04 remove E:\experi\1234567890.zip: The process cannot access the file because it is being used by another process.
Process finished with exit code 1
Any other way to do this same thing ?
Did I go wrong anywhere?
Help Would be Much Appreciated. Thanks in Advance. :)
out, _ := os.Create("E:\\experi\\1234567890.zip") creates or truncates the file and returns you a *File (so the file is open).
defer out.Close() closes the file "the moment the surrounding function returns" (spec).
So at the time you call Unzip you have the file open. To fix this call out.Close() before the call to Unzip (and please don't assume that calls complete without error).
If you close using the defer, it is closed after performing up to the last line of the function. You must explicitly close the file before remove it.
every one,I am new to golang.I wanna get the data from log file generated by my application.cuz roll-back mechanism, I met some problem.For instance,my target log file is chats.log,it will be renamed to chats.log.2018xxx and a new chats.log will be created.so my go routine that read log file will fail to work.
so I need detect the change and shutdown the previous go routine and then establish the new go routine.
I looked for modules that can help me,and I found
func ExampleNewWatcher(fn string, createnoti chan string, wg sync.WaitGroup) {
wg.Add(1)
defer wg.Done()
watcher, err := fsnotify.NewWatcher()
if err != nil {
log.Fatal(err)
}
defer watcher.Close()
done := make(chan bool)
go func() {
for {
select {
case event := <-watcher.Events:
if event.Op == fsnotify.Create && event.Name==fn{
createnoti <- "has been created"
}
case err := <-watcher.Errors:
log.Println("error:", err)
}
}
}()
err = watcher.Add("./")
if err != nil {
log.Fatal(err)
}
<-done
}
I use fsnotify to detech the change,and make sure the event of file is my log file,and then send some message to a channel.
this is my worker go routine:
func tailer(fn string,isfollow bool, outchan chan string, done <-chan interface{},wg sync.WaitGroup) error {
wg.Add(1)
defer wg.Done()
_, err := os.Stat(fn)
if err != nil{
panic(err)
}
t, err := tail.TailFile(fn, tail.Config{Follow:isfollow})
if err != nil{
panic(err)
}
defer t.Stop()
for line := range t.Lines{
select{
case outchan <- line.Text:
case <- done:
return nil
}
}
return nil
}
I using tail module to read the log file,and I add a done channel to it to shutdown the cycle(I don't know whether I put it in the right way)
And I will send every log content to a channel to consuming it.
So here is the question:how should I put it together?
ps: Actually,I can use some tool to do this job.like apache-flume,but all of those tools need dependency.
Thank you a lot!
Here is a complete example that reloads and rereads the file as it changes or gets deleted and recreated:
package main
import (
"github.com/fsnotify/fsnotify"
"io/ioutil"
"log"
)
const filename = "myfile.txt"
func ReadFile(filename string) string {
data, err := ioutil.ReadFile(filename)
if err != nil {
log.Println(err)
}
return string(data)
}
func main() {
watcher, err := fsnotify.NewWatcher()
if err != nil {
log.Fatal(err)
}
defer watcher.Close()
err = watcher.Add("./")
if err != nil {
log.Fatal(err)
}
for {
select {
case event := <-watcher.Events:
if event.Op == fsnotify.Create && event.Name == filename {
log.Println(ReadFile(filename))
}
case err := <-watcher.Errors:
log.Println("error:", err)
}
}
}
Note this doesn't require goroutines, channels or a WaitGroup. Better to keep things simple and reserve those for when they're actually needed.
I have been testing code using io.Pipe to tar and gunzip files into a tar ball and then unzipping using the tar utility. The follow code passes, however the untaring process keeps getting
error:
tar: Truncated input file (needed 1050624 bytes, only 0 available)
tar: Error exit delayed from previous errors.
This issue is really driving me crazy. It has been two weeks. I really need help debugging.
Thanks.
Development enviroment: go version go1.9 darwin/amd64
package main
import (
"archive/tar"
"compress/gzip"
"fmt"
"io"
"log"
"os"
"path/filepath"
"testing"
)
func testTarGzipPipe2(t *testing.T) {
src := "/path/to/file/folder"
pr, pw := io.Pipe()
gzipWriter := gzip.NewWriter(pw)
defer gzipWriter.Close()
tarWriter := tar.NewWriter(gzipWriter)
defer tarWriter.Close()
status := make(chan bool)
go func() {
defer pr.Close()
// tar to local disk
tarFile, err := os.OpenFile("/path/to/tar/ball/test.tar.gz", os.O_RDWR|os.O_CREATE, 0755)
if err != nil {
log.Fatal(err)
}
defer tarFile.Close()
if _, err := io.Copy(tarFile, pr); err != nil {
log.Fatal(err)
}
status <- true
}()
err := filepath.Walk(src, func(path string, info os.FileInfo, err error) error {
if err != nil {
return err
}
header, err := tar.FileInfoHeader(info, info.Name())
if err != nil {
return err
}
// header.Name = strings.TrimPrefix(strings.Replace(path, src, "", -1), string(filepath.Separator))
if err := tarWriter.WriteHeader(header); err != nil {
return err
}
if info.Mode().IsDir() {
return nil
}
fmt.Println(path)
f, err := os.Open(path)
if err != nil {
return err
}
defer f.Close()
if _, err := io.Copy(tarWriter, f); err != nil {
return err
}
return nil
})
if err != nil {
log.Fatal(err)
}
pw.Close()
<-status
}
You are closing the pipe before the deferred Close calls on the gzipWriter and tarWriter. There's no error, because you're not checking the error on either of those close calls. You need to close the tarWriter, then the gzipWriter, then the PipeWriter, in that order.
However, there's no reason for the pipe at all in this code, and you can remove the goroutine and the associated coordination altogether if you write directly to the file.
tarFile, err := os.OpenFile("/tmp/test.tar.gz", os.O_RDWR|os.O_CREATE, 0644)
if err != nil {
log.Fatal(err)
}
defer tarFile.Close()
gzipWriter := gzip.NewWriter(tarFile)
defer gzipWriter.Close()
tarWriter := tar.NewWriter(gzipWriter)
defer tarWriter.Close()
I have the following code which is suppose to download file by splitting it into multiple parts. But right now it only works on images, when I try downloading other files like tar files the output is an invalid file.
UPDATED:
Used os.WriteAt instead of os.Write and removed os.O_APPEND file mode.
package main
import (
"errors"
"flag"
"fmt"
"io/ioutil"
"log"
"net/http"
"os"
"strconv"
)
var file_url string
var workers int
var filename string
func init() {
flag.StringVar(&file_url, "url", "", "URL of the file to download")
flag.StringVar(&filename, "filename", "", "Name of downloaded file")
flag.IntVar(&workers, "workers", 2, "Number of download workers")
}
func get_headers(url string) (map[string]string, error) {
headers := make(map[string]string)
resp, err := http.Head(url)
if err != nil {
return headers, err
}
if resp.StatusCode != 200 {
return headers, errors.New(resp.Status)
}
for key, val := range resp.Header {
headers[key] = val[0]
}
return headers, err
}
func download_chunk(url string, out string, start int, stop int) {
client := new(http.Client)
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Range", fmt.Sprintf("bytes=%d-%d", start, stop))
resp, _ := client.Do(req)
defer resp.Body.Close()
body, err := ioutil.ReadAll(resp.Body)
if err != nil {
log.Fatalln(err)
return
}
file, err := os.OpenFile(out, os.O_WRONLY, 0600)
if err != nil {
if file, err = os.Create(out); err != nil {
log.Fatalln(err)
return
}
}
defer file.Close()
if _, err := file.WriteAt(body, int64(start)); err != nil {
log.Fatalln(err)
return
}
fmt.Println(fmt.Sprintf("Range %d-%d: %d", start, stop, resp.ContentLength))
}
func main() {
flag.Parse()
headers, err := get_headers(file_url)
if err != nil {
fmt.Println(err)
} else {
length, _ := strconv.Atoi(headers["Content-Length"])
bytes_chunk := length / workers
fmt.Println("file length: ", length)
for i := 0; i < workers; i++ {
start := i * bytes_chunk
stop := start + (bytes_chunk - 1)
go download_chunk(file_url, filename, start, stop)
}
var input string
fmt.Scanln(&input)
}
}
Basically, it just reads the length of the file, divides it with the number of workers then each file downloads using HTTP's Range header, after downloading it seeks to a position in the file where that chunk is written.
If you really ignore many errors like seen above then your code is not supposed to work reliably for any file type.
However, I guess I can see on problem in your code. I think that mixing O_APPEND and seek is probably a mistake (Seek should be ignored with this mode). I suggest to use (*os.File).WriteAt instead.
IIRC, O_APPEND forces any write to happen at the [current] end of file. However, your download_chunk function instances for file parts can be executing in unpredictable order, thus "reordering" the file parts. The result is then a corrupted file.
1.the sequence of the go routine is not sure。
eg. the execute result maybe as follows:
...
file length:20902
Range 10451-20901:10451
Range 0-10450:10451
...
so the chunks can't just append.
2.when write chunk datas must have a sys.Mutex
(my english is poor,please forget it)