rm包含数百万个文件的目录

#1 楼

#2 楼

$ strace ls -1 | wc -l
brk(0x4949000)                          = 0x4949000
getdents(3, /* 1025 entries */, 32768)  = 32752
getdents(3, /* 1024 entries */, 32768)  = 32752
getdents(3, /* 1025 entries */, 32768)  = 32760
getdents(3, /* 1025 entries */, 32768)  = 32768
brk(0)                                  = 0x4949000
brk(0x496a000)                          = 0x496a000
getdents(3, /* 1024 entries */, 32768)  = 32752
getdents(3, /* 1026 entries */, 32768)  = 32760
...

$ time ls -1 | wc -l
2616044

real    0m20.609s
user    0m16.241s
sys 0m3.639s

/* I can be compiled with the command "gcc -o dentls dentls.c" */

#define _GNU_SOURCE

#include <dirent.h>     /* Defines DT_* constants */
#include <err.h>
#include <fcntl.h>
#include <getopt.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include <unistd.h>

struct linux_dirent {
        long           d_ino;
        off_t          d_off;
        unsigned short d_reclen;
        char           d_name[256];
        char           d_type;
};

static int delete = 0;
char *path = NULL;

static void parse_config(
        int argc,
        char **argv)
{
    int option_idx = 0;
    static struct option loptions[] = {
      { "delete", no_argument, &delete, 1 },
      { "help", no_argument, NULL, 'h' },
      { 0, 0, 0, 0 }
    };

    while (1) {
        int c = getopt_long(argc, argv, "h", loptions, &option_idx);
        if (c < 0)
            break;

        switch(c) {
          case 0: {
              break;
          }

          case 'h': {
              printf("Usage: %s [--delete] DIRECTORY\n"
                     "List/Delete files in DIRECTORY.\n"
                     "Example %s --delete /var/spool/postfix/deferred\n",
                     argv[0], argv[0]);
              exit(0);                      
              break;
          }

          default:
          break;
        }
    }

    if (optind >= argc)
      errx(EXIT_FAILURE, "Must supply a valid directory\n");

    path = argv[optind];
}

int main(
    int argc,
    char** argv)
{

    parse_config(argc, argv);

    int totalfiles = 0;
    int dirfd = -1;
    int offset = 0;
    int bufcount = 0;
    void *buffer = NULL;
    char *d_type;
    struct linux_dirent *dent = NULL;
    struct stat dstat;

    /* Standard sanity checking stuff */
    if (access(path, R_OK) < 0) 
        err(EXIT_FAILURE, "Could not access directory");

    if (lstat(path, &dstat) < 0) 
        err(EXIT_FAILURE, "Unable to lstat path");

    if (!S_ISDIR(dstat.st_mode))
        errx(EXIT_FAILURE, "The path %s is not a directory.\n", path);

    /* Allocate a buffer of equal size to the directory to store dents */
    if ((buffer = calloc(dstat.st_size*3, 1)) == NULL)
        err(EXIT_FAILURE, "Buffer allocation failure");

    /* Open the directory */
    if ((dirfd = open(path, O_RDONLY)) < 0) 
        err(EXIT_FAILURE, "Open error");

    /* Switch directories */
    fchdir(dirfd);

    if (delete) {
        printf("Deleting files in ");
        for (int i=5; i > 0; i--) {
            printf("%u. . . ", i);
            fflush(stdout);
            sleep(1);
        }
        printf("\n");
    }

    while (bufcount = syscall(SYS_getdents, dirfd, buffer, dstat.st_size*3)) {
        offset = 0;
        dent = buffer;
        while (offset < bufcount) {
            /* Don't print thisdir and parent dir */
            if (!((strcmp(".",dent->d_name) == 0) || (strcmp("..",dent->d_name) == 0))) {
                d_type = (char *)dent + dent->d_reclen-1;
                /* Only print files */
                if (*d_type == DT_REG) {
                    printf ("%s\n", dent->d_name);
                    if (delete) {
                        if (unlink(dent->d_name) < 0)
                            warn("Cannot delete file \"%s\"", dent->d_name);
                    }
                    totalfiles++;
                }
            }
            offset += dent->d_reclen;
            dent = buffer + offset;
        }
    }
    fprintf(stderr, "Total files: %d\n", totalfiles);
    close(dirfd);
    free(buffer);

    exit(0);
}

## Ideal ls Uncached
$ time ls -u1 data >/dev/null

real    0m44.948s
user    0m1.737s
sys 0m22.000s

## Ideal ls Cached
$ time ls -u1 data >/dev/null

real    0m46.012s
user    0m1.746s
sys 0m21.805s


### dentls uncached
$ time ./dentls data >/dev/null
Total files: 1819292

real    0m1.608s
user    0m0.059s
sys 0m0.791s

## dentls cached
$ time ./dentls data >/dev/null
Total files: 1819292

real    0m0.771s
user    0m0.057s
sys 0m0.711s

#3 楼

#4 楼

#5 楼

rsync -a --delete ./emptyDirectoty/ ./hugeDirectory/

#6 楼

# setup
mkdir test && cd test && mkdir empty
# create 800000 files in a folder called x
mkdir x && cd x
seq 800000 | xargs touch
cd ..

strace -c ls -u1 x >/dev/null
% time     seconds  usecs/call     calls    errors syscall
------ ----------- ----------- --------- --------- ----------------
 94.00    7.177356           7   1000000           lstat
  5.96    0.454913        1857       245           getdents
[snip]

strace -c ./dentls x >/dev/null
% time     seconds  usecs/call     calls    errors syscall
------ ----------- ----------- --------- --------- ----------------
 99.91    0.489895       40825        12           getdents
[snip]

#7 楼

<?php 
$dir = '/directory/in/question';
$dh = opendir($dir)) { 
while (($file = readdir($dh)) !== false) { 
    unlink($dir . '/' . $file); 
} 
closedir($dh); 
?>

#8 楼

tune2fs -O ^has_journal <device>

#9 楼

mount -o remount,rw,noatime,nodiratime /mountpoint

#10 楼

find /dir_to_delete ! -iname "*.png" -type f -delete

#11 楼

#12 楼

perl -e 'for(<*>){((stat)[9]<(unlink))}'

#13 楼

#14 楼

100000

real    0m4.208s
user    0m0.270s
sys     0m3.930s 

#15 楼

#!/usr/bin/perl 
open(ANNOYINGDIR,"/path/to/your/directory");
@files = grep("/*\.png/", readdir(ANNOYINGDIR));
close(ANNOYINGDIR);

for (@files) {
    printf "Deleting %s\n",$_;
    unlink $_;
}

#!/usr/bin/perl
unlink(glob("/path/to/your/directory/*.png")) or die("Could not delete files, this happened: $!");

real    2m27.631s
user    0m1.088s
sys     0m13.229s

time perl -e 'opendir(FOO,"./"); @files = readdir(FOO); closedir(FOO); for (@files) { unlink $_; }'

real    0m59.042s
user    0m0.888s
sys     0m18.737s

#16 楼

#17 楼

#18 楼

#19 楼

#20 楼

#21 楼

for i in /u*/app/*/diag/*/*/*/trace/*.tr? ; do rm $i; echo -n . ;  done

#22 楼

ls -1|xargs -P nb_concurrent_jobs -n nb_files_by_job rm -rf

#23 楼

ls|cut -c -4|sort|uniq|awk '{ print "rm -rf "  }' | sh -x

#24 楼

ls|cut -c -4|sort|uniq|awk '{ print "echo "  ";rm -rf "  "*"}' |sh