sparsify - copy non-zero blocks of data from source to destination

sparsify.c

/*
 ***********************************************************************
 *
 *        DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
 *                    Version 2, December 2004
 *
 * Copyright (C) 2004 Sam Hocevar <[email protected]>
 *
 * Everyone is permitted to copy and distribute verbatim or modified
 * copies of this license document, and changing it is allowed as long
 * as the name is changed.
 *
 *            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
 *   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
 *
 *  0. You just DO WHAT THE FUCK YOU WANT TO.
 *
 ***********************************************************************
 *
 *	DISCLAIMER: USE AT YOUR OWN RISK. This program may bring
 *	ancient curses on you, fry your computer, kill kittens and/or
 *	cause space-time discontinuities. It worked for me. YMMV.
 *
 ***********************************************************************
*/

#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/mman.h>

#define MMAP_SIZE	64 * 1024 * 1024 // 64 MiB
#define BLOCK_SIZE	4096
#define DIE(msg)	{ perror(msg); exit(1); }

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

	if (argc != 3) {
		fprintf(stderr, "Usage: %s /path/to/source /path/to/destination\n", argv[0]);
		exit(1);
	}

	int srcfd, dstfd;
	unsigned char zeros[BLOCK_SIZE], src[BLOCK_SIZE], *dst;
	ssize_t rb;
	size_t offset = 0, mapoffset = 0;

	if ((srcfd = open(argv[1], O_RDONLY)) == -1)
		DIE("Failed to open source");
	if ((dstfd = open(argv[2], O_RDWR)) == -1)
		DIE("Failed to open destination");
	if ((dst = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, dstfd, 0)) == (void *) -1)
		DIE("Failed to mmap() destination");

	memset(zeros, 0, BLOCK_SIZE);

	while ((rb = read(srcfd, src, BLOCK_SIZE)) == BLOCK_SIZE) {
		if (memcmp(src, zeros, BLOCK_SIZE) != 0)
			memcpy(dst + mapoffset, src, BLOCK_SIZE);
		offset += rb;
		mapoffset += rb;
		if (mapoffset == MMAP_SIZE) {
			printf("%16lu bytes processed\n", offset);
			assert(munmap(dst, MMAP_SIZE) == 0);
			dst = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, dstfd, offset);
			assert(dst != (void *) -1);
			mapoffset = 0;
		}
	}

	assert(munmap(dst, MMAP_SIZE) == 0);
	assert(close(srcfd) == 0);
	assert(close(dstfd) == 0);

	if (rb == -1)
		DIE("Error reading source");

	return 0;

}