#include <stdlib.h>
#include <string.h>
+#include <zlib.h>
#include "delta.h"
+/* block size: min = 16, max = 64k, power of 2 */
+#define BLK_SIZE 16
+
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+
+#define GR_PRIME 0x9e370001
+#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
+
struct index {
const unsigned char *ptr;
+ unsigned int val;
struct index *next;
};
static struct index ** delta_index(const unsigned char *buf,
unsigned long bufsize,
+ unsigned long trg_bufsize,
unsigned int *hash_shift)
{
- unsigned long hsize;
- unsigned int hshift, i;
+ unsigned int i, hsize, hshift, hlimit, entries, *hash_count;
const unsigned char *data;
struct index *entry, **hash;
void *mem;
/* determine index hash size */
- hsize = bufsize / 4;
- for (i = 8; (1 << i) < hsize && i < 16; i++);
+ entries = bufsize / BLK_SIZE;
+ hsize = entries / 4;
+ for (i = 4; (1 << i) < hsize && i < 31; i++);
hsize = 1 << i;
- hshift = i - 8;
+ hshift = 32 - i;
*hash_shift = hshift;
/* allocate lookup index */
- mem = malloc(hsize * sizeof(*hash) + bufsize * sizeof(*entry));
+ mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
if (!mem)
return NULL;
hash = mem;
entry = mem + hsize * sizeof(*hash);
memset(hash, 0, hsize * sizeof(*hash));
- /* then populate it */
- data = buf + bufsize - 2;
- while (data > buf) {
- entry->ptr = --data;
- i = data[0] ^ data[1] ^ (data[2] << hshift);
+ /* allocate an array to count hash entries */
+ hash_count = calloc(hsize, sizeof(*hash_count));
+ if (!hash_count) {
+ free(hash);
+ return NULL;
+ }
+
+ /* then populate the index */
+ data = buf + entries * BLK_SIZE - BLK_SIZE;
+ while (data >= buf) {
+ unsigned int val = adler32(0, data, BLK_SIZE);
+ i = HASH(val, hshift);
+ entry->ptr = data;
+ entry->val = val;
entry->next = hash[i];
hash[i] = entry++;
+ hash_count[i]++;
+ data -= BLK_SIZE;
}
+ /*
+ * Determine a limit on the number of entries in the same hash
+ * bucket. This guard us against patological data sets causing
+ * really bad hash distribution with most entries in the same hash
+ * bucket that would bring us to O(m*n) computing costs (m and n
+ * corresponding to reference and target buffer sizes).
+ *
+ * The more the target buffer is large, the more it is important to
+ * have small entry lists for each hash buckets. With such a limit
+ * the cost is bounded to something more like O(m+n).
+ */
+ hlimit = (1 << 26) / trg_bufsize;
+ if (hlimit < 4*BLK_SIZE)
+ hlimit = 4*BLK_SIZE;
+
+ /*
+ * Now make sure none of the hash buckets has more entries than
+ * we're willing to test. Otherwise we cull the entry list
+ * uniformly to still preserve a good repartition across
+ * the reference buffer.
+ */
+ for (i = 0; i < hsize; i++) {
+ if (hash_count[i] < hlimit)
+ continue;
+ entry = hash[i];
+ do {
+ struct index *keep = entry;
+ int skip = hash_count[i] / hlimit / 2;
+ do {
+ entry = entry->next;
+ } while(--skip && entry);
+ keep->next = entry;
+ } while(entry);
+ }
+ free(hash_count);
+
return hash;
}
if (!from_size || !to_size)
return NULL;
- hash = delta_index(from_buf, from_size, &hash_shift);
+ hash = delta_index(from_buf, from_size, to_size, &hash_shift);
if (!hash)
return NULL;
while (data < top) {
unsigned int moff = 0, msize = 0;
- if (data + 2 < top) {
- i = data[0] ^ data[1] ^ (data[2] << hash_shift);
+ if (data + BLK_SIZE <= top) {
+ unsigned int val = adler32(0, data, BLK_SIZE);
+ i = HASH(val, hash_shift);
for (entry = hash[i]; entry; entry = entry->next) {
const unsigned char *ref = entry->ptr;
const unsigned char *src = data;
unsigned int ref_size = ref_top - ref;
+ if (entry->val != val)
+ continue;
if (ref_size > top - src)
ref_size = top - src;
if (ref_size > 0x10000)
ref_size = 0x10000;
if (ref_size <= msize)
break;
- while (ref_size && *src++ == *ref) {
+ while (ref_size-- && *src++ == *ref)
ref++;
- ref_size--;
- }
- ref_size = ref - entry->ptr;
if (msize < ref - entry->ptr) {
/* this is our best match so far */
msize = ref - entry->ptr;