X-Git-Url: https://git.octo.it/?a=blobdiff_plain;f=diff-delta.c;h=fdedf94ccec935732a5234708557f7810b5b8bfd;hb=08abe669c05521499149dbf84fedefb04a8fa34d;hp=2ed5984b1c360194d53fd287962d7857e19a097c;hpb=41094b8eeb8f44a3dadafa2fe00b4efac5b397c4;p=git.git

diff --git a/diff-delta.c b/diff-delta.c
index 2ed5984b..fdedf94c 100644
--- a/diff-delta.c
+++ b/diff-delta.c
@@ -27,57 +27,113 @@
 /* block size: min = 16, max = 64k, power of 2 */
 #define BLK_SIZE 16
 
-#define MIN(a, b) ((a) < (b) ? (a) : (b))
+/* maximum hash entry list for the same hash bucket */
+#define HASH_LIMIT 64
 
 #define GR_PRIME 0x9e370001
 #define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
 
-struct index {
+struct index_entry {
 	const unsigned char *ptr;
 	unsigned int val;
-	struct index *next;
+	struct index_entry *next;
 };
 
-static struct index ** delta_index(const unsigned char *buf,
-				   unsigned long bufsize,
-				   unsigned int *hash_shift)
+struct delta_index {
+	const void *src_buf;
+	unsigned long src_size;
+	unsigned int hash_shift;
+	struct index_entry *hash[0];
+};
+
+struct delta_index * create_delta_index(const void *buf, unsigned long bufsize)
 {
-	unsigned int hsize, hshift, entries, blksize, i;
-	const unsigned char *data;
-	struct index *entry, **hash;
+	unsigned int i, hsize, hshift, entries, *hash_count;
+	const unsigned char *data, *buffer = buf;
+	struct delta_index *index;
+	struct index_entry *entry, **hash;
 	void *mem;
 
+	if (!buf || !bufsize)
+		return NULL;
+
 	/* determine index hash size */
-	entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE;
+	entries = bufsize  / BLK_SIZE;
 	hsize = entries / 4;
-	for (i = 4; (1 << i) < hsize && i < 16; i++);
+	for (i = 4; (1 << i) < hsize && i < 31; i++);
 	hsize = 1 << i;
 	hshift = 32 - i;
-	*hash_shift = hshift;
 
 	/* allocate lookup index */
-	mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+	mem = malloc(sizeof(*index) +
+		     sizeof(*hash) * hsize +
+		     sizeof(*entry) * entries);
 	if (!mem)
 		return NULL;
+	index = mem;
+	mem = index + 1;
 	hash = mem;
-	entry = mem + hsize * sizeof(*hash);
+	mem = hash + hsize;
+	entry = mem;
+
+	index->src_buf = buf;
+	index->src_size = bufsize;
+	index->hash_shift = hshift;
 	memset(hash, 0, hsize * sizeof(*hash));
 
-	/* then populate it */
-	data = buf + entries * BLK_SIZE - BLK_SIZE;
-	blksize = bufsize - (data - buf);
-	while (data >= buf) {
-		unsigned int val = adler32(0, data, blksize);
+	/* allocate an array to count hash entries */
+	hash_count = calloc(hsize, sizeof(*hash_count));
+	if (!hash_count) {
+		free(index);
+		return NULL;
+	}
+
+	/* then populate the index */
+	data = buffer + entries * BLK_SIZE - BLK_SIZE;
+	while (data >= buffer) {
+		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++;
-		blksize = BLK_SIZE;
+		hash_count[i]++;
 		data -= BLK_SIZE;
  	}
 
-	return hash;
+	/*
+	 * 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).
+	 *
+	 * 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] < HASH_LIMIT)
+			continue;
+		entry = hash[i];
+		do {
+			struct index_entry *keep = entry;
+			int skip = hash_count[i] / HASH_LIMIT / 2;
+			do {
+				entry = entry->next;
+			} while(--skip && entry);
+			keep->next = entry;
+		} while(entry);
+	}
+	free(hash_count);
+
+	return index;
+}
+
+void free_delta_index(struct delta_index *index)
+{
+	free(index);
 }
 
 /* provide the size of the copy opcode given the block offset and size */
@@ -88,20 +144,17 @@ static struct index ** delta_index(const unsigned char *buf,
 /* the maximum size for any opcode */
 #define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff)
 
-void *diff_delta(void *from_buf, unsigned long from_size,
-		 void *to_buf, unsigned long to_size,
-		 unsigned long *delta_size,
-		 unsigned long max_size)
+void *
+create_delta(const struct delta_index *index,
+	     const void *trg_buf, unsigned long trg_size,
+	     unsigned long *delta_size, unsigned long max_size)
 {
-	unsigned int i, outpos, outsize, inscnt, hash_shift;
+	unsigned int i, outpos, outsize, hash_shift;
+	int inscnt;
 	const unsigned char *ref_data, *ref_top, *data, *top;
 	unsigned char *out;
-	struct index *entry, **hash;
 
-	if (!from_size || !to_size)
-		return NULL;
-	hash = delta_index(from_buf, from_size, &hash_shift);
-	if (!hash)
+	if (!trg_buf || !trg_size)
 		return NULL;
 
 	outpos = 0;
@@ -109,42 +162,38 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 	if (max_size && outsize >= max_size)
 		outsize = max_size + MAX_OP_SIZE + 1;
 	out = malloc(outsize);
-	if (!out) {
-		free(hash);
+	if (!out)
 		return NULL;
-	}
-
-	ref_data = from_buf;
-	ref_top = from_buf + from_size;
-	data = to_buf;
-	top = to_buf + to_size;
 
 	/* store reference buffer size */
-	out[outpos++] = from_size;
-	from_size >>= 7;
-	while (from_size) {
-		out[outpos - 1] |= 0x80;
-		out[outpos++] = from_size;
-		from_size >>= 7;
+	i = index->src_size;
+	while (i >= 0x80) {
+		out[outpos++] = i | 0x80;
+		i >>= 7;
 	}
+	out[outpos++] = i;
 
 	/* store target buffer size */
-	out[outpos++] = to_size;
-	to_size >>= 7;
-	while (to_size) {
-		out[outpos - 1] |= 0x80;
-		out[outpos++] = to_size;
-		to_size >>= 7;
+	i = trg_size;
+	while (i >= 0x80) {
+		out[outpos++] = i | 0x80;
+		i >>= 7;
 	}
+	out[outpos++] = i;
 
+	ref_data = index->src_buf;
+	ref_top = ref_data + index->src_size;
+	data = trg_buf;
+	top = trg_buf + trg_size;
+	hash_shift = index->hash_shift;
 	inscnt = 0;
 
 	while (data < top) {
 		unsigned int moff = 0, msize = 0;
-		unsigned int blksize = MIN(top - data, BLK_SIZE);
-		unsigned int val = adler32(0, data, blksize);
+		struct index_entry *entry;
+		unsigned int val = adler32(0, data, BLK_SIZE);
 		i = HASH(val, hash_shift);
-		for (entry = hash[i]; entry; entry = entry->next) {
+		for (entry = index->hash[i]; entry; entry = entry->next) {
 			const unsigned char *ref = entry->ptr;
 			const unsigned char *src = data;
 			unsigned int ref_size = ref_top - ref;
@@ -152,19 +201,16 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 				continue;
 			if (ref_size > top - src)
 				ref_size = top - src;
-			while (ref_size && *src++ == *ref) {
+			if (ref_size > 0x10000)
+				ref_size = 0x10000;
+			if (ref_size <= msize)
+				break;
+			while (ref_size-- && *src++ == *ref)
 				ref++;
-				ref_size--;
-			}
-			ref_size = ref - entry->ptr;
-			if (ref_size > msize) {
+			if (msize < ref - entry->ptr) {
 				/* this is our best match so far */
+				msize = ref - entry->ptr;
 				moff = entry->ptr - ref_data;
-				msize = ref_size;
-				if (msize >= 0x10000) {
-					msize = 0x10000;
-					break;
-				}
 			}
 		}
 
@@ -181,6 +227,20 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 			unsigned char *op;
 
 			if (inscnt) {
+				while (moff && ref_data[moff-1] == data[-1]) {
+					if (msize == 0x10000)
+						break;
+					/* we can match one byte back */
+					msize++;
+					moff--;
+					data--;
+					outpos--;
+					if (--inscnt)
+						continue;
+					outpos--;  /* remove count slot */
+					inscnt--;  /* make it -1 */
+					break;
+				}
 				out[outpos - inscnt - 1] = inscnt;
 				inscnt = 0;
 			}
@@ -215,7 +275,6 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 				out = realloc(out, outsize);
 			if (!out) {
 				free(tmp);
-				free(hash);
 				return NULL;
 			}
 		}
@@ -224,7 +283,6 @@ void *diff_delta(void *from_buf, unsigned long from_size,
 	if (inscnt)
 		out[outpos - inscnt - 1] = inscnt;
 
-	free(hash);
 	*delta_size = outpos;
 	return out;
 }