*/
/*
- * Copyright 2007 Sun Microsystems, Inc. All rights reserved.
- * Use is subject to license terms.
+ * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
*/
-#pragma ident "%Z%%M% %I% %E% SMI"
-
/*
- * We keep our own copy of this algorithm for 2 main reasons:
- * 1. If we didn't, anyone modifying common/os/compress.c would
+ * We keep our own copy of this algorithm for 3 main reasons:
+ * 1. If we didn't, anyone modifying common/os/compress.c would
* directly break our on disk format
- * 2. Our version of lzjb does not have a number of checks that the
+ * 2. Our version of lzjb does not have a number of checks that the
* common/os version needs and uses
+ * 3. We initialize the lempel to ensure deterministic results,
+ * so that identical blocks can always be deduplicated.
* In particular, we are adding the "feature" that compress() can
- * take a destination buffer size and return -1 if the data will not
- * compress to d_len or less.
+ * take a destination buffer size and returns the compressed length, or the
+ * source length if compression would overflow the destination buffer.
*/
-#include <sys/types.h>
+#include <sys/zfs_context.h>
#define MATCH_BITS 6
#define MATCH_MIN 3
#define MATCH_MAX ((1 << MATCH_BITS) + (MATCH_MIN - 1))
#define OFFSET_MASK ((1 << (16 - MATCH_BITS)) - 1)
-#define LEMPEL_SIZE 256
+#define LEMPEL_SIZE 1024
/*ARGSUSED*/
size_t
{
uchar_t *src = s_start;
uchar_t *dst = d_start;
- uchar_t *cpy, *copymap;
+ uchar_t *cpy, *copymap = NULL;
int copymask = 1 << (NBBY - 1);
- int mlen, offset;
+ int mlen, offset, hash;
uint16_t *hp;
- uint16_t lempel[LEMPEL_SIZE]; /* uninitialized; see above */
+ uint16_t *lempel;
+ lempel = kmem_zalloc(LEMPEL_SIZE * sizeof (uint16_t), KM_PUSHPAGE);
while (src < (uchar_t *)s_start + s_len) {
if ((copymask <<= 1) == (1 << NBBY)) {
if (dst >= (uchar_t *)d_start + d_len - 1 - 2 * NBBY) {
- if (d_len != s_len)
- return (s_len);
- mlen = s_len;
- for (src = s_start, dst = d_start; mlen; mlen--)
- *dst++ = *src++;
+ kmem_free(lempel, LEMPEL_SIZE*sizeof(uint16_t));
return (s_len);
}
copymask = 1;
*dst++ = *src++;
continue;
}
- hp = &lempel[((src[0] + 13) ^ (src[1] - 13) ^ src[2]) &
- (LEMPEL_SIZE - 1)];
+ hash = (src[0] << 16) + (src[1] << 8) + src[2];
+ hash += hash >> 9;
+ hash += hash >> 5;
+ hp = &lempel[hash & (LEMPEL_SIZE - 1)];
offset = (intptr_t)(src - *hp) & OFFSET_MASK;
*hp = (uint16_t)(uintptr_t)src;
cpy = src - offset;
*dst++ = *src++;
}
}
+
+ kmem_free(lempel, LEMPEL_SIZE * sizeof (uint16_t));
return (dst - (uchar_t *)d_start);
}
uchar_t *src = s_start;
uchar_t *dst = d_start;
uchar_t *d_end = (uchar_t *)d_start + d_len;
- uchar_t *cpy, copymap;
+ uchar_t *cpy, copymap = 0;
int copymask = 1 << (NBBY - 1);
while (dst < d_end) {