1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
|
/*-
* Copyright (c) 1990, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Mike Olson.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. All advertising materials mentioning features or use of this software
* must display the following acknowledgement:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#if defined(LIBC_SCCS) && !defined(lint)
static char sccsid[] = "@(#)bt_overflow.c 8.5 (Berkeley) 7/16/94";
#endif /* LIBC_SCCS and not lint */
#include <sys/param.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <db.h>
#include "btree.h"
/*
* Big key/data code.
*
* Big key and data entries are stored on linked lists of pages. The initial
* reference is byte string stored with the key or data and is the page number
* and size. The actual record is stored in a chain of pages linked by the
* nextpg field of the PAGE header.
*
* The first page of the chain has a special property. If the record is used
* by an internal page, it cannot be deleted and the P_PRESERVE bit will be set
* in the header.
*
* XXX
* A single DBT is written to each chain, so a lot of space on the last page
* is wasted. This is a fairly major bug for some data sets.
*/
/*
* __OVFL_GET -- Get an overflow key/data item.
*
* Parameters:
* t: tree
* p: pointer to { pgno_t, u_int32_t }
* buf: storage address
* bufsz: storage size
*
* Returns:
* RET_ERROR, RET_SUCCESS
*/
int
__ovfl_get(t, p, ssz, buf, bufsz)
BTREE *t;
void *p;
size_t *ssz;
void **buf;
size_t *bufsz;
{
PAGE *h;
pgno_t pg;
size_t nb, plen;
u_int32_t sz;
memmove(&pg, p, sizeof(pgno_t));
memmove(&sz, (char *)p + sizeof(pgno_t), sizeof(u_int32_t));
*ssz = sz;
#ifdef DEBUG
if (pg == P_INVALID || sz == 0)
abort();
#endif
/* Make the buffer bigger as necessary. */
if (*bufsz < sz) {
*buf = (char *)(*buf == NULL ? malloc(sz) : realloc(*buf, sz));
if (*buf == NULL)
return (RET_ERROR);
*bufsz = sz;
}
/*
* Step through the linked list of pages, copying the data on each one
* into the buffer. Never copy more than the data's length.
*/
plen = t->bt_psize - BTDATAOFF;
for (p = *buf;; p = (char *)p + nb, pg = h->nextpg) {
if ((h = mpool_get(t->bt_mp, pg, 0)) == NULL)
return (RET_ERROR);
nb = MIN(sz, plen);
memmove(p, (char *)h + BTDATAOFF, nb);
mpool_put(t->bt_mp, h, 0);
if ((sz -= nb) == 0)
break;
}
return (RET_SUCCESS);
}
/*
* __OVFL_PUT -- Store an overflow key/data item.
*
* Parameters:
* t: tree
* data: DBT to store
* pgno: storage page number
*
* Returns:
* RET_ERROR, RET_SUCCESS
*/
int
__ovfl_put(t, dbt, pg)
BTREE *t;
const DBT *dbt;
pgno_t *pg;
{
PAGE *h, *last;
void *p;
pgno_t npg;
size_t nb, plen;
u_int32_t sz;
/*
* Allocate pages and copy the key/data record into them. Store the
* number of the first page in the chain.
*/
plen = t->bt_psize - BTDATAOFF;
for (last = NULL, p = dbt->data, sz = dbt->size;;
p = (char *)p + plen, last = h) {
if ((h = __bt_new(t, &npg)) == NULL)
return (RET_ERROR);
h->pgno = npg;
h->nextpg = h->prevpg = P_INVALID;
h->flags = P_OVERFLOW;
h->lower = h->upper = 0;
nb = MIN(sz, plen);
memmove((char *)h + BTDATAOFF, p, nb);
if (last) {
last->nextpg = h->pgno;
mpool_put(t->bt_mp, last, MPOOL_DIRTY);
} else
*pg = h->pgno;
if ((sz -= nb) == 0) {
mpool_put(t->bt_mp, h, MPOOL_DIRTY);
break;
}
}
return (RET_SUCCESS);
}
/*
* __OVFL_DELETE -- Delete an overflow chain.
*
* Parameters:
* t: tree
* p: pointer to { pgno_t, u_int32_t }
*
* Returns:
* RET_ERROR, RET_SUCCESS
*/
int
__ovfl_delete(t, p)
BTREE *t;
void *p;
{
PAGE *h;
pgno_t pg;
size_t plen;
u_int32_t sz;
memmove(&pg, p, sizeof(pgno_t));
memmove(&sz, (char *)p + sizeof(pgno_t), sizeof(u_int32_t));
#ifdef DEBUG
if (pg == P_INVALID || sz == 0)
abort();
#endif
if ((h = mpool_get(t->bt_mp, pg, 0)) == NULL)
return (RET_ERROR);
/* Don't delete chains used by internal pages. */
if (h->flags & P_PRESERVE) {
mpool_put(t->bt_mp, h, 0);
return (RET_SUCCESS);
}
/* Step through the chain, calling the free routine for each page. */
for (plen = t->bt_psize - BTDATAOFF;; sz -= plen) {
pg = h->nextpg;
__bt_free(t, h);
if (sz <= plen)
break;
if ((h = mpool_get(t->bt_mp, pg, 0)) == NULL)
return (RET_ERROR);
}
return (RET_SUCCESS);
}
|