pack-revindex.c 5.76 KB
Newer Older
1 2
#include "cache.h"
#include "pack-revindex.h"
3
#include "object-store.h"
4
#include "packfile.h"
5 6 7 8 9 10 11 12

/*
 * Pack index for existing packs give us easy access to the offsets into
 * corresponding pack file where each object's data starts, but the entries
 * do not store the size of the compressed representation (uncompressed
 * size is easily available by examining the pack entry header).  It is
 * also rather expensive to find the sha1 for an object given its offset.
 *
13 14
 * The pack index file is sorted by object name mapping to offset;
 * this revindex array is a list of offset/index_nr pairs
15 16 17 18 19
 * ordered by offset, so if you know the offset of an object, next offset
 * is where its packed representation ends and the index_nr can be used to
 * get the object sha1 from the main index.
 */

20 21 22 23 24 25 26 27
/*
 * This is a least-significant-digit radix sort.
 *
 * It sorts each of the "n" items in "entries" by its offset field. The "max"
 * parameter must be at least as large as the largest offset in the array,
 * and lets us quit the sort early.
 */
static void sort_revindex(struct revindex_entry *entries, unsigned n, off_t max)
28
{
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48
	/*
	 * We use a "digit" size of 16 bits. That keeps our memory
	 * usage reasonable, and we can generally (for a 4G or smaller
	 * packfile) quit after two rounds of radix-sorting.
	 */
#define DIGIT_SIZE (16)
#define BUCKETS (1 << DIGIT_SIZE)
	/*
	 * We want to know the bucket that a[i] will go into when we are using
	 * the digit that is N bits from the (least significant) end.
	 */
#define BUCKET_FOR(a, i, bits) (((a)[(i)].offset >> (bits)) & (BUCKETS-1))

	/*
	 * We need O(n) temporary storage. Rather than do an extra copy of the
	 * partial results into "entries", we sort back and forth between the
	 * real array and temporary storage. In each iteration of the loop, we
	 * keep track of them with alias pointers, always sorting from "from"
	 * to "to".
	 */
49
	struct revindex_entry *tmp, *from, *to;
50
	int bits;
51 52 53 54 55 56
	unsigned *pos;

	ALLOC_ARRAY(pos, BUCKETS);
	ALLOC_ARRAY(tmp, n);
	from = entries;
	to = tmp;
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

	/*
	 * If (max >> bits) is zero, then we know that the radix digit we are
	 * on (and any higher) will be zero for all entries, and our loop will
	 * be a no-op, as everybody lands in the same zero-th bucket.
	 */
	for (bits = 0; max >> bits; bits += DIGIT_SIZE) {
		unsigned i;

		memset(pos, 0, BUCKETS * sizeof(*pos));

		/*
		 * We want pos[i] to store the index of the last element that
		 * will go in bucket "i" (actually one past the last element).
		 * To do this, we first count the items that will go in each
		 * bucket, which gives us a relative offset from the last
		 * bucket. We can then cumulatively add the index from the
		 * previous bucket to get the true index.
		 */
		for (i = 0; i < n; i++)
			pos[BUCKET_FOR(from, i, bits)]++;
		for (i = 1; i < BUCKETS; i++)
			pos[i] += pos[i-1];

		/*
		 * Now we can drop the elements into their correct buckets (in
		 * our temporary array).  We iterate the pos counter backwards
		 * to avoid using an extra index to count up. And since we are
		 * going backwards there, we must also go backwards through the
		 * array itself, to keep the sort stable.
		 *
		 * Note that we use an unsigned iterator to make sure we can
		 * handle 2^32-1 objects, even on a 32-bit system. But this
		 * means we cannot use the more obvious "i >= 0" loop condition
		 * for counting backwards, and must instead check for
		 * wrap-around with UINT_MAX.
		 */
		for (i = n - 1; i != UINT_MAX; i--)
			to[--pos[BUCKET_FOR(from, i, bits)]] = from[i];

		/*
		 * Now "to" contains the most sorted list, so we swap "from" and
		 * "to" for the next iteration.
		 */
René Scharfe's avatar
René Scharfe committed
101
		SWAP(from, to);
102 103 104 105 106 107 108
	}

	/*
	 * If we ended with our data in the original array, great. If not,
	 * we have to move it back from the temporary storage.
	 */
	if (from != entries)
René Scharfe's avatar
René Scharfe committed
109
		COPY_ARRAY(entries, tmp, n);
110 111 112 113 114 115
	free(tmp);
	free(pos);

#undef BUCKET_FOR
#undef BUCKETS
#undef DIGIT_SIZE
116 117 118 119 120
}

/*
 * Ordered list of offsets of objects in the pack.
 */
121
static void create_pack_revindex(struct packed_git *p)
122
{
123
	const unsigned num_ent = p->num_objects;
124
	unsigned i;
125
	const char *index = p->index_data;
126
	const unsigned hashsz = the_hash_algo->rawsz;
127

128
	ALLOC_ARRAY(p->revindex, num_ent + 1);
129 130 131 132
	index += 4 * 256;

	if (p->index_version > 1) {
		const uint32_t *off_32 =
133
			(uint32_t *)(index + 8 + p->num_objects * (hashsz + 4));
134 135
		const uint32_t *off_64 = off_32 + p->num_objects;
		for (i = 0; i < num_ent; i++) {
136
			const uint32_t off = ntohl(*off_32++);
137
			if (!(off & 0x80000000)) {
138
				p->revindex[i].offset = off;
139
			} else {
140 141
				p->revindex[i].offset = get_be64(off_64);
				off_64 += 2;
142
			}
143
			p->revindex[i].nr = i;
144 145 146
		}
	} else {
		for (i = 0; i < num_ent; i++) {
147
			const uint32_t hl = *((uint32_t *)(index + (hashsz + 4) * i));
148 149
			p->revindex[i].offset = ntohl(hl);
			p->revindex[i].nr = i;
150 151 152
		}
	}

153 154
	/*
	 * This knows the pack format -- the hash trailer
155 156
	 * follows immediately after the last object data.
	 */
157
	p->revindex[num_ent].offset = p->pack_size - hashsz;
158 159
	p->revindex[num_ent].nr = -1;
	sort_revindex(p->revindex, num_ent, p->pack_size);
160 161
}

162
int load_pack_revindex(struct packed_git *p)
163
{
164 165 166
	if (!p->revindex) {
		if (open_pack_index(p))
			return -1;
167
		create_pack_revindex(p);
168 169
	}
	return 0;
Vicent Marti's avatar
Vicent Marti committed
170 171
}

172
int find_revindex_position(struct packed_git *p, off_t ofs)
Vicent Marti's avatar
Vicent Marti committed
173 174
{
	int lo = 0;
175
	int hi = p->num_objects + 1;
176
	const struct revindex_entry *revindex = p->revindex;
Vicent Marti's avatar
Vicent Marti committed
177

178
	do {
179
		const unsigned mi = lo + (hi - lo) / 2;
180
		if (revindex[mi].offset == ofs) {
Vicent Marti's avatar
Vicent Marti committed
181
			return mi;
182 183 184 185 186
		} else if (ofs < revindex[mi].offset)
			hi = mi;
		else
			lo = mi + 1;
	} while (lo < hi);
Vicent Marti's avatar
Vicent Marti committed
187

188
	error("bad offset for revindex");
Vicent Marti's avatar
Vicent Marti committed
189 190 191 192 193
	return -1;
}

struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs)
{
194 195
	int pos;

196 197 198
	if (load_pack_revindex(p))
		return NULL;

199
	pos = find_revindex_position(p, ofs);
Vicent Marti's avatar
Vicent Marti committed
200 201 202 203

	if (pos < 0)
		return NULL;

204
	return p->revindex + pos;
205
}