git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / mirror / code / Atom feed
9365bc2b1378dc48d230f2ba3108f2b3e28235bd blob 6297 bytes (raw)

  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
229
230
 
#include "cache.h"
#include "pack-revindex.h"

/*
 * 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.
 *
 * We build a hashtable of existing packs (pack_revindex), and keep reverse
 * index here -- pack index file is sorted by object name mapping to offset;
 * this pack_revindex[].revindex array is a list of offset/index_nr pairs
 * 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.
 */

struct pack_revindex {
	struct packed_git *p;
	struct revindex_entry *revindex;
};

static struct pack_revindex *pack_revindex;
static int pack_revindex_hashsz;

static int pack_revindex_ix(struct packed_git *p)
{
	unsigned long ui = (unsigned long)p;
	int i;

	ui = ui ^ (ui >> 16); /* defeat structure alignment */
	i = (int)(ui % pack_revindex_hashsz);
	while (pack_revindex[i].p) {
		if (pack_revindex[i].p == p)
			return i;
		if (++i == pack_revindex_hashsz)
			i = 0;
	}
	return -1 - i;
}

static void init_pack_revindex(void)
{
	int num;
	struct packed_git *p;

	for (num = 0, p = packed_git; p; p = p->next)
		num++;
	if (!num)
		return;
	pack_revindex_hashsz = num * 11;
	pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
	for (p = packed_git; p; p = p->next) {
		num = pack_revindex_ix(p);
		num = - 1 - num;
		pack_revindex[num].p = p;
	}
	/* revindex elements are lazily initialized */
}

/*
 * This is a least-significant-digit radix sort.
 */
static void sort_revindex(struct revindex_entry *entries, unsigned n, off_t max)
{
	/*
	 * 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, so we sort back and forth between
	 * the real array and our tmp storage. To keep them straight, we always
	 * sort from "a" into buckets in "b".
	 */
	struct revindex_entry *tmp = xcalloc(n, sizeof(*tmp));
	struct revindex_entry *a = entries, *b = tmp;
	int bits = 0;
	unsigned *pos = xmalloc(BUCKETS * sizeof(*pos));

	while (max >> bits) {
		struct revindex_entry *swap;
		int 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(a, 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.
		 */
		for (i = n - 1; i >= 0; i--)
			b[--pos[BUCKET_FOR(a, i, bits)]] = a[i];

		/*
		 * Now "b" contains the most sorted list, so we swap "a" and
		 * "b" for the next iteration.
		 */
		swap = a;
		a = b;
		b = swap;

		/* And bump our bits for the next round. */
		bits += DIGIT_SIZE;
	}

	/*
	 * If we ended with our data in the original array, great. If not,
	 * we have to move it back from the temporary storage.
	 */
	if (a != entries)
		memcpy(entries, tmp, n * sizeof(*entries));
	free(tmp);
	free(pos);

#undef BUCKET_FOR
}

/*
 * Ordered list of offsets of objects in the pack.
 */
static void create_pack_revindex(struct pack_revindex *rix)
{
	struct packed_git *p = rix->p;
	unsigned num_ent = p->num_objects;
	unsigned i;
	const char *index = p->index_data;

	rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
	index += 4 * 256;

	if (p->index_version > 1) {
		const uint32_t *off_32 =
			(uint32_t *)(index + 8 + p->num_objects * (20 + 4));
		const uint32_t *off_64 = off_32 + p->num_objects;
		for (i = 0; i < num_ent; i++) {
			uint32_t off = ntohl(*off_32++);
			if (!(off & 0x80000000)) {
				rix->revindex[i].offset = off;
			} else {
				rix->revindex[i].offset =
					((uint64_t)ntohl(*off_64++)) << 32;
				rix->revindex[i].offset |=
					ntohl(*off_64++);
			}
			rix->revindex[i].nr = i;
		}
	} else {
		for (i = 0; i < num_ent; i++) {
			uint32_t hl = *((uint32_t *)(index + 24 * i));
			rix->revindex[i].offset = ntohl(hl);
			rix->revindex[i].nr = i;
		}
	}

	/* This knows the pack format -- the 20-byte trailer
	 * follows immediately after the last object data.
	 */
	rix->revindex[num_ent].offset = p->pack_size - 20;
	rix->revindex[num_ent].nr = -1;
	sort_revindex(rix->revindex, num_ent, p->pack_size);
}

struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs)
{
	int num;
	unsigned lo, hi;
	struct pack_revindex *rix;
	struct revindex_entry *revindex;

	if (!pack_revindex_hashsz)
		init_pack_revindex();
	num = pack_revindex_ix(p);
	if (num < 0)
		die("internal error: pack revindex fubar");

	rix = &pack_revindex[num];
	if (!rix->revindex)
		create_pack_revindex(rix);
	revindex = rix->revindex;

	lo = 0;
	hi = p->num_objects + 1;
	do {
		unsigned mi = lo + (hi - lo) / 2;
		if (revindex[mi].offset == ofs) {
			return revindex + mi;
		} else if (ofs < revindex[mi].offset)
			hi = mi;
		else
			lo = mi + 1;
	} while (lo < hi);
	error("bad offset for revindex");
	return NULL;
}

void discard_revindex(void)
{
	if (pack_revindex_hashsz) {
		int i;
		for (i = 0; i < pack_revindex_hashsz; i++)
			free(pack_revindex[i].revindex);
		free(pack_revindex);
		pack_revindex_hashsz = 0;
	}
}
debug log:

solving 9365bc2 ...
found 9365bc2 in https://public-inbox.org/git/20130710115557.GJ21963@sigill.intra.peff.net/
found 1aa9754 in git.git.git
preparing index
index prepared:
100644 1aa9754384a0463894370ebcabb81ff94774fe0a	pack-revindex.c

applying [1/1] https://public-inbox.org/git/20130710115557.GJ21963@sigill.intra.peff.net/
diff --git a/pack-revindex.c b/pack-revindex.c
index 1aa9754..9365bc2 100644

Checking patch pack-revindex.c...
Applied patch pack-revindex.c cleanly.

index at:
100644 9365bc2b1378dc48d230f2ba3108f2b3e28235bd	pack-revindex.c

Code repositories for project(s) associated with this inbox:

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).