diff --git a/fast-import.c b/fast-import.c
index c29737ef94bd17de7b70064c75191d9b6894b174..74f08bd554ae4cab1dc9ee38272376e5cbec1200 100644 (file)
--- a/fast-import.c
+++ b/fast-import.c
struct last_object
{
struct strbuf data;
- uint32_t offset;
+ off_t offset;
unsigned int depth;
unsigned no_swap : 1;
};
/* Configured limits on output */
static unsigned long max_depth = 10;
-static off_t max_packsize = (1LL << 32) - 1;
+static off_t max_packsize;
static uintmax_t big_file_threshold = 512 * 1024 * 1024;
static int force_update;
static int pack_compression_level = Z_DEFAULT_COMPRESSION;
/* The .pack file being generated */
static unsigned int pack_id;
+static struct sha1file *pack_file;
static struct packed_git *pack_data;
static struct packed_git **all_packs;
-static unsigned long pack_size;
+static off_t pack_size;
/* Table of objects we've written. */
static unsigned int object_entry_alloc = 5000;
p = xcalloc(1, sizeof(*p) + strlen(tmpfile) + 2);
strcpy(p->pack_name, tmpfile);
p->pack_fd = pack_fd;
+ pack_file = sha1fd(pack_fd, p->pack_name);
hdr.hdr_signature = htonl(PACK_SIGNATURE);
hdr.hdr_version = htonl(2);
hdr.hdr_entries = 0;
- write_or_die(p->pack_fd, &hdr, sizeof(hdr));
+ sha1write(pack_file, &hdr, sizeof(hdr));
pack_data = p;
pack_size = sizeof(hdr);
all_packs[pack_id] = p;
}
-static int oecmp (const void *a_, const void *b_)
-{
- struct object_entry *a = *((struct object_entry**)a_);
- struct object_entry *b = *((struct object_entry**)b_);
- return hashcmp(a->idx.sha1, b->idx.sha1);
-}
-
-static char *create_index(void)
+static const char *create_index(void)
{
- static char tmpfile[PATH_MAX];
- git_SHA_CTX ctx;
- struct sha1file *f;
- struct object_entry **idx, **c, **last, *e;
+ const char *tmpfile;
+ struct pack_idx_entry **idx, **c, **last;
+ struct object_entry *e;
struct object_entry_pool *o;
- uint32_t array[256];
- int i, idx_fd;
- /* Build the sorted table of object IDs. */
- idx = xmalloc(object_count * sizeof(struct object_entry*));
+ /* Build the table of object IDs. */
+ idx = xmalloc(object_count * sizeof(*idx));
c = idx;
for (o = blocks; o; o = o->next_pool)
for (e = o->next_free; e-- != o->entries;)
if (pack_id == e->pack_id)
- *c++ = e;
+ *c++ = &e->idx;
last = idx + object_count;
if (c != last)
die("internal consistency error creating the index");
- qsort(idx, object_count, sizeof(struct object_entry*), oecmp);
- /* Generate the fan-out array. */
- c = idx;
- for (i = 0; i < 256; i++) {
- struct object_entry **next = c;
- while (next < last) {
- if ((*next)->idx.sha1[0] != i)
- break;
- next++;
- }
- array[i] = htonl(next - idx);
- c = next;
- }
-
- idx_fd = odb_mkstemp(tmpfile, sizeof(tmpfile),
- "pack/tmp_idx_XXXXXX");
- f = sha1fd(idx_fd, tmpfile);
- sha1write(f, array, 256 * sizeof(int));
- git_SHA1_Init(&ctx);
- for (c = idx; c != last; c++) {
- uint32_t offset = htonl((*c)->idx.offset);
- sha1write(f, &offset, 4);
- sha1write(f, (*c)->idx.sha1, sizeof((*c)->idx.sha1));
- git_SHA1_Update(&ctx, (*c)->idx.sha1, 20);
- }
- sha1write(f, pack_data->sha1, sizeof(pack_data->sha1));
- sha1close(f, NULL, CSUM_FSYNC);
+ tmpfile = write_idx_file(NULL, idx, object_count, pack_data->sha1);
free(idx);
- git_SHA1_Final(pack_data->sha1, &ctx);
return tmpfile;
}
-static char *keep_pack(char *curr_index_name)
+static char *keep_pack(const char *curr_index_name)
{
static char name[PATH_MAX];
static const char *keep_msg = "fast-import";
get_object_directory(), sha1_to_hex(pack_data->sha1));
if (move_temp_to_file(curr_index_name, name))
die("cannot store index file");
+ free((void *)curr_index_name);
return name;
}
clear_delta_base_cache();
if (object_count) {
+ unsigned char cur_pack_sha1[20];
char *idx_name;
int i;
struct branch *b;
struct tag *t;
close_pack_windows(pack_data);
+ sha1close(pack_file, cur_pack_sha1, 0);
fixup_pack_header_footer(pack_data->pack_fd, pack_data->sha1,
pack_data->pack_name, object_count,
- NULL, 0);
+ cur_pack_sha1, pack_size);
close(pack_data->pack_fd);
idx_name = keep_pack(create_index());
return 1;
}
- if (last && last->data.buf && last->depth < max_depth) {
+ if (last && last->data.buf && last->depth < max_depth && dat->len > 20) {
delta = diff_delta(last->data.buf, last->data.len,
dat->buf, dat->len,
- &deltalen, 0);
- if (delta && deltalen >= dat->len) {
- free(delta);
- delta = NULL;
- }
+ &deltalen, dat->len - 20);
} else
delta = NULL;
deflateEnd(&s);
/* Determine if we should auto-checkpoint. */
- if ((pack_size + 60 + s.total_out) > max_packsize
+ if ((max_packsize && (pack_size + 60 + s.total_out) > max_packsize)
|| (pack_size + 60 + s.total_out) < pack_size) {
/* This new object needs to *not* have the current pack_id. */
object_count++;
object_count_by_type[type]++;
+ crc32_begin(pack_file);
+
if (delta) {
- unsigned long ofs = e->idx.offset - last->offset;
+ off_t ofs = e->idx.offset - last->offset;
unsigned pos = sizeof(hdr) - 1;
delta_count_by_type[type]++;
e->depth = last->depth + 1;
hdrlen = encode_header(OBJ_OFS_DELTA, deltalen, hdr);
- write_or_die(pack_data->pack_fd, hdr, hdrlen);
+ sha1write(pack_file, hdr, hdrlen);
pack_size += hdrlen;
hdr[pos] = ofs & 127;
while (ofs >>= 7)
hdr[--pos] = 128 | (--ofs & 127);
- write_or_die(pack_data->pack_fd, hdr + pos, sizeof(hdr) - pos);
+ sha1write(pack_file, hdr + pos, sizeof(hdr) - pos);
pack_size += sizeof(hdr) - pos;
} else {
e->depth = 0;
hdrlen = encode_header(type, dat->len, hdr);
- write_or_die(pack_data->pack_fd, hdr, hdrlen);
+ sha1write(pack_file, hdr, hdrlen);
pack_size += hdrlen;
}
- write_or_die(pack_data->pack_fd, out, s.total_out);
+ sha1write(pack_file, out, s.total_out);
pack_size += s.total_out;
+ e->idx.crc32 = crc32_end(pack_file);
+
free(out);
free(delta);
if (last) {
return 0;
}
-static void truncate_pack(off_t to)
+static void truncate_pack(off_t to, git_SHA_CTX *ctx)
{
if (ftruncate(pack_data->pack_fd, to)
|| lseek(pack_data->pack_fd, to, SEEK_SET) != to)
die_errno("cannot truncate pack to skip duplicate");
pack_size = to;
+
+ /* yes this is a layering violation */
+ pack_file->total = to;
+ pack_file->offset = 0;
+ pack_file->ctx = *ctx;
}
static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
@@ -1188,16 +1161,21 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
unsigned long hdrlen;
off_t offset;
git_SHA_CTX c;
+ git_SHA_CTX pack_file_ctx;
z_stream s;
int status = Z_OK;
/* Determine if we should auto-checkpoint. */
- if ((pack_size + 60 + len) > max_packsize
+ if ((max_packsize && (pack_size + 60 + len) > max_packsize)
|| (pack_size + 60 + len) < pack_size)
cycle_packfile();
offset = pack_size;
+ /* preserve the pack_file SHA1 ctx in case we have to truncate later */
+ sha1flush(pack_file);
+ pack_file_ctx = pack_file->ctx;
+
hdrlen = snprintf((char *)out_buf, out_sz, "blob %" PRIuMAX, len) + 1;
if (out_sz <= hdrlen)
die("impossibly large object header");
@@ -1205,6 +1183,8 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
git_SHA1_Init(&c);
git_SHA1_Update(&c, out_buf, hdrlen);
+ crc32_begin(pack_file);
+
memset(&s, 0, sizeof(s));
deflateInit(&s, pack_compression_level);
@@ -1232,7 +1212,7 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
if (!s.avail_out || status == Z_STREAM_END) {
size_t n = s.next_out - out_buf;
- write_or_die(pack_data->pack_fd, out_buf, n);
+ sha1write(pack_file, out_buf, n);
pack_size += n;
s.next_out = out_buf;
s.avail_out = out_sz;
@@ -1260,20 +1240,21 @@ static void stream_blob(uintmax_t len, unsigned char *sha1out, uintmax_t mark)
if (e->idx.offset) {
duplicate_count_by_type[OBJ_BLOB]++;
- truncate_pack(offset);
+ truncate_pack(offset, &pack_file_ctx);
} else if (find_sha1_pack(sha1, packed_git)) {
e->type = OBJ_BLOB;
e->pack_id = MAX_PACK_ID;
e->idx.offset = 1; /* just not zero! */
duplicate_count_by_type[OBJ_BLOB]++;
- truncate_pack(offset);
+ truncate_pack(offset, &pack_file_ctx);
} else {
e->depth = 0;
e->type = OBJ_BLOB;
e->pack_id = pack_id;
e->idx.offset = offset;
+ e->idx.crc32 = crc32_end(pack_file);
object_count++;
object_count_by_type[OBJ_BLOB]++;
}
* the newly written data.
*/
close_pack_windows(p);
+ sha1flush(pack_file);
/* We have to offer 20 bytes additional on the end of
* the packfile as the core unpacker code assumes the
pack_compression_seen = 1;
return 0;
}
+ if (!strcmp(k, "pack.indexversion")) {
+ pack_idx_default_version = git_config_int(k, v);
+ if (pack_idx_default_version > 2)
+ die("bad pack.indexversion=%"PRIu32,
+ pack_idx_default_version);
+ return 0;
+ }
+ if (!strcmp(k, "pack.packsizelimit")) {
+ max_packsize = git_config_ulong(k, v);
+ return 0;
+ }
if (!strcmp(k, "core.bigfilethreshold")) {
long n = git_config_int(k, v);
big_file_threshold = 0 < n ? n : 0;