![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/fast-import.c b/fast-import.c
index 901784fe911567752c872e5433f0295768654b5a..74f08bd554ae4cab1dc9ee38272376e5cbec1200 100644 (file)
--- a/fast-import.c
+++ b/fast-import.c
struct object_entry
{
+ struct pack_idx_entry idx;
struct object_entry *next;
- uint32_t offset;
uint32_t type : TYPE_BITS,
pack_id : PACK_ID_BITS,
depth : DEPTH_BITS;
- unsigned char sha1[20];
};
struct object_entry_pool
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;
static int pack_compression_seen;
/* 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;
alloc_objects(object_entry_alloc);
e = blocks->next_free++;
- hashcpy(e->sha1, sha1);
+ hashcpy(e->idx.sha1, sha1);
return e;
}
unsigned int h = sha1[0] << 8 | sha1[1];
struct object_entry *e;
for (e = object_table[h]; e; e = e->next)
- if (!hashcmp(sha1, e->sha1))
+ if (!hashcmp(sha1, e->idx.sha1))
return e;
return NULL;
}
struct object_entry *p = NULL;
while (e) {
- if (!hashcmp(sha1, e->sha1))
+ if (!hashcmp(sha1, e->idx.sha1))
return e;
p = e;
e = e->next;
e = new_object(sha1);
e->next = NULL;
- e->offset = 0;
+ e->idx.offset = 0;
if (p)
p->next = e;
else
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->sha1, b->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)->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)->offset);
- sha1write(f, &offset, 4);
- sha1write(f, (*c)->sha1, sizeof((*c)->sha1));
- git_SHA1_Update(&ctx, (*c)->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());
static size_t encode_header(
enum object_type type,
- size_t size,
+ uintmax_t size,
unsigned char *hdr)
{
int n = 1;
e = insert_object(sha1);
if (mark)
insert_mark(mark, e);
- if (e->offset) {
+ if (e->idx.offset) {
duplicate_count_by_type[type]++;
return 1;
} else if (find_sha1_pack(sha1, packed_git)) {
e->type = type;
e->pack_id = MAX_PACK_ID;
- e->offset = 1; /* just not zero! */
+ e->idx.offset = 1; /* just not zero! */
duplicate_count_by_type[type]++;
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. */
e->type = type;
e->pack_id = pack_id;
- e->offset = pack_size;
+ e->idx.offset = pack_size;
object_count++;
object_count_by_type[type]++;
+ crc32_begin(pack_file);
+
if (delta) {
- unsigned long ofs = e->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) {
} else {
strbuf_swap(&last->data, dat);
}
- last->offset = e->offset;
+ last->offset = e->idx.offset;
last->depth = e->depth;
}
return 0;
}
+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)
+{
+ size_t in_sz = 64 * 1024, out_sz = 64 * 1024;
+ unsigned char *in_buf = xmalloc(in_sz);
+ unsigned char *out_buf = xmalloc(out_sz);
+ struct object_entry *e;
+ unsigned char sha1[20];
+ 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 ((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");
+
+ 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);
+
+ hdrlen = encode_header(OBJ_BLOB, len, out_buf);
+ if (out_sz <= hdrlen)
+ die("impossibly large object header");
+
+ s.next_out = out_buf + hdrlen;
+ s.avail_out = out_sz - hdrlen;
+
+ while (status != Z_STREAM_END) {
+ if (0 < len && !s.avail_in) {
+ size_t cnt = in_sz < len ? in_sz : (size_t)len;
+ size_t n = fread(in_buf, 1, cnt, stdin);
+ if (!n && feof(stdin))
+ die("EOF in data (%" PRIuMAX " bytes remaining)", len);
+
+ git_SHA1_Update(&c, in_buf, n);
+ s.next_in = in_buf;
+ s.avail_in = n;
+ len -= n;
+ }
+
+ status = deflate(&s, len ? 0 : Z_FINISH);
+
+ if (!s.avail_out || status == Z_STREAM_END) {
+ size_t n = s.next_out - out_buf;
+ sha1write(pack_file, out_buf, n);
+ pack_size += n;
+ s.next_out = out_buf;
+ s.avail_out = out_sz;
+ }
+
+ switch (status) {
+ case Z_OK:
+ case Z_BUF_ERROR:
+ case Z_STREAM_END:
+ continue;
+ default:
+ die("unexpected deflate failure: %d", status);
+ }
+ }
+ deflateEnd(&s);
+ git_SHA1_Final(sha1, &c);
+
+ if (sha1out)
+ hashcpy(sha1out, sha1);
+
+ e = insert_object(sha1);
+
+ if (mark)
+ insert_mark(mark, e);
+
+ if (e->idx.offset) {
+ duplicate_count_by_type[OBJ_BLOB]++;
+ 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, &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]++;
+ }
+
+ free(in_buf);
+ free(out_buf);
+}
+
/* All calls must be guarded by find_object() or find_mark() to
* ensure the 'struct object_entry' passed was written by this
* process instance. We unpack the entry by the offset, avoiding
* 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
*/
p->pack_size = pack_size + 20;
}
- return unpack_entry(p, oe->offset, &type, sizep);
+ return unpack_entry(p, oe->idx.offset, &type, sizep);
}
static const char *get_mode(const char *str, uint16_t *modep)
if (S_ISDIR(root->versions[0].mode) && le && le->pack_id == pack_id) {
mktree(t, 0, &old_tree);
lo.data = old_tree;
- lo.offset = le->offset;
+ lo.offset = le->idx.offset;
lo.depth = t->delta_depth;
}
for (k = 0; k < 1024; k++) {
if (m->data.marked[k])
fprintf(f, ":%" PRIuMAX " %s\n", base + k,
- sha1_to_hex(m->data.marked[k]->sha1));
+ sha1_to_hex(m->data.marked[k]->idx.sha1));
}
}
}
e = insert_object(sha1);
e->type = type;
e->pack_id = MAX_PACK_ID;
- e->offset = 1; /* just not zero! */
+ e->idx.offset = 1; /* just not zero! */
}
insert_mark(mark, e);
}
next_mark = 0;
}
-static void parse_data(struct strbuf *sb)
+static int parse_data(struct strbuf *sb, uintmax_t limit, uintmax_t *len_res)
{
strbuf_reset(sb);
free(term);
}
else {
- size_t n = 0, length;
+ uintmax_t len = strtoumax(command_buf.buf + 5, NULL, 10);
+ size_t n = 0, length = (size_t)len;
- length = strtoul(command_buf.buf + 5, NULL, 10);
+ if (limit && limit < len) {
+ *len_res = len;
+ return 0;
+ }
+ if (length < len)
+ die("data is too large to use in this context");
while (n < length) {
size_t s = strbuf_fread(sb, length - n, stdin);
}
skip_optional_lf();
+ return 1;
}
static int validate_raw_date(const char *src, char *result, int maxlen)
return ident;
}
-static void parse_new_blob(void)
+static void parse_and_store_blob(
+ struct last_object *last,
+ unsigned char *sha1out,
+ uintmax_t mark)
{
static struct strbuf buf = STRBUF_INIT;
+ uintmax_t len;
+
+ if (parse_data(&buf, big_file_threshold, &len))
+ store_object(OBJ_BLOB, &buf, last, sha1out, mark);
+ else {
+ if (last) {
+ strbuf_release(&last->data);
+ last->offset = 0;
+ last->depth = 0;
+ }
+ stream_blob(len, sha1out, mark);
+ skip_optional_lf();
+ }
+}
+static void parse_new_blob(void)
+{
read_next_command();
parse_mark();
- parse_data(&buf);
- store_object(OBJ_BLOB, &buf, &last_blob, NULL, next_mark);
+ parse_and_store_blob(&last_blob, NULL, next_mark);
}
static void unload_one_branch(void)
if (*p == ':') {
char *x;
oe = find_mark(strtoumax(p + 1, &x, 10));
- hashcpy(sha1, oe->sha1);
+ hashcpy(sha1, oe->idx.sha1);
p = x;
} else if (!prefixcmp(p, "inline")) {
inline_data = 1;
* another repository.
*/
} else if (inline_data) {
- static struct strbuf buf = STRBUF_INIT;
-
if (p != uq.buf) {
strbuf_addstr(&uq, p);
p = uq.buf;
}
read_next_command();
- parse_data(&buf);
- store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0);
+ parse_and_store_blob(&last_blob, sha1, 0);
} else if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
if (*p == ':') {
char *x;
oe = find_mark(strtoumax(p + 1, &x, 10));
- hashcpy(sha1, oe->sha1);
+ hashcpy(sha1, oe->idx.sha1);
p = x;
} else if (!prefixcmp(p, "inline")) {
inline_data = 1;
struct object_entry *commit_oe = find_mark(commit_mark);
if (commit_oe->type != OBJ_COMMIT)
die("Mark :%" PRIuMAX " not a commit", commit_mark);
- hashcpy(commit_sha1, commit_oe->sha1);
+ hashcpy(commit_sha1, commit_oe->idx.sha1);
} else if (!get_sha1(p, commit_sha1)) {
unsigned long size;
char *buf = read_object_with_reference(commit_sha1,
die("Invalid ref name or SHA1 expression: %s", p);
if (inline_data) {
- static struct strbuf buf = STRBUF_INIT;
-
if (p != uq.buf) {
strbuf_addstr(&uq, p);
p = uq.buf;
}
read_next_command();
- parse_data(&buf);
- store_object(OBJ_BLOB, &buf, &last_blob, sha1, 0);
+ parse_and_store_blob(&last_blob, sha1, 0);
} else if (oe) {
if (oe->type != OBJ_BLOB)
die("Not a blob (actually a %s): %s",
struct object_entry *oe = find_mark(idnum);
if (oe->type != OBJ_COMMIT)
die("Mark :%" PRIuMAX " not a commit", idnum);
- hashcpy(b->sha1, oe->sha1);
+ hashcpy(b->sha1, oe->idx.sha1);
if (oe->pack_id != MAX_PACK_ID) {
unsigned long size;
char *buf = gfi_unpack_entry(oe, &size);
struct object_entry *oe = find_mark(idnum);
if (oe->type != OBJ_COMMIT)
die("Mark :%" PRIuMAX " not a commit", idnum);
- hashcpy(n->sha1, oe->sha1);
+ hashcpy(n->sha1, oe->idx.sha1);
} else if (!get_sha1(from, n->sha1)) {
unsigned long size;
char *buf = read_object_with_reference(n->sha1,
}
if (!committer)
die("Expected committer but didn't get one");
- parse_data(&msg);
+ parse_data(&msg, 0, NULL);
read_next_command();
parse_from(b);
merge_list = parse_merge(&merge_count);
from_mark = strtoumax(from + 1, NULL, 10);
oe = find_mark(from_mark);
type = oe->type;
- hashcpy(sha1, oe->sha1);
+ hashcpy(sha1, oe->idx.sha1);
} else if (!get_sha1(from, sha1)) {
unsigned long size;
char *buf;
tagger = NULL;
/* tag payload/message */
- parse_data(&msg);
+ parse_data(&msg, 0, NULL);
/* build the tag object */
strbuf_reset(&new_data);
die("unknown --date-format argument %s", fmt);
}
-static void option_max_pack_size(const char *packsize)
-{
- max_packsize = strtoumax(packsize, NULL, 0) * 1024 * 1024;
-}
-
static void option_depth(const char *depth)
{
max_depth = strtoul(depth, NULL, 0);
static int parse_one_option(const char *option)
{
if (!prefixcmp(option, "max-pack-size=")) {
- option_max_pack_size(option + 14);
+ unsigned long v;
+ if (!git_parse_ulong(option + 14, &v))
+ return 0;
+ if (v < 8192) {
+ warning("max-pack-size is now in bytes, assuming --max-pack-size=%lum", v);
+ v *= 1024 * 1024;
+ } else if (v < 1024 * 1024) {
+ warning("minimum max-pack-size is 1 MiB");
+ v = 1024 * 1024;
+ }
+ max_packsize = v;
+ } else if (!prefixcmp(option, "big-file-threshold=")) {
+ unsigned long v;
+ if (!git_parse_ulong(option + 19, &v))
+ return 0;
+ big_file_threshold = v;
} else if (!prefixcmp(option, "depth=")) {
option_depth(option + 6);
} else if (!prefixcmp(option, "active-branches=")) {
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;
+ }
return git_default_config(k, v, cb);
}
static const char fast_import_usage[] =
-"git fast-import [--date-format=f] [--max-pack-size=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]";
+"git fast-import [--date-format=f] [--max-pack-size=n] [--big-file-threshold=n] [--depth=n] [--active-branches=n] [--export-marks=marks.file]";
static void parse_argv(void)
{