opensourcemirror
/
git
mirror of https://github.com/git/git.git
1
0
Fork 0
Code Issues Releases Wiki Activity

bulk-checkin: only support blobs in index_bulk_checkin 

As the code is written today index_bulk_checkin only accepts blobs.
Remove the enum object_type parameter and rename index_bulk_checkin to
index_blob_bulk_checkin, index_stream to index_blob_stream,
deflate_to_pack to deflate_blob_to_pack, stream_to_pack to
stream_blob_to_pack, to make this explicit.

Not supporting commits, tags, or trees has no downside as it is not
currently supported now, and commits, tags, and trees being smaller by
design do not have the problem that the problem that index_bulk_checkin
was built to solve.

Before we start adding code to support the hash function transition
supporting additional objects types in index_bulk_checkin has no real
additional cost, just an extra function parameter to know what the
object type is.  Once we begin the hash function transition this is not
the case.

The hash function transition document specifies that a repository with
compatObjectFormat enabled will compute and store both the SHA-1 and
SHA-256 hash of every object in the repository.

What makes this a challenge is that it is not just an additional hash
over the same object.  Instead the hash function transition document
specifies that the compatibility hash (specified with
compatObjectFormat) be computed over the equivalent object that another
git repository whose storage hash (specified with objectFormat) would
store.  When comparing equivalent repositories built with different
storage hash functions, the oids embedded in objects used to refer to
other objects differ and the location of signatures within objects
differ.

As blob objects have neither oids referring to other objects nor stored
signatures their storage hash and their compatibility hash are computed
over the same object.

The other kinds of objects: trees, commits, and tags, all store oids
referring to other objects.  Signatures are stored in commit and tag
objects.  As oids and the tags to store signatures are not the same size
in repositories built with different storage hashes the size of the
equivalent objects are also different.

A version of index_bulk_checkin that supports more than just blobs when
computing both the SHA-1 and the SHA-256 of every object added would
need a different, and more expensive structure.  The structure is more
expensive because it would be required to temporarily buffering the
equivalent object the compatibility hash needs to be computed over.

A temporary object is needed, because before a hash over an object can
computed it's object header needs to be computed.  One of the members of
the object header is the entire size of the object.  To know the size of
an equivalent object an entire pass over the original object needs to be
made, as trees, commits, and tags are composed of a variable number of
variable sized pieces.  Unfortunately there is no formula to compute the
size of an equivalent object from just the size of the original object.

Avoid all of those future complications by limiting index_bulk_checkin
to only work on blobs.

Inspired-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Eric W. Biederman 2023-09-26 10:58:43 -05:00 committed by Junio C Hamano
parent 43c8a30d15
commit 9eb5419799
3 changed files with 26 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
bulk-checkin.c
View File

@ -155,10 +155,10 @@ static int already_written(struct bulk_checkin_packfile *state, struct object_id
* status before calling us just in case we ask it to call us again
* with a new pack.
*/
static int stream_to_pack(struct bulk_checkin_packfile *state,
git_hash_ctx *ctx, off_t *already_hashed_to,
int fd, size_t size, enum object_type type,
const char *path, unsigned flags)
static int stream_blob_to_pack(struct bulk_checkin_packfile *state,
git_hash_ctx *ctx, off_t *already_hashed_to,
int fd, size_t size, const char *path,
unsigned flags)
{
git_zstream s;
unsigned char ibuf[16384];
@ -170,7 +170,7 @@ static int stream_to_pack(struct bulk_checkin_packfile *state,
git_deflate_init(&s, pack_compression_level);
hdrlen = encode_in_pack_object_header(obuf, sizeof(obuf), type, size);
hdrlen = encode_in_pack_object_header(obuf, sizeof(obuf), OBJ_BLOB, size);
s.next_out = obuf + hdrlen;
s.avail_out = sizeof(obuf) - hdrlen;
@ -247,11 +247,10 @@ static void prepare_to_stream(struct bulk_checkin_packfile *state,
die_errno("unable to write pack header");
}
static int deflate_to_pack(struct bulk_checkin_packfile *state,
struct object_id *result_oid,
int fd, size_t size,
enum object_type type, const char *path,
unsigned flags)
static int deflate_blob_to_pack(struct bulk_checkin_packfile *state,
struct object_id *result_oid,
int fd, size_t size,
const char *path, unsigned flags)
{
off_t seekback, already_hashed_to;
git_hash_ctx ctx;
@ -265,7 +264,7 @@ static int deflate_to_pack(struct bulk_checkin_packfile *state,
return error("cannot find the current offset");
header_len = format_object_header((char *)obuf, sizeof(obuf),
type, size);
OBJ_BLOB, size);
the_hash_algo->init_fn(&ctx);
the_hash_algo->update_fn(&ctx, obuf, header_len);
@ -282,8 +281,8 @@ static int deflate_to_pack(struct bulk_checkin_packfile *state,
idx->offset = state->offset;
crc32_begin(state->f);
}
if (!stream_to_pack(state, &ctx, &already_hashed_to,
fd, size, type, path, flags))
if (!stream_blob_to_pack(state, &ctx, &already_hashed_to,
fd, size, path, flags))
break;
/*
* Writing this object to the current pack will make
@ -350,12 +349,12 @@ void fsync_loose_object_bulk_checkin(int fd, const char *filename)
}
}
int index_bulk_checkin(struct object_id *oid,
int fd, size_t size, enum object_type type,
const char *path, unsigned flags)
int index_blob_bulk_checkin(struct object_id *oid,
int fd, size_t size,
const char *path, unsigned flags)
{
int status = deflate_to_pack(&bulk_checkin_packfile, oid, fd, size, type,
path, flags);
int status = deflate_blob_to_pack(&bulk_checkin_packfile, oid, fd, size,
path, flags);
if (!odb_transaction_nesting)
flush_bulk_checkin_packfile(&bulk_checkin_packfile);
return status;

6
bulk-checkin.h
View File

@ -9,9 +9,9 @@
void prepare_loose_object_bulk_checkin(void);
void fsync_loose_object_bulk_checkin(int fd, const char *filename);
int index_bulk_checkin(struct object_id *oid,
int fd, size_t size, enum object_type type,
const char *path, unsigned flags);
int index_blob_bulk_checkin(struct object_id *oid,
int fd, size_t size,
const char *path, unsigned flags);
/*
* Tell the object database to optimize for adding

12
object-file.c
View File

@ -2446,11 +2446,11 @@ static int index_core(struct index_state *istate,
* binary blobs, they generally do not want to get any conversion, and
* callers should avoid this code path when filters are requested.
*/
static int index_stream(struct object_id *oid, int fd, size_t size,
enum object_type type, const char *path,
unsigned flags)
static int index_blob_stream(struct object_id *oid, int fd, size_t size,
const char *path,
unsigned flags)
{
return index_bulk_checkin(oid, fd, size, type, path, flags);
return index_blob_bulk_checkin(oid, fd, size, path, flags);
}
int index_fd(struct index_state *istate, struct object_id *oid,
@ -2472,8 +2472,8 @@ int index_fd(struct index_state *istate, struct object_id *oid,
ret = index_core(istate, oid, fd, xsize_t(st->st_size),
type, path, flags);
else
ret = index_stream(oid, fd, xsize_t(st->st_size), type, path,
flags);
ret = index_blob_stream(oid, fd, xsize_t(st->st_size), path,
flags);
close(fd);
return ret;
}