[thirdparty/git.git] / bulk-checkin.c

/*
 * Copyright (c) 2011, Google Inc.
 */
#include "bulk-checkin.h"
#include "csum-file.h"
#include "pack.h"
#include "strbuf.h"

static int pack_compression_level = Z_DEFAULT_COMPRESSION;

static struct bulk_checkin_state {
	unsigned plugged:1;

	char *pack_tmp_name;
	struct sha1file *f;
	off_t offset;
	struct pack_idx_option pack_idx_opts;

	struct pack_idx_entry **written;
	uint32_t alloc_written;
	uint32_t nr_written;
} state;

static void finish_bulk_checkin(struct bulk_checkin_state *state)
{
	unsigned char sha1[20];
	struct strbuf packname = STRBUF_INIT;
	int i;

	if (!state->f)
		return;

	if (state->nr_written == 0) {
		close(state->f->fd);
		unlink(state->pack_tmp_name);
		goto clear_exit;
	} else if (state->nr_written == 1) {
		sha1close(state->f, sha1, CSUM_FSYNC);
	} else {
		int fd = sha1close(state->f, sha1, 0);
		fixup_pack_header_footer(fd, sha1, state->pack_tmp_name,
					 state->nr_written, sha1,
					 state->offset);
		close(fd);
	}

	strbuf_addf(&packname, "%s/pack/pack-", get_object_directory());
	finish_tmp_packfile(&packname, state->pack_tmp_name,
			    state->written, state->nr_written,
			    &state->pack_idx_opts, sha1);
	for (i = 0; i < state->nr_written; i++)
		free(state->written[i]);

clear_exit:
	free(state->written);
	memset(state, 0, sizeof(*state));

	strbuf_release(&packname);
	/* Make objects we just wrote available to ourselves */
	reprepare_packed_git();
}

static int already_written(struct bulk_checkin_state *state, unsigned char sha1[])
{
	int i;

	/* The object may already exist in the repository */
	if (has_sha1_file(sha1))
		return 1;

	/* Might want to keep the list sorted */
	for (i = 0; i < state->nr_written; i++)
		if (!hashcmp(state->written[i]->sha1, sha1))
			return 1;

	/* This is a new object we need to keep */
	return 0;
}

/*
 * Read the contents from fd for size bytes, streaming it to the
 * packfile in state while updating the hash in ctx. Signal a failure
 * by returning a negative value when the resulting pack would exceed
 * the pack size limit and this is not the first object in the pack,
 * so that the caller can discard what we wrote from the current pack
 * by truncating it and opening a new one. The caller will then call
 * us again after rewinding the input fd.
 *
 * The already_hashed_to pointer is kept untouched by the caller to
 * make sure we do not hash the same byte when we are called
 * again. This way, the caller does not have to checkpoint its hash
 * 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_state *state,
			  git_SHA_CTX *ctx, off_t *already_hashed_to,
			  int fd, size_t size, enum object_type type,
			  const char *path, unsigned flags)
{
	git_zstream s;
	unsigned char obuf[16384];
	unsigned hdrlen;
	int status = Z_OK;
	int write_object = (flags & HASH_WRITE_OBJECT);
	off_t offset = 0;

	memset(&s, 0, sizeof(s));
	git_deflate_init(&s, pack_compression_level);

	hdrlen = encode_in_pack_object_header(type, size, obuf);
	s.next_out = obuf + hdrlen;
	s.avail_out = sizeof(obuf) - hdrlen;

	while (status != Z_STREAM_END) {
		unsigned char ibuf[16384];

		if (size && !s.avail_in) {
			ssize_t rsize = size < sizeof(ibuf) ? size : sizeof(ibuf);
			if (read_in_full(fd, ibuf, rsize) != rsize)
				die("failed to read %d bytes from '%s'",
				    (int)rsize, path);
			offset += rsize;
			if (*already_hashed_to < offset) {
				size_t hsize = offset - *already_hashed_to;
				if (rsize < hsize)
					hsize = rsize;
				if (hsize)
					git_SHA1_Update(ctx, ibuf, hsize);
				*already_hashed_to = offset;
			}
			s.next_in = ibuf;
			s.avail_in = rsize;
			size -= rsize;
		}

		status = git_deflate(&s, size ? 0 : Z_FINISH);

		if (!s.avail_out || status == Z_STREAM_END) {
			if (write_object) {
				size_t written = s.next_out - obuf;

				/* would we bust the size limit? */
				if (state->nr_written &&
				    pack_size_limit_cfg &&
				    pack_size_limit_cfg < state->offset + written) {
					git_deflate_abort(&s);
					return -1;
				}

				sha1write(state->f, obuf, written);
				state->offset += written;
			}
			s.next_out = obuf;
			s.avail_out = sizeof(obuf);
		}

		switch (status) {
		case Z_OK:
		case Z_BUF_ERROR:
		case Z_STREAM_END:
			continue;
		default:
			die("unexpected deflate failure: %d", status);
		}
	}
	git_deflate_end(&s);
	return 0;
}

/* Lazily create backing packfile for the state */
static void prepare_to_stream(struct bulk_checkin_state *state,
			      unsigned flags)
{
	if (!(flags & HASH_WRITE_OBJECT) || state->f)
		return;

	state->f = create_tmp_packfile(&state->pack_tmp_name);
	reset_pack_idx_option(&state->pack_idx_opts);

	/* Pretend we are going to write only one object */
	state->offset = write_pack_header(state->f, 1);
	if (!state->offset)
		die_errno("unable to write pack header");
}

static int deflate_to_pack(struct bulk_checkin_state *state,
			   unsigned char result_sha1[],
			   int fd, size_t size,
			   enum object_type type, const char *path,
			   unsigned flags)
{
	off_t seekback, already_hashed_to;
	git_SHA_CTX ctx;
	unsigned char obuf[16384];
	unsigned header_len;
	struct sha1file_checkpoint checkpoint;
	struct pack_idx_entry *idx = NULL;

	seekback = lseek(fd, 0, SEEK_CUR);
	if (seekback == (off_t) -1)
		return error("cannot find the current offset");

	header_len = sprintf((char *)obuf, "%s %" PRIuMAX,
			     typename(type), (uintmax_t)size) + 1;
	git_SHA1_Init(&ctx);
	git_SHA1_Update(&ctx, obuf, header_len);

	/* Note: idx is non-NULL when we are writing */
	if ((flags & HASH_WRITE_OBJECT) != 0)
		idx = xcalloc(1, sizeof(*idx));

	already_hashed_to = 0;

	while (1) {
		prepare_to_stream(state, flags);
		if (idx) {
			sha1file_checkpoint(state->f, &checkpoint);
			idx->offset = state->offset;
			crc32_begin(state->f);
		}
		if (!stream_to_pack(state, &ctx, &already_hashed_to,
				    fd, size, type, path, flags))
			break;
		/*
		 * Writing this object to the current pack will make
		 * it too big; we need to truncate it, start a new
		 * pack, and write into it.
		 */
		if (!idx)
			die("BUG: should not happen");
		sha1file_truncate(state->f, &checkpoint);
		state->offset = checkpoint.offset;
		finish_bulk_checkin(state);
		if (lseek(fd, seekback, SEEK_SET) == (off_t) -1)
			return error("cannot seek back");
	}
	git_SHA1_Final(result_sha1, &ctx);
	if (!idx)
		return 0;

	idx->crc32 = crc32_end(state->f);
	if (already_written(state, result_sha1)) {
		sha1file_truncate(state->f, &checkpoint);
		state->offset = checkpoint.offset;
		free(idx);
	} else {
		hashcpy(idx->sha1, result_sha1);
		ALLOC_GROW(state->written,
			   state->nr_written + 1,
			   state->alloc_written);
		state->written[state->nr_written++] = idx;
	}
	return 0;
}

int index_bulk_checkin(unsigned char *sha1,
		       int fd, size_t size, enum object_type type,
		       const char *path, unsigned flags)
{
	int status = deflate_to_pack(&state, sha1, fd, size, type,
				     path, flags);
	if (!state.plugged)
		finish_bulk_checkin(&state);
	return status;
}

void plug_bulk_checkin(void)
{
	state.plugged = 1;
}

void unplug_bulk_checkin(void)
{
	state.plugged = 0;
	if (state.f)
		finish_bulk_checkin(&state);
}
Commit	Line	Data
568508e7 JH	1	/*
	2	* Copyright (c) 2011, Google Inc.
	3	*/
	4	#include "bulk-checkin.h"
	5	#include "csum-file.h"
	6	#include "pack.h"
58892711	7	#include "strbuf.h"
568508e7 JH	8
	9	static int pack_compression_level = Z_DEFAULT_COMPRESSION;
	10
	11	static struct bulk_checkin_state {
	12	unsigned plugged:1;
	13
	14	char *pack_tmp_name;
	15	struct sha1file *f;
	16	off_t offset;
	17	struct pack_idx_option pack_idx_opts;
	18
	19	struct pack_idx_entry **written;
	20	uint32_t alloc_written;
	21	uint32_t nr_written;
	22	} state;
	23
	24	static void finish_bulk_checkin(struct bulk_checkin_state *state)
	25	{
	26	unsigned char sha1[20];
58892711	27	struct strbuf packname = STRBUF_INIT;
568508e7 JH	28	int i;
	29
	30	if (!state->f)
	31	return;
	32
	33	if (state->nr_written == 0) {
	34	close(state->f->fd);
	35	unlink(state->pack_tmp_name);
	36	goto clear_exit;
	37	} else if (state->nr_written == 1) {
	38	sha1close(state->f, sha1, CSUM_FSYNC);
	39	} else {
	40	int fd = sha1close(state->f, sha1, 0);
	41	fixup_pack_header_footer(fd, sha1, state->pack_tmp_name,
	42	state->nr_written, sha1,
	43	state->offset);
	44	close(fd);
	45	}
	46
58892711 SH	47	strbuf_addf(&packname, "%s/pack/pack-", get_object_directory());
58892711 SH	48	finish_tmp_packfile(&packname, state->pack_tmp_name,
568508e7 JH	49	state->written, state->nr_written,
	50	&state->pack_idx_opts, sha1);
	51	for (i = 0; i < state->nr_written; i++)
	52	free(state->written[i]);
	53
	54	clear_exit:
	55	free(state->written);
	56	memset(state, 0, sizeof(*state));
	57
58892711	58	strbuf_release(&packname);
568508e7 JH	59	/* Make objects we just wrote available to ourselves */
	60	reprepare_packed_git();
	61	}
	62
	63	static int already_written(struct bulk_checkin_state *state, unsigned char sha1[])
	64	{
	65	int i;
	66
	67	/* The object may already exist in the repository */
	68	if (has_sha1_file(sha1))
	69	return 1;
	70
	71	/* Might want to keep the list sorted */
	72	for (i = 0; i < state->nr_written; i++)
	73	if (!hashcmp(state->written[i]->sha1, sha1))
	74	return 1;
	75
	76	/* This is a new object we need to keep */
	77	return 0;
	78	}
	79
	80	/*
	81	* Read the contents from fd for size bytes, streaming it to the
	82	* packfile in state while updating the hash in ctx. Signal a failure
	83	* by returning a negative value when the resulting pack would exceed
	84	* the pack size limit and this is not the first object in the pack,
	85	* so that the caller can discard what we wrote from the current pack
	86	* by truncating it and opening a new one. The caller will then call
	87	* us again after rewinding the input fd.
	88	*
	89	* The already_hashed_to pointer is kept untouched by the caller to
	90	* make sure we do not hash the same byte when we are called
	91	* again. This way, the caller does not have to checkpoint its hash
	92	* status before calling us just in case we ask it to call us again
	93	* with a new pack.
	94	*/
	95	static int stream_to_pack(struct bulk_checkin_state *state,
	96	git_SHA_CTX ctx, off_t already_hashed_to,
	97	int fd, size_t size, enum object_type type,
	98	const char *path, unsigned flags)
	99	{
	100	git_zstream s;
	101	unsigned char obuf[16384];
	102	unsigned hdrlen;
	103	int status = Z_OK;
	104	int write_object = (flags & HASH_WRITE_OBJECT);
	105	off_t offset = 0;
	106
	107	memset(&s, 0, sizeof(s));
	108	git_deflate_init(&s, pack_compression_level);
	109
	110	hdrlen = encode_in_pack_object_header(type, size, obuf);
	111	s.next_out = obuf + hdrlen;
	112	s.avail_out = sizeof(obuf) - hdrlen;
	113
	114	while (status != Z_STREAM_END) {
	115	unsigned char ibuf[16384];
	116
	117	if (size && !s.avail_in) {
	118	ssize_t rsize = size < sizeof(ibuf) ? size : sizeof(ibuf);
e92527c9	119	if (read_in_full(fd, ibuf, rsize) != rsize)
568508e7 JH	120	die("failed to read %d bytes from '%s'",
	121	(int)rsize, path);
	122	offset += rsize;
	123	if (*already_hashed_to < offset) {
	124	size_t hsize = offset - *already_hashed_to;
	125	if (rsize < hsize)
	126	hsize = rsize;
	127	if (hsize)
	128	git_SHA1_Update(ctx, ibuf, hsize);
	129	*already_hashed_to = offset;
	130	}
	131	s.next_in = ibuf;
	132	s.avail_in = rsize;
	133	size -= rsize;
	134	}
	135
	136	status = git_deflate(&s, size ? 0 : Z_FINISH);
	137
	138	if (!s.avail_out \|\| status == Z_STREAM_END) {
	139	if (write_object) {
	140	size_t written = s.next_out - obuf;
	141
	142	/* would we bust the size limit? */
	143	if (state->nr_written &&
	144	pack_size_limit_cfg &&
	145	pack_size_limit_cfg < state->offset + written) {
	146	git_deflate_abort(&s);
	147	return -1;
	148	}
	149
	150	sha1write(state->f, obuf, written);
	151	state->offset += written;
	152	}
	153	s.next_out = obuf;
	154	s.avail_out = sizeof(obuf);
	155	}
	156
	157	switch (status) {
	158	case Z_OK:
	159	case Z_BUF_ERROR:
	160	case Z_STREAM_END:
	161	continue;
	162	default:
	163	die("unexpected deflate failure: %d", status);
	164	}
	165	}
	166	git_deflate_end(&s);
	167	return 0;
	168	}
	169
	170	/* Lazily create backing packfile for the state */
	171	static void prepare_to_stream(struct bulk_checkin_state *state,
	172	unsigned flags)
	173	{
	174	if (!(flags & HASH_WRITE_OBJECT) \|\| state->f)
	175	return;
	176
	177	state->f = create_tmp_packfile(&state->pack_tmp_name);
	178	reset_pack_idx_option(&state->pack_idx_opts);
	179
	180	/* Pretend we are going to write only one object */
	181	state->offset = write_pack_header(state->f, 1);
	182	if (!state->offset)
	183	die_errno("unable to write pack header");
184	}
185
186	static int deflate_to_pack(struct bulk_checkin_state *state,
187	unsigned char result_sha1[],
188	int fd, size_t size,
189	enum object_type type, const char *path,
190	unsigned flags)
191	{
192	off_t seekback, already_hashed_to;
193	git_SHA_CTX ctx;
194	unsigned char obuf[16384];
195	unsigned header_len;
196	struct sha1file_checkpoint checkpoint;
197	struct pack_idx_entry *idx = NULL;
198
199	seekback = lseek(fd, 0, SEEK_CUR);
200	if (seekback == (off_t) -1)
201	return error("cannot find the current offset");
202
203	header_len = sprintf((char *)obuf, "%s %" PRIuMAX,
204	typename(type), (uintmax_t)size) + 1;
205	git_SHA1_Init(&ctx);
206	git_SHA1_Update(&ctx, obuf, header_len);
207
208	/* Note: idx is non-NULL when we are writing */
209	if ((flags & HASH_WRITE_OBJECT) != 0)
210	idx = xcalloc(1, sizeof(*idx));
211
212	already_hashed_to = 0;
213
214	while (1) {
215	prepare_to_stream(state, flags);
216	if (idx) {
217	sha1file_checkpoint(state->f, &checkpoint);
218	idx->offset = state->offset;
219	crc32_begin(state->f);
220	}
221	if (!stream_to_pack(state, &ctx, &already_hashed_to,
222	fd, size, type, path, flags))
223	break;
224	/*
225	* Writing this object to the current pack will make
226	* it too big; we need to truncate it, start a new
227	* pack, and write into it.
228	*/
229	if (!idx)
230	die("BUG: should not happen");
231	sha1file_truncate(state->f, &checkpoint);
232	state->offset = checkpoint.offset;
233	finish_bulk_checkin(state);
234	if (lseek(fd, seekback, SEEK_SET) == (off_t) -1)
235	return error("cannot seek back");
236	}
237	git_SHA1_Final(result_sha1, &ctx);
238	if (!idx)
239	return 0;
240
241	idx->crc32 = crc32_end(state->f);
242	if (already_written(state, result_sha1)) {
243	sha1file_truncate(state->f, &checkpoint);
244	state->offset = checkpoint.offset;
245	free(idx);
246	} else {
247	hashcpy(idx->sha1, result_sha1);
248	ALLOC_GROW(state->written,
249	state->nr_written + 1,
250	state->alloc_written);
251	state->written[state->nr_written++] = idx;
252	}
253	return 0;
254	}
255
256	int index_bulk_checkin(unsigned char *sha1,
257	int fd, size_t size, enum object_type type,
258	const char *path, unsigned flags)
259	{
260	int status = deflate_to_pack(&state, sha1, fd, size, type,
261	path, flags);
262	if (!state.plugged)
263	finish_bulk_checkin(&state);
264	return status;
265	}
266
267	void plug_bulk_checkin(void)
268	{
269	state.plugged = 1;
270	}
271
272	void unplug_bulk_checkin(void)
273	{
274	state.plugged = 0;
275	if (state.f)
276	finish_bulk_checkin(&state);
277	}