LIB_H += attr.h
LIB_H += blob.h
LIB_H += builtin.h
+LIB_H += bulk-checkin.h
LIB_H += cache.h
LIB_H += cache-tree.h
LIB_H += color.h
LIB_OBJS += bisect.o
LIB_OBJS += blob.o
LIB_OBJS += branch.o
+LIB_OBJS += bulk-checkin.o
LIB_OBJS += bundle.o
LIB_OBJS += cache-tree.o
LIB_OBJS += color.o
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
+#include "bulk-checkin.h"
static const char * const builtin_add_usage[] = {
"git add [options] [--] <filepattern>...",
free(seen);
}
+ plug_bulk_checkin();
+
exit_status |= add_files_to_cache(prefix, pathspec, flags);
if (add_new_files)
exit_status |= add_files(&dir, flags);
+ unplug_bulk_checkin();
+
finish:
if (active_cache_changed) {
if (write_cache(newfd, active_cache, active_nr) ||
static const char *base_name;
static int progress = 1;
static int window = 10;
-static unsigned long pack_size_limit, pack_size_limit_cfg;
+static unsigned long pack_size_limit;
static int depth = 50;
static int delta_search_threads;
static int pack_to_stdout;
pack_idx_opts.version);
return 0;
}
- if (!strcmp(k, "pack.packsizelimit")) {
- pack_size_limit_cfg = git_config_ulong(k, v);
- return 0;
- }
return git_default_config(k, v, cb);
}
--- /dev/null
+/*
+ * Copyright (c) 2011, Google Inc.
+ */
+#include "bulk-checkin.h"
+#include "csum-file.h"
+#include "pack.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];
+ char packname[PATH_MAX];
+ 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);
+ }
+
+ sprintf(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));
+
+ /* 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 (xread(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);
+}
--- /dev/null
+/*
+ * Copyright (c) 2011, Google Inc.
+ */
+#ifndef BULK_CHECKIN_H
+#define BULK_CHECKIN_H
+
+#include "cache.h"
+
+extern int index_bulk_checkin(unsigned char sha1[],
+ int fd, size_t size, enum object_type type,
+ const char *path, unsigned flags);
+
+extern void plug_bulk_checkin(void);
+extern void unplug_bulk_checkin(void);
+
+#endif
void git_deflate_init(git_zstream *, int level);
void git_deflate_init_gzip(git_zstream *, int level);
void git_deflate_end(git_zstream *);
+int git_deflate_abort(git_zstream *);
int git_deflate_end_gently(git_zstream *);
int git_deflate(git_zstream *, int flush);
unsigned long git_deflate_bound(git_zstream *, unsigned long);
extern size_t packed_git_limit;
extern size_t delta_base_cache_limit;
extern unsigned long big_file_threshold;
+extern unsigned long pack_size_limit_cfg;
extern int read_replace_refs;
extern int fsync_object_files;
extern int core_preload_index;
return 0;
}
+ if (!strcmp(var, "pack.packsizelimit")) {
+ pack_size_limit_cfg = git_config_ulong(var, value);
+ return 0;
+ }
/* Add other config variables here and to Documentation/config.txt. */
return 0;
}
int grafts_replace_parents = 1;
int core_apply_sparse_checkout;
struct startup_info *startup_info;
+unsigned long pack_size_limit_cfg;
/* Parallel index stat data preload? */
int core_preload_index = 0;
#include "refs.h"
#include "pack-revindex.h"
#include "sha1-lookup.h"
+#include "bulk-checkin.h"
#ifndef O_NOATIME
#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
}
/*
- * This creates one packfile per large blob, because the caller
- * immediately wants the result sha1, and fast-import can report the
- * object name via marks mechanism only by closing the created
- * packfile.
+ * This creates one packfile per large blob unless bulk-checkin
+ * machinery is "plugged".
*
* This also bypasses the usual "convert-to-git" dance, and that is on
* purpose. We could write a streaming version of the converting
enum object_type type, const char *path,
unsigned flags)
{
- struct child_process fast_import;
- char export_marks[512];
- const char *argv[] = { "fast-import", "--quiet", export_marks, NULL };
- char tmpfile[512];
- char fast_import_cmd[512];
- char buf[512];
- int len, tmpfd;
-
- strcpy(tmpfile, git_path("hashstream_XXXXXX"));
- tmpfd = git_mkstemp_mode(tmpfile, 0600);
- if (tmpfd < 0)
- die_errno("cannot create tempfile: %s", tmpfile);
- if (close(tmpfd))
- die_errno("cannot close tempfile: %s", tmpfile);
- sprintf(export_marks, "--export-marks=%s", tmpfile);
-
- memset(&fast_import, 0, sizeof(fast_import));
- fast_import.in = -1;
- fast_import.argv = argv;
- fast_import.git_cmd = 1;
- if (start_command(&fast_import))
- die_errno("index-stream: git fast-import failed");
-
- len = sprintf(fast_import_cmd, "blob\nmark :1\ndata %lu\n",
- (unsigned long) size);
- write_or_whine(fast_import.in, fast_import_cmd, len,
- "index-stream: feeding fast-import");
- while (size) {
- char buf[10240];
- size_t sz = size < sizeof(buf) ? size : sizeof(buf);
- ssize_t actual;
-
- actual = read_in_full(fd, buf, sz);
- if (actual < 0)
- die_errno("index-stream: reading input");
- if (write_in_full(fast_import.in, buf, actual) != actual)
- die_errno("index-stream: feeding fast-import");
- size -= actual;
- }
- if (close(fast_import.in))
- die_errno("index-stream: closing fast-import");
- if (finish_command(&fast_import))
- die_errno("index-stream: finishing fast-import");
-
- tmpfd = open(tmpfile, O_RDONLY);
- if (tmpfd < 0)
- die_errno("index-stream: cannot open fast-import mark");
- len = read(tmpfd, buf, sizeof(buf));
- if (len < 0)
- die_errno("index-stream: reading fast-import mark");
- if (close(tmpfd) < 0)
- die_errno("index-stream: closing fast-import mark");
- if (unlink(tmpfile))
- die_errno("index-stream: unlinking fast-import mark");
- if (len != 44 ||
- memcmp(":1 ", buf, 3) ||
- get_sha1_hex(buf + 3, sha1))
- die_errno("index-stream: unexpected fast-import mark: <%s>", buf);
- return 0;
+ return index_bulk_checkin(sha1, fd, size, type, path, flags);
}
int index_fd(unsigned char *sha1, int fd, struct stat *st,
test_expect_success setup '
git config core.bigfilethreshold 200k &&
- echo X | dd of=large bs=1k seek=2000
+ echo X | dd of=large1 bs=1k seek=2000 &&
+ echo X | dd of=large2 bs=1k seek=2000 &&
+ echo X | dd of=large3 bs=1k seek=2000 &&
+ echo Y | dd of=huge bs=1k seek=2500
'
-test_expect_success 'add a large file' '
- git add large &&
- # make sure we got a packfile and no loose objects
- test -f .git/objects/pack/pack-*.pack &&
- test ! -f .git/objects/??/??????????????????????????????????????
+test_expect_success 'add a large file or two' '
+ git add large1 huge large2 &&
+ # make sure we got a single packfile and no loose objects
+ bad= count=0 idx= &&
+ for p in .git/objects/pack/pack-*.pack
+ do
+ count=$(( $count + 1 ))
+ if test -f "$p" && idx=${p%.pack}.idx && test -f "$idx"
+ then
+ continue
+ fi
+ bad=t
+ done &&
+ test -z "$bad" &&
+ test $count = 1 &&
+ cnt=$(git show-index <"$idx" | wc -l) &&
+ test $cnt = 2 &&
+ for l in .git/objects/??/??????????????????????????????????????
+ do
+ test -f "$l" || continue
+ bad=t
+ done &&
+ test -z "$bad" &&
+
+ # attempt to add another copy of the same
+ git add large3 &&
+ bad= count=0 &&
+ for p in .git/objects/pack/pack-*.pack
+ do
+ count=$(( $count + 1 ))
+ if test -f "$p" && idx=${p%.pack}.idx && test -f "$idx"
+ then
+ continue
+ fi
+ bad=t
+ done &&
+ test -z "$bad" &&
+ test $count = 1
'
test_expect_success 'checkout a large file' '
- large=$(git rev-parse :large) &&
- git update-index --add --cacheinfo 100644 $large another &&
+ large1=$(git rev-parse :large1) &&
+ git update-index --add --cacheinfo 100644 $large1 another &&
git checkout another &&
- cmp large another ;# this must not be test_cmp
+ cmp large1 another ;# this must not be test_cmp
+'
+
+test_expect_success 'packsize limit' '
+ test_create_repo mid &&
+ (
+ cd mid &&
+ git config core.bigfilethreshold 64k &&
+ git config pack.packsizelimit 256k &&
+
+ # mid1 and mid2 will fit within 256k limit but
+ # appending mid3 will bust the limit and will
+ # result in a separate packfile.
+ test-genrandom "a" $(( 66 * 1024 )) >mid1 &&
+ test-genrandom "b" $(( 80 * 1024 )) >mid2 &&
+ test-genrandom "c" $(( 128 * 1024 )) >mid3 &&
+ git add mid1 mid2 mid3 &&
+
+ count=0
+ for pi in .git/objects/pack/pack-*.idx
+ do
+ test -f "$pi" && count=$(( $count + 1 ))
+ done &&
+ test $count = 2 &&
+
+ (
+ git hash-object --stdin <mid1
+ git hash-object --stdin <mid2
+ git hash-object --stdin <mid3
+ ) |
+ sort >expect &&
+
+ for pi in .git/objects/pack/pack-*.idx
+ do
+ git show-index <"$pi"
+ done |
+ sed -e "s/^[0-9]* \([0-9a-f]*\) .*/\1/" |
+ sort >actual &&
+
+ test_cmp expect actual
+ )
'
test_done
strm->z.msg ? strm->z.msg : "no message");
}
-void git_deflate_end(git_zstream *strm)
+int git_deflate_abort(git_zstream *strm)
{
int status;
zlib_pre_call(strm);
status = deflateEnd(&strm->z);
zlib_post_call(strm);
+ return status;
+}
+
+void git_deflate_end(git_zstream *strm)
+{
+ int status = git_deflate_abort(strm);
+
if (status == Z_OK)
return;
error("deflateEnd: %s (%s)", zerr_to_string(status),
projects / git.git / commitdiff