development/git
development/git
1
0
Fork 0
mirror of https://github.com/git/git synced 2024-07-02 15:48:44 +00:00
Code Issues Projects Releases Wiki Activity

chunk-format: allow trailing table of contents

Browse Source 
The existing chunk formats use the table of contents at the beginning of
the file. This is intended as a way to speed up the initial loading of
the file, but comes at a cost during writes. Each example needs to fully
compute how big each chunk will be in advance, which usually requires
storing the full file contents in memory.

Future file formats may want to use the chunk format API in cases where
the writing stage is critical to performance, so we may want to stream
updates from an existing file and then only write the table of contents
at the end.

Add a new 'flags' parameter to write_chunkfile() that allows this
behavior. When this is specified, the defensive programming that checks
that the chunks are written with the precomputed sizes is disabled.
Then, the table of contents is written in reverse order at the end of
the hashfile, so a parser can read the chunk list starting from the end
of the file (minus the hash).

The parsing of these table of contents will come in a later change.

Signed-off-by: Derrick Stolee <derrickstolee@github.com>
Signed-off-by: Taylor Blau <me@ttaylorr.com>
This commit is contained in:
Derrick Stolee 2022-11-07 18:35:44 +00:00 committed by Taylor Blau
parent a17ad58dfc
commit 7056e7f0c8
4 changed files with 47 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
chunk-format.c
View File

@ -57,27 +57,32 @@ void add_chunk(struct chunkfile *cf,
cf->chunks_nr++;
}
int write_chunkfile(struct chunkfile *cf, void *data)
int write_chunkfile(struct chunkfile *cf,
enum chunkfile_flags flags,
void *data)
{
int i, result = 0;
uint64_t cur_offset = hashfile_total(cf->f);
trace2_region_enter("chunkfile", "write", the_repository);
/* Add the table of contents to the current offset */
cur_offset += (cf->chunks_nr + 1) * CHUNK_TOC_ENTRY_SIZE;
if (!(flags & CHUNKFILE_TRAILING_TOC)) {
uint64_t cur_offset = hashfile_total(cf->f);
for (i = 0; i < cf->chunks_nr; i++) {
hashwrite_be32(cf->f, cf->chunks[i].id);
/* Add the table of contents to the current offset */
cur_offset += (cf->chunks_nr + 1) * CHUNK_TOC_ENTRY_SIZE;
for (i = 0; i < cf->chunks_nr; i++) {
hashwrite_be32(cf->f, cf->chunks[i].id);
hashwrite_be64(cf->f, cur_offset);
cur_offset += cf->chunks[i].size;
}
/* Trailing entry marks the end of the chunks */
hashwrite_be32(cf->f, 0);
hashwrite_be64(cf->f, cur_offset);
cur_offset += cf->chunks[i].size;
}
/* Trailing entry marks the end of the chunks */
hashwrite_be32(cf->f, 0);
hashwrite_be64(cf->f, cur_offset);
for (i = 0; i < cf->chunks_nr; i++) {
cf->chunks[i].offset = hashfile_total(cf->f);
result = cf->chunks[i].write_fn(cf->f, data);
@ -85,10 +90,26 @@ int write_chunkfile(struct chunkfile *cf, void *data)
if (result)
goto cleanup;
if (hashfile_total(cf->f) - cf->chunks[i].offset != cf->chunks[i].size)
BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead",
cf->chunks[i].size, cf->chunks[i].id,
hashfile_total(cf->f) - cf->chunks[i].offset);
if (!(flags & CHUNKFILE_TRAILING_TOC)) {
if (hashfile_total(cf->f) - cf->chunks[i].offset != cf->chunks[i].size)
BUG("expected to write %"PRId64" bytes to chunk %"PRIx32", but wrote %"PRId64" instead",
cf->chunks[i].size, cf->chunks[i].id,
hashfile_total(cf->f) - cf->chunks[i].offset);
}
cf->chunks[i].size = hashfile_total(cf->f) - cf->chunks[i].offset;
}
if (flags & CHUNKFILE_TRAILING_TOC) {
size_t last_chunk_tail = hashfile_total(cf->f);
/* First entry marks the end of the chunks */
hashwrite_be32(cf->f, 0);
hashwrite_be64(cf->f, last_chunk_tail);
for (i = cf->chunks_nr - 1; i >= 0; i--) {
hashwrite_be32(cf->f, cf->chunks[i].id);
hashwrite_be64(cf->f, cf->chunks[i].offset);
}
}
cleanup:

9
chunk-format.h
View File

@ -31,7 +31,14 @@ void add_chunk(struct chunkfile *cf,
uint32_t id,
size_t size,
chunk_write_fn fn);
int write_chunkfile(struct chunkfile *cf, void *data);
enum chunkfile_flags {
CHUNKFILE_TRAILING_TOC = (1 << 0),
};
int write_chunkfile(struct chunkfile *cf,
enum chunkfile_flags flags,
void *data);
int read_table_of_contents(struct chunkfile *cf,
const unsigned char *mfile,

2
commit-graph.c
View File

@ -1932,7 +1932,7 @@ static int write_commit_graph_file(struct write_commit_graph_context *ctx)
get_num_chunks(cf) * ctx->commits.nr);
}
write_chunkfile(cf, ctx);
write_chunkfile(cf, 0, ctx);
stop_progress(&ctx->progress);
strbuf_release(&progress_title);

2
midx.c
View File

@ -1510,7 +1510,7 @@ static int write_midx_internal(const char *object_dir,
}
write_midx_header(f, get_num_chunks(cf), ctx.nr - dropped_packs);
write_chunkfile(cf, &ctx);
write_chunkfile(cf, 0, &ctx);
finalize_hashfile(f, midx_hash, FSYNC_COMPONENT_PACK_METADATA,
CSUM_FSYNC | CSUM_HASH_IN_STREAM);