git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: "Derrick Stolee via GitGitGadget" <gitgitgadget@gmail.com>
To: git@vger.kernel.org
Cc: me@ttaylorr.com, gitster@pobox.com, l.s.r@web.de,
	szeder.dev@gmail.com, Chris Torek <chris.torek@gmail.com>,
	Derrick Stolee <stolee@gmail.com>,
	Derrick Stolee <derrickstolee@github.com>,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v3 02/17] chunk-format: create chunk format write API
Date: Fri, 05 Feb 2021 14:30:37 +0000	[thread overview]
Message-ID: <16c37d2370cf4fd5fc309ac6dc8aa6443ffcf3d7.1612535453.git.gitgitgadget@gmail.com> (raw)
In-Reply-To: <pull.848.v3.git.1612535452.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

In anticipation of combining the logic from the commit-graph and
multi-pack-index file formats, create a new chunk-format API. Use a
'struct chunkfile' pointer to keep track of data that has been
registered for writes. This struct is anonymous outside of
chunk-format.c to ensure no user attempts to interfere with the data.

The next change will use this API in commit-graph.c, but the general
approach is:

 1. initialize the chunkfile with init_chunkfile(f).
 2. add chunks in the intended writing order with add_chunk().
 3. write any header information to the hashfile f.
 4. write the chunkfile data using write_chunkfile().
 5. free the chunkfile struct using free_chunkfile().

Helped-by: Taylor Blau <me@ttaylorr.com>
Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 Makefile       |  1 +
 chunk-format.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++
 chunk-format.h | 19 +++++++++++
 3 files changed, 111 insertions(+)
 create mode 100644 chunk-format.c
 create mode 100644 chunk-format.h

diff --git a/Makefile b/Makefile
index 7b64106930a6..50a7663841e9 100644
--- a/Makefile
+++ b/Makefile
@@ -854,6 +854,7 @@ LIB_OBJS += bundle.o
 LIB_OBJS += cache-tree.o
 LIB_OBJS += chdir-notify.o
 LIB_OBJS += checkout.o
+LIB_OBJS += chunk-format.o
 LIB_OBJS += color.o
 LIB_OBJS += column.o
 LIB_OBJS += combine-diff.o
diff --git a/chunk-format.c b/chunk-format.c
new file mode 100644
index 000000000000..6e0f1900213e
--- /dev/null
+++ b/chunk-format.c
@@ -0,0 +1,91 @@
+#include "cache.h"
+#include "chunk-format.h"
+#include "csum-file.h"
+#define CHUNK_LOOKUP_WIDTH 12
+
+/*
+ * When writing a chunk-based file format, collect the chunks in
+ * an array of chunk_info structs. The size stores the _expected_
+ * amount of data that will be written by write_fn.
+ */
+struct chunk_info {
+	uint32_t id;
+	uint64_t size;
+	chunk_write_fn write_fn;
+};
+
+struct chunkfile {
+	struct hashfile *f;
+
+	struct chunk_info *chunks;
+	size_t chunks_nr;
+	size_t chunks_alloc;
+};
+
+struct chunkfile *init_chunkfile(struct hashfile *f)
+{
+	struct chunkfile *cf = xcalloc(1, sizeof(*cf));
+	cf->f = f;
+	return cf;
+}
+
+void free_chunkfile(struct chunkfile *cf)
+{
+	if (!cf)
+		return;
+	free(cf->chunks);
+	free(cf);
+}
+
+int get_num_chunks(struct chunkfile *cf)
+{
+	return cf->chunks_nr;
+}
+
+void add_chunk(struct chunkfile *cf,
+	       uint32_t id,
+	       size_t size,
+	       chunk_write_fn fn)
+{
+	ALLOC_GROW(cf->chunks, cf->chunks_nr + 1, cf->chunks_alloc);
+
+	cf->chunks[cf->chunks_nr].id = id;
+	cf->chunks[cf->chunks_nr].write_fn = fn;
+	cf->chunks[cf->chunks_nr].size = size;
+	cf->chunks_nr++;
+}
+
+int write_chunkfile(struct chunkfile *cf, void *data)
+{
+	int i;
+	uint64_t cur_offset = hashfile_total(cf->f);
+
+	/* Add the table of contents to the current offset */
+	cur_offset += (cf->chunks_nr + 1) * CHUNK_LOOKUP_WIDTH;
+
+	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);
+
+	for (i = 0; i < cf->chunks_nr; i++) {
+		off_t start_offset = hashfile_total(cf->f);
+		int result = cf->chunks[i].write_fn(cf->f, data);
+
+		if (result)
+			return result;
+
+		if (hashfile_total(cf->f) - start_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) - start_offset);
+	}
+
+	return 0;
+}
diff --git a/chunk-format.h b/chunk-format.h
new file mode 100644
index 000000000000..9a1d770accec
--- /dev/null
+++ b/chunk-format.h
@@ -0,0 +1,19 @@
+#ifndef CHUNK_FORMAT_H
+#define CHUNK_FORMAT_H
+
+#include "git-compat-util.h"
+
+struct hashfile;
+struct chunkfile;
+
+struct chunkfile *init_chunkfile(struct hashfile *f);
+void free_chunkfile(struct chunkfile *cf);
+int get_num_chunks(struct chunkfile *cf);
+typedef int (*chunk_write_fn)(struct hashfile *f, void *data);
+void add_chunk(struct chunkfile *cf,
+	       uint32_t id,
+	       size_t size,
+	       chunk_write_fn fn);
+int write_chunkfile(struct chunkfile *cf, void *data);
+
+#endif
-- 
gitgitgadget


  parent reply	other threads:[~2021-02-05 22:03 UTC|newest]

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-26 16:01 [PATCH 00/17] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-01-27  1:53   ` Chris Torek
2021-01-27  2:36     ` Taylor Blau
2021-01-26 16:01 ` [PATCH 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-01-27  2:42   ` Taylor Blau
2021-01-27 13:49     ` Derrick Stolee
2021-01-26 16:01 ` [PATCH 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-01-27  2:47   ` Taylor Blau
2021-01-26 16:01 ` [PATCH 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27  2:49   ` Taylor Blau
2021-01-26 16:01 ` [PATCH 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-01-27  3:02   ` Taylor Blau
2021-01-26 16:01 ` [PATCH 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 14/17] midx: " Derrick Stolee via GitGitGadget
2021-01-27  3:06   ` Taylor Blau
2021-01-27 13:50     ` Derrick Stolee
2021-01-26 16:01 ` [PATCH 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-01-26 16:01 ` [PATCH 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-01-26 22:37 ` [PATCH 00/17] Refactor chunk-format into an API Junio C Hamano
2021-01-27  2:29 ` Taylor Blau
2021-01-27 15:01 ` [PATCH v2 " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-04 21:24     ` Junio C Hamano
2021-02-04 22:40       ` Junio C Hamano
2021-02-05 11:37       ` Derrick Stolee
2021-02-05 19:25         ` Junio C Hamano
2021-01-27 15:01   ` [PATCH v2 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-04 22:59     ` Junio C Hamano
2021-02-05 11:42       ` Derrick Stolee
2021-01-27 15:01   ` [PATCH v2 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-04 23:40     ` Junio C Hamano
2021-02-05 12:19       ` Derrick Stolee
2021-02-05 19:37         ` Junio C Hamano
2021-02-08 22:26           ` Junio C Hamano
2021-02-09  1:33             ` Derrick Stolee
2021-02-09 20:47               ` Junio C Hamano
2021-01-27 15:01   ` [PATCH v2 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 14/17] midx: " Derrick Stolee via GitGitGadget
2021-01-27 15:01   ` [PATCH v2 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-05  0:00     ` Junio C Hamano
2021-02-05 10:59       ` Chris Torek
2021-02-05 20:41         ` Junio C Hamano
2021-02-06 20:35           ` Chris Torek
2021-02-05 12:30       ` Derrick Stolee
2021-02-05 19:42         ` Junio C Hamano
2021-02-07 19:50       ` SZEDER Gábor
2021-02-08  5:41         ` Junio C Hamano
2021-01-27 15:01   ` [PATCH v2 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-05  0:05     ` Junio C Hamano
2021-02-05 12:31       ` Derrick Stolee
2021-01-27 15:01   ` [PATCH v2 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-05  0:15     ` Junio C Hamano
2021-01-27 16:03   ` [PATCH v2 00/17] Refactor chunk-format into an API Taylor Blau
2021-02-05  2:08   ` Junio C Hamano
2021-02-05  2:27     ` Derrick Stolee
2021-02-05 14:30   ` [PATCH v3 " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` Derrick Stolee via GitGitGadget [this message]
2021-02-07 21:13       ` [PATCH v3 02/17] chunk-format: create chunk format write API SZEDER Gábor
2021-02-08 13:44         ` Derrick Stolee
2021-02-11 19:43           ` SZEDER Gábor
2021-02-05 14:30     ` [PATCH v3 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-07 20:20       ` SZEDER Gábor
2021-02-08 13:35         ` Derrick Stolee
2021-02-05 14:30     ` [PATCH v3 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 14/17] midx: " Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-05 14:30     ` [PATCH v3 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-18 14:07     ` [PATCH v4 00/17] Refactor chunk-format into an API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 01/17] commit-graph: anonymize data in chunk_write_fn Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 02/17] chunk-format: create chunk format write API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 03/17] commit-graph: use chunk-format " Derrick Stolee via GitGitGadget
2021-02-24 16:52         ` SZEDER Gábor
2021-02-24 17:12           ` Taylor Blau
2021-02-24 17:52             ` Derrick Stolee
2021-02-24 19:44               ` Junio C Hamano
2021-02-18 14:07       ` [PATCH v4 04/17] midx: rename pack_info to write_midx_context Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 05/17] midx: use context in write_midx_pack_names() Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 06/17] midx: add entries to write_midx_context Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 07/17] midx: add pack_perm " Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 08/17] midx: add num_large_offsets " Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 09/17] midx: return success/failure in chunk write methods Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 10/17] midx: drop chunk progress during write Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 11/17] midx: use chunk-format API in write_midx_internal() Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 12/17] chunk-format: create read chunk API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 13/17] commit-graph: use chunk-format read API Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 14/17] midx: " Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 15/17] midx: use 64-bit multiplication for chunk sizes Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 16/17] chunk-format: restore duplicate chunk checks Derrick Stolee via GitGitGadget
2021-02-18 14:07       ` [PATCH v4 17/17] chunk-format: add technical docs Derrick Stolee via GitGitGadget
2021-02-18 21:47         ` Junio C Hamano
2021-02-19 12:42           ` Derrick Stolee

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=16c37d2370cf4fd5fc309ac6dc8aa6443ffcf3d7.1612535453.git.gitgitgadget@gmail.com \
    --to=gitgitgadget@gmail.com \
    --cc=chris.torek@gmail.com \
    --cc=derrickstolee@github.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=l.s.r@web.de \
    --cc=me@ttaylorr.com \
    --cc=stolee@gmail.com \
    --cc=szeder.dev@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).