git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Taylor Blau <me@ttaylorr.com>
To: git@vger.kernel.org
Cc: Elijah Newren <newren@gmail.com>,
	"Eric W. Biederman" <ebiederm@gmail.com>,
	Jeff King <peff@peff.net>, Junio C Hamano <gitster@pobox.com>,
	Patrick Steinhardt <ps@pks.im>
Subject: [PATCH v5 2/5] bulk-checkin: generify `stream_blob_to_pack()` for arbitrary types
Date: Mon, 23 Oct 2023 18:44:59 -0400	[thread overview]
Message-ID: <596bd028a74f45c8f7ecf46dc5eb25f45ff5f523.1698101088.git.me@ttaylorr.com> (raw)
In-Reply-To: <cover.1698101088.git.me@ttaylorr.com>

The existing `stream_blob_to_pack()` function is named based on the fact
that it knows only how to stream blobs into a bulk-checkin pack.

But there is no longer anything in this function which prevents us from
writing objects of arbitrary types to the bulk-checkin pack. Prepare to
write OBJ_TREEs by removing this assumption, adding an `enum
object_type` parameter to this function's argument list, and renaming it
to `stream_obj_to_pack()` accordingly.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 bulk-checkin.c | 61 +++++++++++++++++++++++++++++---------------------
 1 file changed, 36 insertions(+), 25 deletions(-)

diff --git a/bulk-checkin.c b/bulk-checkin.c
index 174a6c24e4..79776e679e 100644
--- a/bulk-checkin.c
+++ b/bulk-checkin.c
@@ -196,10 +196,10 @@ static void init_bulk_checkin_source_from_fd(struct bulk_checkin_source *source,
  * status before calling us just in case we ask it to call us again
  * with a new pack.
  */
-static int stream_blob_to_pack(struct bulk_checkin_packfile *state,
-			       git_hash_ctx *ctx, off_t *already_hashed_to,
-			       struct bulk_checkin_source *source,
-			       unsigned flags)
+static int stream_obj_to_pack(struct bulk_checkin_packfile *state,
+			      git_hash_ctx *ctx, off_t *already_hashed_to,
+			      struct bulk_checkin_source *source,
+			      enum object_type type, unsigned flags)
 {
 	git_zstream s;
 	unsigned char ibuf[16384];
@@ -212,8 +212,7 @@ static int stream_blob_to_pack(struct bulk_checkin_packfile *state,
 
 	git_deflate_init(&s, pack_compression_level);
 
-	hdrlen = encode_in_pack_object_header(obuf, sizeof(obuf), OBJ_BLOB,
-					      size);
+	hdrlen = encode_in_pack_object_header(obuf, sizeof(obuf), type, size);
 	s.next_out = obuf + hdrlen;
 	s.avail_out = sizeof(obuf) - hdrlen;
 
@@ -293,27 +292,23 @@ static void prepare_to_stream(struct bulk_checkin_packfile *state,
 		die_errno("unable to write pack header");
 }
 
-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)
+
+static int deflate_obj_to_pack(struct bulk_checkin_packfile *state,
+			       struct object_id *result_oid,
+			       struct bulk_checkin_source *source,
+			       enum object_type type,
+			       off_t seekback,
+			       unsigned flags)
 {
-	off_t seekback, already_hashed_to;
+	off_t already_hashed_to = 0;
 	git_hash_ctx ctx;
 	unsigned char obuf[16384];
 	unsigned header_len;
 	struct hashfile_checkpoint checkpoint = {0};
 	struct pack_idx_entry *idx = NULL;
-	struct bulk_checkin_source source;
 
-	init_bulk_checkin_source_from_fd(&source, fd, size, path);
-
-	seekback = lseek(fd, 0, SEEK_CUR);
-	if (seekback == (off_t) -1)
-		return error("cannot find the current offset");
-
-	header_len = format_object_header((char *)obuf, sizeof(obuf),
-					  OBJ_BLOB, size);
+	header_len = format_object_header((char *)obuf, sizeof(obuf), type,
+					  source->size);
 	the_hash_algo->init_fn(&ctx);
 	the_hash_algo->update_fn(&ctx, obuf, header_len);
 	the_hash_algo->init_fn(&checkpoint.ctx);
@@ -322,8 +317,6 @@ static int deflate_blob_to_pack(struct bulk_checkin_packfile *state,
 	if ((flags & HASH_WRITE_OBJECT) != 0)
 		CALLOC_ARRAY(idx, 1);
 
-	already_hashed_to = 0;
-
 	while (1) {
 		prepare_to_stream(state, flags);
 		if (idx) {
@@ -331,8 +324,8 @@ static int deflate_blob_to_pack(struct bulk_checkin_packfile *state,
 			idx->offset = state->offset;
 			crc32_begin(state->f);
 		}
-		if (!stream_blob_to_pack(state, &ctx, &already_hashed_to,
-					 &source, flags))
+		if (!stream_obj_to_pack(state, &ctx, &already_hashed_to,
+					source, type, flags))
 			break;
 		/*
 		 * Writing this object to the current pack will make
@@ -344,7 +337,7 @@ static int deflate_blob_to_pack(struct bulk_checkin_packfile *state,
 		hashfile_truncate(state->f, &checkpoint);
 		state->offset = checkpoint.offset;
 		flush_bulk_checkin_packfile(state);
-		if (source.seek(&source, seekback) == (off_t)-1)
+		if (source->seek(source, seekback) == (off_t)-1)
 			return error("cannot seek back");
 	}
 	the_hash_algo->final_oid_fn(result_oid, &ctx);
@@ -366,6 +359,24 @@ static int deflate_blob_to_pack(struct bulk_checkin_packfile *state,
 	return 0;
 }
 
+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)
+{
+	struct bulk_checkin_source source;
+	off_t seekback;
+
+	init_bulk_checkin_source_from_fd(&source, fd, size, path);
+
+	seekback = lseek(fd, 0, SEEK_CUR);
+	if (seekback == (off_t) -1)
+		return error("cannot find the current offset");
+
+	return deflate_obj_to_pack(state, result_oid, &source, OBJ_BLOB,
+				   seekback, flags);
+}
+
 void prepare_loose_object_bulk_checkin(void)
 {
 	/*
-- 
2.42.0.425.g963d08ddb3.dirty


  parent reply	other threads:[~2023-10-23 22:45 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-19 17:28 [PATCH v4 0/7] merge-ort: implement support for packing objects together Taylor Blau
2023-10-19 17:28 ` [PATCH v4 1/7] bulk-checkin: extract abstract `bulk_checkin_source` Taylor Blau
2023-10-20  7:35   ` Jeff King
2023-10-20 16:55     ` Junio C Hamano
2023-10-19 17:28 ` [PATCH v4 2/7] bulk-checkin: generify `stream_blob_to_pack()` for arbitrary types Taylor Blau
2023-10-19 17:28 ` [PATCH v4 3/7] bulk-checkin: refactor deflate routine to accept a `bulk_checkin_source` Taylor Blau
2023-10-19 17:28 ` [PATCH v4 4/7] bulk-checkin: implement `SOURCE_INCORE` mode for `bulk_checkin_source` Taylor Blau
2023-10-23  9:19   ` Patrick Steinhardt
2023-10-23 18:58     ` Jeff King
2023-10-24  6:34       ` Patrick Steinhardt
2023-10-24 17:08         ` Junio C Hamano
2023-10-19 17:28 ` [PATCH v4 5/7] bulk-checkin: introduce `index_blob_bulk_checkin_incore()` Taylor Blau
2023-10-19 17:28 ` [PATCH v4 6/7] bulk-checkin: introduce `index_tree_bulk_checkin_incore()` Taylor Blau
2023-10-19 17:29 ` [PATCH v4 7/7] builtin/merge-tree.c: implement support for `--write-pack` Taylor Blau
2023-10-19 21:47 ` [PATCH v4 0/7] merge-ort: implement support for packing objects together Junio C Hamano
2023-10-20  7:29 ` Jeff King
2023-10-20 16:53   ` Junio C Hamano
2023-10-23  9:19 ` Patrick Steinhardt
2023-10-23 22:44 ` [PATCH v5 0/5] " Taylor Blau
2023-10-23 22:44   ` [PATCH v5 1/5] bulk-checkin: extract abstract `bulk_checkin_source` Taylor Blau
2023-10-25  7:37     ` Jeff King
2023-10-25 15:39       ` Taylor Blau
2023-10-27 23:12       ` Junio C Hamano
2023-10-23 22:44   ` Taylor Blau [this message]
2023-10-23 22:45   ` [PATCH v5 3/5] bulk-checkin: introduce `index_blob_bulk_checkin_incore()` Taylor Blau
2023-10-25  7:58     ` Patrick Steinhardt
2023-10-25 15:44       ` Taylor Blau
2023-10-25 17:21         ` Eric Sunshine
2023-10-26  8:16           ` Patrick Steinhardt
2023-11-11  0:17           ` Elijah Newren
2023-10-23 22:45   ` [PATCH v5 4/5] bulk-checkin: introduce `index_tree_bulk_checkin_incore()` Taylor Blau
2023-10-23 22:45   ` [PATCH v5 5/5] builtin/merge-tree.c: implement support for `--write-pack` Taylor Blau
2023-10-25  7:58     ` Patrick Steinhardt
2023-10-25 15:46       ` Taylor Blau
2023-11-10 23:51     ` Elijah Newren
2023-11-11  0:27       ` Junio C Hamano
2023-11-11  1:34         ` Taylor Blau
2023-11-11  1:24       ` Taylor Blau
2023-11-13 22:05         ` Jeff King
2023-11-14  1:40           ` Junio C Hamano
2023-11-14  2:54             ` Elijah Newren
2023-11-14 21:55             ` Jeff King
2023-11-14  3:08           ` Elijah Newren
2023-11-13 22:02       ` Jeff King
2023-11-13 22:34         ` Taylor Blau
2023-11-14  2:50           ` Elijah Newren
2023-11-14 21:53             ` Jeff King
2023-11-14 22:04           ` Jeff King
2023-10-23 23:31   ` [PATCH v5 0/5] merge-ort: implement support for packing objects together Junio C Hamano
2023-11-06 15:46     ` Johannes Schindelin
2023-11-06 23:19       ` Junio C Hamano
2023-11-07  3:42       ` Jeff King
2023-11-07 15:58       ` Taylor Blau
2023-11-07 18:22         ` [RFC PATCH 0/3] replay: implement support for writing new objects to a pack Taylor Blau
2023-11-07 18:22           ` [RFC PATCH 1/3] merge-ort.c: finalize ODB transactions after each step Taylor Blau
2023-11-11  3:45             ` Elijah Newren
2023-11-07 18:22           ` [RFC PATCH 2/3] tmp-objdir: introduce `tmp_objdir_repack()` Taylor Blau
2023-11-08  7:05             ` Patrick Steinhardt
2023-11-09 19:26               ` Taylor Blau
2023-11-07 18:23           ` [RFC PATCH 3/3] builtin/replay.c: introduce `--write-pack` Taylor Blau
2023-11-11  3:42           ` [RFC PATCH 0/3] replay: implement support for writing new objects to a pack Elijah Newren
2023-11-11  4:04           ` Elijah Newren
2023-10-25  7:58   ` [PATCH v5 0/5] merge-ort: implement support for packing objects together Patrick Steinhardt

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

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

  git send-email \
    --in-reply-to=596bd028a74f45c8f7ecf46dc5eb25f45ff5f523.1698101088.git.me@ttaylorr.com \
    --to=me@ttaylorr.com \
    --cc=ebiederm@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=newren@gmail.com \
    --cc=peff@peff.net \
    --cc=ps@pks.im \
    /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.
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 NNTP newsgroup(s).