git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Taylor Blau <me@ttaylorr.com>
To: git@vger.kernel.org
Cc: Jeff King <peff@peff.net>, Patrick Steinhardt <ps@pks.im>,
	Junio C Hamano <gitster@pobox.com>
Subject: [PATCH v2 13/26] pack-objects: pass `bitmapped_pack`'s to pack-reuse functions
Date: Thu, 14 Dec 2023 17:24:12 -0500	[thread overview]
Message-ID: <5492d11f25ec54c8eff59e3fa266abd766a1f40c.1702592604.git.me@ttaylorr.com> (raw)
In-Reply-To: <cover.1702592603.git.me@ttaylorr.com>

Further prepare pack-objects to perform verbatim pack-reuse over
multiple packfiles by converting functions that take in a pointer to a
`struct packed_git` to instead take in a pointer to a `struct
bitmapped_pack`.

The additional information found in the bitmapped_pack struct (such as
the bit position corresponding to the beginning of the pack) will be
necessary in order to perform verbatim pack-reuse.

Note that we don't use any of the extra pieces of information contained
in the bitmapped_pack struct, so this step is merely preparatory and
does not introduce any functional changes.

Note further that we do not change the argument type to
write_reused_pack_one(). That function is responsible for copying
sections of the packfile directly and optionally patching any OFS_DELTAs
to account for not reusing sections of the packfile in between a delta
and its base.

As such, that function is (and should remain) oblivious to multi-pack
reuse, and does not require any of the extra pieces of information
stored in the bitmapped_pack struct.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 builtin/pack-objects.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index f51b86d99f..07c849b5d4 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -221,7 +221,8 @@ static int thin;
 static int num_preferred_base;
 static struct progress *progress_state;
 
-static struct packed_git *reuse_packfile;
+static struct bitmapped_pack *reuse_packfiles;
+static size_t reuse_packfiles_nr;
 static uint32_t reuse_packfile_objects;
 static struct bitmap *reuse_packfile_bitmap;
 
@@ -1094,7 +1095,7 @@ static void write_reused_pack_one(struct packed_git *reuse_packfile,
 	copy_pack_data(out, reuse_packfile, w_curs, offset, next - offset);
 }
 
-static size_t write_reused_pack_verbatim(struct packed_git *reuse_packfile,
+static size_t write_reused_pack_verbatim(struct bitmapped_pack *reuse_packfile,
 					 struct hashfile *out,
 					 off_t pack_start UNUSED,
 					 struct pack_window **w_curs)
@@ -1109,13 +1110,13 @@ static size_t write_reused_pack_verbatim(struct packed_git *reuse_packfile,
 		off_t to_write;
 
 		written = (pos * BITS_IN_EWORD);
-		to_write = pack_pos_to_offset(reuse_packfile, written)
+		to_write = pack_pos_to_offset(reuse_packfile->p, written)
 			- sizeof(struct pack_header);
 
 		/* We're recording one chunk, not one object. */
 		record_reused_object(sizeof(struct pack_header), 0);
 		hashflush(out);
-		copy_pack_data(out, reuse_packfile, w_curs,
+		copy_pack_data(out, reuse_packfile->p, w_curs,
 			sizeof(struct pack_header), to_write);
 
 		display_progress(progress_state, written);
@@ -1123,7 +1124,7 @@ static size_t write_reused_pack_verbatim(struct packed_git *reuse_packfile,
 	return pos;
 }
 
-static void write_reused_pack(struct packed_git *reuse_packfile,
+static void write_reused_pack(struct bitmapped_pack *reuse_packfile,
 			      struct hashfile *f)
 {
 	size_t i = 0;
@@ -1149,8 +1150,8 @@ static void write_reused_pack(struct packed_git *reuse_packfile,
 			 * bitmaps. See comment in try_partial_reuse()
 			 * for why.
 			 */
-			write_reused_pack_one(reuse_packfile, pos + offset, f,
-					      pack_start, &w_curs);
+			write_reused_pack_one(reuse_packfile->p, pos + offset,
+					      f, pack_start, &w_curs);
 			display_progress(progress_state, ++written);
 		}
 	}
@@ -1206,9 +1207,12 @@ static void write_pack_file(void)
 
 		offset = write_pack_header(f, nr_remaining);
 
-		if (reuse_packfile) {
+		if (reuse_packfiles_nr) {
 			assert(pack_to_stdout);
-			write_reused_pack(reuse_packfile, f);
+			for (j = 0; j < reuse_packfiles_nr; j++) {
+				reused_chunks_nr = 0;
+				write_reused_pack(&reuse_packfiles[j], f);
+			}
 			offset = hashfile_total(f);
 		}
 
@@ -3949,19 +3953,16 @@ static int pack_options_allow_reuse(void)
 
 static int get_object_list_from_bitmap(struct rev_info *revs)
 {
-	struct bitmapped_pack *packs = NULL;
-	size_t packs_nr = 0;
-
 	if (!(bitmap_git = prepare_bitmap_walk(revs, 0)))
 		return -1;
 
 	if (pack_options_allow_reuse())
-		reuse_partial_packfile_from_bitmap(bitmap_git, &packs,
-						   &packs_nr,
+		reuse_partial_packfile_from_bitmap(bitmap_git,
+						   &reuse_packfiles,
+						   &reuse_packfiles_nr,
 						   &reuse_packfile_bitmap);
 
-	if (packs) {
-		reuse_packfile = packs[0].p;
+	if (reuse_packfiles) {
 		reuse_packfile_objects = bitmap_popcount(reuse_packfile_bitmap);
 		if (!reuse_packfile_objects)
 			BUG("expected non-empty reuse bitmap");
-- 
2.43.0.102.ga31d690331.dirty


  parent reply	other threads:[~2023-12-14 22:24 UTC|newest]

Thread overview: 107+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-11-28 19:07 [PATCH 00/24] pack-objects: multi-pack verbatim reuse Taylor Blau
2023-11-28 19:07 ` [PATCH 01/24] pack-objects: free packing_data in more places Taylor Blau
2023-11-30 10:18   ` Patrick Steinhardt
2023-11-30 19:08     ` Taylor Blau
2023-11-28 19:07 ` [PATCH 02/24] pack-bitmap-write: deep-clear the `bb_commit` slab Taylor Blau
2023-11-30 10:18   ` Patrick Steinhardt
2023-11-30 19:11     ` Taylor Blau
2023-12-12  7:04   ` Jeff King
2023-12-12 16:48     ` Taylor Blau
2023-11-28 19:08 ` [PATCH 03/24] pack-bitmap: plug leak in find_objects() Taylor Blau
2023-12-12  7:04   ` Jeff King
2023-11-28 19:08 ` [PATCH 04/24] midx: factor out `fill_pack_info()` Taylor Blau
2023-11-30 10:18   ` Patrick Steinhardt
2023-11-30 19:19     ` Taylor Blau
2023-11-28 19:08 ` [PATCH 05/24] midx: implement `DISP` chunk Taylor Blau
2023-11-30 10:18   ` Patrick Steinhardt
2023-11-30 19:27     ` Taylor Blau
2023-12-03 13:15   ` Junio C Hamano
2023-12-05 19:26     ` Taylor Blau
2023-12-09  1:40       ` Junio C Hamano
2023-12-09  2:30         ` Taylor Blau
2023-12-12  8:03           ` Jeff King
2023-12-13 18:28             ` Taylor Blau
2023-12-13 19:20               ` Junio C Hamano
2023-11-28 19:08 ` [PATCH 06/24] midx: implement `midx_locate_pack()` Taylor Blau
2023-11-28 19:08 ` [PATCH 07/24] midx: implement `--retain-disjoint` mode Taylor Blau
2023-11-30 10:18   ` Patrick Steinhardt
2023-11-30 19:29     ` Taylor Blau
2023-12-01  8:02       ` Patrick Steinhardt
2023-11-28 19:08 ` [PATCH 08/24] pack-objects: implement `--ignore-disjoint` mode Taylor Blau
2023-11-30 10:18   ` Patrick Steinhardt
2023-11-30 19:32     ` Taylor Blau
2023-12-01  8:17       ` Patrick Steinhardt
2023-12-01 19:58         ` Taylor Blau
2023-11-28 19:08 ` [PATCH 09/24] repack: implement `--extend-disjoint` mode Taylor Blau
2023-12-07 13:13   ` Patrick Steinhardt
2023-12-07 20:28     ` Taylor Blau
2023-12-08  8:19       ` Patrick Steinhardt
2023-12-08 22:48         ` Taylor Blau
2023-12-11  8:18           ` Patrick Steinhardt
2023-12-11 19:59             ` Taylor Blau
2023-11-28 19:08 ` [PATCH 10/24] pack-bitmap: pass `bitmapped_pack` struct to pack-reuse functions Taylor Blau
2023-12-07 13:13   ` Patrick Steinhardt
2023-12-07 20:34     ` Taylor Blau
2023-12-08  8:19       ` Patrick Steinhardt
2023-11-28 19:08 ` [PATCH 11/24] pack-bitmap: simplify `reuse_partial_packfile_from_bitmap()` signature Taylor Blau
2023-12-07 13:13   ` Patrick Steinhardt
2023-12-07 14:36     ` Taylor Blau
2023-11-28 19:08 ` [PATCH 12/24] pack-bitmap: return multiple packs via `reuse_partial_packfile_from_bitmap()` Taylor Blau
2023-11-28 19:08 ` [PATCH 13/24] pack-objects: parameterize pack-reuse routines over a single pack Taylor Blau
2023-11-28 19:08 ` [PATCH 14/24] pack-objects: keep track of `pack_start` for each reuse pack Taylor Blau
2023-12-07 13:13   ` Patrick Steinhardt
2023-12-07 20:43     ` Taylor Blau
2023-11-28 19:08 ` [PATCH 15/24] pack-objects: pass `bitmapped_pack`'s to pack-reuse functions Taylor Blau
2023-11-28 19:08 ` [PATCH 16/24] pack-objects: prepare `write_reused_pack()` for multi-pack reuse Taylor Blau
2023-12-07 13:13   ` Patrick Steinhardt
2023-12-07 20:47     ` Taylor Blau
2023-11-28 19:08 ` [PATCH 17/24] pack-objects: prepare `write_reused_pack_verbatim()` " Taylor Blau
2023-11-28 19:08 ` [PATCH 18/24] pack-objects: include number of packs reused in output Taylor Blau
2023-11-28 19:08 ` [PATCH 19/24] pack-bitmap: prepare to mark objects from multiple packs for reuse Taylor Blau
2023-11-28 19:08 ` [PATCH 20/24] pack-objects: add tracing for various packfile metrics Taylor Blau
2023-11-28 19:08 ` [PATCH 21/24] t/test-lib-functions.sh: implement `test_trace2_data` helper Taylor Blau
2023-11-28 19:08 ` [PATCH 22/24] pack-objects: allow setting `pack.allowPackReuse` to "single" Taylor Blau
2023-11-28 19:08 ` [PATCH 23/24] pack-bitmap: reuse objects from all disjoint packs Taylor Blau
2023-11-28 19:08 ` [PATCH 24/24] t/perf: add performance tests for multi-pack reuse Taylor Blau
2023-11-30 10:18 ` [PATCH 00/24] pack-objects: multi-pack verbatim reuse Patrick Steinhardt
2023-11-30 19:39   ` Taylor Blau
2023-12-01  8:31     ` Patrick Steinhardt
2023-12-01 20:02       ` Taylor Blau
2023-12-04  8:49         ` Patrick Steinhardt
2023-12-12  8:12 ` Jeff King
2023-12-15 15:37   ` Taylor Blau
2023-12-21 11:13     ` Jeff King
2024-01-04 22:22       ` Taylor Blau
2023-12-14 22:23 ` [PATCH v2 00/26] " Taylor Blau
2023-12-14 22:23   ` [PATCH v2 01/26] pack-objects: free packing_data in more places Taylor Blau
2023-12-14 22:23   ` [PATCH v2 02/26] pack-bitmap-write: deep-clear the `bb_commit` slab Taylor Blau
2023-12-14 22:23   ` [PATCH v2 03/26] pack-bitmap: plug leak in find_objects() Taylor Blau
2023-12-14 22:23   ` [PATCH v2 04/26] midx: factor out `fill_pack_info()` Taylor Blau
2023-12-14 22:23   ` [PATCH v2 05/26] midx: implement `BTMP` chunk Taylor Blau
2023-12-14 22:23   ` [PATCH v2 06/26] midx: implement `midx_locate_pack()` Taylor Blau
2023-12-14 22:23   ` [PATCH v2 07/26] pack-bitmap: pass `bitmapped_pack` struct to pack-reuse functions Taylor Blau
2023-12-14 22:23   ` [PATCH v2 08/26] ewah: implement `bitmap_is_empty()` Taylor Blau
2023-12-14 22:24   ` [PATCH v2 09/26] pack-bitmap: simplify `reuse_partial_packfile_from_bitmap()` signature Taylor Blau
2023-12-14 22:24   ` [PATCH v2 10/26] pack-bitmap: return multiple packs via `reuse_partial_packfile_from_bitmap()` Taylor Blau
2023-12-14 22:24   ` [PATCH v2 11/26] pack-objects: parameterize pack-reuse routines over a single pack Taylor Blau
2023-12-14 22:24   ` [PATCH v2 12/26] pack-objects: keep track of `pack_start` for each reuse pack Taylor Blau
2023-12-14 22:24   ` Taylor Blau [this message]
2023-12-14 22:24   ` [PATCH v2 14/26] pack-objects: prepare `write_reused_pack()` for multi-pack reuse Taylor Blau
2023-12-14 22:24   ` [PATCH v2 15/26] pack-objects: prepare `write_reused_pack_verbatim()` " Taylor Blau
2023-12-14 22:24   ` [PATCH v2 16/26] pack-objects: include number of packs reused in output Taylor Blau
2023-12-14 22:24   ` [PATCH v2 17/26] git-compat-util.h: implement checked size_t to uint32_t conversion Taylor Blau
2023-12-14 22:24   ` [PATCH v2 18/26] midx: implement `midx_preferred_pack()` Taylor Blau
2023-12-14 22:24   ` [PATCH v2 19/26] pack-revindex: factor out `midx_key_to_pack_pos()` helper Taylor Blau
2023-12-14 22:24   ` [PATCH v2 20/26] pack-revindex: implement `midx_pair_to_pack_pos()` Taylor Blau
2023-12-14 22:24   ` [PATCH v2 21/26] pack-bitmap: prepare to mark objects from multiple packs for reuse Taylor Blau
2023-12-14 22:24   ` [PATCH v2 22/26] pack-objects: add tracing for various packfile metrics Taylor Blau
2023-12-14 22:24   ` [PATCH v2 23/26] t/test-lib-functions.sh: implement `test_trace2_data` helper Taylor Blau
2023-12-14 22:24   ` [PATCH v2 24/26] pack-objects: allow setting `pack.allowPackReuse` to "single" Taylor Blau
2023-12-14 22:24   ` [PATCH v2 25/26] pack-bitmap: enable reuse from all bitmapped packs Taylor Blau
2023-12-14 22:24   ` [PATCH v2 26/26] t/perf: add performance tests for multi-pack reuse Taylor Blau
2023-12-15  0:06   ` [PATCH v2 00/26] pack-objects: multi-pack verbatim reuse Junio C Hamano
2023-12-15  0:38     ` Taylor Blau
2023-12-15  0:40     ` Junio C Hamano
2023-12-15  1:25       ` Taylor Blau
2023-12-21 10:51         ` Jeff King
2024-01-04 22:24           ` Taylor Blau

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=5492d11f25ec54c8eff59e3fa266abd766a1f40c.1702592604.git.me@ttaylorr.com \
    --to=me@ttaylorr.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.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).