git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / Atom feed
From: Derrick Stolee <stolee@gmail.com>
To: git@vger.kernel.org
Cc: sbeller@google.com, pclouds@gmail.com, avarab@gmail.com,
	Derrick Stolee <dstolee@microsoft.com>
Subject: [PATCH v2 09/24] multi-pack-index: read packfile list
Date: Mon, 25 Jun 2018 10:34:19 -0400
Message-ID: <20180625143434.89044-10-dstolee@microsoft.com> (raw)
In-Reply-To: <20180625143434.89044-1-dstolee@microsoft.com>

When constructing a multi-pack-index file for a given object directory,
read the files within the enclosed pack directory and find matches that
end with ".idx" and find the correct paired packfile using
add_packed_git().

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 midx.c                      | 45 ++++++++++++++++++++++++++++++++++++-
 t/t5319-multi-pack-index.sh | 16 ++++++-------
 2 files changed, 52 insertions(+), 9 deletions(-)

diff --git a/midx.c b/midx.c
index 0977397d6a..e79ffb5576 100644
--- a/midx.c
+++ b/midx.c
@@ -1,6 +1,8 @@
 #include "cache.h"
 #include "csum-file.h"
+#include "dir.h"
 #include "lockfile.h"
+#include "packfile.h"
 #include "object-store.h"
 #include "midx.h"
 
@@ -107,12 +109,40 @@ static size_t write_midx_header(struct hashfile *f,
 	return MIDX_HEADER_SIZE;
 }
 
+struct pack_list
+{
+	struct packed_git **list;
+	uint32_t nr;
+	uint32_t alloc;
+};
+
+static void add_pack_to_midx(const char *full_path, size_t full_path_len,
+			     const char *file_name, void *data)
+{
+	struct pack_list *packs = (struct pack_list *)data;
+
+	if (ends_with(file_name, ".idx")) {
+		ALLOC_GROW(packs->list, packs->nr + 1, packs->alloc);
+
+		packs->list[packs->nr] = add_packed_git(full_path,
+							 full_path_len,
+							 0);
+		if (!packs->list[packs->nr])
+			warning(_("failed to add packfile '%s'"),
+				full_path);
+		else
+			packs->nr++;
+	}
+}
+
 int write_midx_file(const char *object_dir)
 {
 	unsigned char num_chunks = 0;
 	char *midx_name;
+	uint32_t i;
 	struct hashfile *f;
 	struct lock_file lk;
+	struct pack_list packs;
 
 	midx_name = get_midx_filename(object_dir);
 	if (safe_create_leading_directories(midx_name)) {
@@ -121,14 +151,27 @@ int write_midx_file(const char *object_dir)
 			  midx_name);
 	}
 
+	packs.nr = 0;
+	packs.alloc = 16;
+	packs.list = NULL;
+	ALLOC_ARRAY(packs.list, packs.alloc);
+
+	for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
+
 	hold_lock_file_for_update(&lk, midx_name, LOCK_DIE_ON_ERROR);
 	f = hashfd(lk.tempfile->fd, lk.tempfile->filename.buf);
 	FREE_AND_NULL(midx_name);
 
-	write_midx_header(f, num_chunks, 0);
+	write_midx_header(f, num_chunks, packs.nr);
 
 	finalize_hashfile(f, NULL, CSUM_FSYNC | CSUM_HASH_IN_STREAM);
 	commit_lock_file(&lk);
 
+	for (i = 0; i < packs.nr; i++) {
+		close_pack(packs.list[i]);
+		FREE_AND_NULL(packs.list[i]);
+	}
+
+	FREE_AND_NULL(packs.list);
 	return 0;
 }
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index d533fd0dbc..4d4d6ca0a6 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -4,8 +4,9 @@ test_description='multi-pack-indexes'
 . ./test-lib.sh
 
 midx_read_expect() {
+	NUM_PACKS=$1
 	cat >expect <<- EOF
-	header: 4d494458 1 0 0
+	header: 4d494458 1 0 $NUM_PACKS
 	object_dir: .
 	EOF
 	test-tool read-midx . >actual &&
@@ -15,8 +16,7 @@ midx_read_expect() {
 test_expect_success 'write midx with no packs' '
 	test_when_finished rm pack/multi-pack-index &&
 	git multi-pack-index --object-dir=. write &&
-	test_path_is_file pack/multi-pack-index &&
-	midx_read_expect
+	midx_read_expect 0
 '
 
 test_expect_success 'create objects' '
@@ -47,13 +47,13 @@ test_expect_success 'write midx with one v1 pack' '
 	pack=$(git pack-objects --index-version=1 pack/test <obj-list) &&
 	test_when_finished rm pack/test-$pack.pack pack/test-$pack.idx pack/multi-pack-index &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect
+	midx_read_expect 1
 '
 
 test_expect_success 'write midx with one v2 pack' '
 	git pack-objects --index-version=2,0x40 pack/test <obj-list &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect
+	midx_read_expect 1
 '
 
 test_expect_success 'Add more objects' '
@@ -83,7 +83,7 @@ test_expect_success 'Add more objects' '
 test_expect_success 'write midx with two packs' '
 	git pack-objects --index-version=1 pack/test-2 <obj-list2 &&
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect
+	midx_read_expect 2
 '
 
 test_expect_success 'Add more packs' '
@@ -106,7 +106,7 @@ test_expect_success 'Add more packs' '
 		git ls-tree $tree | sed -e "s/.* \\([0-9a-f]*\\)	.*/\\1/"
 		} >obj-list &&
 		git update-ref HEAD $commit &&
-		git pack-objects --index-version=2 test-pack <obj-list &&
+		git pack-objects --index-version=2 pack/test-pack <obj-list &&
 		i=$(expr $i + 1) || return 1 &&
 		j=$(expr $j + 1) || return 1
 	done
@@ -114,7 +114,7 @@ test_expect_success 'Add more packs' '
 
 test_expect_success 'write midx with twelve packs' '
 	git multi-pack-index --object-dir=. write &&
-	midx_read_expect
+	midx_read_expect 12
 '
 
 test_done
-- 
2.18.0.24.g1b579a2ee9


  parent reply index

Thread overview: 192+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-07 14:03 [PATCH 00/23] Multi-pack-index (MIDX) Derrick Stolee
2018-06-07 14:03 ` [PATCH 01/23] midx: add design document Derrick Stolee
2018-06-11 19:04   ` Stefan Beller
2018-06-18 18:48     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 02/23] midx: add midx format details to pack-format.txt Derrick Stolee
2018-06-11 19:19   ` Stefan Beller
2018-06-18 19:01     ` Derrick Stolee
2018-06-18 19:41       ` Stefan Beller
2018-06-07 14:03 ` [PATCH 03/23] midx: add midx builtin Derrick Stolee
2018-06-07 17:20   ` Duy Nguyen
2018-06-18 19:23     ` Derrick Stolee
2018-06-11 21:02   ` Stefan Beller
2018-06-18 19:40     ` Derrick Stolee
2018-06-18 19:55       ` Stefan Beller
2018-06-18 19:58         ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 04/23] midx: add 'write' subcommand and basic wiring Derrick Stolee
2018-06-07 17:27   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 05/23] midx: write header information to lockfile Derrick Stolee
2018-06-07 17:35   ` Duy Nguyen
2018-06-12 15:00   ` Duy Nguyen
2018-06-19 12:54     ` Derrick Stolee
2018-06-19 14:59       ` Duy Nguyen
2018-06-19 15:24         ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 06/23] midx: struct midxed_git and 'read' subcommand Derrick Stolee
2018-06-07 17:54   ` Duy Nguyen
2018-06-20 13:13     ` Derrick Stolee
2018-06-07 18:31   ` Duy Nguyen
2018-06-20 13:33     ` Derrick Stolee
2018-06-20 15:07       ` Duy Nguyen
2018-06-20 16:39         ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 07/23] midx: expand test data Derrick Stolee
2018-06-07 14:03 ` [PATCH 08/23] midx: read packfiles from pack directory Derrick Stolee
2018-06-07 18:03   ` Duy Nguyen
2018-06-20 16:33     ` [PATCH] packfile: generalize pack directory list Derrick Stolee
2018-06-07 14:03 ` [PATCH 09/23] midx: write pack names in chunk Derrick Stolee
2018-06-07 18:26   ` Duy Nguyen
2018-06-21 15:25     ` Derrick Stolee
2018-06-21 17:38       ` Junio C Hamano
2018-06-22 18:25         ` Derrick Stolee
2018-06-22 18:31           ` Junio C Hamano
2018-06-22 18:32             ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 10/23] midx: write a lookup into the pack names chunk Derrick Stolee
2018-06-09 16:43   ` Duy Nguyen
2018-06-21 17:23     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 11/23] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-06-09 17:07   ` Duy Nguyen
2018-06-21 17:54     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 12/23] midx: write object ids in a chunk Derrick Stolee
2018-06-09 17:25   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 13/23] midx: write object id fanout chunk Derrick Stolee
2018-06-09 17:28   ` Duy Nguyen
2018-06-21 19:49     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 14/23] midx: write object offsets Derrick Stolee
2018-06-09 17:41   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 15/23] midx: create core.midx config setting Derrick Stolee
2018-06-07 14:03 ` [PATCH 16/23] midx: prepare midxed_git struct Derrick Stolee
2018-06-09 17:47   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 17/23] midx: read objects from multi-pack-index Derrick Stolee
2018-06-09 17:56   ` Duy Nguyen
2018-06-21 20:03     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 18/23] midx: use midx in abbreviation calculations Derrick Stolee
2018-06-09 18:01   ` Duy Nguyen
2018-06-22 18:38     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 19/23] midx: use existing midx when writing new one Derrick Stolee
2018-06-07 14:03 ` [PATCH 20/23] midx: use midx in approximate_object_count Derrick Stolee
2018-06-09 18:03   ` Duy Nguyen
2018-06-22 18:39     ` Derrick Stolee
2018-06-07 14:03 ` [PATCH 21/23] midx: prevent duplicate packfile loads Derrick Stolee
2018-06-09 18:05   ` Duy Nguyen
2018-06-07 14:03 ` [PATCH 22/23] midx: use midx to find ref-deltas Derrick Stolee
2018-06-07 14:03 ` [PATCH 23/23] midx: clear midx on repack Derrick Stolee
2018-06-09 18:13   ` Duy Nguyen
2018-06-22 18:44     ` Derrick Stolee
2018-06-07 14:06 ` [PATCH 00/23] Multi-pack-index (MIDX) Derrick Stolee
2018-06-07 14:45 ` Ævar Arnfjörð Bjarmason
2018-06-07 14:54   ` Derrick Stolee
2018-06-25 14:34 ` [PATCH v2 00/24] " Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 01/24] multi-pack-index: add design document Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 02/24] multi-pack-index: add format details Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 03/24] multi-pack-index: add builtin Derrick Stolee
2018-06-25 19:15     ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 04/24] multi-pack-index: add 'write' verb Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 05/24] midx: write header information to lockfile Derrick Stolee
2018-06-25 19:19     ` Junio C Hamano
2018-07-05 19:13       ` Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 06/24] multi-pack-index: load into memory Derrick Stolee
2018-06-25 19:38     ` Junio C Hamano
2018-07-05 14:19       ` Derrick Stolee
2018-07-05 18:58         ` Eric Sunshine
2018-07-06 19:20           ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 07/24] multi-pack-index: expand test data Derrick Stolee
2018-06-25 19:45     ` Junio C Hamano
2018-06-25 14:34   ` [PATCH v2 08/24] packfile: generalize pack directory list Derrick Stolee
2018-06-25 19:57     ` Junio C Hamano
2018-06-25 14:34   ` Derrick Stolee [this message]
2018-06-25 14:34   ` [PATCH v2 10/24] multi-pack-index: write pack names in chunk Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 11/24] midx: read pack names into array Derrick Stolee
2018-06-25 23:52     ` Eric Sunshine
2018-06-25 14:34   ` [PATCH v2 12/24] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 13/24] midx: write object ids in a chunk Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 14/24] midx: write object id fanout chunk Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 15/24] midx: write object offsets Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 16/24] config: create core.multiPackIndex setting Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 17/24] midx: prepare midxed_git struct Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 18/24] midx: read objects from multi-pack-index Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 19/24] midx: use midx in abbreviation calculations Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 20/24] midx: use existing midx when writing new one Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 21/24] midx: use midx in approximate_object_count Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 22/24] midx: prevent duplicate packfile loads Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 23/24] packfile: skip loading index if in multi-pack-index Derrick Stolee
2018-06-25 14:34   ` [PATCH v2 24/24] midx: clear midx on repack Derrick Stolee
2018-07-06  0:52   ` [PATCH v3 00/24] Multi-pack-index (MIDX) Derrick Stolee
2018-07-06  0:52     ` [PATCH v3 01/24] multi-pack-index: add design document Derrick Stolee
2018-07-06  0:52     ` [PATCH v3 02/24] multi-pack-index: add format details Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 03/24] multi-pack-index: add builtin Derrick Stolee
2018-07-06  3:54       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 04/24] multi-pack-index: add 'write' verb Derrick Stolee
2018-07-06  4:07       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 05/24] midx: write header information to lockfile Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 06/24] multi-pack-index: load into memory Derrick Stolee
2018-07-06  4:19       ` Eric Sunshine
2018-07-06  5:18         ` Eric Sunshine
2018-07-09 19:08       ` Junio C Hamano
2018-07-12 16:06         ` Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 07/24] multi-pack-index: expand test data Derrick Stolee
2018-07-06  4:36       ` Eric Sunshine
2018-07-06  5:20         ` Eric Sunshine
2018-07-12 14:10         ` Derrick Stolee
2018-07-12 18:02           ` Eric Sunshine
2018-07-12 18:06             ` Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 08/24] packfile: generalize pack directory list Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 09/24] multi-pack-index: read packfile list Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 10/24] multi-pack-index: write pack names in chunk Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 11/24] midx: read pack names into array Derrick Stolee
2018-07-06  4:58       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 12/24] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 13/24] midx: write object ids in a chunk Derrick Stolee
2018-07-06  5:04       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 14/24] midx: write object id fanout chunk Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 15/24] midx: write object offsets Derrick Stolee
2018-07-06  5:27       ` Eric Sunshine
2018-07-12 16:33         ` Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 16/24] config: create core.multiPackIndex setting Derrick Stolee
2018-07-06  5:39       ` Eric Sunshine
2018-07-12 13:19         ` Derrick Stolee
2018-07-12 16:30           ` Derrick Stolee
2018-07-11  9:48       ` SZEDER Gábor
2018-07-12 13:01         ` Derrick Stolee
2018-07-12 13:31           ` SZEDER Gábor
2018-07-12 15:40             ` Derrick Stolee
2018-07-12 17:29             ` Junio C Hamano
2018-07-06  0:53     ` [PATCH v3 17/24] midx: prepare midxed_git struct Derrick Stolee
2018-07-06  5:41       ` Eric Sunshine
2018-07-06  0:53     ` [PATCH v3 18/24] midx: read objects from multi-pack-index Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 19/24] midx: use midx in abbreviation calculations Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 20/24] midx: use existing midx when writing new one Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 21/24] midx: use midx in approximate_object_count Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 22/24] midx: prevent duplicate packfile loads Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 23/24] packfile: skip loading index if in multi-pack-index Derrick Stolee
2018-07-06  0:53     ` [PATCH v3 24/24] midx: clear midx on repack Derrick Stolee
2018-07-06  5:52       ` Eric Sunshine
2018-07-12 19:39     ` [PATCH v4 00/23] Multi-pack-index (MIDX) Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 01/23] multi-pack-index: add design document Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 02/23] multi-pack-index: add format details Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 03/23] multi-pack-index: add builtin Derrick Stolee
2018-07-20 18:22         ` Junio C Hamano
2018-07-20 22:15           ` brian m. carlson
2018-07-20 22:28             ` Junio C Hamano
2018-07-12 19:39       ` [PATCH v4 04/23] multi-pack-index: add 'write' verb Derrick Stolee
2018-07-12 22:56         ` Eric Sunshine
2018-07-12 19:39       ` [PATCH v4 05/23] midx: write header information to lockfile Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 06/23] multi-pack-index: load into memory Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 07/23] t5319: expand test data Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 08/23] packfile: generalize pack directory list Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 09/23] multi-pack-index: read packfile list Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 10/23] multi-pack-index: write pack names in chunk Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 11/23] midx: read pack names into array Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 12/23] midx: sort and deduplicate objects from packfiles Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 13/23] midx: write object ids in a chunk Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 14/23] midx: write object id fanout chunk Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 15/23] midx: write object offsets Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 16/23] config: create core.multiPackIndex setting Derrick Stolee
2018-07-12 21:05         ` Junio C Hamano
2018-07-13  0:50           ` Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 17/23] midx: read objects from multi-pack-index Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 18/23] midx: use midx in abbreviation calculations Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 19/23] midx: use existing midx when writing new one Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 20/23] midx: use midx in approximate_object_count Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 21/23] midx: prevent duplicate packfile loads Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 22/23] packfile: skip loading index if in multi-pack-index Derrick Stolee
2018-07-12 19:39       ` [PATCH v4 23/23] midx: clear midx on repack Derrick Stolee
2018-07-12 21:11       ` [PATCH v4 00/23] Multi-pack-index (MIDX) Junio C Hamano

Reply instructions:

You may reply publically 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=20180625143434.89044-10-dstolee@microsoft.com \
    --to=stolee@gmail.com \
    --cc=avarab@gmail.com \
    --cc=dstolee@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=pclouds@gmail.com \
    --cc=sbeller@google.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

git@vger.kernel.org list mirror (unofficial, one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox