Midx/upstream

.gitignore

@@ -99,8 +99,9 @@
 /git-mergetool--lib
 /git-mktag
 /git-mktree
-/git-name-rev
+/git-multi-pack-index
 /git-mv
+/git-name-rev
 /git-notes
 /git-p4
 /git-pack-redundant

Documentation/config.txt

@@ -908,6 +908,11 @@ core.commitGraph::
 	Enable git commit graph feature. Allows reading from the
 	commit-graph file.
 
+core.multiPackIndex::
+	Use the multi-pack-index file to track multiple packfiles using a
+	single index. See link:technical/multi-pack-index.html[the
+	multi-pack-index design document].
+
 core.sparseCheckout::
 	Enable "sparse checkout" feature. See section "Sparse checkout" in
 	linkgit:git-read-tree[1] for more information.

Documentation/git-multi-pack-index.txt

@@ -0,0 +1,56 @@
+git-multi-pack-index(1)
+======================
+
+NAME
+----
+git-multi-pack-index - Write and verify multi-pack-indexes
+
+
+SYNOPSIS
+--------
+[verse]
+'git multi-pack-index' [--object-dir=<dir>] <verb>
+
+DESCRIPTION
+-----------
+Write or verify a multi-pack-index (MIDX) file.
+
+OPTIONS
+-------
+
+--object-dir=<dir>::
+	Use given directory for the location of Git objects. We check
+	`<dir>/packs/multi-pack-index` for the current MIDX file, and
+	`<dir>/packs` for the pack-files to index.
+
+write::
+	When given as the verb, write a new MIDX file to
+	`<dir>/packs/multi-pack-index`.
+
+
+EXAMPLES
+--------
+
+* Write a MIDX file for the packfiles in the current .git folder.
++
+-----------------------------------------------
+$ git multi-pack-index write
+-----------------------------------------------
+
+* Write a MIDX file for the packfiles in an alternate object store.
++
+-----------------------------------------------
+$ git multi-pack-index --object-dir <alt> write
+-----------------------------------------------
+
+
+SEE ALSO
+--------
+See link:technical/multi-pack-index.html[The Multi-Pack-Index Design
+Document] and link:technical/pack-format.html[The Multi-Pack-Index
+Format] for more information on the multi-pack-index feature.
+
+
+GIT
+---
+Part of the linkgit:git[1] suite

Documentation/technical/multi-pack-index.txt

@@ -0,0 +1,109 @@
+Multi-Pack-Index (MIDX) Design Notes
+====================================
+
+The Git object directory contains a 'pack' directory containing
+packfiles (with suffix ".pack") and pack-indexes (with suffix
+".idx"). The pack-indexes provide a way to lookup objects and
+navigate to their offset within the pack, but these must come
+in pairs with the packfiles. This pairing depends on the file
+names, as the pack-index differs only in suffix with its pack-
+file. While the pack-indexes provide fast lookup per packfile,
+this performance degrades as the number of packfiles increases,
+because abbreviations need to inspect every packfile and we are
+more likely to have a miss on our most-recently-used packfile.
+For some large repositories, repacking into a single packfile
+is not feasible due to storage space or excessive repack times.
+
+The multi-pack-index (MIDX for short) stores a list of objects
+and their offsets into multiple packfiles. It contains:
+
+- A list of packfile names.
+- A sorted list of object IDs.
+- A list of metadata for the ith object ID including:
+  - A value j referring to the jth packfile.
+  - An offset within the jth packfile for the object.
+- If large offsets are required, we use another list of large
+  offsets similar to version 2 pack-indexes.
+
+Thus, we can provide O(log N) lookup time for any number
+of packfiles.
+
+Design Details
+--------------
+
+- The MIDX is stored in a file named 'multi-pack-index' in the
+  .git/objects/pack directory. This could be stored in the pack
+  directory of an alternate. It refers only to packfiles in that
+  same directory.
+
+- The pack.multiIndex config setting must be on to consume MIDX files.
+
+- The file format includes parameters for the object ID hash
+  function, so a future change of hash algorithm does not require
+  a change in format.
+
+- The MIDX keeps only one record per object ID. If an object appears
+  in multiple packfiles, then the MIDX selects the copy in the most-
+  recently modified packfile.
+
+- If there exist packfiles in the pack directory not registered in
+  the MIDX, then those packfiles are loaded into the `packed_git`
+  list and `packed_git_mru` cache.
+
+- The pack-indexes (.idx files) remain in the pack directory so we
+  can delete the MIDX file, set core.midx to false, or downgrade
+  without any loss of information.
+
+- The MIDX file format uses a chunk-based approach (similar to the
+  commit-graph file) that allows optional data to be added.
+
+Future Work
+-----------
+
+- Add a 'verify' subcommand to the 'git midx' builtin to verify the
+  contents of the multi-pack-index file match the offsets listed in
+  the corresponding pack-indexes.
+
+- The multi-pack-index allows many packfiles, especially in a context
+  where repacking is expensive (such as a very large repo), or
+  unexpected maintenance time is unacceptable (such as a high-demand
+  build machine). However, the multi-pack-index needs to be rewritten
+  in full every time. We can extend the format to be incremental, so
+  writes are fast. By storing a small "tip" multi-pack-index that
+  points to large "base" MIDX files, we can keep writes fast while
+  still reducing the number of binary searches required for object
+  lookups.
+
+- The reachability bitmap is currently paired directly with a single
+  packfile, using the pack-order as the object order to hopefully
+  compress the bitmaps well using run-length encoding. This could be
+  extended to pair a reachability bitmap with a multi-pack-index. If
+  the multi-pack-index is extended to store a "stable object order"
+  (a function Order(hash) = integer that is constant for a given hash,
+  even as the multi-pack-index is updated) then a reachability bitmap
+  could point to a multi-pack-index and be updated independently.
+
+- Packfiles can be marked as "special" using empty files that share
+  the initial name but replace ".pack" with ".keep" or ".promisor".
+  We can add an optional chunk of data to the multi-pack-index that
+  records flags of information about the packfiles. This allows new
+  states, such as 'repacked' or 'redeltified', that can help with
+  pack maintenance in a multi-pack environment. It may also be
+  helpful to organize packfiles by object type (commit, tree, blob,
+  etc.) and use this metadata to help that maintenance.
+
+- The partial clone feature records special "promisor" packs that
+  may point to objects that are not stored locally, but available
+  on request to a server. The multi-pack-index does not currently
+  track these promisor packs.
+
+Related Links
+-------------
+[0] https://bugs.chromium.org/p/git/issues/detail?id=6
+    Chromium work item for: Multi-Pack Index (MIDX)
+
+[1] https://public-inbox.org/git/[email protected]/
+    An earlier RFC for the multi-pack-index feature
+
+[2] https://public-inbox.org/git/alpine.DEB.2.20.1803091557510.23109@alexmv-linux/
+    Git Merge 2018 Contributor's summit notes (includes discussion of MIDX)

Documentation/technical/pack-format.txt

@@ -252,3 +252,80 @@ Pack file entry: <+
     corresponding packfile.
 
     20-byte SHA-1-checksum of all of the above.
+
+== multi-pack-index (MIDX) files have the following format:
+
+The multi-pack-index files refer to multiple pack-files and loose objects.
+
+In order to allow extensions that add extra data to the MIDX, we organize
+the body into "chunks" and provide a lookup table at the beginning of the
+body. The header includes certain length values, such as the number of packs,
+the number of base MIDX files, hash lengths and types.
+
+All 4-byte numbers are in network order.
+
+HEADER:
+
+	4-byte signature:
+	    The signature is: {'M', 'I', 'D', 'X'}
+
+	1-byte version number:
+	    Git only writes or recognizes version 1.
+
+	1-byte Object Id Version
+	    Git only writes or recognizes version 1 (SHA1).
+
+	1-byte number of "chunks"
+
+	1-byte number of base multi-pack-index files:
+	    This value is currently always zero.
+
+	4-byte number of pack files
+
+CHUNK LOOKUP:
+
+	(C + 1) * 12 bytes providing the chunk offsets:
+	    First 4 bytes describe chunk id. Value 0 is a terminating label.
+	    Other 8 bytes provide offset in current file for chunk to start.
+	    (Chunks are provided in file-order, so you can infer the length
+	    using the next chunk position if necessary.)
+
+	The remaining data in the body is described one chunk at a time, and
+	these chunks may be given in any order. Chunks are required unless
+	otherwise specified.
+
+CHUNK DATA:
+
+	Packfile Names (ID: {'P', 'N', 'A', 'M'})
+	    Stores the packfile names as concatenated, null-terminated strings.
+	    Packfiles must be listed in lexicographic order for fast lookups by
+	    name. This is the only chunk not guaranteed to be a multiple of four
+	    bytes in length, so should be the last chunk for alignment reasons.
+
+	OID Fanout (ID: {'O', 'I', 'D', 'F'})
+	    The ith entry, F[i], stores the number of OIDs with first
+	    byte at most i. Thus F[255] stores the total
+	    number of objects.
+
+	OID Lookup (ID: {'O', 'I', 'D', 'L'})
+	    The OIDs for all objects in the MIDX are stored in lexicographic
+	    order in this chunk.
+
+	Object Offsets (ID: {'O', 'O', 'F', 'F'})
+	    Stores two 4-byte values for every object.
+	    1: The pack-int-id for the pack storing this object.
+	    2: The offset within the pack.
+		If all offsets are less than 2^31, then the large offset chunk
+		will not exist and offsets are stored as in IDX v1.
+		If there is at least one offset value larger than 2^32-1, then
+		the large offset chunk must exist. If the large offset chunk
+		exists and the 31st bit is on, then removing that bit reveals
+		the row in the large offsets containing the 8-byte offset of
+		this object.
+
+	[Optional] Object Large Offsets (ID: {'L', 'O', 'F', 'F'})
+	    8-byte offsets into large packfiles.
+
+TRAILER:
+
+	20-byte SHA1-checksum of the above contents.

Makefile

@@ -717,6 +717,7 @@ TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-path-utils.o
 TEST_BUILTINS_OBJS += test-prio-queue.o
 TEST_BUILTINS_OBJS += test-read-cache.o
+TEST_BUILTINS_OBJS += test-read-midx.o
 TEST_BUILTINS_OBJS += test-ref-store.o
 TEST_BUILTINS_OBJS += test-regex.o
 TEST_BUILTINS_OBJS += test-revision-walking.o
@@ -890,6 +891,7 @@ LIB_OBJS += merge.o
 LIB_OBJS += merge-blobs.o
 LIB_OBJS += merge-recursive.o
 LIB_OBJS += mergesort.o
+LIB_OBJS += midx.o
 LIB_OBJS += name-hash.o
 LIB_OBJS += notes.o
 LIB_OBJS += notes-cache.o
@@ -1047,6 +1049,7 @@ BUILTIN_OBJS += builtin/merge-recursive.o
 BUILTIN_OBJS += builtin/merge-tree.o
 BUILTIN_OBJS += builtin/mktag.o
 BUILTIN_OBJS += builtin/mktree.o
+BUILTIN_OBJS += builtin/multi-pack-index.o
 BUILTIN_OBJS += builtin/mv.o
 BUILTIN_OBJS += builtin/name-rev.o
 BUILTIN_OBJS += builtin/notes.o

builtin.h

@@ -191,6 +191,7 @@ extern int cmd_merge_recursive(int argc, const char **argv, const char *prefix);
 extern int cmd_merge_tree(int argc, const char **argv, const char *prefix);
 extern int cmd_mktag(int argc, const char **argv, const char *prefix);
 extern int cmd_mktree(int argc, const char **argv, const char *prefix);
+extern int cmd_multi_pack_index(int argc, const char **argv, const char *prefix);
 extern int cmd_mv(int argc, const char **argv, const char *prefix);
 extern int cmd_name_rev(int argc, const char **argv, const char *prefix);
 extern int cmd_notes(int argc, const char **argv, const char *prefix);

builtin/multi-pack-index.c

@@ -0,0 +1,47 @@
+#include "builtin.h"
+#include "cache.h"
+#include "config.h"
+#include "parse-options.h"
+#include "midx.h"
+
+static char const * const builtin_multi_pack_index_usage[] = {
+	N_("git multi-pack-index [--object-dir=<dir>] write"),
+	NULL
+};
+
+static struct opts_multi_pack_index {
+	const char *object_dir;
+} opts;
+
+int cmd_multi_pack_index(int argc, const char **argv,
+			 const char *prefix)
+{
+	static struct option builtin_multi_pack_index_options[] = {
+		OPT_FILENAME(0, "object-dir", &opts.object_dir,
+		  N_("object directory containing set of packfile and pack-index pairs")),
+		OPT_END(),
+	};
+
+	git_config(git_default_config, NULL);
+
+	argc = parse_options(argc, argv, prefix,
+			     builtin_multi_pack_index_options,
+			     builtin_multi_pack_index_usage, 0);
+
+	if (!opts.object_dir)
+		opts.object_dir = get_object_directory();
+
+	if (argc == 0)
+		goto usage;
+
+	if (!strcmp(argv[0], "write")) {
+		if (argc > 1)
+			goto usage;
+
+		return write_midx_file(opts.object_dir);
+	}
+
+usage:
+	usage_with_options(builtin_multi_pack_index_usage,
+			   builtin_multi_pack_index_options);
+}

builtin/repack.c

@@ -8,6 +8,7 @@
 #include "strbuf.h"
 #include "string-list.h"
 #include "argv-array.h"
+#include "midx.h"
 
 static int delta_base_offset = 1;
 static int pack_kept_objects = -1;
@@ -174,6 +175,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int no_update_server_info = 0;
 	int quiet = 0;
 	int local = 0;
+	int midx_cleared = 0;
 
 	struct option builtin_repack_options[] = {
 		OPT_BIT('a', NULL, &pack_everything,
@@ -333,6 +335,13 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	for_each_string_list_item(item, &names) {
 		for (ext = 0; ext < ARRAY_SIZE(exts); ext++) {
 			char *fname, *fname_old;
+
+			if (!midx_cleared) {
+				/* if we move a packfile, it will invalidated the midx */
+				clear_midx_file(get_object_directory());
+				midx_cleared = 1;
+			}
+
 			fname = mkpathdup("%s/pack-%s%s", packdir,
 						item->string, exts[ext].name);
 			if (!file_exists(fname)) {

command-list.txt

@@ -123,6 +123,7 @@ git-merge-index                         plumbingmanipulators
 git-merge-one-file                      purehelpers
 git-mergetool                           ancillarymanipulators           complete
 git-merge-tree                          ancillaryinterrogators
+git-multi-pack-index                    plumbingmanipulators
 git-mktag                               plumbingmanipulators
 git-mktree                              plumbingmanipulators
 git-mv                                  mainporcelain           worktree

git.c

@@ -505,6 +505,7 @@ static struct cmd_struct commands[] = {
 	{ "merge-tree", cmd_merge_tree, RUN_SETUP | NO_PARSEOPT },
 	{ "mktag", cmd_mktag, RUN_SETUP | NO_PARSEOPT },
 	{ "mktree", cmd_mktree, RUN_SETUP },
+	{ "multi-pack-index", cmd_multi_pack_index, RUN_SETUP_GENTLY },
 	{ "mv", cmd_mv, RUN_SETUP | NEED_WORK_TREE },
 	{ "name-rev", cmd_name_rev, RUN_SETUP },
 	{ "notes", cmd_notes, RUN_SETUP },