Merge branch 'tb/pack-revindex-on-disk'

Introduce an on-disk file to record revindex for packdata, which
traditionally was always created on the fly and only in-core.

* tb/pack-revindex-on-disk:
  t5325: check both on-disk and in-memory reverse index
  pack-revindex: ensure that on-disk reverse indexes are given precedence
  t: support GIT_TEST_WRITE_REV_INDEX
  t: prepare for GIT_TEST_WRITE_REV_INDEX
  Documentation/config/pack.txt: advertise 'pack.writeReverseIndex'
  builtin/pack-objects.c: respect 'pack.writeReverseIndex'
  builtin/index-pack.c: write reverse indexes
  builtin/index-pack.c: allow stripping arbitrary extensions
  pack-write.c: prepare to write 'pack-*.rev' files
  packfile: prepare for the existence of '*.rev' files

Author: gitster

Documentation/config/pack.txt

@@ -133,3 +133,10 @@ pack.writeBitmapHashCache::
 	between an older, bitmapped pack and objects that have been
 	pushed since the last gc). The downside is that it consumes 4
 	bytes per object of disk space. Defaults to true.
+
+pack.writeReverseIndex::
+	When true, git will write a corresponding .rev file (see:
+	link:../technical/pack-format.html[Documentation/technical/pack-format.txt])
+	for each new packfile that it writes in all places except for
+	linkgit:git-fast-import[1] and in the bulk checkin mechanism.
+	Defaults to false.

Documentation/git-index-pack.txt

@@ -9,17 +9,18 @@ git-index-pack - Build pack index file for an existing packed archive
 SYNOPSIS
 --------
 [verse]
-'git index-pack' [-v] [-o <index-file>] <pack-file>
+'git index-pack' [-v] [-o <index-file>] [--[no-]rev-index] <pack-file>
 'git index-pack' --stdin [--fix-thin] [--keep] [-v] [-o <index-file>]
-                 [<pack-file>]
+		  [--[no-]rev-index] [<pack-file>]
 
 
 DESCRIPTION
 -----------
 Reads a packed archive (.pack) from the specified file, and
-builds a pack index file (.idx) for it.  The packed archive
-together with the pack index can then be placed in the
-objects/pack/ directory of a Git repository.
+builds a pack index file (.idx) for it. Optionally writes a
+reverse-index (.rev) for the specified pack. The packed
+archive together with the pack index can then be placed in
+the objects/pack/ directory of a Git repository.
 
 
 OPTIONS
@@ -35,6 +36,13 @@ OPTIONS
 	fails if the name of packed archive does not end
 	with .pack).
 
+--[no-]rev-index::
+	When this flag is provided, generate a reverse index
+	(a `.rev` file) corresponding to the given pack. If
+	`--verify` is given, ensure that the existing
+	reverse index is correct. Takes precedence over
+	`pack.writeReverseIndex`.
+
 --stdin::
 	When this flag is provided, the pack is read from stdin
 	instead and a copy is then written to <pack-file>. If

Documentation/technical/pack-format.txt

@@ -274,6 +274,26 @@ Pack file entry: <+
 
     Index checksum of all of the above.
 
+== pack-*.rev files have the format:
+
+  - A 4-byte magic number '0x52494458' ('RIDX').
+
+  - A 4-byte version identifier (= 1).
+
+  - A 4-byte hash function identifier (= 1 for SHA-1, 2 for SHA-256).
+
+  - A table of index positions (one per packed object, num_objects in
+    total, each a 4-byte unsigned integer in network order), sorted by
+    their corresponding offsets in the packfile.
+
+  - A trailer, containing a:
+
+    checksum of the corresponding packfile, and
+
+    a checksum of all of the above.
+
+All 4-byte numbers are in network order.
+
 == multi-pack-index (MIDX) files have the following format:
 
 The multi-pack-index files refer to multiple pack-files and loose objects.

builtin/index-pack.c

@@ -17,7 +17,7 @@
 #include "promisor-remote.h"
 
 static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
 
 struct object_entry {
 	struct pack_idx_entry idx;
@@ -1436,15 +1436,15 @@ static void fix_unresolved_deltas(struct hashfile *f)
 	free(sorted_by_pos);
 }
 
-static const char *derive_filename(const char *pack_name, const char *suffix,
-				   struct strbuf *buf)
+static const char *derive_filename(const char *pack_name, const char *strip,
+				   const char *suffix, struct strbuf *buf)
 {
 	size_t len;
-	if (!strip_suffix(pack_name, ".pack", &len))
-		die(_("packfile name '%s' does not end with '.pack'"),
-		    pack_name);
+	if (!strip_suffix(pack_name, strip, &len) || !len ||
+	    pack_name[len - 1] != '.')
+		die(_("packfile name '%s' does not end with '.%s'"),
+		    pack_name, strip);
 	strbuf_add(buf, pack_name, len);
-	strbuf_addch(buf, '.');
 	strbuf_addstr(buf, suffix);
 	return buf->buf;
 }
@@ -1459,7 +1459,7 @@ static void write_special_file(const char *suffix, const char *msg,
 	int msg_len = strlen(msg);
 
 	if (pack_name)
-		filename = derive_filename(pack_name, suffix, &name_buf);
+		filename = derive_filename(pack_name, "pack", suffix, &name_buf);
 	else
 		filename = odb_pack_name(&name_buf, hash, suffix);
 
@@ -1484,12 +1484,14 @@ static void write_special_file(const char *suffix, const char *msg,
 
 static void final(const char *final_pack_name, const char *curr_pack_name,
 		  const char *final_index_name, const char *curr_index_name,
+		  const char *final_rev_index_name, const char *curr_rev_index_name,
 		  const char *keep_msg, const char *promisor_msg,
 		  unsigned char *hash)
 {
 	const char *report = "pack";
 	struct strbuf pack_name = STRBUF_INIT;
 	struct strbuf index_name = STRBUF_INIT;
+	struct strbuf rev_index_name = STRBUF_INIT;
 	int err;
 
 	if (!from_stdin) {
@@ -1524,6 +1526,16 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 	} else
 		chmod(final_index_name, 0444);
 
+	if (curr_rev_index_name) {
+		if (final_rev_index_name != curr_rev_index_name) {
+			if (!final_rev_index_name)
+				final_rev_index_name = odb_pack_name(&rev_index_name, hash, "rev");
+			if (finalize_object_file(curr_rev_index_name, final_rev_index_name))
+				die(_("cannot store reverse index file"));
+		} else
+			chmod(final_rev_index_name, 0444);
+	}
+
 	if (do_fsck_object) {
 		struct packed_git *p;
 		p = add_packed_git(final_index_name, strlen(final_index_name), 0);
@@ -1553,6 +1565,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 		}
 	}
 
+	strbuf_release(&rev_index_name);
 	strbuf_release(&index_name);
 	strbuf_release(&pack_name);
 }
@@ -1578,6 +1591,12 @@ static int git_index_pack_config(const char *k, const char *v, void *cb)
 		}
 		return 0;
 	}
+	if (!strcmp(k, "pack.writereverseindex")) {
+		if (git_config_bool(k, v))
+			opts->flags |= WRITE_REV;
+		else
+			opts->flags &= ~WRITE_REV;
+	}
 	return git_default_config(k, v, cb);
 }
 
@@ -1695,12 +1714,14 @@ static void show_pack_info(int stat_only)
 
 int cmd_index_pack(int argc, const char **argv, const char *prefix)
 {
-	int i, fix_thin_pack = 0, verify = 0, stat_only = 0;
+	int i, fix_thin_pack = 0, verify = 0, stat_only = 0, rev_index;
 	const char *curr_index;
-	const char *index_name = NULL, *pack_name = NULL;
+	const char *curr_rev_index = NULL;
+	const char *index_name = NULL, *pack_name = NULL, *rev_index_name = NULL;
 	const char *keep_msg = NULL;
 	const char *promisor_msg = NULL;
 	struct strbuf index_name_buf = STRBUF_INIT;
+	struct strbuf rev_index_name_buf = STRBUF_INIT;
 	struct pack_idx_entry **idx_objects;
 	struct pack_idx_option opts;
 	unsigned char pack_hash[GIT_MAX_RAWSZ];
@@ -1727,6 +1748,11 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (prefix && chdir(prefix))
 		die(_("Cannot come back to cwd"));
 
+	if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0))
+		rev_index = 1;
+	else
+		rev_index = !!(opts.flags & (WRITE_REV_VERIFY | WRITE_REV));
+
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
 
@@ -1805,6 +1831,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				if (hash_algo == GIT_HASH_UNKNOWN)
 					die(_("unknown hash algorithm '%s'"), arg);
 				repo_set_hash_algo(the_repository, hash_algo);
+			} else if (!strcmp(arg, "--rev-index")) {
+				rev_index = 1;
+			} else if (!strcmp(arg, "--no-rev-index")) {
+				rev_index = 0;
 			} else
 				usage(index_pack_usage);
 			continue;
@@ -1824,7 +1854,16 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (from_stdin && hash_algo)
 		die(_("--object-format cannot be used with --stdin"));
 	if (!index_name && pack_name)
-		index_name = derive_filename(pack_name, "idx", &index_name_buf);
+		index_name = derive_filename(pack_name, "pack", "idx", &index_name_buf);
+
+	opts.flags &= ~(WRITE_REV | WRITE_REV_VERIFY);
+	if (rev_index) {
+		opts.flags |= verify ? WRITE_REV_VERIFY : WRITE_REV;
+		if (index_name)
+			rev_index_name = derive_filename(index_name,
+							 "idx", "rev",
+							 &rev_index_name_buf);
+	}
 
 	if (verify) {
 		if (!index_name)
@@ -1878,11 +1917,16 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	for (i = 0; i < nr_objects; i++)
 		idx_objects[i] = &objects[i].idx;
 	curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_hash);
+	if (rev_index)
+		curr_rev_index = write_rev_file(rev_index_name, idx_objects,
+						nr_objects, pack_hash,
+						opts.flags);
 	free(idx_objects);
 
 	if (!verify)
 		final(pack_name, curr_pack,
 		      index_name, curr_index,
+		      rev_index_name, curr_rev_index,
 		      keep_msg, promisor_msg,
 		      pack_hash);
 	else
@@ -1893,10 +1937,13 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 
 	free(objects);
 	strbuf_release(&index_name_buf);
+	strbuf_release(&rev_index_name_buf);
 	if (pack_name == NULL)
 		free((void *) curr_pack);
 	if (index_name == NULL)
 		free((void *) curr_index);
+	if (rev_index_name == NULL)
+		free((void *) curr_rev_index);
 
 	/*
 	 * Let the caller know this pack is not self contained

builtin/pack-objects.c

@@ -2953,6 +2953,13 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 			    pack_idx_opts.version);
 		return 0;
 	}
+	if (!strcmp(k, "pack.writereverseindex")) {
+		if (git_config_bool(k, v))
+			pack_idx_opts.flags |= WRITE_REV;
+		else
+			pack_idx_opts.flags &= ~WRITE_REV;
+		return 0;
+	}
 	if (!strcmp(k, "uploadpack.blobpackfileuri")) {
 		struct configured_exclusion *ex = xmalloc(sizeof(*ex));
 		const char *oid_end, *pack_end;
@@ -3592,6 +3599,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 
 	reset_pack_idx_option(&pack_idx_opts);
 	git_config(git_pack_config, NULL);
+	if (git_env_bool(GIT_TEST_WRITE_REV_INDEX, 0))
+		pack_idx_opts.flags |= WRITE_REV;
 
 	progress = isatty(2);
 	argc = parse_options(argc, argv, prefix, pack_objects_options,

builtin/repack.c

@@ -209,6 +209,7 @@ static struct {
 } exts[] = {
 	{".pack"},
 	{".idx"},
+	{".rev", 1},
 	{".bitmap", 1},
 	{".promisor", 1},
 };

ci/run-build-and-tests.sh

@@ -24,6 +24,7 @@ linux-gcc)
 	export GIT_TEST_MULTI_PACK_INDEX=1
 	export GIT_TEST_ADD_I_USE_BUILTIN=1
 	export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=master
+	export GIT_TEST_WRITE_REV_INDEX=1
 	make test
 	;;
 linux-clang)

object-store.h

@@ -85,6 +85,9 @@ struct packed_git {
 		 multi_pack_index:1;
 	unsigned char hash[GIT_MAX_RAWSZ];
 	struct revindex_entry *revindex;
+	const uint32_t *revindex_data;
+	const uint32_t *revindex_map;
+	size_t revindex_size;
 	/* something like ".git/objects/pack/xxxxx.pack" */
 	char pack_name[FLEX_ARRAY]; /* more */
 };