1 files changed, 196 insertions, 86 deletions

diff --git a/builtin/repack.c b/builtin/repack.c
index a5bacc7797..0541c3ce15 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -1,9 +1,13 @@
 #include "builtin.h"
-#include "cache.h"
+#include "alloc.h"
 #include "config.h"
 #include "dir.h"
+#include "environment.h"
+#include "gettext.h"
+#include "hex.h"
 #include "parse-options.h"
 #include "run-command.h"
+#include "server-info.h"
 #include "sigchain.h"
 #include "strbuf.h"
 #include "string-list.h"
@@ -32,7 +36,6 @@ static int write_bitmaps = -1;
 static int use_delta_islands;
 static int run_update_server_info = 1;
 static char *packdir, *packtmp_name, *packtmp;
-static char *cruft_expiration;
 
 static const char *const git_repack_usage[] = {
 	N_("git repack [<options>]"),
@@ -92,44 +95,6 @@ static int repack_config(const char *var, const char *value, void *cb)
 }
 
 /*
- * Remove temporary $GIT_OBJECT_DIRECTORY/pack/.tmp-$$-pack-* files.
- */
-static void remove_temporary_files(void)
-{
-	struct strbuf buf = STRBUF_INIT;
-	size_t dirlen, prefixlen;
-	DIR *dir;
-	struct dirent *e;
-
-	dir = opendir(packdir);
-	if (!dir)
-		return;
-
-	/* Point at the slash at the end of ".../objects/pack/" */
-	dirlen = strlen(packdir) + 1;
-	strbuf_addstr(&buf, packtmp);
-	/* Hold the length of  ".tmp-%d-pack-" */
-	prefixlen = buf.len - dirlen;
-
-	while ((e = readdir(dir))) {
-		if (strncmp(e->d_name, buf.buf + dirlen, prefixlen))
-			continue;
-		strbuf_setlen(&buf, dirlen);
-		strbuf_addstr(&buf, e->d_name);
-		unlink(buf.buf);
-	}
-	closedir(dir);
-	strbuf_release(&buf);
-}
-
-static void remove_pack_on_signal(int signo)
-{
-	remove_temporary_files();
-	sigchain_pop(signo);
-	raise(signo);
-}
-
-/*
  * Adds all packs hex strings to either fname_nonkept_list or
  * fname_kept_list based on whether each pack has a corresponding
  * .keep file or not.  Packs without a .keep file are not to be kept
@@ -188,7 +153,8 @@ static void remove_redundant_pack(const char *dir_name, const char *base_name)
 }
 
 static void prepare_pack_objects(struct child_process *cmd,
-				 const struct pack_objects_args *args)
+				 const struct pack_objects_args *args,
+				 const char *out)
 {
 	strvec_push(&cmd->args, "pack-objects");
 	if (args->window)
@@ -211,7 +177,7 @@ static void prepare_pack_objects(struct child_process *cmd,
 		strvec_push(&cmd->args,  "--quiet");
 	if (delta_base_offset)
 		strvec_push(&cmd->args,  "--delta-base-offset");
-	strvec_push(&cmd->args, packtmp);
+	strvec_push(&cmd->args, out);
 	cmd->git_cmd = 1;
 	cmd->out = -1;
 }
@@ -220,8 +186,9 @@ static void prepare_pack_objects(struct child_process *cmd,
  * Write oid to the given struct child_process's stdin, starting it first if
  * necessary.
  */
-static int write_oid(const struct object_id *oid, struct packed_git *pack,
-		     uint32_t pos, void *data)
+static int write_oid(const struct object_id *oid,
+		     struct packed_git *pack UNUSED,
+		     uint32_t pos UNUSED, void *data)
 {
 	struct child_process *cmd = data;
 
@@ -247,11 +214,15 @@ static struct {
 	{".idx"},
 };
 
-static unsigned populate_pack_exts(char *name)
+struct generated_pack_data {
+	struct tempfile *tempfiles[ARRAY_SIZE(exts)];
+};
+
+static struct generated_pack_data *populate_pack_exts(const char *name)
 {
 	struct stat statbuf;
 	struct strbuf path = STRBUF_INIT;
-	unsigned ret = 0;
+	struct generated_pack_data *data = xcalloc(1, sizeof(*data));
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(exts); i++) {
@@ -261,11 +232,11 @@ static unsigned populate_pack_exts(char *name)
 		if (stat(path.buf, &statbuf))
 			continue;
 
-		ret |= (1 << i);
+		data->tempfiles[i] = register_tempfile(path.buf);
 	}
 
 	strbuf_release(&path);
-	return ret;
+	return data;
 }
 
 static void repack_promisor_objects(const struct pack_objects_args *args,
@@ -275,7 +246,7 @@ static void repack_promisor_objects(const struct pack_objects_args *args,
 	FILE *out;
 	struct strbuf line = STRBUF_INIT;
 
-	prepare_pack_objects(&cmd, args);
+	prepare_pack_objects(&cmd, args, packtmp);
 	cmd.in = -1;
 
 	/*
@@ -320,7 +291,7 @@ static void repack_promisor_objects(const struct pack_objects_args *args,
 					  line.buf);
 		write_promisor_file(promisor_name, NULL, 0);
 
-		item->util = (void *)(uintptr_t)populate_pack_exts(item->string);
+		item->util = populate_pack_exts(item->string);
 
 		free(promisor_name);
 	}
@@ -355,7 +326,8 @@ static int geometry_cmp(const void *va, const void *vb)
 }
 
 static void init_pack_geometry(struct pack_geometry **geometry_p,
-			       struct string_list *existing_kept_packs)
+			       struct string_list *existing_kept_packs,
+			       const struct pack_objects_args *args)
 {
 	struct packed_git *p;
 	struct pack_geometry *geometry;
@@ -365,6 +337,14 @@ static void init_pack_geometry(struct pack_geometry **geometry_p,
 	geometry = *geometry_p;
 
 	for (p = get_all_packs(the_repository); p; p = p->next) {
+		if (args->local && !p->pack_local)
+			/*
+			 * When asked to only repack local packfiles we skip
+			 * over any packfiles that are borrowed from alternate
+			 * object directories.
+			 */
+			continue;
+
 		if (!pack_kept_objects) {
 			/*
 			 * Any pack that has its pack_keep bit set will appear
@@ -478,8 +458,10 @@ static void split_pack_geometry(struct pack_geometry *geometry, int factor)
 	geometry->split = split;
 }
 
-static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry)
+static struct packed_git *get_preferred_pack(struct pack_geometry *geometry)
 {
+	uint32_t i;
+
 	if (!geometry) {
 		/*
 		 * No geometry means either an all-into-one repack (in which
@@ -494,7 +476,21 @@ static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry
 	}
 	if (geometry->split == geometry->pack_nr)
 		return NULL;
-	return geometry->pack[geometry->pack_nr - 1];
+
+	/*
+	 * The preferred pack is the largest pack above the split line. In
+	 * other words, it is the largest pack that does not get rolled up in
+	 * the geometric repack.
+	 */
+	for (i = geometry->pack_nr; i > geometry->split; i--)
+		/*
+		 * A pack that is not local would never be included in a
+		 * multi-pack index. We thus skip over any non-local packs.
+		 */
+		if (geometry->pack[i - 1]->pack_local)
+			return geometry->pack[i - 1];
+
+	return NULL;
 }
 
 static void clear_pack_geometry(struct pack_geometry *geometry)
@@ -588,6 +584,17 @@ static void midx_included_packs(struct string_list *include,
 		for (i = geometry->split; i < geometry->pack_nr; i++) {
 			struct packed_git *p = geometry->pack[i];
 
+			/*
+			 * The multi-pack index never refers to packfiles part
+			 * of an alternate object database, so we skip these.
+			 * While git-multi-pack-index(1) would silently ignore
+			 * them anyway, this allows us to skip executing the
+			 * command completely when we have only non-local
+			 * packfiles.
+			 */
+			if (!p->pack_local)
+				continue;
+
 			strbuf_addstr(&buf, pack_basename(p));
 			strbuf_strip_suffix(&buf, ".pack");
 			strbuf_addstr(&buf, ".idx");
@@ -621,7 +628,7 @@ static int write_midx_included_packs(struct string_list *include,
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
 	struct string_list_item *item;
-	struct packed_git *largest = get_largest_active_pack(geometry);
+	struct packed_git *preferred = get_preferred_pack(geometry);
 	FILE *in;
 	int ret;
 
@@ -642,9 +649,9 @@ static int write_midx_included_packs(struct string_list *include,
 	if (write_bitmaps)
 		strvec_push(&cmd.args, "--bitmap");
 
-	if (largest)
+	if (preferred)
 		strvec_pushf(&cmd.args, "--preferred-pack=%s",
-			     pack_basename(largest));
+			     pack_basename(preferred));
 
 	if (refs_snapshot)
 		strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot);
@@ -661,8 +668,39 @@ static int write_midx_included_packs(struct string_list *include,
 	return finish_command(&cmd);
 }
 
+static void remove_redundant_bitmaps(struct string_list *include,
+				     const char *packdir)
+{
+	struct strbuf path = STRBUF_INIT;
+	struct string_list_item *item;
+	size_t packdir_len;
+
+	strbuf_addstr(&path, packdir);
+	strbuf_addch(&path, '/');
+	packdir_len = path.len;
+
+	/*
+	 * Remove any pack bitmaps corresponding to packs which are now
+	 * included in the MIDX.
+	 */
+	for_each_string_list_item(item, include) {
+		strbuf_addstr(&path, item->string);
+		strbuf_strip_suffix(&path, ".idx");
+		strbuf_addstr(&path, ".bitmap");
+
+		if (unlink(path.buf) && errno != ENOENT)
+			warning_errno(_("could not remove stale bitmap: %s"),
+				      path.buf);
+
+		strbuf_setlen(&path, packdir_len);
+	}
+	strbuf_release(&path);
+}
+
 static int write_cruft_pack(const struct pack_objects_args *args,
+			    const char *destination,
 			    const char *pack_prefix,
+			    const char *cruft_expiration,
 			    struct string_list *names,
 			    struct string_list *existing_packs,
 			    struct string_list *existing_kept_packs)
@@ -672,8 +710,10 @@ static int write_cruft_pack(const struct pack_objects_args *args,
 	struct string_list_item *item;
 	FILE *in, *out;
 	int ret;
+	const char *scratch;
+	int local = skip_prefix(destination, packdir, &scratch);
 
-	prepare_pack_objects(&cmd, args);
+	prepare_pack_objects(&cmd, args, destination);
 
 	strvec_push(&cmd.args, "--cruft");
 	if (cruft_expiration)
@@ -698,6 +738,10 @@ static int write_cruft_pack(const struct pack_objects_args *args,
 	 * By the time it is read here, it contains only the pack(s)
 	 * that were just written, which is exactly the set of packs we
 	 * want to consider kept.
+	 *
+	 * If `--expire-to` is given, the double-use served by `names`
+	 * ensures that the pack written to `--expire-to` excludes any
+	 * objects contained in the cruft pack.
 	 */
 	in = xfdopen(cmd.in, "w");
 	for_each_string_list_item(item, names)
@@ -710,10 +754,19 @@ static int write_cruft_pack(const struct pack_objects_args *args,
 
 	out = xfdopen(cmd.out, "r");
 	while (strbuf_getline_lf(&line, out) != EOF) {
+		struct string_list_item *item;
+
 		if (line.len != the_hash_algo->hexsz)
 			die(_("repack: Expecting full hex object ID lines only "
 			      "from pack-objects."));
-		string_list_append(names, line.buf);
+		/*
+		 * avoid putting packs written outside of the repository in the
+		 * list of names
+		 */
+		if (local) {
+			item = string_list_append(names, line.buf);
+			item->util = populate_pack_exts(line.buf);
+		}
 	}
 	fclose(out);
 
@@ -745,6 +798,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	struct pack_objects_args cruft_po_args = {NULL};
 	int geometric_factor = 0;
 	int write_midx = 0;
+	const char *cruft_expiration = NULL;
+	const char *expire_to = NULL;
 
 	struct option builtin_repack_options[] = {
 		OPT_BIT('a', NULL, &pack_everything,
@@ -756,7 +811,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				N_("same as -a, pack unreachable cruft objects separately"),
 				   PACK_CRUFT),
 		OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"),
-				N_("with -C, expire objects older than this")),
+				N_("with --cruft, expire objects older than this")),
 		OPT_BOOL('d', NULL, &delete_redundant,
 				N_("remove redundant packs, and run git-prune-packed")),
 		OPT_BOOL('f', NULL, &po_args.no_reuse_delta,
@@ -794,6 +849,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			    N_("find a geometric progression with factor <N>")),
 		OPT_BOOL('m', "write-midx", &write_midx,
 			   N_("write a multi-pack index of the resulting packs")),
+		OPT_STRING(0, "expire-to", &expire_to, N_("dir"),
+			   N_("pack prefix to store a pack containing pruned objects")),
 		OPT_END()
 	};
 
@@ -833,6 +890,18 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (write_bitmaps && !(pack_everything & ALL_INTO_ONE) && !write_midx)
 		die(_(incremental_bitmap_conflict_error));
 
+	if (write_bitmaps && po_args.local && has_alt_odb(the_repository)) {
+		/*
+		 * When asked to do a local repack, but we have
+		 * packfiles that are inherited from an alternate, then
+		 * we cannot guarantee that the multi-pack-index would
+		 * have full coverage of all objects. We thus disable
+		 * writing bitmaps in that case.
+		 */
+		warning(_("disabling bitmap writing, as some objects are not being packed"));
+		write_bitmaps = 0;
+	}
+
 	if (write_midx && write_bitmaps) {
 		struct strbuf path = STRBUF_INIT;
 
@@ -855,13 +924,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (geometric_factor) {
 		if (pack_everything)
 			die(_("options '%s' and '%s' cannot be used together"), "--geometric", "-A/-a");
-		init_pack_geometry(&geometry, &existing_kept_packs);
+		init_pack_geometry(&geometry, &existing_kept_packs, &po_args);
 		split_pack_geometry(geometry, geometric_factor);
 	}
 
-	sigchain_push_common(remove_pack_on_signal);
-
-	prepare_pack_objects(&cmd, &po_args);
+	prepare_pack_objects(&cmd, &po_args, packtmp);
 
 	show_progress = !po_args.quiet && isatty(2);
 
@@ -887,7 +954,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		strvec_push(&cmd.args, "--reflog");
 		strvec_push(&cmd.args, "--indexed-objects");
 	}
-	if (has_promisor_remote())
+	if (repo_has_promisor_remote(the_repository))
 		strvec_push(&cmd.args, "--exclude-promisor-objects");
 	if (!write_midx) {
 		if (write_bitmaps > 0)
@@ -934,7 +1001,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 
 	ret = start_command(&cmd);
 	if (ret)
-		return ret;
+		goto cleanup;
 
 	if (geometry) {
 		FILE *in = xfdopen(cmd.in, "w");
@@ -952,14 +1019,18 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 
 	out = xfdopen(cmd.out, "r");
 	while (strbuf_getline_lf(&line, out) != EOF) {
+		struct string_list_item *item;
+
 		if (line.len != the_hash_algo->hexsz)
 			die(_("repack: Expecting full hex object ID lines only from pack-objects."));
-		string_list_append(&names, line.buf);
+		item = string_list_append(&names, line.buf);
+		item->util = populate_pack_exts(item->string);
 	}
+	strbuf_release(&line);
 	fclose(out);
 	ret = finish_command(&cmd);
 	if (ret)
-		return ret;
+		goto cleanup;
 
 	if (!names.nr && !po_args.quiet)
 		printf_ln(_("Nothing new to pack."));
@@ -984,49 +1055,81 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		cruft_po_args.local = po_args.local;
 		cruft_po_args.quiet = po_args.quiet;
 
-		ret = write_cruft_pack(&cruft_po_args, pack_prefix, &names,
+		ret = write_cruft_pack(&cruft_po_args, packtmp, pack_prefix,
+				       cruft_expiration, &names,
 				       &existing_nonkept_packs,
 				       &existing_kept_packs);
 		if (ret)
-			return ret;
+			goto cleanup;
+
+		if (delete_redundant && expire_to) {
+			/*
+			 * If `--expire-to` is given with `-d`, it's possible
+			 * that we're about to prune some objects. With cruft
+			 * packs, pruning is implicit: any objects from existing
+			 * packs that weren't picked up by new packs are removed
+			 * when their packs are deleted.
+			 *
+			 * Generate an additional cruft pack, with one twist:
+			 * `names` now includes the name of the cruft pack
+			 * written in the previous step. So the contents of
+			 * _this_ cruft pack exclude everything contained in the
+			 * existing cruft pack (that is, all of the unreachable
+			 * objects which are no older than
+			 * `--cruft-expiration`).
+			 *
+			 * To make this work, cruft_expiration must become NULL
+			 * so that this cruft pack doesn't actually prune any
+			 * objects. If it were non-NULL, this call would always
+			 * generate an empty pack (since every object not in the
+			 * cruft pack generated above will have an mtime older
+			 * than the expiration).
+			 */
+			ret = write_cruft_pack(&cruft_po_args, expire_to,
+					       pack_prefix,
+					       NULL,
+					       &names,
+					       &existing_nonkept_packs,
+					       &existing_kept_packs);
+			if (ret)
+				goto cleanup;
+		}
 	}
 
 	string_list_sort(&names);
 
-	for_each_string_list_item(item, &names) {
-		item->util = (void *)(uintptr_t)populate_pack_exts(item->string);
-	}
-
 	close_object_store(the_repository->objects);
 
 	/*
 	 * Ok we have prepared all new packfiles.
 	 */
 	for_each_string_list_item(item, &names) {
+		struct generated_pack_data *data = item->util;
+
 		for (ext = 0; ext < ARRAY_SIZE(exts); ext++) {
-			char *fname, *fname_old;
+			char *fname;
 
 			fname = mkpathdup("%s/pack-%s%s",
 					packdir, item->string, exts[ext].name);
-			fname_old = mkpathdup("%s-%s%s",
-					packtmp, item->string, exts[ext].name);
 
-			if (((uintptr_t)item->util) & ((uintptr_t)1 << ext)) {
+			if (data->tempfiles[ext]) {
+				const char *fname_old = get_tempfile_path(data->tempfiles[ext]);
 				struct stat statbuffer;
+
 				if (!stat(fname_old, &statbuffer)) {
 					statbuffer.st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH);
 					chmod(fname_old, statbuffer.st_mode);
 				}
 
-				if (rename(fname_old, fname))
-					die_errno(_("renaming '%s' failed"), fname_old);
+				if (rename_tempfile(&data->tempfiles[ext], fname))
+					die_errno(_("renaming pack to '%s' failed"), fname);
 			} else if (!exts[ext].optional)
-				die(_("missing required file: %s"), fname_old);
+				die(_("pack-objects did not write a '%s' file for pack %s-%s"),
+				    exts[ext].name, packtmp, item->string);
 			else if (unlink(fname) < 0 && errno != ENOENT)
 				die_errno(_("could not unlink: %s"), fname);
 
 			free(fname);
-			free(fname_old);
 		}
 	}
 	/* End of pack replacement. */
@@ -1059,10 +1162,13 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 						refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL,
 						show_progress, write_bitmaps > 0);
 
+		if (!ret && write_bitmaps)
+			remove_redundant_bitmaps(&include, packdir);
+
 		string_list_clear(&include, 0);
 
 		if (ret)
-			return ret;
+			goto cleanup;
 	}
 
 	reprepare_packed_git(the_repository);
@@ -1089,6 +1195,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				strbuf_addstr(&buf, pack_basename(p));
 				strbuf_strip_suffix(&buf, ".pack");
 
+				if ((p->pack_keep) ||
+				    (string_list_has_string(&existing_kept_packs,
+							    buf.buf)))
+					continue;
+
 				remove_redundant_pack(packdir, buf.buf);
 			}
 			strbuf_release(&buf);
@@ -1106,7 +1217,6 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 
 	if (run_update_server_info)
 		update_server_info(0);
-	remove_temporary_files();
 
 	if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX, 0)) {
 		unsigned flags = 0;
@@ -1115,11 +1225,11 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		write_midx_file(get_object_directory(), NULL, NULL, flags);
 	}
 
-	string_list_clear(&names, 0);
+cleanup:
+	string_list_clear(&names, 1);
 	string_list_clear(&existing_nonkept_packs, 0);
 	string_list_clear(&existing_kept_packs, 0);
 	clear_pack_geometry(geometry);
-	strbuf_release(&line);
 
-	return 0;
+	return ret;
 }