From: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date: Sat, 30 Aug 2014 08:33:55 GMT
Subject: [PATCH 25/32] prune: strategies for linked checkouts
Message-ID: <1409387642-24492-26-git-send-email-pclouds@gmail.com>
In-Reply-To: <1409387642-24492-1-git-send-email-pclouds@gmail.com>

(alias R=$GIT_COMMON_DIR/repos/<id>)

 - linked checkouts are supposed to keep its location in $R/gitdir up
   to date. The use case is auto fixup after a manual checkout move.

 - linked checkouts are supposed to update mtime of $R/gitdir. If
   $R/gitdir's mtime is older than a limit, and it points to nowhere,
   repos/<id> is to be pruned.

 - If $R/locked exists, repos/<id> is not supposed to be pruned. If
   $R/locked exists and $R/gitdir's mtime is older than a really long
   limit, warn about old unused repo.

 - "git checkout --to" is supposed to make a hard link named $R/link
   pointing to the .git file on supported file systems to help detect
   the user manually deleting the checkout. If $R/link exists and its
   link count is greated than 1, the repo is kept.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/git-prune.txt                |  3 +
 Documentation/gitrepository-layout.txt     | 19 ++++++
 builtin/checkout.c                         | 14 +++++
 builtin/prune.c                            | 95 ++++++++++++++++++++++++++++++
 setup.c                                    | 13 ++++
 t/t2026-prune-linked-checkouts.sh (new +x) | 84 ++++++++++++++++++++++++++
 6 files changed, 228 insertions(+)
 create mode 100755 t/t2026-prune-linked-checkouts.sh

diff --git a/Documentation/git-prune.txt b/Documentation/git-prune.txt
index 7a493c8..50e39ec 100644
--- a/Documentation/git-prune.txt
+++ b/Documentation/git-prune.txt
@@ -48,6 +48,9 @@ OPTIONS
 --expire <time>::
 	Only expire loose objects older than <time>.
 
+--repos::
+	Prune directories in $GIT_DIR/repos.
+
 <head>...::
 	In addition to objects
 	reachable from any of our references, keep objects
diff --git a/Documentation/gitrepository-layout.txt b/Documentation/gitrepository-layout.txt
index fab398a..c9a7d1a 100644
--- a/Documentation/gitrepository-layout.txt
+++ b/Documentation/gitrepository-layout.txt
@@ -255,6 +255,25 @@ repos::
 	$GIT_COMMON_DIR is set and "$GIT_COMMON_DIR/repos" will be
 	used instead.
 
+repos/<id>/gitdir::
+	A text file containing the absolute path back to the .git file
+	that points to here. This is used to check if the linked
+	repository has been manually removed and there is no need to
+	keep this directory any more. mtime of this file should be
+	updated every time the linked repository is accessed.
+
+repos/<id>/locked::
+	If this file exists, the linked repository may be on a
+	portable device and not available. It does not mean that the
+	linked repository is gone and `repos/<id>` could be
+	removed. The file's content contains a reason string on why
+	the repository is locked.
+
+repos/<id>/link::
+	If this file exists, it is a hard link to the linked .git
+	file. It is used to detect if the linked repository is
+	manually removed.
+
 SEE ALSO
 --------
 linkgit:git-init[1],
diff --git a/builtin/checkout.c b/builtin/checkout.c
index 614db34..0f28b4a 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -895,12 +895,22 @@ static int prepare_linked_checkout(const struct checkout_opts *opts,
 	junk_git_dir = xstrdup(sb_repo.buf);
 	is_junk = 1;
 
+	/*
+	 * lock the incomplete repo so prune won't delete it, unlock
+	 * after the preparation is over.
+	 */
+	strbuf_addf(&sb, "%s/locked", sb_repo.buf);
+	write_file(sb.buf, 1, "initializing\n");
+
 	strbuf_addf(&sb_git, "%s/.git", path);
 	if (safe_create_leading_directories_const(sb_git.buf))
 		die_errno(_("could not create leading directories of '%s'"),
 			  sb_git.buf);
 	junk_work_tree = xstrdup(path);
 
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%s/gitdir", sb_repo.buf);
+	write_file(sb.buf, 1, "%s\n", real_path(sb_git.buf));
 	write_file(sb_git.buf, 1, "gitdir: %s/repos/%s\n",
 		   real_path(get_git_common_dir()), name);
 	/*
@@ -909,6 +919,7 @@ static int prepare_linked_checkout(const struct checkout_opts *opts,
 	 * value would do because this value will be ignored and
 	 * replaced at the next (real) checkout.
 	 */
+	strbuf_reset(&sb);
 	strbuf_addf(&sb, "%s/HEAD", sb_repo.buf);
 	write_file(sb.buf, 1, "%s\n", sha1_to_hex(new->commit->object.sha1));
 	strbuf_reset(&sb);
@@ -932,6 +943,9 @@ static int prepare_linked_checkout(const struct checkout_opts *opts,
 		junk_work_tree = NULL;
 		junk_git_dir = NULL;
 	}
+	strbuf_reset(&sb);
+	strbuf_addf(&sb, "%s/locked", sb_repo.buf);
+	unlink_or_warn(sb.buf);
 	strbuf_release(&sb);
 	strbuf_release(&sb_repo);
 	strbuf_release(&sb_git);
diff --git a/builtin/prune.c b/builtin/prune.c
index 144a3bd..e72c391 100644
--- a/builtin/prune.c
+++ b/builtin/prune.c
@@ -112,6 +112,91 @@ static void prune_object_dir(const char *path)
 	}
 }
 
+static int prune_repo_dir(const char *id, struct strbuf *reason)
+{
+	struct stat st;
+	char *path;
+	int fd, len;
+
+	if (!is_directory(git_path("repos/%s", id))) {
+		strbuf_addf(reason, _("Removing repos/%s: not a valid directory"), id);
+		return 1;
+	}
+	if (file_exists(git_path("repos/%s/locked", id)))
+		return 0;
+	if (stat(git_path("repos/%s/gitdir", id), &st)) {
+		strbuf_addf(reason, _("Removing repos/%s: gitdir file does not exist"), id);
+		return 1;
+	}
+	fd = open(git_path("repos/%s/gitdir", id), O_RDONLY);
+	if (fd < 0) {
+		strbuf_addf(reason, _("Removing repos/%s: unable to read gitdir file (%s)"),
+			    id, strerror(errno));
+		return 1;
+	}
+	len = st.st_size;
+	path = xmalloc(len + 1);
+	read_in_full(fd, path, len);
+	close(fd);
+	while (len && (path[len - 1] == '\n' || path[len - 1] == '\r'))
+		len--;
+	if (!len) {
+		strbuf_addf(reason, _("Removing repos/%s: invalid gitdir file"), id);
+		free(path);
+		return 1;
+	}
+	path[len] = '\0';
+	if (!file_exists(path)) {
+		struct stat st_link;
+		free(path);
+		/*
+		 * the repo is moved manually and has not been
+		 * accessed since?
+		 */
+		if (!stat(git_path("repos/%s/link", id), &st_link) &&
+		    st_link.st_nlink > 1)
+			return 0;
+		strbuf_addf(reason, _("Removing repos/%s: gitdir file points to non-existent location"), id);
+		return 1;
+	}
+	free(path);
+	return st.st_mtime <= expire;
+}
+
+static void prune_repos_dir(void)
+{
+	struct strbuf reason = STRBUF_INIT;
+	struct strbuf path = STRBUF_INIT;
+	DIR *dir = opendir(git_path("repos"));
+	struct dirent *d;
+	int ret;
+	if (!dir)
+		return;
+	while ((d = readdir(dir)) != NULL) {
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+		strbuf_reset(&reason);
+		if (!prune_repo_dir(d->d_name, &reason))
+			continue;
+		if (show_only || verbose)
+			printf("%s\n", reason.buf);
+		if (show_only)
+			continue;
+		strbuf_reset(&path);
+		strbuf_addstr(&path, git_path("repos/%s", d->d_name));
+		ret = remove_dir_recursively(&path, 0);
+		if (ret < 0 && errno == ENOTDIR)
+			ret = unlink(path.buf);
+		if (ret)
+			error(_("failed to remove: %s"), strerror(errno));
+	}
+	closedir(dir);
+	if (!show_only)
+		rmdir(git_path("repos"));
+	strbuf_release(&reason);
+	strbuf_release(&path);
+}
+
 /*
  * Write errors (particularly out of space) can result in
  * failed temporary packs (and more rarely indexes and other
@@ -138,10 +223,12 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
 	struct progress *progress = NULL;
+	int prune_repos = 0;
 	const struct option options[] = {
 		OPT__DRY_RUN(&show_only, N_("do not remove, show only")),
 		OPT__VERBOSE(&verbose, N_("report pruned objects")),
 		OPT_BOOL(0, "progress", &show_progress, N_("show progress")),
+		OPT_BOOL(0, "repos", &prune_repos, N_("prune .git/repos/")),
 		OPT_EXPIRY_DATE(0, "expire", &expire,
 				N_("expire objects older than <time>")),
 		OPT_END()
@@ -154,6 +241,14 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 	init_revisions(&revs, prefix);
 
 	argc = parse_options(argc, argv, prefix, options, prune_usage, 0);
+
+	if (prune_repos) {
+		if (argc)
+			die(_("--repos does not take extra arguments"));
+		prune_repos_dir();
+		return 0;
+	}
+
 	while (argc--) {
 		unsigned char sha1[20];
 		const char *name = *argv++;
diff --git a/setup.c b/setup.c
index 8f90bc3..da2d669 100644
--- a/setup.c
+++ b/setup.c
@@ -390,6 +390,17 @@ static int check_repository_format_gently(const char *gitdir, int *nongit_ok)
 	return ret;
 }
 
+static void update_linked_gitdir(const char *gitfile, const char *gitdir)
+{
+	struct strbuf path = STRBUF_INIT;
+	struct stat st;
+
+	strbuf_addf(&path, "%s/gitfile", gitdir);
+	if (stat(path.buf, &st) || st.st_mtime + 24 * 3600 < time(NULL))
+		write_file(path.buf, 0, "%s\n", gitfile);
+	strbuf_release(&path);
+}
+
 /*
  * Try to read the location of the git directory from the .git file,
  * return path to git directory if found.
@@ -438,6 +449,8 @@ const char *read_gitfile(const char *path)
 
 	if (!is_git_directory(dir))
 		die("Not a git repository: %s", dir);
+
+	update_linked_gitdir(path, dir);
 	path = real_path(dir);
 
 	free(buf);
diff --git a/t/t2026-prune-linked-checkouts.sh b/t/t2026-prune-linked-checkouts.sh
new file mode 100755
index 0000000..79d84cb
--- /dev/null
+++ b/t/t2026-prune-linked-checkouts.sh
@@ -0,0 +1,84 @@
+#!/bin/sh
+
+test_description='prune $GIT_DIR/repos'
+
+. ./test-lib.sh
+
+test_expect_success 'prune --repos on normal repo' '
+	git prune --repos &&
+	test_must_fail git prune --repos abc
+'
+
+test_expect_success 'prune files inside $GIT_DIR/repos' '
+	mkdir .git/repos &&
+	: >.git/repos/abc &&
+	git prune --repos --verbose >actual &&
+	cat >expect <<EOF &&
+Removing repos/abc: not a valid directory
+EOF
+	test_i18ncmp expect actual &&
+	! test -f .git/repos/abc &&
+	! test -d .git/repos
+'
+
+test_expect_success 'prune directories without gitdir' '
+	mkdir -p .git/repos/def/abc &&
+	: >.git/repos/def/def &&
+	cat >expect <<EOF &&
+Removing repos/def: gitdir file does not exist
+EOF
+	git prune --repos --verbose >actual &&
+	test_i18ncmp expect actual &&
+	! test -d .git/repos/def &&
+	! test -d .git/repos
+'
+
+test_expect_success POSIXPERM 'prune directories with unreadable gitdir' '
+	mkdir -p .git/repos/def/abc &&
+	: >.git/repos/def/def &&
+	: >.git/repos/def/gitdir &&
+	chmod u-r .git/repos/def/gitdir &&
+	git prune --repos --verbose >actual &&
+	test_i18ngrep "Removing repos/def: unable to read gitdir file" actual &&
+	! test -d .git/repos/def &&
+	! test -d .git/repos
+'
+
+test_expect_success 'prune directories with invalid gitdir' '
+	mkdir -p .git/repos/def/abc &&
+	: >.git/repos/def/def &&
+	: >.git/repos/def/gitdir &&
+	git prune --repos --verbose >actual &&
+	test_i18ngrep "Removing repos/def: invalid gitdir file" actual &&
+	! test -d .git/repos/def &&
+	! test -d .git/repos
+'
+
+test_expect_success 'prune directories with gitdir pointing to nowhere' '
+	mkdir -p .git/repos/def/abc &&
+	: >.git/repos/def/def &&
+	echo "$TRASH_DIRECTORY"/nowhere >.git/repos/def/gitdir &&
+	git prune --repos --verbose >actual &&
+	test_i18ngrep "Removing repos/def: gitdir file points to non-existent location" actual &&
+	! test -d .git/repos/def &&
+	! test -d .git/repos
+'
+
+test_expect_success 'not prune locked checkout' '
+	test_when_finished rm -r .git/repos
+	mkdir -p .git/repos/ghi &&
+	: >.git/repos/ghi/locked &&
+	git prune --repos &&
+	test -d .git/repos/ghi
+'
+
+test_expect_success 'not prune recent checkouts' '
+	test_when_finished rm -r .git/repos
+	mkdir zz &&
+	mkdir -p .git/repos/jlm &&
+	echo "$TRASH_DIRECTORY"/zz >.git/repos/jlm/gitdir &&
+	git prune --repos --verbose --expire=2.days.ago &&
+	test -d .git/repos/jlm
+'
+
+test_done
-- 
2.1.0.rc0.78.gc0d8480