Merge branch 'nd/count-garbage'

"git count-objects -v" did not count leftover temporary packfiles
and other kinds of garbage.

* nd/count-garbage:
  count-objects: report how much disk space taken by garbage files
  count-objects: report garbage files in pack directory too
  sha1_file: reorder code in prepare_packed_git_one()
  git-count-objects.txt: describe each line in -v output

Documentation/git-count-objects.txt

@@ -20,11 +20,23 @@ OPTIONS
 -------
 -v::
 --verbose::
-	In addition to the number of loose objects and disk
-	space consumed, it reports the number of in-pack
-	objects, number of packs, disk space consumed by those packs,
-	and number of objects that can be removed by running
-	`git prune-packed`.
+	Report in more detail:
++
+count: the number of loose objects
++
+size: disk space consumed by loose objects, in KiB
++
+in-pack: the number of in-pack objects
++
+size-pack: disk space consumed by the packs, in KiB
++
+prune-packable: the number of loose objects that are also present in
+the packs. These objects could be pruned using `git prune-packed`.
++
+garbage: the number of files in object database that are not valid
+loose objects nor valid packs
++
+size-garbage: disk space consumed by garbage files, in KiB
 
 GIT
 ---

builtin/count-objects.c

@@ -9,11 +9,22 @@
 #include "builtin.h"
 #include "parse-options.h"
 
+static unsigned long garbage;
+static off_t size_garbage;
+
+static void real_report_garbage(const char *desc, const char *path)
+{
+	struct stat st;
+	if (!stat(path, &st))
+		size_garbage += st.st_size;
+	warning("%s: %s", desc, path);
+	garbage++;
+}
+
 static void count_objects(DIR *d, char *path, int len, int verbose,
 			  unsigned long *loose,
 			  off_t *loose_size,
-			  unsigned long *packed_loose,
-			  unsigned long *garbage)
+			  unsigned long *packed_loose)
 {
 	struct dirent *ent;
 	while ((ent = readdir(d)) != NULL) {
@@ -46,9 +57,11 @@ static void count_objects(DIR *d, char *path, int len, int verbose,
 		}
 		if (bad) {
 			if (verbose) {
-				error("garbage found: %.*s/%s",
-				      len + 2, path, ent->d_name);
-				(*garbage)++;
+				struct strbuf sb = STRBUF_INIT;
+				strbuf_addf(&sb, "%.*s/%s",
+					    len + 2, path, ent->d_name);
+				report_garbage("garbage found", sb.buf);
+				strbuf_release(&sb);
 			}
 			continue;
 		}
@@ -76,7 +89,7 @@ int cmd_count_objects(int argc, const char **argv, const char *prefix)
 	const char *objdir = get_object_directory();
 	int len = strlen(objdir);
 	char *path = xmalloc(len + 50);
-	unsigned long loose = 0, packed = 0, packed_loose = 0, garbage = 0;
+	unsigned long loose = 0, packed = 0, packed_loose = 0;
 	off_t loose_size = 0;
 	struct option opts[] = {
 		OPT__VERBOSE(&verbose, N_("be verbose")),
@@ -87,6 +100,8 @@ int cmd_count_objects(int argc, const char **argv, const char *prefix)
 	/* we do not take arguments other than flags for now */
 	if (argc)
 		usage_with_options(count_objects_usage, opts);
+	if (verbose)
+		report_garbage = real_report_garbage;
 	memcpy(path, objdir, len);
 	if (len && objdir[len-1] != '/')
 		path[len++] = '/';
@@ -97,7 +112,7 @@ int cmd_count_objects(int argc, const char **argv, const char *prefix)
 		if (!d)
 			continue;
 		count_objects(d, path, len, verbose,
-			      &loose, &loose_size, &packed_loose, &garbage);
+			      &loose, &loose_size, &packed_loose);
 		closedir(d);
 	}
 	if (verbose) {
@@ -122,6 +137,7 @@ int cmd_count_objects(int argc, const char **argv, const char *prefix)
 		printf("size-pack: %lu\n", (unsigned long) (size_pack / 1024));
 		printf("prune-packable: %lu\n", packed_loose);
 		printf("garbage: %lu\n", garbage);
+		printf("size-garbage: %lu\n", (unsigned long) (size_garbage / 1024));
 	}
 	else
 		printf("%lu objects, %lu kilobytes\n",

cache.h

@@ -1058,6 +1058,9 @@ extern const char *parse_feature_value(const char *feature_list, const char *fea
 
 extern struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path);
 
+/* A hook for count-objects to report invalid files in pack directory */
+extern void (*report_garbage)(const char *desc, const char *path);
+
 extern void prepare_packed_git(void);
 extern void reprepare_packed_git(void);
 extern void install_packed_git(struct packed_git *pack);

sha1_file.c

@@ -21,6 +21,7 @@
 #include "sha1-lookup.h"
 #include "bulk-checkin.h"
 #include "streaming.h"
+#include "dir.h"
 
 #ifndef O_NOATIME
 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -1000,6 +1001,63 @@ void install_packed_git(struct packed_git *pack)
 	packed_git = pack;
 }
 
+void (*report_garbage)(const char *desc, const char *path);
+
+static void report_helper(const struct string_list *list,
+			  int seen_bits, int first, int last)
+{
+	const char *msg;
+	switch (seen_bits) {
+	case 0:
+		msg = "no corresponding .idx nor .pack";
+		break;
+	case 1:
+		msg = "no corresponding .idx";
+		break;
+	case 2:
+		msg = "no corresponding .pack";
+		break;
+	default:
+		return;
+	}
+	for (; first < last; first++)
+		report_garbage(msg, list->items[first].string);
+}
+
+static void report_pack_garbage(struct string_list *list)
+{
+	int i, baselen = -1, first = 0, seen_bits = 0;
+
+	if (!report_garbage)
+		return;
+
+	sort_string_list(list);
+
+	for (i = 0; i < list->nr; i++) {
+		const char *path = list->items[i].string;
+		if (baselen != -1 &&
+		    strncmp(path, list->items[first].string, baselen)) {
+			report_helper(list, seen_bits, first, i);
+			baselen = -1;
+			seen_bits = 0;
+		}
+		if (baselen == -1) {
+			const char *dot = strrchr(path, '.');
+			if (!dot) {
+				report_garbage("garbage found", path);
+				continue;
+			}
+			baselen = dot - path + 1;
+			first = i;
+		}
+		if (!strcmp(path + baselen, "pack"))
+			seen_bits |= 1;
+		else if (!strcmp(path + baselen, "idx"))
+			seen_bits |= 2;
+	}
+	report_helper(list, seen_bits, first, list->nr);
+}
+
 static void prepare_packed_git_one(char *objdir, int local)
 {
 	/* Ensure that this buffer is large enough so that we can
@@ -1009,6 +1067,7 @@ static void prepare_packed_git_one(char *objdir, int local)
 	int len;
 	DIR *dir;
 	struct dirent *de;
+	struct string_list garbage = STRING_LIST_INIT_DUP;
 
 	sprintf(path, "%s/pack", objdir);
 	len = strlen(path);
@@ -1024,29 +1083,49 @@ static void prepare_packed_git_one(char *objdir, int local)
 		int namelen = strlen(de->d_name);
 		struct packed_git *p;
 
-		if (!has_extension(de->d_name, ".idx"))
+		if (len + namelen + 1 > sizeof(path)) {
+			if (report_garbage) {
+				struct strbuf sb = STRBUF_INIT;
+				strbuf_addf(&sb, "%.*s/%s", len - 1, path, de->d_name);
+				report_garbage("path too long", sb.buf);
+				strbuf_release(&sb);
+			}
 			continue;
+		}
 
-		if (len + namelen + 1 > sizeof(path))
+		if (is_dot_or_dotdot(de->d_name))
 			continue;
 
-		/* Don't reopen a pack we already have. */
 		strcpy(path + len, de->d_name);
-		for (p = packed_git; p; p = p->next) {
-			if (!memcmp(path, p->pack_name, len + namelen - 4))
-				break;
+
+		if (has_extension(de->d_name, ".idx")) {
+			/* Don't reopen a pack we already have. */
+			for (p = packed_git; p; p = p->next) {
+				if (!memcmp(path, p->pack_name, len + namelen - 4))
+					break;
+			}
+			if (p == NULL &&
+			    /*
+			     * See if it really is a valid .idx file with
+			     * corresponding .pack file that we can map.
+			     */
+			    (p = add_packed_git(path, len + namelen, local)) != NULL)
+				install_packed_git(p);
 		}
-		if (p)
-			continue;
-		/* See if it really is a valid .idx file with corresponding
-		 * .pack file that we can map.
-		 */
-		p = add_packed_git(path, len + namelen, local);
-		if (!p)
+
+		if (!report_garbage)
 			continue;
-		install_packed_git(p);
+
+		if (has_extension(de->d_name, ".idx") ||
+		    has_extension(de->d_name, ".pack") ||
+		    has_extension(de->d_name, ".keep"))
+			string_list_append(&garbage, path);
+		else
+			report_garbage("garbage found", path);
 	}
 	closedir(dir);
+	report_pack_garbage(&garbage);
+	string_list_clear(&garbage, 0);
 }
 
 static int sort_pack(const void *a_, const void *b_)

t/t5304-prune.sh

@@ -195,4 +195,30 @@ test_expect_success 'gc: prune old objects after local clone' '
 	)
 '
 
+test_expect_success 'garbage report in count-objects -v' '
+	: >.git/objects/pack/foo &&
+	: >.git/objects/pack/foo.bar &&
+	: >.git/objects/pack/foo.keep &&
+	: >.git/objects/pack/foo.pack &&
+	: >.git/objects/pack/fake.bar &&
+	: >.git/objects/pack/fake.keep &&
+	: >.git/objects/pack/fake.pack &&
+	: >.git/objects/pack/fake.idx &&
+	: >.git/objects/pack/fake2.keep &&
+	: >.git/objects/pack/fake3.idx &&
+	git count-objects -v 2>stderr &&
+	grep "index file .git/objects/pack/fake.idx is too small" stderr &&
+	grep "^warning:" stderr | sort >actual &&
+	cat >expected <<\EOF &&
+warning: garbage found: .git/objects/pack/fake.bar
+warning: garbage found: .git/objects/pack/foo
+warning: garbage found: .git/objects/pack/foo.bar
+warning: no corresponding .idx nor .pack: .git/objects/pack/fake2.keep
+warning: no corresponding .idx: .git/objects/pack/foo.keep
+warning: no corresponding .idx: .git/objects/pack/foo.pack
+warning: no corresponding .pack: .git/objects/pack/fake3.idx
+EOF
+	test_cmp expected actual
+'
+
 test_done