Merge branch 'nd/fsck-progress'

* nd/fsck-progress:
  fsck: print progress
  fsck: avoid reading every object twice
  verify_packfile(): check as many object as possible in a pack
  fsck: return error code when verify_pack() goes wrong

Documentation/git-fsck.txt

@@ -10,7 +10,8 @@ SYNOPSIS
 --------
 [verse]
 'git fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
-	 [--[no-]full] [--strict] [--verbose] [--lost-found] [<object>*]
+	 [--[no-]full] [--strict] [--verbose] [--lost-found]
+	 [--[no-]progress] [<object>*]
 
 DESCRIPTION
 -----------
@@ -72,6 +73,14 @@ index file, all SHA1 references in .git/refs/*, and all reflogs (unless
 	a blob, the contents are written into the file, rather than
 	its object name.
 
+--progress::
+--no-progress::
+	Progress status is reported on the standard error stream by
+	default when it is attached to a terminal, unless
+	--no-progress or --verbose is specified. --progress forces
+	progress status even if the standard error stream is not
+	directed to a terminal.
+
 It tests SHA1 and general object sanity, and it does full tracking of
 the resulting reachability and everything else. It prints out any
 corruption it finds (missing or bad objects), and if you use the

builtin/fsck.c

@@ -11,6 +11,7 @@
 #include "fsck.h"
 #include "parse-options.h"
 #include "dir.h"
+#include "progress.h"
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
@@ -27,8 +28,10 @@ static const char *head_points_at;
 static int errors_found;
 static int write_lost_and_found;
 static int verbose;
+static int show_progress = -1;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
+#define ERROR_PACK 04
 
 #ifdef NO_D_INO_IN_DIRENT
 #define SORT_DIRENT 0
@@ -137,7 +140,11 @@ static int traverse_one_object(struct object *obj)
 
 static int traverse_reachable(void)
 {
+	struct progress *progress = NULL;
+	unsigned int nr = 0;
 	int result = 0;
+	if (show_progress)
+		progress = start_progress_delay("Checking connectivity", 0, 0, 2);
 	while (pending.nr) {
 		struct object_array_entry *entry;
 		struct object *obj;
@@ -145,7 +152,9 @@ static int traverse_reachable(void)
 		entry = pending.objects + --pending.nr;
 		obj = entry->item;
 		result |= traverse_one_object(obj);
+		display_progress(progress, ++nr);
 	}
+	stop_progress(&progress);
 	return !!result;
 }
 
@@ -281,14 +290,8 @@ static void check_connectivity(void)
 	}
 }
 
-static int fsck_sha1(const unsigned char *sha1)
+static int fsck_obj(struct object *obj)
 {
-	struct object *obj = parse_object(sha1);
-	if (!obj) {
-		errors_found |= ERROR_OBJECT;
-		return error("%s: object corrupt or missing",
-			     sha1_to_hex(sha1));
-	}
 	if (obj->flags & SEEN)
 		return 0;
 	obj->flags |= SEEN;
@@ -331,6 +334,29 @@ static int fsck_sha1(const unsigned char *sha1)
 	return 0;
 }
 
+static int fsck_sha1(const unsigned char *sha1)
+{
+	struct object *obj = parse_object(sha1);
+	if (!obj) {
+		errors_found |= ERROR_OBJECT;
+		return error("%s: object corrupt or missing",
+			     sha1_to_hex(sha1));
+	}
+	return fsck_obj(obj);
+}
+
+static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
+			   unsigned long size, void *buffer, int *eaten)
+{
+	struct object *obj;
+	obj = parse_object_buffer(sha1, type, size, buffer, eaten);
+	if (!obj) {
+		errors_found |= ERROR_OBJECT;
+		return error("%s: object corrupt or missing", sha1_to_hex(sha1));
+	}
+	return fsck_obj(obj);
+}
+
 /*
  * This is the sorting chunk size: make it reasonably
  * big so that we can sort well..
@@ -512,15 +538,20 @@ static void get_default_heads(void)
 static void fsck_object_dir(const char *path)
 {
 	int i;
+	struct progress *progress = NULL;
 
 	if (verbose)
 		fprintf(stderr, "Checking object directory\n");
 
+	if (show_progress)
+		progress = start_progress("Checking object directories", 256);
 	for (i = 0; i < 256; i++) {
 		static char dir[4096];
 		sprintf(dir, "%s/%02x", path, i);
 		fsck_dir(i, dir);
+		display_progress(progress, i+1);
 	}
+	stop_progress(&progress);
 	fsck_sha1_list();
 }
 
@@ -591,6 +622,7 @@ static struct option fsck_opts[] = {
 	OPT_BOOLEAN(0, "strict", &check_strict, "enable more strict checking"),
 	OPT_BOOLEAN(0, "lost-found", &write_lost_and_found,
 				"write dangling objects in .git/lost-found"),
+	OPT_BOOL(0, "progress", &show_progress, "show progress"),
 	OPT_END(),
 };
 
@@ -603,6 +635,12 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 	read_replace_refs = 0;
 
 	argc = parse_options(argc, argv, prefix, fsck_opts, fsck_usage, 0);
+
+	if (show_progress == -1)
+		show_progress = isatty(2);
+	if (verbose)
+		show_progress = 0;
+
 	if (write_lost_and_found) {
 		check_full = 1;
 		include_reflogs = 0;
@@ -622,20 +660,28 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 
 	if (check_full) {
 		struct packed_git *p;
+		uint32_t total = 0, count = 0;
+		struct progress *progress = NULL;
 
 		prepare_packed_git();
-		for (p = packed_git; p; p = p->next)
-			/* verify gives error messages itself */
-			verify_pack(p);
 
+		if (show_progress) {
+			for (p = packed_git; p; p = p->next) {
+				if (open_pack_index(p))
+					continue;
+				total += p->num_objects;
+			}
+
+			progress = start_progress("Checking objects", total);
+		}
 		for (p = packed_git; p; p = p->next) {
-			uint32_t j, num;
-			if (open_pack_index(p))
-				continue;
-			num = p->num_objects;
-			for (j = 0; j < num; j++)
-				fsck_sha1(nth_packed_object_sha1(p, j));
+			/* verify gives error messages itself */
+			if (verify_pack(p, fsck_obj_buffer,
+					progress, count))
+				errors_found |= ERROR_PACK;
+			count += p->num_objects;
 		}
+		stop_progress(&progress);
 	}
 
 	heads = 0;

pack-check.c

@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "pack.h"
 #include "pack-revindex.h"
+#include "progress.h"
 
 struct idx_entry {
 	off_t                offset;
@@ -42,7 +43,10 @@ int check_pack_crc(struct packed_git *p, struct pack_window **w_curs,
 }
 
 static int verify_packfile(struct packed_git *p,
-		struct pack_window **w_curs)
+			   struct pack_window **w_curs,
+			   verify_fn fn,
+			   struct progress *progress, uint32_t base_count)
+
 {
 	off_t index_size = p->index_size;
 	const unsigned char *index_base = p->index_data;
@@ -113,20 +117,25 @@ static int verify_packfile(struct packed_git *p,
 					    p->pack_name, (uintmax_t)offset);
 		}
 		data = unpack_entry(p, entries[i].offset, &type, &size);
-		if (!data) {
+		if (!data)
 			err = error("cannot unpack %s from %s at offset %"PRIuMAX"",
 				    sha1_to_hex(entries[i].sha1), p->pack_name,
 				    (uintmax_t)entries[i].offset);
-			break;
-		}
-		if (check_sha1_signature(entries[i].sha1, data, size, typename(type))) {
+		else if (check_sha1_signature(entries[i].sha1, data, size, typename(type)))
 			err = error("packed %s from %s is corrupt",
 				    sha1_to_hex(entries[i].sha1), p->pack_name);
-			free(data);
-			break;
+		else if (fn) {
+			int eaten = 0;
+			fn(entries[i].sha1, type, size, data, &eaten);
+			if (eaten)
+				data = NULL;
 		}
+		if (((base_count + i) & 1023) == 0)
+			display_progress(progress, base_count + i);
 		free(data);
+
 	}
+	display_progress(progress, base_count + i);
 	free(entries);
 
 	return err;
@@ -155,7 +164,8 @@ int verify_pack_index(struct packed_git *p)
 	return err;
 }
 
-int verify_pack(struct packed_git *p)
+int verify_pack(struct packed_git *p, verify_fn fn,
+		struct progress *progress, uint32_t base_count)
 {
 	int err = 0;
 	struct pack_window *w_curs = NULL;
@@ -164,7 +174,7 @@ int verify_pack(struct packed_git *p)
 	if (!p->index_data)
 		return -1;
 
-	err |= verify_packfile(p, &w_curs);
+	err |= verify_packfile(p, &w_curs, fn, progress, base_count);
 	unuse_pack(&w_curs);
 
 	return err;

pack.h

@@ -70,10 +70,14 @@ struct pack_idx_entry {
 	off_t offset;
 };
 
+
+struct progress;
+typedef int (*verify_fn)(const unsigned char*, enum object_type, unsigned long, void*, int*);
+
 extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, const struct pack_idx_option *, unsigned char *sha1);
 extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr);
 extern int verify_pack_index(struct packed_git *);
-extern int verify_pack(struct packed_git *);
+extern int verify_pack(struct packed_git *, verify_fn fn, struct progress *, uint32_t);
 extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t, unsigned char *, off_t);
 extern char *index_pack_lockfile(int fd);
 extern int encode_in_pack_object_header(enum object_type, uintmax_t, unsigned char *);