Partial clone part 2: fsck and promisors

index 6440e2b..35e3f5e 100644
@@ -860,10 +860,12 @@ extern int grafts_replace_parents;
 #define GIT_REPO_VERSION 0
 #define GIT_REPO_VERSION_READ 1
 extern int repository_format_precious_objects;
+extern char *repository_format_partial_clone;
 
 struct repository_format {
 	int version;
 	int precious_objects;
+	char *partial_clone; /* value of extensions.partialclone */
 	int is_bare;
 	char *work_tree;
 	struct string_list unknown_extensions;

index 8289c25..e52aab3 100644
@@ -27,6 +27,7 @@ int warn_ambiguous_refs = 1;
 int warn_on_object_refname_ambiguity = 1;
 int ref_paranoia = -1;
 int repository_format_precious_objects;
+char *repository_format_partial_clone;
 const char *git_commit_encoding;
 const char *git_log_output_encoding;
 const char *apply_default_whitespace;

index 03f51e0..58536bd 100644
@@ -420,7 +420,11 @@ static int check_repo_format(const char *var, const char *value, void *vdata)
 			;
 		else if (!strcmp(ext, "preciousobjects"))
 			data->precious_objects = git_config_bool(var, value);
-		else
+		else if (!strcmp(ext, "partialclone")) {
+			if (!value)
+				return config_error_nonbool(var);
+			data->partial_clone = xstrdup(value);
+		} else
 			string_list_append(&data->unknown_extensions, ext);
 	} else if (strcmp(var, "core.bare") == 0) {
 		data->is_bare = git_config_bool(var, value);

@@ -463,6 +467,7 @@ static int check_repository_format_gently(const char *gitdir, int *nongit_ok)
 	}
 
 	repository_format_precious_objects = candidate.precious_objects;
+	repository_format_partial_clone = candidate.partial_clone;
 	string_list_clear(&candidate.unknown_extensions, 0);
 	if (!has_common) {
 		if (candidate.is_bare != -1) {

index 56afe40..2934299 100644
@@ -398,7 +398,7 @@ static void fsck_handle_reflog_oid(const char *refname, struct object_id *oid,
 					xstrfmt("%s@{%"PRItime"}", refname, timestamp));
 			obj->flags |= USED;
 			mark_object_reachable(obj);
-		} else {
+		} else if (!is_promisor_object(oid)) {
 			error("%s: invalid reflog entry %s", refname, oid_to_hex(oid));
 			errors_found |= ERROR_REACHABLE;
 		}

index 35e3f5e..c76f2e9 100644
@@ -1587,7 +1587,8 @@ extern struct packed_git {
 	unsigned pack_local:1,
 		 pack_keep:1,
 		 freshened:1,
-		 do_not_close:1;
+		 do_not_close:1,
+		 pack_promisor:1;
 	unsigned char sha1[20];
 	struct revindex_entry *revindex;
 	/* something like ".git/objects/pack/xxxxx.pack" */

112 lines not on this page · raw message

index 0cdeb54..a7fca59 100644
@@ -1,6 +1,8 @@
 #ifndef PACKFILE_H
 #define PACKFILE_H
 
+#include "oidset.h"
+
 /*
  * Generate the filename to be used for a pack file with checksum "sha1" and
  * extension "ext". The result is written into the strbuf "buf", overwriting

@@ -125,6 +127,11 @@ extern int has_sha1_pack(const unsigned char *sha1);
 extern int has_pack_index(const unsigned char *sha1);
 
 /*
+ * Only iterate over packs obtained from the promisor remote.
+ */
+#define FOR_EACH_OBJECT_PROMISOR_ONLY 2
+
+/*
  * Iterate over packed objects in both the local
  * repository and any alternates repositories (unless the
  * FOR_EACH_OBJECT_LOCAL_ONLY flag, defined in cache.h, is set).

@@ -135,4 +142,10 @@ typedef int each_packed_object_fn(const struct object_id *oid,
 				  void *data);
 extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags);
 
+/*
+ * Return 1 if an object in a promisor packfile is or refers to the given
+ * object, 0 otherwise.
+ */
+extern int is_promisor_object(const struct object_id *oid);
+
 #endif

index 2934299..ee937bb 100644
@@ -434,6 +434,14 @@ static int fsck_handle_ref(const char *refname, const struct object_id *oid,
 
 	obj = parse_object(oid);
 	if (!obj) {
+		if (is_promisor_object(oid)) {
+			/*
+			 * Increment default_refs anyway, because this is a
+			 * valid ref.
+			 */
+			 default_refs++;
+			 return 0;
+		}
 		error("%s: invalid sha1 pointer %s", refname, oid_to_hex(oid));
 		errors_found |= ERROR_REACHABLE;
 		/* We'll continue with the rest despite the error.. */

index ee937bb..4c2a56d 100644
@@ -149,6 +149,15 @@ static int mark_object(struct object *obj, int type, void *data, struct fsck_opt
 	if (obj->flags & REACHABLE)
 		return 0;
 	obj->flags |= REACHABLE;
+
+	if (is_promisor_object(&obj->oid))
+		/*
+		 * Further recursion does not need to be performed on this
+		 * object since it is a promisor object (so it does not need to
+		 * be added to "pending").
+		 */
+		return 0;
+
 	if (!(obj->flags & HAS_OBJ)) {
 		if (parent && !has_object_file(&obj->oid)) {
 			printf("broken link from %7s %s\n",

@@ -208,6 +217,8 @@ static void check_reachable_object(struct object *obj)
 	 * do a full fsck
 	 */
 	if (!(obj->flags & HAS_OBJ)) {
+		if (is_promisor_object(&obj->oid))
+			return;
 		if (has_sha1_pack(obj->oid.hash))
 			return; /* it is in pack - forget about it */
 		printf("missing %s %s\n", printable_type(obj),

index 4c2a56d..578a7c8 100644
@@ -750,6 +750,8 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 			struct object *obj = lookup_object(oid.hash);
 
 			if (!obj || !(obj->flags & HAS_OBJ)) {
+				if (is_promisor_object(&oid))
+					continue;
 				error("%s: object missing", oid_to_hex(&oid));
 				errors_found |= ERROR_OBJECT;
 				continue;

index 8ec459f..4f305a7 100644
@@ -1389,15 +1389,58 @@ static void fix_unresolved_deltas(struct sha1file *f)
 	free(sorted_by_pos);
 }
 
+static const char *derive_filename(const char *pack_name, 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);
+	strbuf_add(buf, pack_name, len);
+	strbuf_addch(buf, '.');
+	strbuf_addstr(buf, suffix);
+	return buf->buf;
+}
+
+static void write_special_file(const char *suffix, const char *msg,
+			       const char *pack_name, const unsigned char *sha1,
+			       const char **report)
+{
+	struct strbuf name_buf = STRBUF_INIT;
+	const char *filename;
+	int fd;
+	int msg_len = strlen(msg);
+
+	if (pack_name)
+		filename = derive_filename(pack_name, suffix, &name_buf);
+	else
+		filename = odb_pack_name(&name_buf, sha1, suffix);
+
+	fd = odb_pack_keep(filename);
+	if (fd < 0) {
+		if (errno != EEXIST)
+			die_errno(_("cannot write %s file '%s'"),
+				  suffix, filename);
+	} else {
+		if (msg_len > 0) {
+			write_or_die(fd, msg, msg_len);
+			write_or_die(fd, "\n", 1);
+		}
+		if (close(fd) != 0)
+			die_errno(_("cannot close written %s file '%s'"),
+				  suffix, filename);
+		*report = suffix;
+	}
+	strbuf_release(&name_buf);
+}
+
 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 *keep_name, const char *keep_msg,
-		  unsigned char *sha1)
+		  const char *keep_msg, unsigned char *sha1)
 {
 	const char *report = "pack";
 	struct strbuf pack_name = STRBUF_INIT;
 	struct strbuf index_name = STRBUF_INIT;
-	struct strbuf keep_name_buf = STRBUF_INIT;
 	int err;
 
 	if (!from_stdin) {

@@ -1409,28 +1452,9 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 			die_errno(_("error while closing pack file"));
 	}
 
-	if (keep_msg) {
-		int keep_fd, keep_msg_len = strlen(keep_msg);
-
-		if (!keep_name)
-			keep_name = odb_pack_name(&keep_name_buf, sha1, "keep");
-
-		keep_fd = odb_pack_keep(keep_name);
-		if (keep_fd < 0) {
-			if (errno != EEXIST)
-				die_errno(_("cannot write keep file '%s'"),
-					  keep_name);
-		} else {
-			if (keep_msg_len > 0) {
-				write_or_die(keep_fd, keep_msg, keep_msg_len);
-				write_or_die(keep_fd, "\n", 1);
-			}
-			if (close(keep_fd) != 0)
-				die_errno(_("cannot close written keep file '%s'"),
-					  keep_name);
-			report = "keep";
-		}
-	}
+	if (keep_msg)
+		write_special_file("keep", keep_msg, final_pack_name, sha1,
+				   &report);
 
 	if (final_pack_name != curr_pack_name) {
 		if (!final_pack_name)

@@ -1472,7 +1496,6 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 
 	strbuf_release(&index_name);
 	strbuf_release(&pack_name);
-	strbuf_release(&keep_name_buf);
 }
 
 static int git_index_pack_config(const char *k, const char *v, void *cb)

@@ -1615,26 +1638,13 @@ static void show_pack_info(int stat_only)
 	}
 }
 
-static const char *derive_filename(const char *pack_name, 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);
-	strbuf_add(buf, pack_name, len);
-	strbuf_addstr(buf, suffix);
-	return buf->buf;
-}
-
 int cmd_index_pack(int argc, const char **argv, const char *prefix)
 {
 	int i, fix_thin_pack = 0, verify = 0, stat_only = 0;
 	const char *curr_index;
 	const char *index_name = NULL, *pack_name = NULL;
-	const char *keep_name = NULL, *keep_msg = NULL;
-	struct strbuf index_name_buf = STRBUF_INIT,
-		      keep_name_buf = STRBUF_INIT;
+	const char *keep_msg = NULL;
+	struct strbuf index_name_buf = STRBUF_INIT;
 	struct pack_idx_entry **idx_objects;
 	struct pack_idx_option opts;
 	unsigned char pack_sha1[20];

@@ -1745,9 +1755,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (from_stdin && !startup_info->have_repository)
 		die(_("--stdin requires a git repository"));
 	if (!index_name && pack_name)
-		index_name = derive_filename(pack_name, ".idx", &index_name_buf);
-	if (keep_msg && !keep_name && pack_name)
-		keep_name = derive_filename(pack_name, ".keep", &keep_name_buf);
+		index_name = derive_filename(pack_name, "idx", &index_name_buf);
 
 	if (verify) {
 		if (!index_name)

@@ -1795,13 +1803,12 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (!verify)
 		final(pack_name, curr_pack,
 		      index_name, curr_index,
-		      keep_name, keep_msg,
+		      keep_msg,
 		      pack_sha1);
 	else
 		close(input_fd);
 	free(objects);
 	strbuf_release(&index_name_buf);
-	strbuf_release(&keep_name_buf);
 	if (pack_name == NULL)
 		free((void *) curr_pack);
 	if (index_name == NULL)

index 366b9d1..9f303cf 100644
@@ -143,6 +143,14 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
 			args.update_shallow = 1;
 			continue;
 		}
+		if (!strcmp("--from-promisor", arg)) {
+			args.from_promisor = 1;
+			continue;
+		}
+		if (!strcmp("--no-haves", arg)) {
+			args.no_haves = 1;
+			continue;
+		}
 		usage(fetch_pack_usage);
 	}
 	if (deepen_not.nr)

index 4f305a7..24c2f05 100644
@@ -1429,14 +1429,16 @@ static void write_special_file(const char *suffix, const char *msg,
 		if (close(fd) != 0)
 			die_errno(_("cannot close written %s file '%s'"),
 				  suffix, filename);
-		*report = suffix;
+		if (report)
+			*report = suffix;
 	}
 	strbuf_release(&name_buf);
 }
 
 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 *keep_msg, unsigned char *sha1)
+		  const char *keep_msg, const char *promisor_msg,
+		  unsigned char *sha1)
 {
 	const char *report = "pack";
 	struct strbuf pack_name = STRBUF_INIT;

@@ -1455,6 +1457,9 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
 	if (keep_msg)
 		write_special_file("keep", keep_msg, final_pack_name, sha1,
 				   &report);
+	if (promisor_msg)
+		write_special_file("promisor", promisor_msg, final_pack_name,
+				   sha1, NULL);
 
 	if (final_pack_name != curr_pack_name) {
 		if (!final_pack_name)

@@ -1644,6 +1649,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	const char *curr_index;
 	const char *index_name = NULL, *pack_name = NULL;
 	const char *keep_msg = NULL;
+	const char *promisor_msg = NULL;
 	struct strbuf index_name_buf = STRBUF_INIT;
 	struct pack_idx_entry **idx_objects;
 	struct pack_idx_option opts;

@@ -1693,6 +1699,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				keep_msg = "";
 			} else if (starts_with(arg, "--keep=")) {
 				keep_msg = arg + 7;
+			} else if (!strcmp(arg, "--promisor")) {
+				promisor_msg = "";
+			} else if (starts_with(arg, "--promisor=")) {
+				promisor_msg = arg + strlen("--promisor=");
 			} else if (starts_with(arg, "--threads=")) {
 				char *end;
 				nr_threads = strtoul(arg+10, &end, 0);

@@ -1803,7 +1813,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (!verify)
 		final(pack_name, curr_pack,
 		      index_name, curr_index,
-		      keep_msg,
+		      keep_msg, promisor_msg,
 		      pack_sha1);
 	else
 		close(input_fd);

new file mode 100644
index 0000000..78c939d
@@ -0,0 +1,24 @@
+#include "cache.h"
+#include "packfile.h"
+#include "pkt-line.h"
+#include "strbuf.h"
+#include "transport.h"
+#include "fetch-object.h"
+
+void fetch_object(const char *remote_name, const unsigned char *sha1)
+{
+	struct remote *remote;
+	struct transport *transport;
+	struct ref *ref;
+
+	remote = remote_get(remote_name);
+	if (!remote->url[0])
+		die(_("Remote with no URL"));
+	transport = transport_get(remote, remote->url[0]);
+
+	ref = alloc_ref(sha1_to_hex(sha1));
+	hashcpy(ref->old_oid.hash, sha1);
+	transport_set_option(transport, TRANS_OPT_FROM_PROMISOR, "1");
+	transport_set_option(transport, TRANS_OPT_NO_HAVES, "1");
+	transport_fetch_refs(transport, ref);
+}

new file mode 100644
index 0000000..f371300
@@ -0,0 +1,6 @@
+#ifndef FETCH_OBJECT_H
+#define FETCH_OBJECT_H
+
+extern void fetch_object(const char *remote_name, const unsigned char *sha1);
+
+#endif

index 008b25d..4640b4e 100644
@@ -450,6 +450,8 @@ static int find_common(struct fetch_pack_args *args,
 
 	flushes = 0;
 	retval = -1;
+	if (args->no_haves)
+		goto done;
 	while ((oid = get_rev())) {
 		packet_buf_write(&req_buf, "have %s\n", oid_to_hex(oid));
 		print_verbose(args, "have %s", oid_to_hex(oid));

@@ -832,7 +834,7 @@ static int get_pack(struct fetch_pack_args *args,
 		argv_array_push(&cmd.args, alternate_shallow_file);
 	}
 
-	if (do_keep) {
+	if (do_keep || args->from_promisor) {
 		if (pack_lockfile)
 			cmd.out = -1;
 		cmd_name = "index-pack";

@@ -842,7 +844,7 @@ static int get_pack(struct fetch_pack_args *args,
 			argv_array_push(&cmd.args, "-v");
 		if (args->use_thin_pack)
 			argv_array_push(&cmd.args, "--fix-thin");
-		if (args->lock_pack || unpack_limit) {
+		if (do_keep && (args->lock_pack || unpack_limit)) {
 			char hostname[HOST_NAME_MAX + 1];
 			if (xgethostname(hostname, sizeof(hostname)))
 				xsnprintf(hostname, sizeof(hostname), "localhost");

@@ -852,6 +854,8 @@ static int get_pack(struct fetch_pack_args *args,
 		}
 		if (args->check_self_contained_and_connected)
 			argv_array_push(&cmd.args, "--check-self-contained-and-connected");
+		if (args->from_promisor)
+			argv_array_push(&cmd.args, "--promisor");
 	}
 	else {
 		cmd_name = "unpack-objects";

index b6aeb43..84904c3 100644
@@ -29,6 +29,8 @@ struct fetch_pack_args {
 	unsigned cloning:1;
 	unsigned update_shallow:1;
 	unsigned deepen:1;
+	unsigned from_promisor:1;
+	unsigned no_haves:1;
 };
 
 /*

index 0053b09..34a81b8 100644
@@ -33,7 +33,9 @@ struct options {
 		thin : 1,
 		/* One of the SEND_PACK_PUSH_CERT_* constants. */
 		push_cert : 2,
-		deepen_relative : 1;
+		deepen_relative : 1,
+		from_promisor : 1,
+		no_haves : 1;
 };
 static struct options options;
 static struct string_list cas_options = STRING_LIST_INIT_DUP;

@@ -157,6 +159,12 @@ static int set_option(const char *name, const char *value)
 			return -1;
 		return 0;
 #endif /* LIBCURL_VERSION_NUM >= 0x070a08 */
+	} else if (!strcmp(name, "from-promisor")) {
+		options.from_promisor = 1;
+		return 0;
+	} else if (!strcmp(name, "no-haves")) {
+		options.no_haves = 1;
+		return 0;
 	} else {
 		return 1 /* unsupported */;
 	}

@@ -822,6 +830,10 @@ static int fetch_git(struct discovery *heads,
 				 options.deepen_not.items[i].string);
 	if (options.deepen_relative && options.depth)
 		argv_array_push(&args, "--deepen-relative");
+	if (options.from_promisor)
+		argv_array_push(&args, "--from-promisor");
+	if (options.no_haves)
+		argv_array_push(&args, "--no-haves");
 	argv_array_push(&args, url.buf);
 
 	for (i = 0; i < nr_heads; i++) {

index f1e2f61..8211f82 100644
@@ -160,6 +160,12 @@ static int set_git_option(struct git_transport_options *opts,
 	} else if (!strcmp(name, TRANS_OPT_DEEPEN_RELATIVE)) {
 		opts->deepen_relative = !!value;
 		return 0;
+	} else if (!strcmp(name, TRANS_OPT_FROM_PROMISOR)) {
+		opts->from_promisor = !!value;
+		return 0;
+	} else if (!strcmp(name, TRANS_OPT_NO_HAVES)) {
+		opts->no_haves = !!value;
+		return 0;
 	}
 	return 1;
 }

@@ -228,6 +234,8 @@ static int fetch_refs_via_pack(struct transport *transport,
 		data->options.check_self_contained_and_connected;
 	args.cloning = transport->cloning;
 	args.update_shallow = data->options.update_shallow;
+	args.from_promisor = data->options.from_promisor;
+	args.no_haves = data->options.no_haves;
 
 	if (!data->got_remote_heads) {
 		connect_setup(transport, 0);

index bc55715..67428f6 100644
@@ -15,6 +15,8 @@ struct git_transport_options {
 	unsigned self_contained_and_connected : 1;
 	unsigned update_shallow : 1;
 	unsigned deepen_relative : 1;
+	unsigned from_promisor : 1;
+	unsigned no_haves : 1;
 	int depth;
 	const char *deepen_since;
 	const struct string_list *deepen_not;

@@ -210,6 +212,12 @@ void transport_check_allowed(const char *type);
 /* Send push certificates */
 #define TRANS_OPT_PUSH_CERT "pushcert"
 
+/* Indicate that these objects are being fetched by a promisor */
+#define TRANS_OPT_FROM_PROMISOR "from-promisor"
+
+/* Do not send "have" lines */
+#define TRANS_OPT_NO_HAVES "no-haves"
+
 /**
  * Returns 0 if the option was used, non-zero otherwise. Prints a
  * message to stderr if the option is not used.

index f5fa4fd..cf9ea5c 100644
@@ -475,6 +475,8 @@ static int batch_objects(struct batch_options *opt)
 
 		for_each_loose_object(batch_loose_object, &sa, 0);
 		for_each_packed_object(batch_packed_object, &sa, 0);
+		if (repository_format_partial_clone)
+			warning("This repository has extensions.partialClone set. Some objects may not be loaded.");
 
 		cb.opt = opt;
 		cb.expand = &data;

index 9f303cf..9a7ebf6 100644
@@ -53,6 +53,8 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
 	struct oid_array shallow = OID_ARRAY_INIT;
 	struct string_list deepen_not = STRING_LIST_INIT_DUP;
 
+	fetch_if_missing = 0;
+
 	packet_trace_identity("fetch-pack");
 
 	memset(&args, 0, sizeof(args));

index 578a7c8..3b76c0e 100644
@@ -678,6 +678,9 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 	int i;
 	struct alternate_object_database *alt;
 
+	/* fsck knows how to handle missing promisor objects */
+	fetch_if_missing = 0;
+
 	errors_found = 0;
 	check_replace_refs = 0;
 

index 24c2f05..a0a35e6 100644
@@ -1657,6 +1657,12 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	unsigned foreign_nr = 1;	/* zero is a "good" value, assume bad */
 	int report_end_of_input = 0;
 
+	/*
+	 * index-pack never needs to fetch missing objects, since it only
+	 * accesses the repo to do hash collision checks
+	 */
+	fetch_if_missing = 0;
+
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage(index_pack_usage);
 

index c76f2e9..6980072 100644
@@ -1727,6 +1727,14 @@ struct object_info {
 #define OBJECT_INFO_QUICK 8
 extern int sha1_object_info_extended(const unsigned char *, struct object_info *, unsigned flags);
 
+/*
+ * Set this to 0 to prevent sha1_object_info_extended() from fetching missing
+ * blobs. This has a difference only if extensions.partialClone is set.
+ *
+ * Its default value is 1.
+ */
+extern int fetch_if_missing;
+
 /* Dumb servers support */
 extern int update_server_info(int);
 

index 78c939d..fc086fc 100644
@@ -10,7 +10,9 @@ void fetch_object(const char *remote_name, const unsigned char *sha1)
 	struct remote *remote;
 	struct transport *transport;
 	struct ref *ref;
+	int original_fetch_if_missing = fetch_if_missing;
 
+	fetch_if_missing = 0;
 	remote = remote_get(remote_name);
 	if (!remote->url[0])
 		die(_("Remote with no URL"));

@@ -21,4 +23,5 @@ void fetch_object(const char *remote_name, const unsigned char *sha1)
 	transport_set_option(transport, TRANS_OPT_FROM_PROMISOR, "1");
 	transport_set_option(transport, TRANS_OPT_NO_HAVES, "1");
 	transport_fetch_refs(transport, ref);
+	fetch_if_missing = original_fetch_if_missing;
 }

index 10c3a00..fc7718a 100644
@@ -29,6 +29,7 @@
 #include "mergesort.h"
 #include "quote.h"
 #include "packfile.h"
+#include "fetch-object.h"
 
 const unsigned char null_sha1[GIT_MAX_RAWSZ];
 const struct object_id null_oid;

@@ -1144,6 +1145,8 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 	return (status < 0) ? status : 0;
 }
 
+int fetch_if_missing = 1;
+
 int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi, unsigned flags)
 {
 	static struct object_info blank_oi = OBJECT_INFO_INIT;

@@ -1152,6 +1155,7 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 	const unsigned char *real = (flags & OBJECT_INFO_LOOKUP_REPLACE) ?
 				    lookup_replace_object(sha1) :
 				    sha1;
+	int already_retried = 0;
 
 	if (!oi)
 		oi = &blank_oi;

@@ -1176,28 +1180,36 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		}
 	}
 
-	if (!find_pack_entry(real, &e)) {
-		/* Most likely it's a loose object. */
-		if (!sha1_loose_object_info(real, oi, flags))
-			return 0;
+retry:
+	if (find_pack_entry(real, &e))
+		goto found_packed;
 
-		/* Not a loose object; someone else may have just packed it. */
-		if (flags & OBJECT_INFO_QUICK) {
-			return -1;
-		} else {
-			reprepare_packed_git();
-			if (!find_pack_entry(real, &e))
-				return -1;
-		}
+	/* Most likely it's a loose object. */
+	if (!sha1_loose_object_info(real, oi, flags))
+		return 0;
+
+	/* Not a loose object; someone else may have just packed it. */
+	reprepare_packed_git();
+	if (find_pack_entry(real, &e))
+		goto found_packed;
+
+	/* Check if it is a missing object */
+	if (fetch_if_missing && repository_format_partial_clone &&
+	    !already_retried) {
+		fetch_object(repository_format_partial_clone, real);
+		already_retried = 1;
+		goto retry;
 	}
 
+	return -1;
+
+found_packed:
 	if (oi == &blank_oi)
 		/*
 		 * We know that the caller doesn't actually need the
 		 * information below, so return early.
 		 */
 		return 0;
-
 	rtype = packed_object_info(e.p, e.offset, oi);
 	if (rtype < 0) {
 		mark_bad_packed_object(e.p, real);

134 lines not on this page · raw message

index d9e83d0..58621fc 100644
@@ -9,6 +9,7 @@
 #include "list-objects.h"
 #include "list-objects-filter.h"
 #include "list-objects-filter-options.h"
+#include "packfile.h"
 
 static void process_blob(struct rev_info *revs,
 			 struct blob *blob,

@@ -30,6 +31,20 @@ static void process_blob(struct rev_info *revs,
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
 
+	/*
+	 * Pre-filter known-missing objects when explicitly requested.
+	 * Otherwise, a missing object error message may be reported
+	 * later (depending on other filtering criteria).
+	 *
+	 * Note that this "--exclude-promisor-objects" pre-filtering
+	 * may cause the actual filter to report an incomplete list
+	 * of missing objects.
+	 */
+	if (revs->exclude_promisor_objects &&
+	    !has_object_file(&obj->oid) &&
+	    is_promisor_object(&obj->oid))
+		return;
+
 	pathlen = path->len;
 	strbuf_addstr(path, name);
 	if (filter_fn)

@@ -91,6 +106,8 @@ static void process_tree(struct rev_info *revs,
 		all_entries_interesting: entry_not_interesting;
 	int baselen = base->len;
 	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
+	int gently = revs->ignore_missing_links ||
+		     revs->exclude_promisor_objects;
 
 	if (!revs->tree_objects)
 		return;

@@ -98,9 +115,19 @@ static void process_tree(struct rev_info *revs,
 		die("bad tree object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
-	if (parse_tree_gently(tree, revs->ignore_missing_links) < 0) {
+	if (parse_tree_gently(tree, gently) < 0) {
 		if (revs->ignore_missing_links)
 			return;
+
+		/*
+		 * Pre-filter known-missing tree objects when explicitly
+		 * requested.  This may cause the actual filter to report
+		 * an incomplete list of missing objects.
+		 */
+		if (revs->exclude_promisor_objects &&
+		    is_promisor_object(&obj->oid))
+			return;
+
 		die("bad tree object %s", oid_to_hex(&obj->oid));
 	}
 

index b9a4a0e..4c222d6 100644
@@ -252,7 +252,7 @@ struct object *parse_object(const struct object_id *oid)
 	if (obj && obj->parsed)
 		return obj;
 
-	if ((obj && obj->type == OBJ_BLOB) ||
+	if ((obj && obj->type == OBJ_BLOB && has_object_file(oid)) ||
 	    (!obj && has_object_file(oid) &&
 	     sha1_object_info(oid->hash, NULL) == OBJ_BLOB)) {
 		if (check_sha1_signature(repl, NULL, 0, NULL) < 0) {

index d167223..05a7aac 100644
@@ -198,6 +198,8 @@ static struct object *get_reference(struct rev_info *revs, const char *name,
 	if (!object) {
 		if (revs->ignore_missing)
 			return object;
+		if (revs->exclude_promisor_objects && is_promisor_object(oid))
+			return NULL;
 		die("bad object %s", name);
 	}
 	object->flags |= flags;

@@ -790,9 +792,17 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit,
 
 	for (parent = commit->parents; parent; parent = parent->next) {
 		struct commit *p = parent->item;
-
-		if (parse_commit_gently(p, revs->ignore_missing_links) < 0)
+		int gently = revs->ignore_missing_links ||
+			     revs->exclude_promisor_objects;
+		if (parse_commit_gently(p, gently) < 0) {
+			if (revs->exclude_promisor_objects &&
+			    is_promisor_object(&p->object.oid)) {
+				if (revs->first_parent_only)
+					break;
+				continue;
+			}
 			return -1;
+		}
 		if (revs->show_source && !p->util)
 			p->util = commit->util;
 		p->object.flags |= left_flag;

@@ -2088,6 +2098,10 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 		revs->limited = 1;
 	} else if (!strcmp(arg, "--ignore-missing")) {
 		revs->ignore_missing = 1;
+	} else if (!strcmp(arg, "--exclude-promisor-objects")) {
+		if (fetch_if_missing)
+			die("BUG: exclude_promisor_objects can only be used when fetch_if_missing is 0");
+		revs->exclude_promisor_objects = 1;
 	} else {
 		int opts = diff_opt_parse(&revs->diffopt, argv, argc, revs->prefix);
 		if (!opts)

@@ -2830,6 +2844,16 @@ void reset_revision_walk(void)
 	clear_object_flags(SEEN | ADDED | SHOWN);
 }
 
+static int mark_uninteresting(const struct object_id *oid,
+			      struct packed_git *pack,
+			      uint32_t pos,
+			      void *unused)
+{
+	struct object *o = parse_object(oid);
+	o->flags |= UNINTERESTING | SEEN;
+	return 0;
+}
+
 int prepare_revision_walk(struct rev_info *revs)
 {
 	int i;

@@ -2858,6 +2882,11 @@ int prepare_revision_walk(struct rev_info *revs)
 	    (revs->limited && limiting_can_increase_treesame(revs)))
 		revs->treesame.name = "treesame";
 
+	if (revs->exclude_promisor_objects) {
+		for_each_packed_object(mark_uninteresting, NULL,
+				       FOR_EACH_OBJECT_PROMISOR_ONLY);
+	}
+
 	if (revs->no_walk != REVISION_WALK_NO_WALK_UNSORTED)
 		commit_list_sort_by_date(&revs->commits);
 	if (revs->no_walk)

index 5476120..5f9a49c 100644
@@ -121,7 +121,10 @@ struct rev_info {
 			bisect:1,
 			ancestry_path:1,
 			first_parent_only:1,
-			line_level_traverse:1;
+			line_level_traverse:1,
+
+			/* for internal use only */
+			exclude_promisor_objects:1;
 
 	/* Diff flags */
 	unsigned int	diff:1,

index 3c5eae0..77fa720 100644
@@ -458,6 +458,9 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 			argv_array_push(&prune, prune_expire);
 			if (quiet)
 				argv_array_push(&prune, "--no-progress");
+			if (repository_format_partial_clone)
+				argv_array_push(&prune,
+						"--exclude-promisor-objects");
 			if (run_command_v_opt(prune.argv, RUN_GIT_CMD))
 				return error(FAILED_RUN, prune.argv[0]);
 		}

index 45ad35d..f5fc401 100644
@@ -75,6 +75,8 @@ static int use_bitmap_index = -1;
 static int write_bitmap_index;
 static uint16_t write_bitmap_options;
 
+static int exclude_promisor_objects;
+
 static unsigned long delta_cache_size = 0;
 static unsigned long max_delta_cache_size = 256 * 1024 * 1024;
 static unsigned long cache_max_small_delta_size = 1000;

@@ -84,8 +86,9 @@ static unsigned long window_memory_limit = 0;
 static struct list_objects_filter_options filter_options;
 
 enum missing_action {
-	MA_ERROR = 0,    /* fail if any missing objects are encountered */
-	MA_ALLOW_ANY,    /* silently allow ALL missing objects */
+	MA_ERROR = 0,      /* fail if any missing objects are encountered */
+	MA_ALLOW_ANY,      /* silently allow ALL missing objects */
+	MA_ALLOW_PROMISOR, /* silently allow all missing PROMISOR objects */
 };
 static enum missing_action arg_missing_action;
 static show_object_fn fn_show_object;

@@ -2577,6 +2580,20 @@ static void show_object__ma_allow_any(struct object *obj, const char *name, void
 	show_object(obj, name, data);
 }
 
+static void show_object__ma_allow_promisor(struct object *obj, const char *name, void *data)
+{
+	assert(arg_missing_action == MA_ALLOW_PROMISOR);
+
+	/*
+	 * Quietly ignore EXPECTED missing objects.  This avoids problems with
+	 * staging them now and getting an odd error later.
+	 */
+	if (!has_object_file(&obj->oid) && is_promisor_object(&obj->oid))
+		return;
+
+	show_object(obj, name, data);
+}
+
 static int option_parse_missing_action(const struct option *opt,
 				       const char *arg, int unset)
 {

@@ -2591,10 +2608,18 @@ static int option_parse_missing_action(const struct option *opt,
 
 	if (!strcmp(arg, "allow-any")) {
 		arg_missing_action = MA_ALLOW_ANY;
+		fetch_if_missing = 0;
 		fn_show_object = show_object__ma_allow_any;
 		return 0;
 	}
 
+	if (!strcmp(arg, "allow-promisor")) {
+		arg_missing_action = MA_ALLOW_PROMISOR;
+		fetch_if_missing = 0;
+		fn_show_object = show_object__ma_allow_promisor;
+		return 0;
+	}
+
 	die(_("invalid value for --missing"));
 	return 0;
 }

@@ -3008,6 +3033,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		{ OPTION_CALLBACK, 0, "missing", NULL, N_("action"),
 		  N_("handling for missing objects"), PARSE_OPT_NONEG,
 		  option_parse_missing_action },
+		OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects,
+			 N_("do not pack objects in promisor packfiles")),
 		OPT_END(),
 	};
 

@@ -3053,6 +3080,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		argv_array_push(&rp, "--unpacked");
 	}
 
+	if (exclude_promisor_objects) {
+		use_internal_rev_list = 1;
+		fetch_if_missing = 0;
+		argv_array_push(&rp, "--exclude-promisor-objects");
+	}
+
 	if (!reuse_object)
 		reuse_delta = 0;
 	if (pack_compression_level == -1)

index cddabf2..be34645 100644
@@ -101,12 +101,15 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
 	struct progress *progress = NULL;
+	int exclude_promisor_objects = 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_EXPIRY_DATE(0, "expire", &expire,
 				N_("expire objects older than <time>")),
+		OPT_BOOL(0, "exclude-promisor-objects", &exclude_promisor_objects,
+			 N_("limit traversal to objects outside promisor packfiles")),
 		OPT_END()
 	};
 	char *s;

@@ -139,6 +142,10 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 		show_progress = isatty(2);
 	if (show_progress)
 		progress = start_delayed_progress(_("Checking connectivity"), 0);
+	if (exclude_promisor_objects) {
+		fetch_if_missing = 0;
+		revs.exclude_promisor_objects = 1;
+	}
 
 	mark_reachable_objects(&revs, 1, expire, progress);
 	stop_progress(&progress);

index f17a68a..7bdb401 100644
@@ -83,7 +83,8 @@ static void remove_pack_on_signal(int signo)
 
 /*
  * Adds all packs hex strings to the fname list, which do not
- * have a corresponding .keep file.
+ * have a corresponding .keep or .promisor file. These packs are not to
+ * be kept if we are going to pack everything into one file.
  */
 static void get_non_kept_pack_filenames(struct string_list *fname_list)
 {

@@ -101,7 +102,8 @@ static void get_non_kept_pack_filenames(struct string_list *fname_list)
 
 		fname = xmemdupz(e->d_name, len);
 
-		if (!file_exists(mkpath("%s/%s.keep", packdir, fname)))
+		if (!file_exists(mkpath("%s/%s.keep", packdir, fname)) &&
+		    !file_exists(mkpath("%s/%s.promisor", packdir, fname)))
 			string_list_append_nodup(fname_list, fname);
 		else
 			free(fname);

@@ -232,6 +234,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	argv_array_push(&cmd.args, "--all");
 	argv_array_push(&cmd.args, "--reflog");
 	argv_array_push(&cmd.args, "--indexed-objects");
+	if (repository_format_partial_clone)
+		argv_array_push(&cmd.args, "--exclude-promisor-objects");
 	if (window)
 		argv_array_pushf(&cmd.args, "--window=%s", window);
 	if (window_memory)