WIP PC Part 2

Makefile

@@ -792,6 +792,7 @@ LIB_OBJS += ewah/ewah_bitmap.o
 LIB_OBJS += ewah/ewah_io.o
 LIB_OBJS += ewah/ewah_rlw.o
 LIB_OBJS += exec_cmd.o
+LIB_OBJS += fetch-object.o
 LIB_OBJS += fetch-pack.o
 LIB_OBJS += fsck.o
 LIB_OBJS += gettext.o

builtin/cat-file.c

@@ -13,6 +13,7 @@
 #include "tree-walk.h"
 #include "sha1-array.h"
 #include "packfile.h"
+#include "partial-clone-utils.h"
 
 struct batch_options {
 	int enabled;
@@ -475,6 +476,8 @@ 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 (is_partial_clone_registered())
+			warning("This repository has partial clone enabled. Some objects may not be loaded.");
 
 		cb.opt = opt;
 		cb.expand = &data;

builtin/fetch-pack.c

@@ -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));
@@ -143,6 +145,14 @@ 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)

builtin/fsck.c

@@ -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),
@@ -398,7 +409,7 @@ 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;
 		}
@@ -434,6 +445,14 @@ 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.. */
@@ -659,6 +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;
 
@@ -731,6 +753,8 @@ 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;

builtin/index-pack.c

@@ -1389,15 +1389,60 @@ 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);
+		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_name, const char *keep_msg,
+		  const char *keep_msg, const char *promisor_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 +1454,12 @@ 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 (promisor_msg)
+		write_special_file("promisor", promisor_msg, final_pack_name,
+				   sha1, NULL);
 
 	if (final_pack_name != curr_pack_name) {
 		if (!final_pack_name)
@@ -1472,7 +1501,6 @@ 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)
@@ -1615,32 +1643,26 @@ 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;
+	const char *promisor_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];
 	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);
 
@@ -1683,6 +1705,10 @@ 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);
@@ -1745,9 +1771,7 @@ 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 +1819,12 @@ 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, promisor_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)

cache.h

@@ -866,6 +866,7 @@ extern char *repository_format_partial_clone_filter;
 struct repository_format {
 	int version;
 	int precious_objects;
+	char *partial_clone;
 	int is_bare;
 	char *work_tree;
 	char *partial_clone_remote; /* value of extensions.partialcloneremote */
@@ -1589,7 +1590,8 @@ 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" */
@@ -1728,6 +1730,14 @@ 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 is_partial_clone_registered() is true.
+ *
+ * Its default value is 1.
+ */
+extern int fetch_if_missing;
+
 /* Dumb servers support */
 extern int update_server_info(int);
 

fetch-object.c

@@ -0,0 +1,26 @@
+#include "cache.h"
+#include "packfile.h"
+#include "pkt-line.h"
+#include "strbuf.h"
+#include "transport.h"
+
+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"));
+	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);
+	fetch_if_missing = original_fetch_if_missing;
+}

fetch-object.h

@@ -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