Merge branch 'jt/cdn-offload'

The "fetch/clone" protocol has been updated to allow the server to
instruct the clients to grab pre-packaged packfile(s) in addition
to the packed object data coming over the wire.

* jt/cdn-offload:
  upload-pack: fix a sparse '0 as NULL pointer' warning
  upload-pack: send part of packfile response as uri
  fetch-pack: support more than one pack lockfile
  upload-pack: refactor reading of pack-objects out
  Documentation: add Packfile URIs design doc
  Documentation: order protocol v2 sections
  http-fetch: support fetching packfiles by URL
  http-fetch: refactor into function
  http: refactor finish_http_pack_request()
  http: use --stdin when indexing dumb HTTP pack

1 files changed, 121 insertions, 16 deletions

diff --git a/fetch-pack.c b/fetch-pack.c
index d8bbf45ee2..acd55ba6e8 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -38,6 +38,7 @@ static int server_supports_filtering;
 static struct shallow_lock shallow_lock;
 static const char *alternate_shallow_file;
 static struct strbuf fsck_msg_types = STRBUF_INIT;
+static struct string_list uri_protocols = STRING_LIST_INIT_DUP;
 
 /* Remember to update object flag allocation in object.h */
 #define COMPLETE	(1U << 0)
@@ -794,7 +795,8 @@ static void write_promisor_file(const char *keep_name,
 }
 
 static int get_pack(struct fetch_pack_args *args,
-		    int xd[2], char **pack_lockfile,
+		    int xd[2], struct string_list *pack_lockfiles,
+		    int only_packfile,
 		    struct ref **sought, int nr_sought)
 {
 	struct async demux;
@@ -838,7 +840,7 @@ static int get_pack(struct fetch_pack_args *args,
 	}
 
 	if (do_keep || args->from_promisor) {
-		if (pack_lockfile)
+		if (pack_lockfiles)
 			cmd.out = -1;
 		cmd_name = "index-pack";
 		argv_array_push(&cmd.args, cmd_name);
@@ -855,15 +857,22 @@ static int get_pack(struct fetch_pack_args *args,
 					"--keep=fetch-pack %"PRIuMAX " on %s",
 					(uintmax_t)getpid(), hostname);
 		}
-		if (args->check_self_contained_and_connected)
+		if (only_packfile && args->check_self_contained_and_connected)
 			argv_array_push(&cmd.args, "--check-self-contained-and-connected");
+		else
+			/*
+			 * We cannot perform any connectivity checks because
+			 * not all packs have been downloaded; let the caller
+			 * have this responsibility.
+			 */
+			args->check_self_contained_and_connected = 0;
 		/*
 		 * If we're obtaining the filename of a lockfile, we'll use
 		 * that filename to write a .promisor file with more
 		 * information below. If not, we need index-pack to do it for
 		 * us.
 		 */
-		if (!(do_keep && pack_lockfile) && args->from_promisor)
+		if (!(do_keep && pack_lockfiles) && args->from_promisor)
 			argv_array_push(&cmd.args, "--promisor");
 	}
 	else {
@@ -899,8 +908,9 @@ static int get_pack(struct fetch_pack_args *args,
 	cmd.git_cmd = 1;
 	if (start_command(&cmd))
 		die(_("fetch-pack: unable to fork off %s"), cmd_name);
-	if (do_keep && pack_lockfile) {
-		*pack_lockfile = index_pack_lockfile(cmd.out);
+	if (do_keep && pack_lockfiles) {
+		string_list_append_nodup(pack_lockfiles,
+					 index_pack_lockfile(cmd.out));
 		close(cmd.out);
 	}
 
@@ -922,8 +932,8 @@ static int get_pack(struct fetch_pack_args *args,
 	 * Now that index-pack has succeeded, write the promisor file using the
 	 * obtained .keep filename if necessary
 	 */
-	if (do_keep && pack_lockfile && args->from_promisor)
-		write_promisor_file(*pack_lockfile, sought, nr_sought);
+	if (do_keep && pack_lockfiles && pack_lockfiles->nr && args->from_promisor)
+		write_promisor_file(pack_lockfiles->items[0].string, sought, nr_sought);
 
 	return 0;
 }
@@ -940,7 +950,7 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 				 const struct ref *orig_ref,
 				 struct ref **sought, int nr_sought,
 				 struct shallow_info *si,
-				 char **pack_lockfile)
+				 struct string_list *pack_lockfiles)
 {
 	struct repository *r = the_repository;
 	struct ref *ref = copy_ref_list(orig_ref);
@@ -1067,7 +1077,7 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 		alternate_shallow_file = setup_temporary_shallow(si->shallow);
 	else
 		alternate_shallow_file = NULL;
-	if (get_pack(args, fd, pack_lockfile, sought, nr_sought))
+	if (get_pack(args, fd, pack_lockfiles, 1, sought, nr_sought))
 		die(_("git fetch-pack: fetch failed."));
 
  all_done:
@@ -1221,6 +1231,26 @@ static int send_fetch_request(struct fetch_negotiator *negotiator, int fd_out,
 		warning("filtering not recognized by server, ignoring");
 	}
 
+	if (server_supports_feature("fetch", "packfile-uris", 0)) {
+		int i;
+		struct strbuf to_send = STRBUF_INIT;
+
+		for (i = 0; i < uri_protocols.nr; i++) {
+			const char *s = uri_protocols.items[i].string;
+
+			if (!strcmp(s, "https") || !strcmp(s, "http")) {
+				if (to_send.len)
+					strbuf_addch(&to_send, ',');
+				strbuf_addstr(&to_send, s);
+			}
+		}
+		if (to_send.len) {
+			packet_buf_write(&req_buf, "packfile-uris %s",
+					 to_send.buf);
+			strbuf_release(&to_send);
+		}
+	}
+
 	/* add wants */
 	add_wants(args->no_dependents, wants, &req_buf);
 
@@ -1443,6 +1473,21 @@ static void receive_wanted_refs(struct packet_reader *reader,
 		die(_("error processing wanted refs: %d"), reader->status);
 }
 
+static void receive_packfile_uris(struct packet_reader *reader,
+				  struct string_list *uris)
+{
+	process_section_header(reader, "packfile-uris", 0);
+	while (packet_reader_read(reader) == PACKET_READ_NORMAL) {
+		if (reader->pktlen < the_hash_algo->hexsz ||
+		    reader->line[the_hash_algo->hexsz] != ' ')
+			die("expected '<hash> <uri>', got: %s\n", reader->line);
+
+		string_list_append(uris, reader->line);
+	}
+	if (reader->status != PACKET_READ_DELIM)
+		die("expected DELIM");
+}
+
 enum fetch_state {
 	FETCH_CHECK_LOCAL = 0,
 	FETCH_SEND_REQUEST,
@@ -1464,7 +1509,7 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 				    struct ref **sought, int nr_sought,
 				    struct oid_array *shallows,
 				    struct shallow_info *si,
-				    char **pack_lockfile)
+				    struct string_list *pack_lockfiles)
 {
 	struct repository *r = the_repository;
 	struct ref *ref = copy_ref_list(orig_ref);
@@ -1476,6 +1521,8 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 	struct fetch_negotiator negotiator_alloc;
 	struct fetch_negotiator *negotiator;
 	int seen_ack = 0;
+	struct string_list packfile_uris = STRING_LIST_INIT_DUP;
+	int i;
 
 	if (args->no_dependents) {
 		negotiator = NULL;
@@ -1569,9 +1616,12 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 			if (process_section_header(&reader, "wanted-refs", 1))
 				receive_wanted_refs(&reader, sought, nr_sought);
 
-			/* get the pack */
+			/* get the pack(s) */
+			if (process_section_header(&reader, "packfile-uris", 1))
+				receive_packfile_uris(&reader, &packfile_uris);
 			process_section_header(&reader, "packfile", 0);
-			if (get_pack(args, fd, pack_lockfile, sought, nr_sought))
+			if (get_pack(args, fd, pack_lockfiles,
+				     !packfile_uris.nr, sought, nr_sought))
 				die(_("git fetch-pack: fetch failed."));
 			do_check_stateless_delimiter(args, &reader);
 
@@ -1582,8 +1632,55 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 		}
 	}
 
+	for (i = 0; i < packfile_uris.nr; i++) {
+		struct child_process cmd = CHILD_PROCESS_INIT;
+		char packname[GIT_MAX_HEXSZ + 1];
+		const char *uri = packfile_uris.items[i].string +
+			the_hash_algo->hexsz + 1;
+
+		argv_array_push(&cmd.args, "http-fetch");
+		argv_array_pushf(&cmd.args, "--packfile=%.*s",
+				 (int) the_hash_algo->hexsz,
+				 packfile_uris.items[i].string);
+		argv_array_push(&cmd.args, uri);
+		cmd.git_cmd = 1;
+		cmd.no_stdin = 1;
+		cmd.out = -1;
+		if (start_command(&cmd))
+			die("fetch-pack: unable to spawn http-fetch");
+
+		if (read_in_full(cmd.out, packname, 5) < 0 ||
+		    memcmp(packname, "keep\t", 5))
+			die("fetch-pack: expected keep then TAB at start of http-fetch output");
+
+		if (read_in_full(cmd.out, packname,
+				 the_hash_algo->hexsz + 1) < 0 ||
+		    packname[the_hash_algo->hexsz] != '\n')
+			die("fetch-pack: expected hash then LF at end of http-fetch output");
+
+		packname[the_hash_algo->hexsz] = '\0';
+
+		close(cmd.out);
+
+		if (finish_command(&cmd))
+			die("fetch-pack: unable to finish http-fetch");
+
+		if (memcmp(packfile_uris.items[i].string, packname,
+			   the_hash_algo->hexsz))
+			die("fetch-pack: pack downloaded from %s does not match expected hash %.*s",
+			    uri, (int) the_hash_algo->hexsz,
+			    packfile_uris.items[i].string);
+
+		string_list_append_nodup(pack_lockfiles,
+					 xstrfmt("%s/pack/pack-%s.keep",
+						 get_object_directory(),
+						 packname));
+	}
+	string_list_clear(&packfile_uris, 0);
+
 	if (negotiator)
 		negotiator->release(negotiator);
+
 	oidset_clear(&common);
 	return ref;
 }
@@ -1620,6 +1717,14 @@ static void fetch_pack_config(void)
 	git_config_get_bool("repack.usedeltabaseoffset", &prefer_ofs_delta);
 	git_config_get_bool("fetch.fsckobjects", &fetch_fsck_objects);
 	git_config_get_bool("transfer.fsckobjects", &transfer_fsck_objects);
+	if (!uri_protocols.nr) {
+		char *str;
+
+		if (!git_config_get_string("fetch.uriprotocols", &str) && str) {
+			string_list_split(&uri_protocols, str, ',', -1);
+			free(str);
+		}
+	}
 
 	git_config(fetch_pack_config_cb, NULL);
 }
@@ -1772,7 +1877,7 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		       const struct ref *ref,
 		       struct ref **sought, int nr_sought,
 		       struct oid_array *shallow,
-		       char **pack_lockfile,
+		       struct string_list *pack_lockfiles,
 		       enum protocol_version version)
 {
 	struct ref *ref_cpy;
@@ -1807,11 +1912,11 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		memset(&si, 0, sizeof(si));
 		ref_cpy = do_fetch_pack_v2(args, fd, ref, sought, nr_sought,
 					   &shallows_scratch, &si,
-					   pack_lockfile);
+					   pack_lockfiles);
 	} else {
 		prepare_shallow_info(&si, shallow);
 		ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought,
-					&si, pack_lockfile);
+					&si, pack_lockfiles);
 	}
 	reprepare_packed_git(the_repository);