upload-pack: send part of packfile response as uri

Teach upload-pack to send part of its packfile response as URIs.

An administrator may configure a repository with one or more
"uploadpack.blobpackfileuri" lines, each line containing an OID, a pack
hash, and a URI. A client may configure fetch.uriprotocols to be a
comma-separated list of protocols that it is willing to use to fetch
additional packfiles - this list will be sent to the server. Whenever an
object with one of those OIDs would appear in the packfile transmitted
by upload-pack, the server may exclude that object, and instead send the
URI. The client will then download the packs referred to by those URIs
before performing the connectivity check.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/pack-objects.c

@@ -117,6 +117,8 @@ static unsigned long window_memory_limit = 0;
 
 static struct list_objects_filter_options filter_options;
 
+static struct string_list uri_protocols = STRING_LIST_INIT_NODUP;
+
 enum missing_action {
 	MA_ERROR = 0,      /* fail if any missing objects are encountered */
 	MA_ALLOW_ANY,      /* silently allow ALL missing objects */
@@ -125,6 +127,15 @@ enum missing_action {
 static enum missing_action arg_missing_action;
 static show_object_fn fn_show_object;
 
+struct configured_exclusion {
+	struct oidmap_entry e;
+	char *pack_hash_hex;
+	char *uri;
+};
+static struct oidmap configured_exclusions;
+
+static struct oidset excluded_by_config;
+
 /*
  * stats
  */
@@ -969,6 +980,25 @@ static void write_reused_pack(struct hashfile *f)
 	unuse_pack(&w_curs);
 }
 
+static void write_excluded_by_configs(void)
+{
+	struct oidset_iter iter;
+	const struct object_id *oid;
+
+	oidset_iter_init(&excluded_by_config, &iter);
+	while ((oid = oidset_iter_next(&iter))) {
+		struct configured_exclusion *ex =
+			oidmap_get(&configured_exclusions, oid);
+
+		if (!ex)
+			BUG("configured exclusion wasn't configured");
+		write_in_full(1, ex->pack_hash_hex, strlen(ex->pack_hash_hex));
+		write_in_full(1, " ", 1);
+		write_in_full(1, ex->uri, strlen(ex->uri));
+		write_in_full(1, "\n", 1);
+	}
+}
+
 static const char no_split_warning[] = N_(
 "disabling bitmap writing, packs are split due to pack.packSizeLimit"
 );
@@ -1266,6 +1296,25 @@ static int want_object_in_pack(const struct object_id *oid,
 		}
 	}
 
+	if (uri_protocols.nr) {
+		struct configured_exclusion *ex =
+			oidmap_get(&configured_exclusions, oid);
+		int i;
+		const char *p;
+
+		if (ex) {
+			for (i = 0; i < uri_protocols.nr; i++) {
+				if (skip_prefix(ex->uri,
+						uri_protocols.items[i].string,
+						&p) &&
+				    *p == ':') {
+					oidset_insert(&excluded_by_config, oid);
+					return 0;
+				}
+			}
+		}
+	}
+
 	return 1;
 }
 
@@ -2864,6 +2913,29 @@ static int git_pack_config(const char *k, const char *v, void *cb)
 			    pack_idx_opts.version);
 		return 0;
 	}
+	if (!strcmp(k, "uploadpack.blobpackfileuri")) {
+		struct configured_exclusion *ex = xmalloc(sizeof(*ex));
+		const char *oid_end, *pack_end;
+		/*
+		 * Stores the pack hash. This is not a true object ID, but is
+		 * of the same form.
+		 */
+		struct object_id pack_hash;
+
+		if (parse_oid_hex(v, &ex->e.oid, &oid_end) ||
+		    *oid_end != ' ' ||
+		    parse_oid_hex(oid_end + 1, &pack_hash, &pack_end) ||
+		    *pack_end != ' ')
+			die(_("value of uploadpack.blobpackfileuri must be "
+			      "of the form '<object-hash> <pack-hash> <uri>' (got '%s')"), v);
+		if (oidmap_get(&configured_exclusions, &ex->e.oid))
+			die(_("object already configured in another "
+			      "uploadpack.blobpackfileuri (got '%s')"), v);
+		ex->pack_hash_hex = xcalloc(1, pack_end - oid_end);
+		memcpy(ex->pack_hash_hex, oid_end + 1, pack_end - oid_end - 1);
+		ex->uri = xstrdup(pack_end + 1);
+		oidmap_put(&configured_exclusions, ex);
+	}
 	return git_default_config(k, v, cb);
 }
 
@@ -3462,6 +3534,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 			 N_("do not pack objects in promisor packfiles")),
 		OPT_BOOL(0, "delta-islands", &use_delta_islands,
 			 N_("respect islands during delta compression")),
+		OPT_STRING_LIST(0, "uri-protocol", &uri_protocols,
+				N_("protocol"),
+				N_("exclude any configured uploadpack.blobpackfileuri with this protocol")),
 		OPT_END(),
 	};
 
@@ -3650,6 +3725,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	}
 
 	trace2_region_enter("pack-objects", "write-pack-file", the_repository);
+	write_excluded_by_configs();
 	write_pack_file();
 	trace2_region_leave("pack-objects", "write-pack-file", the_repository);