From dd4b732df73b06878b81fce050e7dcac4366a38e Mon Sep 17 00:00:00 2001 From: Jonathan Tan Date: Wed, 10 Jun 2020 13:57:23 -0700 Subject: 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 Signed-off-by: Junio C Hamano --- fetch-pack.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 108 insertions(+), 4 deletions(-) (limited to 'fetch-pack.c') diff --git a/fetch-pack.c b/fetch-pack.c index bc3af3c726..ca2b101b8d 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) @@ -795,6 +796,7 @@ static void write_promisor_file(const char *keep_name, static int get_pack(struct fetch_pack_args *args, int xd[2], struct string_list *pack_lockfiles, + int only_packfile, struct ref **sought, int nr_sought) { struct async demux; @@ -855,8 +857,15 @@ 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 @@ -1068,7 +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_lockfiles, sought, nr_sought)) + if (get_pack(args, fd, pack_lockfiles, 1, sought, nr_sought)) die(_("git fetch-pack: fetch failed.")); all_done: @@ -1222,6 +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); @@ -1444,6 +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 ' ', 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, @@ -1470,6 +1514,8 @@ 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; @@ -1558,9 +1604,12 @@ 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_lockfiles, sought, nr_sought)) + if (get_pack(args, fd, pack_lockfiles, + !packfile_uris.nr, sought, nr_sought)) die(_("git fetch-pack: fetch failed.")); state = FETCH_DONE; @@ -1570,8 +1619,55 @@ 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; } @@ -1608,6 +1704,14 @@ 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); } -- cgit v1.2.3