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>
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 */
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
*/
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"
);
}
}
+ 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;
}
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);
}
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(),
};
}
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);
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)
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;
"--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
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:
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);
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,
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;
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;
}
}
+ 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;
}
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);
}
test_i18ngrep "expected no other sections to be sent after no .ready." err
'
+configure_exclusion () {
+ git -C "$1" hash-object "$2" >objh &&
+ git -C "$1" pack-objects "$HTTPD_DOCUMENT_ROOT_PATH/mypack" <objh >packh &&
+ git -C "$1" config --add \
+ "uploadpack.blobpackfileuri" \
+ "$(cat objh) $(cat packh) $HTTPD_URL/dumb/mypack-$(cat packh).pack" &&
+ cat objh
+}
+
+test_expect_success 'part of packfile response provided as URI' '
+ P="$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ rm -rf "$P" http_child log &&
+
+ git init "$P" &&
+ git -C "$P" config "uploadpack.allowsidebandall" "true" &&
+
+ echo my-blob >"$P/my-blob" &&
+ git -C "$P" add my-blob &&
+ echo other-blob >"$P/other-blob" &&
+ git -C "$P" add other-blob &&
+ git -C "$P" commit -m x &&
+
+ configure_exclusion "$P" my-blob >h &&
+ configure_exclusion "$P" other-blob >h2 &&
+
+ GIT_TRACE=1 GIT_TRACE_PACKET="$(pwd)/log" GIT_TEST_SIDEBAND_ALL=1 \
+ git -c protocol.version=2 \
+ -c fetch.uriprotocols=http,https \
+ clone "$HTTPD_URL/smart/http_parent" http_child &&
+
+ # Ensure that my-blob and other-blob are in separate packfiles.
+ for idx in http_child/.git/objects/pack/*.idx
+ do
+ git verify-pack --verbose $idx >out &&
+ {
+ grep "^[0-9a-f]\{16,\} " out || :
+ } >out.objectlist &&
+ if test_line_count = 1 out.objectlist
+ then
+ if grep $(cat h) out
+ then
+ >hfound
+ fi &&
+ if grep $(cat h2) out
+ then
+ >h2found
+ fi
+ fi
+ done &&
+ test -f hfound &&
+ test -f h2found &&
+
+ # Ensure that there are exactly 6 files (3 .pack and 3 .idx).
+ ls http_child/.git/objects/pack/* >filelist &&
+ test_line_count = 6 filelist
+'
+
+test_expect_success 'fetching with valid packfile URI but invalid hash fails' '
+ P="$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
+ rm -rf "$P" http_child log &&
+
+ git init "$P" &&
+ git -C "$P" config "uploadpack.allowsidebandall" "true" &&
+
+ echo my-blob >"$P/my-blob" &&
+ git -C "$P" add my-blob &&
+ echo other-blob >"$P/other-blob" &&
+ git -C "$P" add other-blob &&
+ git -C "$P" commit -m x &&
+
+ configure_exclusion "$P" my-blob >h &&
+ # Configure a URL for other-blob. Just reuse the hash of the object as
+ # the hash of the packfile, since the hash does not matter for this
+ # test as long as it is not the hash of the pack, and it is of the
+ # expected length.
+ git -C "$P" hash-object other-blob >objh &&
+ git -C "$P" pack-objects "$HTTPD_DOCUMENT_ROOT_PATH/mypack" <objh >packh &&
+ git -C "$P" config --add \
+ "uploadpack.blobpackfileuri" \
+ "$(cat objh) $(cat objh) $HTTPD_URL/dumb/mypack-$(cat packh).pack" &&
+
+ test_must_fail env GIT_TEST_SIDEBAND_ALL=1 \
+ git -c protocol.version=2 \
+ -c fetch.uriprotocols=http,https \
+ clone "$HTTPD_URL/smart/http_parent" http_child 2>err &&
+ test_i18ngrep "pack downloaded from.*does not match expected hash" err
+'
+
# DO NOT add non-httpd-specific tests here, because the last part of this
# test script is only executed when httpd is available and enabled.
/* 0 for no sideband, otherwise DEFAULT_PACKET_MAX or LARGE_PACKET_MAX */
int use_sideband;
+ struct string_list uri_protocols;
+
struct list_objects_filter_options filter_options;
struct packet_writer writer;
struct oid_array haves = OID_ARRAY_INIT;
struct object_array shallows = OBJECT_ARRAY_INIT;
struct string_list deepen_not = STRING_LIST_INIT_DUP;
+ struct string_list uri_protocols = STRING_LIST_INIT_DUP;
memset(data, 0, sizeof(*data));
data->symref = symref;
data->haves = haves;
data->shallows = shallows;
data->deepen_not = deepen_not;
+ data->uri_protocols = uri_protocols;
packet_writer_init(&data->writer, 1);
data->keepalive = 5;
struct output_state {
char buffer[8193];
int used;
+ unsigned packfile_uris_started : 1;
+ unsigned packfile_started : 1;
};
static int relay_pack_data(int pack_objects_out, struct output_state *os,
- int use_sideband)
+ int use_sideband, int write_packfile_line)
{
/*
* We keep the last byte to ourselves
}
os->used += readsz;
+ while (!os->packfile_started) {
+ char *p;
+ if (os->used >= 4 && !memcmp(os->buffer, "PACK", 4)) {
+ os->packfile_started = 1;
+ if (write_packfile_line) {
+ if (os->packfile_uris_started)
+ packet_delim(1);
+ packet_write_fmt(1, "\1packfile\n");
+ }
+ break;
+ }
+ if ((p = memchr(os->buffer, '\n', os->used))) {
+ if (!os->packfile_uris_started) {
+ os->packfile_uris_started = 1;
+ if (!write_packfile_line)
+ BUG("packfile_uris requires sideband-all");
+ packet_write_fmt(1, "\1packfile-uris\n");
+ }
+ *p = '\0';
+ packet_write_fmt(1, "\1%s\n", os->buffer);
+
+ os->used -= p - os->buffer + 1;
+ memmove(os->buffer, p + 1, os->used);
+ } else {
+ /*
+ * Incomplete line.
+ */
+ return readsz;
+ }
+ }
+
if (os->used > 1) {
send_client_data(1, os->buffer, os->used - 1, use_sideband);
os->buffer[0] = os->buffer[os->used - 1];
return readsz;
}
-static void create_pack_file(struct upload_pack_data *pack_data)
+static void create_pack_file(struct upload_pack_data *pack_data,
+ const struct string_list *uri_protocols)
{
struct child_process pack_objects = CHILD_PROCESS_INIT;
struct output_state output_state = { { 0 } };
spec);
}
}
+ if (uri_protocols) {
+ for (i = 0; i < uri_protocols->nr; i++)
+ argv_array_pushf(&pack_objects.args, "--uri-protocol=%s",
+ uri_protocols->items[i].string);
+ }
pack_objects.in = -1;
pack_objects.out = -1;
if (0 <= pu && (pfd[pu].revents & (POLLIN|POLLHUP))) {
int result = relay_pack_data(pack_objects.out,
&output_state,
- pack_data->use_sideband);
+ pack_data->use_sideband,
+ !!uri_protocols);
if (result == 0) {
close(pack_objects.out);
receive_needs(&data, &reader);
if (data.want_obj.nr) {
get_common_commits(&data, &reader);
- create_pack_file(&data);
+ create_pack_file(&data, 0);
}
}
continue;
}
+ if (skip_prefix(arg, "packfile-uris ", &p)) {
+ string_list_split(&data->uri_protocols, p, ',', -1);
+ continue;
+ }
+
/* ignore unknown lines maybe? */
die("unexpected line: '%s'", arg);
}
+ if (data->uri_protocols.nr && !data->writer.use_sideband)
+ string_list_clear(&data->uri_protocols, 0);
+
if (request->status != PACKET_READ_FLUSH)
die(_("expected flush after fetch arguments"));
}
send_wanted_ref_info(&data);
send_shallow_info(&data);
- packet_writer_write(&data.writer, "packfile\n");
- create_pack_file(&data);
+ if (data.uri_protocols.nr) {
+ create_pack_file(&data, &data.uri_protocols);
+ } else {
+ packet_writer_write(&data.writer, "packfile\n");
+ create_pack_file(&data, NULL);
+ }
state = FETCH_DONE;
break;
case FETCH_DONE:
int allow_filter_value;
int allow_ref_in_want;
int allow_sideband_all_value;
+ char *str = NULL;
strbuf_addstr(value, "shallow");
&allow_sideband_all_value) &&
allow_sideband_all_value))
strbuf_addstr(value, " sideband-all");
+
+ if (!repo_config_get_string(the_repository,
+ "uploadpack.blobpackfileuri",
+ &str) &&
+ str) {
+ strbuf_addstr(value, " packfile-uris");
+ free(str);
+ }
}
return 1;
projects / thirdparty / git.git / commitdiff
