1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-13 02:56:30 +02:00
git/connected.c
Jonathan Tan cf1e7c0770 fetch-pack: write shallow, then check connectivity
When fetching, connectivity is checked after the shallow file is
updated. There are 2 issues with this: (1) the connectivity check is
only performed up to ancestors of existing refs (which is not thorough
enough if we were deepening an existing ref in the first place), and (2)
there is no rollback of the shallow file if the connectivity check
fails.

To solve (1), update the connectivity check to check the ancestry chain
completely in the case of a deepening fetch by refraining from passing
"--not --all" when invoking rev-list in connected.c.

To solve (2), have fetch_pack() perform its own connectivity check
before updating the shallow file. To support existing use cases in which
"git fetch-pack" is used to download objects without much regard as to
the connectivity of the resulting objects with respect to the existing
repository, the connectivity check is only done if necessary (that is,
the fetch is not a clone, and the fetch involves shallow/deepen
functionality). "git fetch" still performs its own connectivity check,
preserving correctness but sometimes performing redundant work. This
redundancy is mitigated by the fact that fetch_pack() reports if it has
performed a connectivity check itself, and if the transport supports
connect or stateless-connect, it will bubble up that report so that "git
fetch" knows not to perform the connectivity check in such a case.

This was noticed when a user tried to deepen an existing repository by
fetching with --no-shallow from a server that did not send all necessary
objects - the connectivity check as run by "git fetch" succeeded, but a
subsequent "git fsck" failed.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-07-03 14:57:44 -07:00

112 lines
3.2 KiB
C

#include "cache.h"
#include "run-command.h"
#include "sigchain.h"
#include "connected.h"
#include "transport.h"
#include "packfile.h"
/*
* If we feed all the commits we want to verify to this command
*
* $ git rev-list --objects --stdin --not --all
*
* and if it does not error out, that means everything reachable from
* these commits locally exists and is connected to our existing refs.
* Note that this does _not_ validate the individual objects.
*
* Returns 0 if everything is connected, non-zero otherwise.
*/
int check_connected(oid_iterate_fn fn, void *cb_data,
struct check_connected_options *opt)
{
struct child_process rev_list = CHILD_PROCESS_INIT;
struct check_connected_options defaults = CHECK_CONNECTED_INIT;
char commit[GIT_MAX_HEXSZ + 1];
struct object_id oid;
int err = 0;
struct packed_git *new_pack = NULL;
struct transport *transport;
size_t base_len;
if (!opt)
opt = &defaults;
transport = opt->transport;
if (fn(cb_data, &oid)) {
if (opt->err_fd)
close(opt->err_fd);
return err;
}
if (transport && transport->smart_options &&
transport->smart_options->self_contained_and_connected &&
transport->pack_lockfile &&
strip_suffix(transport->pack_lockfile, ".keep", &base_len)) {
struct strbuf idx_file = STRBUF_INIT;
strbuf_add(&idx_file, transport->pack_lockfile, base_len);
strbuf_addstr(&idx_file, ".idx");
new_pack = add_packed_git(idx_file.buf, idx_file.len, 1);
strbuf_release(&idx_file);
}
if (opt->shallow_file) {
argv_array_push(&rev_list.args, "--shallow-file");
argv_array_push(&rev_list.args, opt->shallow_file);
}
argv_array_push(&rev_list.args,"rev-list");
argv_array_push(&rev_list.args, "--objects");
argv_array_push(&rev_list.args, "--stdin");
if (repository_format_partial_clone)
argv_array_push(&rev_list.args, "--exclude-promisor-objects");
if (!opt->is_deepening_fetch) {
argv_array_push(&rev_list.args, "--not");
argv_array_push(&rev_list.args, "--all");
}
argv_array_push(&rev_list.args, "--quiet");
if (opt->progress)
argv_array_pushf(&rev_list.args, "--progress=%s",
_("Checking connectivity"));
rev_list.git_cmd = 1;
rev_list.env = opt->env;
rev_list.in = -1;
rev_list.no_stdout = 1;
if (opt->err_fd)
rev_list.err = opt->err_fd;
else
rev_list.no_stderr = opt->quiet;
if (start_command(&rev_list))
return error(_("Could not run 'git rev-list'"));
sigchain_push(SIGPIPE, SIG_IGN);
commit[GIT_SHA1_HEXSZ] = '\n';
do {
/*
* If index-pack already checked that:
* - there are no dangling pointers in the new pack
* - the pack is self contained
* Then if the updated ref is in the new pack, then we
* are sure the ref is good and not sending it to
* rev-list for verification.
*/
if (new_pack && find_pack_entry_one(oid.hash, new_pack))
continue;
memcpy(commit, oid_to_hex(&oid), GIT_SHA1_HEXSZ);
if (write_in_full(rev_list.in, commit, GIT_SHA1_HEXSZ + 1) < 0) {
if (errno != EPIPE && errno != EINVAL)
error_errno(_("failed write to rev-list"));
err = -1;
break;
}
} while (!fn(cb_data, &oid));
if (close(rev_list.in))
err = error_errno(_("failed to close rev-list's stdin"));
sigchain_pop(SIGPIPE);
return finish_command(&rev_list) || err;
}