git-commit-vandalism/builtin/clone.c

1189 lines
33 KiB
C
Raw Normal View History

/*
* Builtin "git clone"
*
* Copyright (c) 2007 Kristian Høgsberg <krh@redhat.com>,
* 2008 Daniel Barkalow <barkalow@iabervon.org>
* Based on git-commit.sh by Junio C Hamano and Linus Torvalds
*
* Clone a repository into a different directory that does not yet exist.
*/
Fix sparse warnings Fix warnings from 'make check'. - These files don't include 'builtin.h' causing sparse to complain that cmd_* isn't declared: builtin/clone.c:364, builtin/fetch-pack.c:797, builtin/fmt-merge-msg.c:34, builtin/hash-object.c:78, builtin/merge-index.c:69, builtin/merge-recursive.c:22 builtin/merge-tree.c:341, builtin/mktag.c:156, builtin/notes.c:426 builtin/notes.c:822, builtin/pack-redundant.c:596, builtin/pack-refs.c:10, builtin/patch-id.c:60, builtin/patch-id.c:149, builtin/remote.c:1512, builtin/remote-ext.c:240, builtin/remote-fd.c:53, builtin/reset.c:236, builtin/send-pack.c:384, builtin/unpack-file.c:25, builtin/var.c:75 - These files have symbols which should be marked static since they're only file scope: submodule.c:12, diff.c:631, replace_object.c:92, submodule.c:13, submodule.c:14, trace.c:78, transport.c:195, transport-helper.c:79, unpack-trees.c:19, url.c:3, url.c:18, url.c:104, url.c:117, url.c:123, url.c:129, url.c:136, thread-utils.c:21, thread-utils.c:48 - These files redeclare symbols to be different types: builtin/index-pack.c:210, parse-options.c:564, parse-options.c:571, usage.c:49, usage.c:58, usage.c:63, usage.c:72 - These files use a literal integer 0 when they really should use a NULL pointer: daemon.c:663, fast-import.c:2942, imap-send.c:1072, notes-merge.c:362 While we're in the area, clean up some unused #includes in builtin files (mostly exec_cmd.h). Signed-off-by: Stephen Boyd <bebarino@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-03-22 08:51:05 +01:00
#include "builtin.h"
#include "lockfile.h"
#include "parse-options.h"
#include "fetch-pack.h"
#include "refs.h"
#include "tree.h"
#include "tree-walk.h"
#include "unpack-trees.h"
#include "transport.h"
#include "strbuf.h"
#include "dir.h"
#include "sigchain.h"
#include "branch.h"
#include "remote.h"
#include "run-command.h"
#include "connected.h"
/*
* Overall FIXMEs:
* - respect DB_ENVIRONMENT for .git/objects.
*
* Implementation notes:
* - dropping use-separate-remote and no-separate-remote compatibility
*
*/
static const char * const builtin_clone_usage[] = {
N_("git clone [<options>] [--] <repo> [<dir>]"),
NULL
};
static int option_no_checkout, option_bare, option_mirror, option_single_branch = -1;
static int option_local = -1, option_no_hardlinks, option_shared;
static int option_shallow_submodules;
static int deepen;
static char *option_template, *option_depth, *option_since;
static char *option_origin = NULL;
static char *option_branch = NULL;
static struct string_list option_not = STRING_LIST_INIT_NODUP;
static const char *real_git_dir;
static char *option_upload_pack = "git-upload-pack";
static int option_verbosity;
static int option_progress = -1;
static enum transport_family family;
static struct string_list option_config = STRING_LIST_INIT_NODUP;
static struct string_list option_required_reference = STRING_LIST_INIT_NODUP;
static struct string_list option_optional_reference = STRING_LIST_INIT_NODUP;
static int option_dissociate;
static int max_jobs = -1;
static struct string_list option_recurse_submodules = STRING_LIST_INIT_NODUP;
static int recurse_submodules_cb(const struct option *opt,
const char *arg, int unset)
{
if (unset)
string_list_clear((struct string_list *)opt->value, 0);
else if (arg)
string_list_append((struct string_list *)opt->value, arg);
else
string_list_append((struct string_list *)opt->value,
(const char *)opt->defval);
return 0;
}
static struct option builtin_clone_options[] = {
OPT__VERBOSITY(&option_verbosity),
OPT_BOOL(0, "progress", &option_progress,
N_("force progress reporting")),
OPT_BOOL('n', "no-checkout", &option_no_checkout,
N_("don't create a checkout")),
OPT_BOOL(0, "bare", &option_bare, N_("create a bare repository")),
OPT_HIDDEN_BOOL(0, "naked", &option_bare,
N_("create a bare repository")),
OPT_BOOL(0, "mirror", &option_mirror,
N_("create a mirror repository (implies bare)")),
OPT_BOOL('l', "local", &option_local,
N_("to clone from a local repository")),
OPT_BOOL(0, "no-hardlinks", &option_no_hardlinks,
N_("don't use local hardlinks, always copy")),
OPT_BOOL('s', "shared", &option_shared,
N_("setup as shared repository")),
{ OPTION_CALLBACK, 0, "recursive", &option_recurse_submodules,
N_("pathspec"), N_("initialize submodules in the clone"),
PARSE_OPT_OPTARG | PARSE_OPT_HIDDEN, recurse_submodules_cb,
(intptr_t)"." },
{ OPTION_CALLBACK, 0, "recurse-submodules", &option_recurse_submodules,
N_("pathspec"), N_("initialize submodules in the clone"),
PARSE_OPT_OPTARG, recurse_submodules_cb, (intptr_t)"." },
OPT_INTEGER('j', "jobs", &max_jobs,
N_("number of submodules cloned in parallel")),
OPT_STRING(0, "template", &option_template, N_("template-directory"),
N_("directory from which templates will be used")),
OPT_STRING_LIST(0, "reference", &option_required_reference, N_("repo"),
N_("reference repository")),
OPT_STRING_LIST(0, "reference-if-able", &option_optional_reference,
N_("repo"), N_("reference repository")),
OPT_BOOL(0, "dissociate", &option_dissociate,
N_("use --reference only while cloning")),
OPT_STRING('o', "origin", &option_origin, N_("name"),
N_("use <name> instead of 'origin' to track upstream")),
OPT_STRING('b', "branch", &option_branch, N_("branch"),
N_("checkout <branch> instead of the remote's HEAD")),
OPT_STRING('u', "upload-pack", &option_upload_pack, N_("path"),
N_("path to git-upload-pack on the remote")),
OPT_STRING(0, "depth", &option_depth, N_("depth"),
N_("create a shallow clone of that depth")),
OPT_STRING(0, "shallow-since", &option_since, N_("time"),
N_("create a shallow clone since a specific time")),
OPT_STRING_LIST(0, "shallow-exclude", &option_not, N_("revision"),
N_("deepen history of shallow clone, excluding rev")),
OPT_BOOL(0, "single-branch", &option_single_branch,
N_("clone only one branch, HEAD or --branch")),
clone: add `--shallow-submodules` flag When creating a shallow clone of a repository with submodules, the depth argument does not influence the submodules, i.e. the submodules are done as non-shallow clones. It is unclear what the best default is for the depth of submodules of a shallow clone, so we need to have the possibility to do all kinds of combinations: * shallow super project with shallow submodules e.g. build bots starting always from scratch. They want to transmit the least amount of network data as well as using the least amount of space on their hard drive. * shallow super project with unshallow submodules e.g. The superproject is just there to track a collection of repositories and it is not important to have the relationship between the repositories intact. However the history of the individual submodules matter. * unshallow super project with shallow submodules e.g. The superproject is the actual project and the submodule is a library which is rarely touched. The new switch to select submodules to be shallow or unshallow supports all of these three cases. It is easy to transition from the first to the second case by just unshallowing the submodules (`git submodule foreach git fetch --unshallow`), but it is not possible to transition from the second to the first case (as we would have already transmitted the non shallow over the network). That is why we want to make the first case the default in case of a shallow super project. This leads to the inconvenience in the second case with the shallow super project and unshallow submodules, as you need to pass `--no-shallow-submodules`. Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-04-26 03:12:27 +02:00
OPT_BOOL(0, "shallow-submodules", &option_shallow_submodules,
N_("any cloned submodules will be shallow")),
OPT_STRING(0, "separate-git-dir", &real_git_dir, N_("gitdir"),
N_("separate git dir from working tree")),
OPT_STRING_LIST('c', "config", &option_config, N_("key=value"),
N_("set config inside the new repository")),
OPT_SET_INT('4', "ipv4", &family, N_("use IPv4 addresses only"),
TRANSPORT_FAMILY_IPV4),
OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"),
TRANSPORT_FAMILY_IPV6),
OPT_END()
};
static const char *get_repo_path_1(struct strbuf *path, int *is_bundle)
{
standardize and improve lookup rules for external local repos When you specify a local repository on the command line of clone, ls-remote, upload-pack, receive-pack, or upload-archive, or in a request to git-daemon, we perform a little bit of lookup magic, doing things like looking in working trees for .git directories and appending ".git" for bare repos. For clone, this magic happens in get_repo_path. For everything else, it happens in enter_repo. In both cases, there are some ambiguous or confusing cases that aren't handled well, and there is one case that is not handled the same by both methods. This patch tries to provide (and test!) standard, sensible lookup rules for both code paths. The intended changes are: 1. When looking up "foo", we have always preferred a working tree "foo" (containing "foo/.git" over the bare "foo.git". But we did not prefer a bare "foo" over "foo.git". With this patch, we do so. 2. We would select directories that existed but didn't actually look like git repositories. With this patch, we make sure a selected directory looks like a git repo. Not only is this more sensible in general, but it will help anybody who is negatively affected by change (1) negatively (e.g., if they had "foo.git" next to its separate work tree "foo", and expect to keep finding "foo.git" when they reference "foo"). 3. The enter_repo code path would, given "foo", look for "foo.git/.git" (i.e., do the ".git" append magic even for a repo with working tree). The clone code path did not; with this patch, they now behave the same. In the unlikely case of a working tree overlaying a bare repo (i.e., a ".git" directory _inside_ a bare repo), we continue to treat it as a working tree (prefering the "inner" .git over the bare repo). This is mainly because the combination seems nonsensical, and I'd rather stick with existing behavior on the off chance that somebody is relying on it. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-02-02 22:59:13 +01:00
static char *suffix[] = { "/.git", "", ".git/.git", ".git" };
static char *bundle_suffix[] = { ".bundle", "" };
size_t baselen = path->len;
struct stat st;
int i;
for (i = 0; i < ARRAY_SIZE(suffix); i++) {
strbuf_setlen(path, baselen);
strbuf_addstr(path, suffix[i]);
if (stat(path->buf, &st))
continue;
if (S_ISDIR(st.st_mode) && is_git_directory(path->buf)) {
*is_bundle = 0;
return path->buf;
} else if (S_ISREG(st.st_mode) && st.st_size > 8) {
/* Is it a "gitfile"? */
char signature[8];
const char *dst;
int len, fd = open(path->buf, O_RDONLY);
if (fd < 0)
continue;
len = read_in_full(fd, signature, 8);
close(fd);
if (len != 8 || strncmp(signature, "gitdir: ", 8))
continue;
dst = read_gitfile(path->buf);
if (dst) {
*is_bundle = 0;
return dst;
}
}
}
for (i = 0; i < ARRAY_SIZE(bundle_suffix); i++) {
strbuf_setlen(path, baselen);
strbuf_addstr(path, bundle_suffix[i]);
if (!stat(path->buf, &st) && S_ISREG(st.st_mode)) {
*is_bundle = 1;
return path->buf;
}
}
return NULL;
}
static char *get_repo_path(const char *repo, int *is_bundle)
{
struct strbuf path = STRBUF_INIT;
const char *raw;
char *canon;
strbuf_addstr(&path, repo);
raw = get_repo_path_1(&path, is_bundle);
canon = raw ? absolute_pathdup(raw) : NULL;
strbuf_release(&path);
return canon;
}
static char *guess_dir_name(const char *repo, int is_bundle, int is_bare)
{
const char *end = repo + strlen(repo), *start, *ptr;
size_t len;
char *dir;
/*
* Skip scheme.
*/
start = strstr(repo, "://");
if (start == NULL)
start = repo;
else
start += 3;
/*
* Skip authentication data. The stripping does happen
* greedily, such that we strip up to the last '@' inside
* the host part.
*/
for (ptr = start; ptr < end && !is_dir_sep(*ptr); ptr++) {
if (*ptr == '@')
start = ptr + 1;
}
/*
* Strip trailing spaces, slashes and /.git
*/
while (start < end && (is_dir_sep(end[-1]) || isspace(end[-1])))
end--;
if (end - start > 5 && is_dir_sep(end[-5]) &&
!strncmp(end - 4, ".git", 4)) {
end -= 5;
while (start < end && is_dir_sep(end[-1]))
end--;
}
/*
* Strip trailing port number if we've got only a
* hostname (that is, there is no dir separator but a
* colon). This check is required such that we do not
* strip URI's like '/foo/bar:2222.git', which should
* result in a dir '2222' being guessed due to backwards
* compatibility.
*/
if (memchr(start, '/', end - start) == NULL
&& memchr(start, ':', end - start) != NULL) {
ptr = end;
while (start < ptr && isdigit(ptr[-1]) && ptr[-1] != ':')
ptr--;
if (start < ptr && ptr[-1] == ':')
end = ptr - 1;
}
/*
* Find last component. To remain backwards compatible we
* also regard colons as path separators, such that
* cloning a repository 'foo:bar.git' would result in a
* directory 'bar' being guessed.
*/
ptr = end;
while (start < ptr && !is_dir_sep(ptr[-1]) && ptr[-1] != ':')
ptr--;
start = ptr;
/*
* Strip .{bundle,git}.
*/
len = end - start;
strip_suffix_mem(start, &len, is_bundle ? ".bundle" : ".git");
if (!len || (len == 1 && *start == '/'))
die(_("No directory name could be guessed.\n"
"Please specify a directory on the command line"));
if (is_bare)
dir = xstrfmt("%.*s.git", (int)len, start);
else
dir = xstrndup(start, len);
/*
* Replace sequences of 'control' characters and whitespace
* with one ascii space, remove leading and trailing spaces.
*/
if (*dir) {
char *out = dir;
int prev_space = 1 /* strip leading whitespace */;
for (end = dir; *end; ++end) {
char ch = *end;
if ((unsigned char)ch < '\x20')
ch = '\x20';
if (isspace(ch)) {
if (prev_space)
continue;
prev_space = 1;
} else
prev_space = 0;
*out++ = ch;
}
*out = '\0';
if (out > dir && prev_space)
out[-1] = '\0';
}
return dir;
}
static void strip_trailing_slashes(char *dir)
{
char *end = dir + strlen(dir);
while (dir < end - 1 && is_dir_sep(end[-1]))
end--;
*end = '\0';
}
static int add_one_reference(struct string_list_item *item, void *cb_data)
{
struct strbuf err = STRBUF_INIT;
int *required = cb_data;
char *ref_git = compute_alternate_path(item->string, &err);
if (!ref_git) {
if (*required)
die("%s", err.buf);
else
fprintf(stderr,
_("info: Could not add alternate for '%s': %s\n"),
item->string, err.buf);
} else {
struct strbuf sb = STRBUF_INIT;
strbuf_addf(&sb, "%s/objects", ref_git);
add_to_alternates_file(sb.buf);
strbuf_release(&sb);
}
strbuf_release(&err);
free(ref_git);
return 0;
}
static void setup_reference(void)
{
int required = 1;
for_each_string_list(&option_required_reference,
add_one_reference, &required);
required = 0;
for_each_string_list(&option_optional_reference,
add_one_reference, &required);
}
static void copy_alternates(struct strbuf *src, struct strbuf *dst,
const char *src_repo)
{
/*
* Read from the source objects/info/alternates file
* and copy the entries to corresponding file in the
* destination repository with add_to_alternates_file().
* Both src and dst have "$path/objects/info/alternates".
*
* Instead of copying bit-for-bit from the original,
* we need to append to existing one so that the already
* created entry via "clone -s" is not lost, and also
* to turn entries with paths relative to the original
* absolute, so that they can be used in the new repository.
*/
FILE *in = fopen(src->buf, "r");
struct strbuf line = STRBUF_INIT;
while (strbuf_getline(&line, in) != EOF) {
char *abs_path;
if (!line.len || line.buf[0] == '#')
continue;
if (is_absolute_path(line.buf)) {
add_to_alternates_file(line.buf);
continue;
}
abs_path = mkpathdup("%s/objects/%s", src_repo, line.buf);
if (!normalize_path_copy(abs_path, abs_path))
add_to_alternates_file(abs_path);
else
warning("skipping invalid relative alternate: %s/%s",
src_repo, line.buf);
free(abs_path);
}
strbuf_release(&line);
fclose(in);
}
static void copy_or_link_directory(struct strbuf *src, struct strbuf *dest,
const char *src_repo, int src_baselen)
{
struct dirent *de;
struct stat buf;
int src_len, dest_len;
DIR *dir;
dir = opendir(src->buf);
if (!dir)
die_errno(_("failed to open '%s'"), src->buf);
if (mkdir(dest->buf, 0777)) {
if (errno != EEXIST)
die_errno(_("failed to create directory '%s'"), dest->buf);
else if (stat(dest->buf, &buf))
die_errno(_("failed to stat '%s'"), dest->buf);
else if (!S_ISDIR(buf.st_mode))
die(_("%s exists and is not a directory"), dest->buf);
}
strbuf_addch(src, '/');
src_len = src->len;
strbuf_addch(dest, '/');
dest_len = dest->len;
while ((de = readdir(dir)) != NULL) {
strbuf_setlen(src, src_len);
strbuf_addstr(src, de->d_name);
strbuf_setlen(dest, dest_len);
strbuf_addstr(dest, de->d_name);
if (stat(src->buf, &buf)) {
warning (_("failed to stat %s\n"), src->buf);
continue;
}
if (S_ISDIR(buf.st_mode)) {
if (de->d_name[0] != '.')
copy_or_link_directory(src, dest,
src_repo, src_baselen);
continue;
}
/* Files that cannot be copied bit-for-bit... */
if (!strcmp(src->buf + src_baselen, "/info/alternates")) {
copy_alternates(src, dest, src_repo);
continue;
}
if (unlink(dest->buf) && errno != ENOENT)
die_errno(_("failed to unlink '%s'"), dest->buf);
if (!option_no_hardlinks) {
if (!link(src->buf, dest->buf))
continue;
if (option_local > 0)
die_errno(_("failed to create link '%s'"), dest->buf);
option_no_hardlinks = 1;
}
if (copy_file_with_time(dest->buf, src->buf, 0666))
die_errno(_("failed to copy file to '%s'"), dest->buf);
}
closedir(dir);
}
static void clone_local(const char *src_repo, const char *dest_repo)
{
if (option_shared) {
struct strbuf alt = STRBUF_INIT;
strbuf_addf(&alt, "%s/objects", src_repo);
add_to_alternates_file(alt.buf);
strbuf_release(&alt);
} else {
struct strbuf src = STRBUF_INIT;
struct strbuf dest = STRBUF_INIT;
get_common_dir(&src, src_repo);
get_common_dir(&dest, dest_repo);
strbuf_addstr(&src, "/objects");
strbuf_addstr(&dest, "/objects");
copy_or_link_directory(&src, &dest, src_repo, src.len);
strbuf_release(&src);
strbuf_release(&dest);
}
if (0 <= option_verbosity)
fprintf(stderr, _("done.\n"));
}
static const char *junk_work_tree;
static const char *junk_git_dir;
static enum {
JUNK_LEAVE_NONE,
JUNK_LEAVE_REPO,
JUNK_LEAVE_ALL
} junk_mode = JUNK_LEAVE_NONE;
static const char junk_leave_repo_msg[] =
N_("Clone succeeded, but checkout failed.\n"
"You can inspect what was checked out with 'git status'\n"
"and retry the checkout with 'git checkout -f HEAD'\n");
static void remove_junk(void)
{
struct strbuf sb = STRBUF_INIT;
switch (junk_mode) {
case JUNK_LEAVE_REPO:
warning("%s", _(junk_leave_repo_msg));
/* fall-through */
case JUNK_LEAVE_ALL:
return;
default:
/* proceed to removal */
break;
}
if (junk_git_dir) {
strbuf_addstr(&sb, junk_git_dir);
remove_dir_recursively(&sb, 0);
strbuf_reset(&sb);
}
if (junk_work_tree) {
strbuf_addstr(&sb, junk_work_tree);
remove_dir_recursively(&sb, 0);
strbuf_reset(&sb);
}
}
static void remove_junk_on_signal(int signo)
{
remove_junk();
sigchain_pop(signo);
raise(signo);
}
static struct ref *find_remote_branch(const struct ref *refs, const char *branch)
{
struct ref *ref;
struct strbuf head = STRBUF_INIT;
strbuf_addstr(&head, "refs/heads/");
strbuf_addstr(&head, branch);
ref = find_ref_by_name(refs, head.buf);
strbuf_release(&head);
if (ref)
return ref;
strbuf_addstr(&head, "refs/tags/");
strbuf_addstr(&head, branch);
ref = find_ref_by_name(refs, head.buf);
strbuf_release(&head);
return ref;
}
static struct ref *wanted_peer_refs(const struct ref *refs,
struct refspec *refspec)
{
struct ref *head = copy_ref(find_ref_by_name(refs, "HEAD"));
struct ref *local_refs = head;
struct ref **tail = head ? &head->next : &local_refs;
if (option_single_branch) {
struct ref *remote_head = NULL;
if (!option_branch)
remote_head = guess_remote_head(head, refs, 0);
else {
local_refs = NULL;
tail = &local_refs;
remote_head = copy_ref(find_remote_branch(refs, option_branch));
}
if (!remote_head && option_branch)
warning(_("Could not find remote branch %s to clone."),
option_branch);
else {
get_fetch_map(remote_head, refspec, &tail, 0);
/* if --branch=tag, pull the requested tag explicitly */
get_fetch_map(remote_head, tag_refspec, &tail, 0);
}
} else
get_fetch_map(refs, refspec, &tail, 0);
if (!option_mirror && !option_single_branch)
get_fetch_map(refs, tag_refspec, &tail, 0);
return local_refs;
}
static void write_remote_refs(const struct ref *local_refs)
{
const struct ref *r;
struct ref_transaction *t;
struct strbuf err = STRBUF_INIT;
t = ref_transaction_begin(&err);
if (!t)
die("%s", err.buf);
for (r = local_refs; r; r = r->next) {
if (!r->peer_ref)
continue;
if (ref_transaction_create(t, r->peer_ref->name, r->old_oid.hash,
0, NULL, &err))
die("%s", err.buf);
}
if (initial_ref_transaction_commit(t, &err))
die("%s", err.buf);
strbuf_release(&err);
ref_transaction_free(t);
}
static void write_followtags(const struct ref *refs, const char *msg)
{
const struct ref *ref;
for (ref = refs; ref; ref = ref->next) {
if (!starts_with(ref->name, "refs/tags/"))
continue;
if (ends_with(ref->name, "^{}"))
continue;
if (!has_object_file(&ref->old_oid))
continue;
update_ref(msg, ref->name, ref->old_oid.hash,
NULL, 0, UPDATE_REFS_DIE_ON_ERR);
}
}
static int iterate_ref_map(void *cb_data, unsigned char sha1[20])
{
struct ref **rm = cb_data;
struct ref *ref = *rm;
/*
* Skip anything missing a peer_ref, which we are not
* actually going to write a ref for.
*/
while (ref && !ref->peer_ref)
ref = ref->next;
/* Returning -1 notes "end of list" to the caller. */
if (!ref)
return -1;
hashcpy(sha1, ref->old_oid.hash);
*rm = ref->next;
return 0;
}
static void update_remote_refs(const struct ref *refs,
const struct ref *mapped_refs,
const struct ref *remote_head_points_at,
const char *branch_top,
clone: open a shortcut for connectivity check In order to make sure the cloned repository is good, we run "rev-list --objects --not --all $new_refs" on the repository. This is expensive on large repositories. This patch attempts to mitigate the impact in this special case. In the "good" clone case, we only have one pack. If all of the following are met, we can be sure that all objects reachable from the new refs exist, which is the intention of running "rev-list ...": - all refs point to an object in the pack - there are no dangling pointers in any object in the pack - no objects in the pack point to objects outside the pack The second and third checks can be done with the help of index-pack as a slight variation of --strict check (which introduces a new condition for the shortcut: pack transfer must be used and the number of objects large enough to call index-pack). The first is checked in check_everything_connected after we get an "ok" from index-pack. "index-pack + new checks" is still faster than the current "index-pack + rev-list", which is the whole point of this patch. If any of the conditions fail, we fall back to the good old but expensive "rev-list ..". In that case it's even more expensive because we have to pay for the new checks in index-pack. But that should only happen when the other side is either buggy or malicious. Cloning linux-2.6 over file:// before after real 3m25.693s 2m53.050s user 5m2.037s 4m42.396s sys 0m13.750s 0m16.574s A more realistic test with ssh:// over wireless before after real 11m26.629s 10m4.213s user 5m43.196s 5m19.444s sys 0m35.812s 0m37.630s This shortcut is not applied to shallow clones, partly because shallow clones should have no more objects than a usual fetch and the cost of rev-list is acceptable, partly to avoid dealing with corner cases when grafting is involved. This shortcut does not apply to unpack-objects code path either because the number of objects must be small in order to trigger that code path. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-05-26 03:16:17 +02:00
const char *msg,
struct transport *transport,
clone: drop connectivity check for local clones Commit 0433ad1 (clone: run check_everything_connected, 2013-03-25) added the same connectivity check to clone that we use for fetching. The intent was to provide enough safety checks that "git clone git://..." could be counted on to detect bit errors and other repo corruption, and not silently propagate them to the clone. For local clones, this turns out to be a bad idea, for two reasons: 1. Local clones use hard linking (or even shared object stores), and so complete far more quickly. The time spent on the connectivity check is therefore proportionally much more painful. 2. Local clones do not actually meet our safety guarantee anyway. The connectivity check makes sure we have all of the objects we claim to, but it does not check for bit errors. We will notice bit errors in commits and trees, but we do not load blob objects at all. Whereas over the pack transport, we actually recompute the sha1 of each object in the incoming packfile; bit errors change the sha1 of the object, which is then caught by the connectivity check. This patch drops the connectivity check in the local case. Note that we have to revert the changes from 0433ad1 to t5710, as we no longer notice the corruption during clone. We could go a step further and provide a "verify even local clones" option, but it is probably not worthwhile. You can already spell that as "cd foo.git && git fsck && git clone ." or as "git clone --no-local foo.git". Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-08 09:30:41 +02:00
int check_connectivity)
{
const struct ref *rm = mapped_refs;
clone: drop connectivity check for local clones Commit 0433ad1 (clone: run check_everything_connected, 2013-03-25) added the same connectivity check to clone that we use for fetching. The intent was to provide enough safety checks that "git clone git://..." could be counted on to detect bit errors and other repo corruption, and not silently propagate them to the clone. For local clones, this turns out to be a bad idea, for two reasons: 1. Local clones use hard linking (or even shared object stores), and so complete far more quickly. The time spent on the connectivity check is therefore proportionally much more painful. 2. Local clones do not actually meet our safety guarantee anyway. The connectivity check makes sure we have all of the objects we claim to, but it does not check for bit errors. We will notice bit errors in commits and trees, but we do not load blob objects at all. Whereas over the pack transport, we actually recompute the sha1 of each object in the incoming packfile; bit errors change the sha1 of the object, which is then caught by the connectivity check. This patch drops the connectivity check in the local case. Note that we have to revert the changes from 0433ad1 to t5710, as we no longer notice the corruption during clone. We could go a step further and provide a "verify even local clones" option, but it is probably not worthwhile. You can already spell that as "cd foo.git && git fsck && git clone ." or as "git clone --no-local foo.git". Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-08 09:30:41 +02:00
if (check_connectivity) {
check_everything_connected: use a struct with named options The number of variants of check_everything_connected has grown over the years, so that the "real" function takes several possibly-zero, possibly-NULL arguments. We hid the complexity behind some wrapper functions, but this doesn't scale well when we want to add new options. If we add more wrapper variants to handle the new options, then we can get a combinatorial explosion when those options might be used together (right now nobody wants to use both "shallow" and "transport" together, so we get by with just a few wrappers). If instead we add new parameters to each function, each of which can have a default value, then callers who want the defaults end up with confusing invocations like: check_everything_connected(fn, 0, data, -1, 0, NULL); where it is unclear which parameter is which (and every caller needs updated when we add new options). Instead, let's add a struct to hold all of the optional parameters. This is a little more verbose for the callers (who have to declare the struct and fill it in), but it makes their code much easier to follow, because every option is named as it is set (and unused options do not have to be mentioned at all). Note that we could also stick the iteration function and its callback data into the option struct, too. But since those are required for each call, by avoiding doing so, we can let very simple callers just pass "NULL" for the options and not worry about the struct at all. While we're touching each site, let's also rename the function to check_connected(). The existing name was quite long, and not all of the wrappers even used the full name. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-07-15 12:30:40 +02:00
struct check_connected_options opt = CHECK_CONNECTED_INIT;
opt.transport = transport;
opt.progress = transport->progress;
check_everything_connected: use a struct with named options The number of variants of check_everything_connected has grown over the years, so that the "real" function takes several possibly-zero, possibly-NULL arguments. We hid the complexity behind some wrapper functions, but this doesn't scale well when we want to add new options. If we add more wrapper variants to handle the new options, then we can get a combinatorial explosion when those options might be used together (right now nobody wants to use both "shallow" and "transport" together, so we get by with just a few wrappers). If instead we add new parameters to each function, each of which can have a default value, then callers who want the defaults end up with confusing invocations like: check_everything_connected(fn, 0, data, -1, 0, NULL); where it is unclear which parameter is which (and every caller needs updated when we add new options). Instead, let's add a struct to hold all of the optional parameters. This is a little more verbose for the callers (who have to declare the struct and fill it in), but it makes their code much easier to follow, because every option is named as it is set (and unused options do not have to be mentioned at all). Note that we could also stick the iteration function and its callback data into the option struct, too. But since those are required for each call, by avoiding doing so, we can let very simple callers just pass "NULL" for the options and not worry about the struct at all. While we're touching each site, let's also rename the function to check_connected(). The existing name was quite long, and not all of the wrappers even used the full name. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-07-15 12:30:40 +02:00
if (check_connected(iterate_ref_map, &rm, &opt))
clone: drop connectivity check for local clones Commit 0433ad1 (clone: run check_everything_connected, 2013-03-25) added the same connectivity check to clone that we use for fetching. The intent was to provide enough safety checks that "git clone git://..." could be counted on to detect bit errors and other repo corruption, and not silently propagate them to the clone. For local clones, this turns out to be a bad idea, for two reasons: 1. Local clones use hard linking (or even shared object stores), and so complete far more quickly. The time spent on the connectivity check is therefore proportionally much more painful. 2. Local clones do not actually meet our safety guarantee anyway. The connectivity check makes sure we have all of the objects we claim to, but it does not check for bit errors. We will notice bit errors in commits and trees, but we do not load blob objects at all. Whereas over the pack transport, we actually recompute the sha1 of each object in the incoming packfile; bit errors change the sha1 of the object, which is then caught by the connectivity check. This patch drops the connectivity check in the local case. Note that we have to revert the changes from 0433ad1 to t5710, as we no longer notice the corruption during clone. We could go a step further and provide a "verify even local clones" option, but it is probably not worthwhile. You can already spell that as "cd foo.git && git fsck && git clone ." or as "git clone --no-local foo.git". Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-08 09:30:41 +02:00
die(_("remote did not send all necessary objects"));
}
if (refs) {
write_remote_refs(mapped_refs);
if (option_single_branch)
write_followtags(refs, msg);
}
if (remote_head_points_at && !option_bare) {
struct strbuf head_ref = STRBUF_INIT;
strbuf_addstr(&head_ref, branch_top);
strbuf_addstr(&head_ref, "HEAD");
if (create_symref(head_ref.buf,
remote_head_points_at->peer_ref->name,
msg) < 0)
die(_("unable to update %s"), head_ref.buf);
strbuf_release(&head_ref);
}
}
static void update_head(const struct ref *our, const struct ref *remote,
const char *msg)
{
const char *head;
if (our && skip_prefix(our->name, "refs/heads/", &head)) {
/* Local default branch link */
if (create_symref("HEAD", our->name, NULL) < 0)
die(_("unable to update HEAD"));
if (!option_bare) {
update_ref(msg, "HEAD", our->old_oid.hash, NULL, 0,
UPDATE_REFS_DIE_ON_ERR);
install_branch_config(0, head, option_origin, our->name);
}
} else if (our) {
Convert lookup_commit* to struct object_id Convert lookup_commit, lookup_commit_or_die, lookup_commit_reference, and lookup_commit_reference_gently to take struct object_id arguments. Introduce a temporary in parse_object buffer in order to convert this function. This is required since in order to convert parse_object and parse_object_buffer, lookup_commit_reference_gently and lookup_commit_or_die would need to be converted. Not introducing a temporary would therefore require that lookup_commit_or_die take a struct object_id *, but lookup_commit would take unsigned char *, leaving a confusing and hard-to-use interface. parse_object_buffer will lose this temporary in a later patch. This commit was created with manual changes to commit.c, commit.h, and object.c, plus the following semantic patch: @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1.hash, E2) + lookup_commit_reference_gently(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1->hash, E2) + lookup_commit_reference_gently(E1, E2) @@ expression E1; @@ - lookup_commit_reference(E1.hash) + lookup_commit_reference(&E1) @@ expression E1; @@ - lookup_commit_reference(E1->hash) + lookup_commit_reference(E1) @@ expression E1; @@ - lookup_commit(E1.hash) + lookup_commit(&E1) @@ expression E1; @@ - lookup_commit(E1->hash) + lookup_commit(E1) @@ expression E1, E2; @@ - lookup_commit_or_die(E1.hash, E2) + lookup_commit_or_die(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_or_die(E1->hash, E2) + lookup_commit_or_die(E1, E2) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 00:10:10 +02:00
struct commit *c = lookup_commit_reference(&our->old_oid);
/* --branch specifies a non-branch (i.e. tags), detach HEAD */
update_ref(msg, "HEAD", c->object.oid.hash,
NULL, REF_NODEREF, UPDATE_REFS_DIE_ON_ERR);
} else if (remote) {
/*
* We know remote HEAD points to a non-branch, or
* HEAD points to a branch but we don't know which one.
* Detach HEAD in all these cases.
*/
update_ref(msg, "HEAD", remote->old_oid.hash,
NULL, REF_NODEREF, UPDATE_REFS_DIE_ON_ERR);
}
}
clone: pass --progress decision to recursive submodules When cloning with "--recursive", we'd generally expect submodules to show progress reports if the main clone did, too. In older versions of git, this mostly worked out of the box. Since we show progress by default when stderr is a tty, and since the child clones inherit the parent stderr, then both processes would come to the same decision by default. If the parent clone was asked for "--quiet", we passed down "--quiet" to the child. However, if stderr was not a tty and the user specified "--progress", we did not propagate this to the child. That's a minor bug, but things got much worse when we switched recently to submodule--helper's update_clone command. With that change, the stderr of the child clones are always connected to a pipe, and we never output progress at all. This patch teaches git-submodule and git-submodule--helper how to pass down an explicit "--progress" flag when cloning. The clone command then decides to propagate that flag based on the cloning decision made earlier (which takes into account isatty(2) of the parent process, existing --progress or --quiet flags, etc). Since the child processes always run without a tty on stderr, we don't have to worry about passing an explicit "--no-progress"; it's the default for them. This fixes the recent loss of progress during recursive clones. And as a bonus, it makes: git clone --recursive --progress ... 2>&1 | cat work by triggering progress explicitly in the children. Signed-off-by: Jeff King <peff@peff.net> Acked-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-22 07:24:46 +02:00
static int checkout(int submodule_progress)
{
struct object_id oid;
char *head;
struct lock_file *lock_file;
struct unpack_trees_options opts;
struct tree *tree;
struct tree_desc t;
int err = 0;
if (option_no_checkout)
return 0;
head = resolve_refdup("HEAD", RESOLVE_REF_READING, oid.hash, NULL);
if (!head) {
warning(_("remote HEAD refers to nonexistent ref, "
"unable to checkout.\n"));
return 0;
}
if (!strcmp(head, "HEAD")) {
if (advice_detached_head)
detach_advice(oid_to_hex(&oid));
} else {
if (!starts_with(head, "refs/heads/"))
die(_("HEAD not found below refs/heads!"));
}
free(head);
/* We need to be in the new work tree for the checkout */
setup_work_tree();
lock_file = xcalloc(1, sizeof(struct lock_file));
hold_locked_index(): align error handling with hold_lockfile_for_update() Callers of the hold_locked_index() function pass 0 when they want to prepare to write a new version of the index file without wishing to die or emit an error message when the request fails (e.g. somebody else already held the lock), and pass 1 when they want the call to die upon failure. This option is called LOCK_DIE_ON_ERROR by the underlying lockfile API, and the hold_locked_index() function translates the paramter to LOCK_DIE_ON_ERROR when calling the hold_lock_file_for_update(). Replace these hardcoded '1' with LOCK_DIE_ON_ERROR and stop translating. Callers other than the ones that are replaced with this change pass '0' to the function; no behaviour change is intended with this patch. Signed-off-by: Junio C Hamano <gitster@pobox.com> --- Among the callers of hold_locked_index() that passes 0: - diff.c::refresh_index_quietly() at the end of "git diff" is an opportunistic update; it leaks the lockfile structure but it is just before the program exits and nobody should care. - builtin/describe.c::cmd_describe(), builtin/commit.c::cmd_status(), sequencer.c::read_and_refresh_cache() are all opportunistic updates and they are OK. - builtin/update-index.c::cmd_update_index() takes a lock upfront but we may end up not needing to update the index (i.e. the entries may be fully up-to-date), in which case we do not need to issue an error upon failure to acquire the lock. We do diagnose and die if we indeed need to update, so it is OK. - wt-status.c::require_clean_work_tree() IS BUGGY. It asks silence, does not check the returned value. Compare with callsites like cmd_describe() and cmd_status() to notice that it is wrong to call update_index_if_able() unconditionally.
2016-12-07 19:33:54 +01:00
hold_locked_index(lock_file, LOCK_DIE_ON_ERROR);
memset(&opts, 0, sizeof opts);
opts.update = 1;
opts.merge = 1;
opts.fn = oneway_merge;
opts.verbose_update = (option_verbosity >= 0);
opts.src_index = &the_index;
opts.dst_index = &the_index;
tree = parse_tree_indirect(oid.hash);
parse_tree(tree);
init_tree_desc(&t, tree->buffer, tree->size);
if (unpack_trees(1, &t, &opts) < 0)
die(_("unable to checkout working tree"));
if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
die(_("unable to write new index file"));
err |= run_hook_le(NULL, "post-checkout", sha1_to_hex(null_sha1),
oid_to_hex(&oid), "1", NULL);
if (!err && (option_recurse_submodules.nr > 0)) {
struct argv_array args = ARGV_ARRAY_INIT;
argv_array_pushl(&args, "submodule", "update", "--init", "--recursive", NULL);
if (option_shallow_submodules == 1)
clone: add `--shallow-submodules` flag When creating a shallow clone of a repository with submodules, the depth argument does not influence the submodules, i.e. the submodules are done as non-shallow clones. It is unclear what the best default is for the depth of submodules of a shallow clone, so we need to have the possibility to do all kinds of combinations: * shallow super project with shallow submodules e.g. build bots starting always from scratch. They want to transmit the least amount of network data as well as using the least amount of space on their hard drive. * shallow super project with unshallow submodules e.g. The superproject is just there to track a collection of repositories and it is not important to have the relationship between the repositories intact. However the history of the individual submodules matter. * unshallow super project with shallow submodules e.g. The superproject is the actual project and the submodule is a library which is rarely touched. The new switch to select submodules to be shallow or unshallow supports all of these three cases. It is easy to transition from the first to the second case by just unshallowing the submodules (`git submodule foreach git fetch --unshallow`), but it is not possible to transition from the second to the first case (as we would have already transmitted the non shallow over the network). That is why we want to make the first case the default in case of a shallow super project. This leads to the inconvenience in the second case with the shallow super project and unshallow submodules, as you need to pass `--no-shallow-submodules`. Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-04-26 03:12:27 +02:00
argv_array_push(&args, "--depth=1");
if (max_jobs != -1)
argv_array_pushf(&args, "--jobs=%d", max_jobs);
clone: pass --progress decision to recursive submodules When cloning with "--recursive", we'd generally expect submodules to show progress reports if the main clone did, too. In older versions of git, this mostly worked out of the box. Since we show progress by default when stderr is a tty, and since the child clones inherit the parent stderr, then both processes would come to the same decision by default. If the parent clone was asked for "--quiet", we passed down "--quiet" to the child. However, if stderr was not a tty and the user specified "--progress", we did not propagate this to the child. That's a minor bug, but things got much worse when we switched recently to submodule--helper's update_clone command. With that change, the stderr of the child clones are always connected to a pipe, and we never output progress at all. This patch teaches git-submodule and git-submodule--helper how to pass down an explicit "--progress" flag when cloning. The clone command then decides to propagate that flag based on the cloning decision made earlier (which takes into account isatty(2) of the parent process, existing --progress or --quiet flags, etc). Since the child processes always run without a tty on stderr, we don't have to worry about passing an explicit "--no-progress"; it's the default for them. This fixes the recent loss of progress during recursive clones. And as a bonus, it makes: git clone --recursive --progress ... 2>&1 | cat work by triggering progress explicitly in the children. Signed-off-by: Jeff King <peff@peff.net> Acked-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-22 07:24:46 +02:00
if (submodule_progress)
argv_array_push(&args, "--progress");
err = run_command_v_opt(args.argv, RUN_GIT_CMD);
argv_array_clear(&args);
}
return err;
}
static int write_one_config(const char *key, const char *value, void *data)
{
return git_config_set_multivar_gently(key, value ? value : "true", "^$", 0);
}
static void write_config(struct string_list *config)
{
int i;
for (i = 0; i < config->nr; i++) {
if (git_config_parse_parameter(config->items[i].string,
write_one_config, NULL) < 0)
die(_("unable to write parameters to config file"));
}
}
static void write_refspec_config(const char *src_ref_prefix,
const struct ref *our_head_points_at,
const struct ref *remote_head_points_at,
struct strbuf *branch_top)
{
struct strbuf key = STRBUF_INIT;
struct strbuf value = STRBUF_INIT;
if (option_mirror || !option_bare) {
if (option_single_branch && !option_mirror) {
if (option_branch) {
if (starts_with(our_head_points_at->name, "refs/tags/"))
strbuf_addf(&value, "+%s:%s", our_head_points_at->name,
our_head_points_at->name);
else
strbuf_addf(&value, "+%s:%s%s", our_head_points_at->name,
branch_top->buf, option_branch);
} else if (remote_head_points_at) {
const char *head = remote_head_points_at->name;
if (!skip_prefix(head, "refs/heads/", &head))
die("BUG: remote HEAD points at non-head?");
strbuf_addf(&value, "+%s:%s%s", remote_head_points_at->name,
branch_top->buf, head);
}
/*
* otherwise, the next "git fetch" will
* simply fetch from HEAD without updating
* any remote-tracking branch, which is what
* we want.
*/
} else {
strbuf_addf(&value, "+%s*:%s*", src_ref_prefix, branch_top->buf);
}
/* Configure the remote */
if (value.len) {
strbuf_addf(&key, "remote.%s.fetch", option_origin);
git_config_set_multivar(key.buf, value.buf, "^$", 0);
strbuf_reset(&key);
if (option_mirror) {
strbuf_addf(&key, "remote.%s.mirror", option_origin);
git_config_set(key.buf, "true");
strbuf_reset(&key);
}
}
}
strbuf_release(&key);
strbuf_release(&value);
}
static void dissociate_from_references(void)
{
static const char* argv[] = { "repack", "-a", "-d", NULL };
char *alternates = git_pathdup("objects/info/alternates");
if (!access(alternates, F_OK)) {
if (run_command_v_opt(argv, RUN_GIT_CMD|RUN_COMMAND_NO_STDIN))
die(_("cannot repack to clean up"));
if (unlink(alternates) && errno != ENOENT)
die_errno(_("cannot unlink temporary alternates file"));
}
free(alternates);
}
int cmd_clone(int argc, const char **argv, const char *prefix)
{
int is_bundle = 0, is_local;
struct stat buf;
const char *repo_name, *repo, *work_tree, *git_dir;
char *path, *dir;
int dest_exists;
const struct ref *refs, *remote_head;
const struct ref *remote_head_points_at;
const struct ref *our_head_points_at;
struct ref *mapped_refs;
clone: fix up delay cloning conditions 6f48d39 (clone: delay cloning until after remote HEAD checking - 2012-01-16) allows us to perform some checks on remote refs before the actual cloning happens. But not all transport types support this. Remote helper with "import" capability will not return complete ref information until fetch is performed and therefore the clone cannot be delayed. foreign_vcs field in struct remote was used to detect this kind of transport and save the result. This is a mistake because foreign_vcs is designed to override url-based transport detection. As a result, if the same "struct transport *" object is used on many different urls and one of them attached remote transport, the following urls will be mistakenly attached to the same transport. This fault is worked around by dad0b3d (push: do not let configured foreign-vcs permanently clobbered - 2012-01-23) To fix this, detect incomplete refs from transport_get_remote_refs() by SHA-1. Incomplete ones must have null SHA-1 (*). Then revert changes related to foreign_cvs field in 6f48d39 and dad0b3d. A good thing from this change is that cloning smart http transport can also be delayed. Earlier it falls into the same category "remote transport, no delay". (*) Theoretically if one of the remote refs happens to have null SHA-1, it will trigger false alarm and the clone will not be delayed. But that chance may be too small for us to pay attention to. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-24 12:10:38 +01:00
const struct ref *ref;
struct strbuf key = STRBUF_INIT, value = STRBUF_INIT;
struct strbuf branch_top = STRBUF_INIT, reflog_msg = STRBUF_INIT;
struct transport *transport = NULL;
const char *src_ref_prefix = "refs/heads/";
struct remote *remote;
clone: fix up delay cloning conditions 6f48d39 (clone: delay cloning until after remote HEAD checking - 2012-01-16) allows us to perform some checks on remote refs before the actual cloning happens. But not all transport types support this. Remote helper with "import" capability will not return complete ref information until fetch is performed and therefore the clone cannot be delayed. foreign_vcs field in struct remote was used to detect this kind of transport and save the result. This is a mistake because foreign_vcs is designed to override url-based transport detection. As a result, if the same "struct transport *" object is used on many different urls and one of them attached remote transport, the following urls will be mistakenly attached to the same transport. This fault is worked around by dad0b3d (push: do not let configured foreign-vcs permanently clobbered - 2012-01-23) To fix this, detect incomplete refs from transport_get_remote_refs() by SHA-1. Incomplete ones must have null SHA-1 (*). Then revert changes related to foreign_cvs field in 6f48d39 and dad0b3d. A good thing from this change is that cloning smart http transport can also be delayed. Earlier it falls into the same category "remote transport, no delay". (*) Theoretically if one of the remote refs happens to have null SHA-1, it will trigger false alarm and the clone will not be delayed. But that chance may be too small for us to pay attention to. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-24 12:10:38 +01:00
int err = 0, complete_refs_before_fetch = 1;
clone: pass --progress decision to recursive submodules When cloning with "--recursive", we'd generally expect submodules to show progress reports if the main clone did, too. In older versions of git, this mostly worked out of the box. Since we show progress by default when stderr is a tty, and since the child clones inherit the parent stderr, then both processes would come to the same decision by default. If the parent clone was asked for "--quiet", we passed down "--quiet" to the child. However, if stderr was not a tty and the user specified "--progress", we did not propagate this to the child. That's a minor bug, but things got much worse when we switched recently to submodule--helper's update_clone command. With that change, the stderr of the child clones are always connected to a pipe, and we never output progress at all. This patch teaches git-submodule and git-submodule--helper how to pass down an explicit "--progress" flag when cloning. The clone command then decides to propagate that flag based on the cloning decision made earlier (which takes into account isatty(2) of the parent process, existing --progress or --quiet flags, etc). Since the child processes always run without a tty on stderr, we don't have to worry about passing an explicit "--no-progress"; it's the default for them. This fixes the recent loss of progress during recursive clones. And as a bonus, it makes: git clone --recursive --progress ... 2>&1 | cat work by triggering progress explicitly in the children. Signed-off-by: Jeff King <peff@peff.net> Acked-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-22 07:24:46 +02:00
int submodule_progress;
struct refspec *refspec;
const char *fetch_pattern;
packet_trace_identity("clone");
argc = parse_options(argc, argv, prefix, builtin_clone_options,
builtin_clone_usage, 0);
if (argc > 2)
usage_msg_opt(_("Too many arguments."),
builtin_clone_usage, builtin_clone_options);
if (argc == 0)
usage_msg_opt(_("You must specify a repository to clone."),
builtin_clone_usage, builtin_clone_options);
if (option_depth || option_since || option_not.nr)
deepen = 1;
if (option_single_branch == -1)
option_single_branch = deepen ? 1 : 0;
if (option_mirror)
option_bare = 1;
if (option_bare) {
if (option_origin)
die(_("--bare and --origin %s options are incompatible."),
option_origin);
if (real_git_dir)
die(_("--bare and --separate-git-dir are incompatible."));
option_no_checkout = 1;
}
if (!option_origin)
option_origin = "origin";
repo_name = argv[0];
path = get_repo_path(repo_name, &is_bundle);
if (path)
repo = absolute_pathdup(repo_name);
else if (!strchr(repo_name, ':'))
die(_("repository '%s' does not exist"), repo_name);
else
repo = repo_name;
/* no need to be strict, transport_set_option() will validate it again */
if (option_depth && atoi(option_depth) < 1)
die(_("depth %s is not a positive number"), option_depth);
if (argc == 2)
dir = xstrdup(argv[1]);
else
dir = guess_dir_name(repo_name, is_bundle, option_bare);
strip_trailing_slashes(dir);
dest_exists = !stat(dir, &buf);
if (dest_exists && !is_empty_dir(dir))
die(_("destination path '%s' already exists and is not "
"an empty directory."), dir);
strbuf_addf(&reflog_msg, "clone: from %s", repo);
if (option_bare)
work_tree = NULL;
else {
work_tree = getenv("GIT_WORK_TREE");
if (work_tree && !stat(work_tree, &buf))
die(_("working tree '%s' already exists."), work_tree);
}
if (option_bare || work_tree)
git_dir = xstrdup(dir);
else {
work_tree = dir;
git_dir = mkpathdup("%s/.git", dir);
}
clone: initialize atexit cleanup handler earlier If clone fails, we generally try to clean up any directories we've created. We do this by installing an atexit handler, so that we don't have to manually trigger cleanup. However, since we install this after touching the filesystem, any errors between our initial mkdir() and our atexit() call will result in us leaving a crufty directory around. We can fix this by moving our atexit() call earlier. It's OK to do it before the junk_work_tree variable is set, because remove_junk makes sure the variable is initialized. This means we "activate" the handler by assigning to the junk_work_tree variable, which we now bump down to just after we call mkdir(). We probably do not want to do it before, because a plausible reason for mkdir() to fail is EEXIST (i.e., we are racing with another "git init"), and we would not want to remove their work. OTOH, this is probably not that big a deal; we will allow cloning into an empty directory (and skip the mkdir), which is already racy (i.e., one clone may see the other's empty dir and start writing into it). Still, it does not hurt to err on the side of caution here. Note that writing into junk_work_tree and junk_git_dir after installing the handler is also technically racy, as we call our handler on an async signal. Depending on the platform, we could see a sheared write to the variables. Traditionally we have not worried about this, and indeed we already do this later in the function. If we want to address that, it can come as a separate topic. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-18 19:55:32 +01:00
atexit(remove_junk);
sigchain_push_common(remove_junk_on_signal);
if (!option_bare) {
if (safe_create_leading_directories_const(work_tree) < 0)
die_errno(_("could not create leading directories of '%s'"),
work_tree);
if (!dest_exists && mkdir(work_tree, 0777))
die_errno(_("could not create work tree dir '%s'"),
work_tree);
clone: initialize atexit cleanup handler earlier If clone fails, we generally try to clean up any directories we've created. We do this by installing an atexit handler, so that we don't have to manually trigger cleanup. However, since we install this after touching the filesystem, any errors between our initial mkdir() and our atexit() call will result in us leaving a crufty directory around. We can fix this by moving our atexit() call earlier. It's OK to do it before the junk_work_tree variable is set, because remove_junk makes sure the variable is initialized. This means we "activate" the handler by assigning to the junk_work_tree variable, which we now bump down to just after we call mkdir(). We probably do not want to do it before, because a plausible reason for mkdir() to fail is EEXIST (i.e., we are racing with another "git init"), and we would not want to remove their work. OTOH, this is probably not that big a deal; we will allow cloning into an empty directory (and skip the mkdir), which is already racy (i.e., one clone may see the other's empty dir and start writing into it). Still, it does not hurt to err on the side of caution here. Note that writing into junk_work_tree and junk_git_dir after installing the handler is also technically racy, as we call our handler on an async signal. Depending on the platform, we could see a sheared write to the variables. Traditionally we have not worried about this, and indeed we already do this later in the function. If we want to address that, it can come as a separate topic. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-03-18 19:55:32 +01:00
junk_work_tree = work_tree;
set_git_work_tree(work_tree);
}
junk_git_dir = real_git_dir ? real_git_dir : git_dir;
if (safe_create_leading_directories_const(git_dir) < 0)
die(_("could not create leading directories of '%s'"), git_dir);
if (0 <= option_verbosity) {
if (option_bare)
fprintf(stderr, _("Cloning into bare repository '%s'...\n"), dir);
else
fprintf(stderr, _("Cloning into '%s'...\n"), dir);
}
if (option_recurse_submodules.nr > 0) {
struct string_list_item *item;
struct strbuf sb = STRBUF_INIT;
/* remove duplicates */
string_list_sort(&option_recurse_submodules);
string_list_remove_duplicates(&option_recurse_submodules, 0);
/*
* NEEDSWORK: In a multi-working-tree world, this needs to be
* set in the per-worktree config.
*/
for_each_string_list_item(item, &option_recurse_submodules) {
strbuf_addf(&sb, "submodule.active=%s",
item->string);
string_list_append(&option_config,
strbuf_detach(&sb, NULL));
}
if (option_required_reference.nr &&
option_optional_reference.nr)
die(_("clone --recursive is not compatible with "
"both --reference and --reference-if-able"));
else if (option_required_reference.nr) {
string_list_append(&option_config,
"submodule.alternateLocation=superproject");
string_list_append(&option_config,
"submodule.alternateErrorStrategy=die");
} else if (option_optional_reference.nr) {
string_list_append(&option_config,
"submodule.alternateLocation=superproject");
string_list_append(&option_config,
"submodule.alternateErrorStrategy=info");
}
}
init_db(git_dir, real_git_dir, option_template, INIT_DB_QUIET);
if (real_git_dir)
git_dir = real_git_dir;
write_config(&option_config);
git_config(git_default_config, NULL);
if (option_bare) {
if (option_mirror)
src_ref_prefix = "refs/";
strbuf_addstr(&branch_top, src_ref_prefix);
git_config_set("core.bare", "true");
} else {
strbuf_addf(&branch_top, "refs/remotes/%s/", option_origin);
}
strbuf_addf(&value, "+%s*:%s*", src_ref_prefix, branch_top.buf);
strbuf_addf(&key, "remote.%s.url", option_origin);
git_config_set(key.buf, repo);
strbuf_reset(&key);
if (option_required_reference.nr || option_optional_reference.nr)
setup_reference();
fetch_pattern = value.buf;
refspec = parse_fetch_refspec(1, &fetch_pattern);
strbuf_reset(&value);
remote = remote_get(option_origin);
transport = transport_get(remote, remote->url[0]);
transport_set_verbosity(transport, option_verbosity, option_progress);
transport->family = family;
path = get_repo_path(remote->url[0], &is_bundle);
is_local = option_local != 0 && path && !is_bundle;
if (is_local) {
if (option_depth)
warning(_("--depth is ignored in local clones; use file:// instead."));
if (option_since)
warning(_("--shallow-since is ignored in local clones; use file:// instead."));
if (option_not.nr)
warning(_("--shallow-exclude is ignored in local clones; use file:// instead."));
if (!access(mkpath("%s/shallow", path), F_OK)) {
if (option_local > 0)
warning(_("source repository is shallow, ignoring --local"));
is_local = 0;
}
}
if (option_local > 0 && !is_local)
warning(_("--local is ignored"));
transport->cloning = 1;
if (!transport->get_refs_list || (!is_local && !transport->fetch))
die(_("Don't know how to clone %s"), transport->url);
transport_set_option(transport, TRANS_OPT_KEEP, "yes");
if (option_depth)
transport_set_option(transport, TRANS_OPT_DEPTH,
option_depth);
if (option_since)
transport_set_option(transport, TRANS_OPT_DEEPEN_SINCE,
option_since);
if (option_not.nr)
transport_set_option(transport, TRANS_OPT_DEEPEN_NOT,
(const char *)&option_not);
if (option_single_branch)
transport_set_option(transport, TRANS_OPT_FOLLOWTAGS, "1");
if (option_upload_pack)
transport_set_option(transport, TRANS_OPT_UPLOADPACK,
option_upload_pack);
clone: open a shortcut for connectivity check In order to make sure the cloned repository is good, we run "rev-list --objects --not --all $new_refs" on the repository. This is expensive on large repositories. This patch attempts to mitigate the impact in this special case. In the "good" clone case, we only have one pack. If all of the following are met, we can be sure that all objects reachable from the new refs exist, which is the intention of running "rev-list ...": - all refs point to an object in the pack - there are no dangling pointers in any object in the pack - no objects in the pack point to objects outside the pack The second and third checks can be done with the help of index-pack as a slight variation of --strict check (which introduces a new condition for the shortcut: pack transfer must be used and the number of objects large enough to call index-pack). The first is checked in check_everything_connected after we get an "ok" from index-pack. "index-pack + new checks" is still faster than the current "index-pack + rev-list", which is the whole point of this patch. If any of the conditions fail, we fall back to the good old but expensive "rev-list ..". In that case it's even more expensive because we have to pay for the new checks in index-pack. But that should only happen when the other side is either buggy or malicious. Cloning linux-2.6 over file:// before after real 3m25.693s 2m53.050s user 5m2.037s 4m42.396s sys 0m13.750s 0m16.574s A more realistic test with ssh:// over wireless before after real 11m26.629s 10m4.213s user 5m43.196s 5m19.444s sys 0m35.812s 0m37.630s This shortcut is not applied to shallow clones, partly because shallow clones should have no more objects than a usual fetch and the cost of rev-list is acceptable, partly to avoid dealing with corner cases when grafting is involved. This shortcut does not apply to unpack-objects code path either because the number of objects must be small in order to trigger that code path. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-05-26 03:16:17 +02:00
if (transport->smart_options && !deepen)
transport->smart_options->check_self_contained_and_connected = 1;
refs = transport_get_remote_refs(transport);
if (refs) {
mapped_refs = wanted_peer_refs(refs, refspec);
/*
* transport_get_remote_refs() may return refs with null sha-1
* in mapped_refs (see struct transport->get_refs_list
* comment). In that case we need fetch it early because
* remote_head code below relies on it.
*
* for normal clones, transport_get_remote_refs() should
* return reliable ref set, we can delay cloning until after
* remote HEAD check.
*/
for (ref = refs; ref; ref = ref->next)
if (is_null_oid(&ref->old_oid)) {
complete_refs_before_fetch = 0;
break;
}
clone: fix up delay cloning conditions 6f48d39 (clone: delay cloning until after remote HEAD checking - 2012-01-16) allows us to perform some checks on remote refs before the actual cloning happens. But not all transport types support this. Remote helper with "import" capability will not return complete ref information until fetch is performed and therefore the clone cannot be delayed. foreign_vcs field in struct remote was used to detect this kind of transport and save the result. This is a mistake because foreign_vcs is designed to override url-based transport detection. As a result, if the same "struct transport *" object is used on many different urls and one of them attached remote transport, the following urls will be mistakenly attached to the same transport. This fault is worked around by dad0b3d (push: do not let configured foreign-vcs permanently clobbered - 2012-01-23) To fix this, detect incomplete refs from transport_get_remote_refs() by SHA-1. Incomplete ones must have null SHA-1 (*). Then revert changes related to foreign_cvs field in 6f48d39 and dad0b3d. A good thing from this change is that cloning smart http transport can also be delayed. Earlier it falls into the same category "remote transport, no delay". (*) Theoretically if one of the remote refs happens to have null SHA-1, it will trigger false alarm and the clone will not be delayed. But that chance may be too small for us to pay attention to. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-24 12:10:38 +01:00
if (!is_local && !complete_refs_before_fetch)
transport_fetch_refs(transport, mapped_refs);
remote_head = find_ref_by_name(refs, "HEAD");
remote_head_points_at =
guess_remote_head(remote_head, mapped_refs, 0);
if (option_branch) {
our_head_points_at =
find_remote_branch(mapped_refs, option_branch);
if (!our_head_points_at)
die(_("Remote branch %s not found in upstream %s"),
option_branch, option_origin);
}
else
our_head_points_at = remote_head_points_at;
}
else {
if (option_branch)
die(_("Remote branch %s not found in upstream %s"),
option_branch, option_origin);
warning(_("You appear to have cloned an empty repository."));
mapped_refs = NULL;
our_head_points_at = NULL;
remote_head_points_at = NULL;
remote_head = NULL;
option_no_checkout = 1;
if (!option_bare)
install_branch_config(0, "master", option_origin,
"refs/heads/master");
}
write_refspec_config(src_ref_prefix, our_head_points_at,
remote_head_points_at, &branch_top);
if (is_local)
clone_local(path, git_dir);
clone: fix up delay cloning conditions 6f48d39 (clone: delay cloning until after remote HEAD checking - 2012-01-16) allows us to perform some checks on remote refs before the actual cloning happens. But not all transport types support this. Remote helper with "import" capability will not return complete ref information until fetch is performed and therefore the clone cannot be delayed. foreign_vcs field in struct remote was used to detect this kind of transport and save the result. This is a mistake because foreign_vcs is designed to override url-based transport detection. As a result, if the same "struct transport *" object is used on many different urls and one of them attached remote transport, the following urls will be mistakenly attached to the same transport. This fault is worked around by dad0b3d (push: do not let configured foreign-vcs permanently clobbered - 2012-01-23) To fix this, detect incomplete refs from transport_get_remote_refs() by SHA-1. Incomplete ones must have null SHA-1 (*). Then revert changes related to foreign_cvs field in 6f48d39 and dad0b3d. A good thing from this change is that cloning smart http transport can also be delayed. Earlier it falls into the same category "remote transport, no delay". (*) Theoretically if one of the remote refs happens to have null SHA-1, it will trigger false alarm and the clone will not be delayed. But that chance may be too small for us to pay attention to. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-01-24 12:10:38 +01:00
else if (refs && complete_refs_before_fetch)
transport_fetch_refs(transport, mapped_refs);
update_remote_refs(refs, mapped_refs, remote_head_points_at,
branch_top.buf, reflog_msg.buf, transport, !is_local);
update_head(our_head_points_at, remote_head, reflog_msg.buf);
clone: pass --progress decision to recursive submodules When cloning with "--recursive", we'd generally expect submodules to show progress reports if the main clone did, too. In older versions of git, this mostly worked out of the box. Since we show progress by default when stderr is a tty, and since the child clones inherit the parent stderr, then both processes would come to the same decision by default. If the parent clone was asked for "--quiet", we passed down "--quiet" to the child. However, if stderr was not a tty and the user specified "--progress", we did not propagate this to the child. That's a minor bug, but things got much worse when we switched recently to submodule--helper's update_clone command. With that change, the stderr of the child clones are always connected to a pipe, and we never output progress at all. This patch teaches git-submodule and git-submodule--helper how to pass down an explicit "--progress" flag when cloning. The clone command then decides to propagate that flag based on the cloning decision made earlier (which takes into account isatty(2) of the parent process, existing --progress or --quiet flags, etc). Since the child processes always run without a tty on stderr, we don't have to worry about passing an explicit "--no-progress"; it's the default for them. This fixes the recent loss of progress during recursive clones. And as a bonus, it makes: git clone --recursive --progress ... 2>&1 | cat work by triggering progress explicitly in the children. Signed-off-by: Jeff King <peff@peff.net> Acked-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-22 07:24:46 +02:00
/*
* We want to show progress for recursive submodule clones iff
* we did so for the main clone. But only the transport knows
* the final decision for this flag, so we need to rescue the value
* before we free the transport.
*/
submodule_progress = transport->progress;
transport_unlock_pack(transport);
transport_disconnect(transport);
if (option_dissociate) {
close_all_packs();
dissociate_from_references();
}
junk_mode = JUNK_LEAVE_REPO;
clone: pass --progress decision to recursive submodules When cloning with "--recursive", we'd generally expect submodules to show progress reports if the main clone did, too. In older versions of git, this mostly worked out of the box. Since we show progress by default when stderr is a tty, and since the child clones inherit the parent stderr, then both processes would come to the same decision by default. If the parent clone was asked for "--quiet", we passed down "--quiet" to the child. However, if stderr was not a tty and the user specified "--progress", we did not propagate this to the child. That's a minor bug, but things got much worse when we switched recently to submodule--helper's update_clone command. With that change, the stderr of the child clones are always connected to a pipe, and we never output progress at all. This patch teaches git-submodule and git-submodule--helper how to pass down an explicit "--progress" flag when cloning. The clone command then decides to propagate that flag based on the cloning decision made earlier (which takes into account isatty(2) of the parent process, existing --progress or --quiet flags, etc). Since the child processes always run without a tty on stderr, we don't have to worry about passing an explicit "--no-progress"; it's the default for them. This fixes the recent loss of progress during recursive clones. And as a bonus, it makes: git clone --recursive --progress ... 2>&1 | cat work by triggering progress explicitly in the children. Signed-off-by: Jeff King <peff@peff.net> Acked-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-09-22 07:24:46 +02:00
err = checkout(submodule_progress);
strbuf_release(&reflog_msg);
strbuf_release(&branch_top);
strbuf_release(&key);
strbuf_release(&value);
junk_mode = JUNK_LEAVE_ALL;
free(refspec);
return err;
}