git/builtin/fetch-pack.c

1135 lines
27 KiB
C
Raw Normal View History

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 15:51:05 +08:00
#include "builtin.h"
#include "refs.h"
#include "pkt-line.h"
#include "commit.h"
#include "tag.h"
#include "exec_cmd.h"
#include "pack.h"
#include "sideband.h"
#include "fetch-pack.h"
#include "remote.h"
#include "run-command.h"
#include "transport.h"
#include "version.h"
static int transfer_unpack_limit = -1;
static int fetch_unpack_limit = -1;
static int unpack_limit = 100;
static int prefer_ofs_delta = 1;
static int no_done;
static int fetch_fsck_objects = -1;
static int transfer_fsck_objects = -1;
static int agent_supported;
static struct fetch_pack_args args = {
/* .uploadpack = */ "git-upload-pack",
};
static const char fetch_pack_usage[] =
fetch-pack: new --stdin option to read refs from stdin If a remote repo has too many tags (or branches), cloning it over the smart HTTP transport can fail because remote-curl.c puts all the refs from the remote repo on the fetch-pack command line. This can make the command line longer than the global OS command line limit, causing fetch-pack to fail. This is especially a problem on Windows where the command line limit is orders of magnitude shorter than Linux. There are already real repos out there that msysGit cannot clone over smart HTTP due to this problem. Here is an easy way to trigger this problem: git init too-many-refs cd too-many-refs echo bla > bla.txt git add . git commit -m test sha=$(git rev-parse HEAD) tag=$(perl -e 'print "bla" x 30') for i in `seq 50000`; do echo $sha refs/tags/$tag-$i >> .git/packed-refs done Then share this repo over the smart HTTP protocol and try cloning it: $ git clone http://localhost/.../too-many-refs/.git Cloning into 'too-many-refs'... fatal: cannot exec 'fetch-pack': Argument list too long 50k tags is obviously an absurd number, but it is required to demonstrate the problem on Linux because it has a much more generous command line limit. On Windows the clone fails with as little as 500 tags in the above loop, which is getting uncomfortably close to the number of tags you might see in real long lived repos. This is not just theoretical, msysGit is already failing to clone our company repo due to this. It's a large repo converted from CVS, nearly 10 years of history. Four possible solutions were discussed on the Git mailing list (in no particular order): 1) Call fetch-pack multiple times with smaller batches of refs. This was dismissed as inefficient and inelegant. 2) Add option --refs-fd=$n to pass a an fd from where to read the refs. This was rejected because inheriting descriptors other than stdin/stdout/stderr through exec() is apparently problematic on Windows, plus it would require changes to the run-command API to open extra pipes. 3) Add option --refs-from=$tmpfile to pass the refs using a temp file. This was not favored because of the temp file requirement. 4) Add option --stdin to pass the refs on stdin, one per line. In the end this option was chosen as the most efficient and most desirable from scripting perspective. There was however a small complication when using stdin to pass refs to fetch-pack. The --stateless-rpc option to fetch-pack also uses stdin for communication with the remote server. If we are going to sneak refs on stdin line by line, it would have to be done very carefully in the presence of --stateless-rpc, because when reading refs line by line we might read ahead too much data into our buffer and eat some of the remote protocol data which is also coming on stdin. One way to solve this would be to refactor get_remote_heads() in fetch-pack.c to accept a residual buffer from our stdin line parsing above, but this function is used in several places so other callers would be burdened by this residual buffer interface even when most of them don't need it. In the end we settled on the following solution: If --stdin is specified without --stateless-rpc, fetch-pack would read the refs from stdin one per line, in a script friendly format. However if --stdin is specified together with --stateless-rpc, fetch-pack would read the refs from stdin in packetized format (pkt-line) with a flush packet terminating the list of refs. This way we can read the exact number of bytes that we need from stdin, and then get_remote_heads() can continue reading from the same fd without losing a single byte of remote protocol data. This way the --stdin option only loses generality and scriptability when used together with --stateless-rpc, which is not easily scriptable anyway because it also uses pkt-line when talking to the remote server. Signed-off-by: Ivan Todoroski <grnch@gmx.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-04-02 23:13:48 +08:00
"git fetch-pack [--all] [--stdin] [--quiet|-q] [--keep|-k] [--thin] "
"[--include-tag] [--upload-pack=<git-upload-pack>] [--depth=<n>] "
"[--no-progress] [-v] [<host>:]<directory> [<refs>...]";
#define COMPLETE (1U << 0)
#define COMMON (1U << 1)
#define COMMON_REF (1U << 2)
#define SEEN (1U << 3)
#define POPPED (1U << 4)
static int marked;
/*
* After sending this many "have"s if we do not get any new ACK , we
* give up traversing our history.
*/
#define MAX_IN_VAIN 256
static struct commit_list *rev_list;
static int non_common_revs, multi_ack, use_sideband;
static void rev_list_push(struct commit *commit, int mark)
{
if (!(commit->object.flags & mark)) {
commit->object.flags |= mark;
if (!(commit->object.parsed))
if (parse_commit(commit))
return;
commit_list_insert_by_date(commit, &rev_list);
if (!(commit->object.flags & COMMON))
non_common_revs++;
}
}
static int rev_list_insert_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
{
struct object *o = deref_tag(parse_object(sha1), refname, 0);
if (o && o->type == OBJ_COMMIT)
rev_list_push((struct commit *)o, SEEN);
return 0;
}
static int clear_marks(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
{
struct object *o = deref_tag(parse_object(sha1), refname, 0);
if (o && o->type == OBJ_COMMIT)
clear_commit_marks((struct commit *)o,
COMMON | COMMON_REF | SEEN | POPPED);
return 0;
}
/*
This function marks a rev and its ancestors as common.
In some cases, it is desirable to mark only the ancestors (for example
when only the server does not yet know that they are common).
*/
static void mark_common(struct commit *commit,
int ancestors_only, int dont_parse)
{
if (commit != NULL && !(commit->object.flags & COMMON)) {
struct object *o = (struct object *)commit;
if (!ancestors_only)
o->flags |= COMMON;
if (!(o->flags & SEEN))
rev_list_push(commit, SEEN);
else {
struct commit_list *parents;
if (!ancestors_only && !(o->flags & POPPED))
non_common_revs--;
if (!o->parsed && !dont_parse)
if (parse_commit(commit))
return;
for (parents = commit->parents;
parents;
parents = parents->next)
mark_common(parents->item, 0, dont_parse);
}
}
}
/*
Get the next rev to send, ignoring the common.
*/
static const unsigned char *get_rev(void)
{
struct commit *commit = NULL;
while (commit == NULL) {
unsigned int mark;
struct commit_list *parents;
if (rev_list == NULL || non_common_revs == 0)
return NULL;
commit = rev_list->item;
if (!commit->object.parsed)
parse_commit(commit);
parents = commit->parents;
commit->object.flags |= POPPED;
if (!(commit->object.flags & COMMON))
non_common_revs--;
if (commit->object.flags & COMMON) {
/* do not send "have", and ignore ancestors */
commit = NULL;
mark = COMMON | SEEN;
} else if (commit->object.flags & COMMON_REF)
/* send "have", and ignore ancestors */
mark = COMMON | SEEN;
else
/* send "have", also for its ancestors */
mark = SEEN;
while (parents) {
if (!(parents->item->object.flags & SEEN))
rev_list_push(parents->item, mark);
if (mark & COMMON)
mark_common(parents->item, 1, 0);
parents = parents->next;
}
rev_list = rev_list->next;
}
return commit->object.sha1;
}
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
enum ack_type {
NAK = 0,
ACK,
ACK_continue,
ACK_common,
ACK_ready
};
static void consume_shallow_list(int fd)
{
if (args.stateless_rpc && args.depth > 0) {
/* If we sent a depth we will get back "duplicate"
* shallow and unshallow commands every time there
* is a block of have lines exchanged.
*/
char line[1000];
while (packet_read_line(fd, line, sizeof(line))) {
if (!prefixcmp(line, "shallow "))
continue;
if (!prefixcmp(line, "unshallow "))
continue;
die("git fetch-pack: expected shallow list");
}
}
}
struct write_shallow_data {
struct strbuf *out;
int use_pack_protocol;
int count;
};
static int write_one_shallow(const struct commit_graft *graft, void *cb_data)
{
struct write_shallow_data *data = cb_data;
const char *hex = sha1_to_hex(graft->sha1);
data->count++;
if (data->use_pack_protocol)
packet_buf_write(data->out, "shallow %s", hex);
else {
strbuf_addstr(data->out, hex);
strbuf_addch(data->out, '\n');
}
return 0;
}
static int write_shallow_commits(struct strbuf *out, int use_pack_protocol)
{
struct write_shallow_data data;
data.out = out;
data.use_pack_protocol = use_pack_protocol;
data.count = 0;
for_each_commit_graft(write_one_shallow, &data);
return data.count;
}
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
static enum ack_type get_ack(int fd, unsigned char *result_sha1)
{
static char line[1000];
int len = packet_read_line(fd, line, sizeof(line));
if (!len)
die("git fetch-pack: expected ACK/NAK, got EOF");
if (line[len-1] == '\n')
line[--len] = 0;
if (!strcmp(line, "NAK"))
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
return NAK;
if (!prefixcmp(line, "ACK ")) {
if (!get_sha1_hex(line+4, result_sha1)) {
if (strstr(line+45, "continue"))
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
return ACK_continue;
if (strstr(line+45, "common"))
return ACK_common;
if (strstr(line+45, "ready"))
return ACK_ready;
return ACK;
}
}
die("git fetch_pack: expected ACK/NAK, got '%s'", line);
}
static void send_request(int fd, struct strbuf *buf)
{
if (args.stateless_rpc) {
send_sideband(fd, -1, buf->buf, buf->len, LARGE_PACKET_MAX);
packet_flush(fd);
} else
safe_write(fd, buf->buf, buf->len);
}
static void insert_one_alternate_ref(const struct ref *ref, void *unused)
{
rev_list_insert_ref(NULL, ref->old_sha1, 0, NULL);
}
#define INITIAL_FLUSH 16
#define PIPESAFE_FLUSH 32
#define LARGE_FLUSH 1024
static int next_flush(int count)
{
int flush_limit = args.stateless_rpc ? LARGE_FLUSH : PIPESAFE_FLUSH;
if (count < flush_limit)
count <<= 1;
else
count += flush_limit;
return count;
}
static int find_common(int fd[2], unsigned char *result_sha1,
struct ref *refs)
{
int fetching;
int count = 0, flushes = 0, flush_at = INITIAL_FLUSH, retval;
const unsigned char *sha1;
unsigned in_vain = 0;
int got_continue = 0;
int got_ready = 0;
struct strbuf req_buf = STRBUF_INIT;
size_t state_len = 0;
if (args.stateless_rpc && multi_ack == 1)
die("--stateless-rpc requires multi_ack_detailed");
if (marked)
for_each_ref(clear_marks, NULL);
marked = 1;
for_each_ref(rev_list_insert_ref, NULL);
for_each_alternate_ref(insert_one_alternate_ref, NULL);
fetching = 0;
for ( ; refs ; refs = refs->next) {
unsigned char *remote = refs->old_sha1;
const char *remote_hex;
struct object *o;
/*
* If that object is complete (i.e. it is an ancestor of a
* local ref), we tell them we have it but do not have to
* tell them about its ancestors, which they already know
* about.
*
* We use lookup_object here because we are only
* interested in the case we *know* the object is
* reachable and we have already scanned it.
*/
if (((o = lookup_object(remote)) != NULL) &&
(o->flags & COMPLETE)) {
continue;
}
remote_hex = sha1_to_hex(remote);
if (!fetching) {
struct strbuf c = STRBUF_INIT;
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
if (multi_ack == 2) strbuf_addstr(&c, " multi_ack_detailed");
if (multi_ack == 1) strbuf_addstr(&c, " multi_ack");
if (no_done) strbuf_addstr(&c, " no-done");
if (use_sideband == 2) strbuf_addstr(&c, " side-band-64k");
if (use_sideband == 1) strbuf_addstr(&c, " side-band");
if (args.use_thin_pack) strbuf_addstr(&c, " thin-pack");
if (args.no_progress) strbuf_addstr(&c, " no-progress");
if (args.include_tag) strbuf_addstr(&c, " include-tag");
if (prefer_ofs_delta) strbuf_addstr(&c, " ofs-delta");
if (agent_supported) strbuf_addf(&c, " agent=%s",
git_user_agent_sanitized());
packet_buf_write(&req_buf, "want %s%s\n", remote_hex, c.buf);
strbuf_release(&c);
} else
packet_buf_write(&req_buf, "want %s\n", remote_hex);
fetching++;
}
if (!fetching) {
strbuf_release(&req_buf);
packet_flush(fd[1]);
return 1;
}
if (is_repository_shallow())
write_shallow_commits(&req_buf, 1);
if (args.depth > 0)
packet_buf_write(&req_buf, "deepen %d", args.depth);
packet_buf_flush(&req_buf);
state_len = req_buf.len;
if (args.depth > 0) {
char line[1024];
unsigned char sha1[20];
send_request(fd[1], &req_buf);
while (packet_read_line(fd[0], line, sizeof(line))) {
if (!prefixcmp(line, "shallow ")) {
if (get_sha1_hex(line + 8, sha1))
die("invalid shallow line: %s", line);
register_shallow(sha1);
continue;
}
if (!prefixcmp(line, "unshallow ")) {
if (get_sha1_hex(line + 10, sha1))
die("invalid unshallow line: %s", line);
if (!lookup_object(sha1))
die("object not found: %s", line);
/* make sure that it is parsed as shallow */
if (!parse_object(sha1))
die("error in object: %s", line);
if (unregister_shallow(sha1))
die("no shallow found: %s", line);
continue;
}
die("expected shallow/unshallow, got %s", line);
}
} else if (!args.stateless_rpc)
send_request(fd[1], &req_buf);
if (!args.stateless_rpc) {
/* If we aren't using the stateless-rpc interface
* we don't need to retain the headers.
*/
strbuf_setlen(&req_buf, 0);
state_len = 0;
}
flushes = 0;
retval = -1;
while ((sha1 = get_rev())) {
packet_buf_write(&req_buf, "have %s\n", sha1_to_hex(sha1));
if (args.verbose)
fprintf(stderr, "have %s\n", sha1_to_hex(sha1));
in_vain++;
if (flush_at <= ++count) {
int ack;
packet_buf_flush(&req_buf);
send_request(fd[1], &req_buf);
strbuf_setlen(&req_buf, state_len);
flushes++;
flush_at = next_flush(count);
/*
* We keep one window "ahead" of the other side, and
* will wait for an ACK only on the next one
*/
if (!args.stateless_rpc && count == INITIAL_FLUSH)
continue;
consume_shallow_list(fd[0]);
do {
ack = get_ack(fd[0], result_sha1);
if (args.verbose && ack)
fprintf(stderr, "got ack %d %s\n", ack,
sha1_to_hex(result_sha1));
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
switch (ack) {
case ACK:
flushes = 0;
multi_ack = 0;
retval = 0;
goto done;
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
case ACK_common:
case ACK_ready:
case ACK_continue: {
struct commit *commit =
lookup_commit(result_sha1);
if (!commit)
die("invalid commit %s", sha1_to_hex(result_sha1));
if (args.stateless_rpc
&& ack == ACK_common
&& !(commit->object.flags & COMMON)) {
/* We need to replay the have for this object
* on the next RPC request so the peer knows
* it is in common with us.
*/
const char *hex = sha1_to_hex(result_sha1);
packet_buf_write(&req_buf, "have %s\n", hex);
state_len = req_buf.len;
}
mark_common(commit, 0, 1);
retval = 0;
in_vain = 0;
got_continue = 1;
if (ack == ACK_ready) {
fetch-pack: Finish negotation if remote replies "ACK %s ready" If multi_ack_detailed was selected in the protocol capabilities (both client and server are >= Git 1.6.6) the upload-pack side will send "ACK %s ready" when it knows how to safely cut the graph and produce a reasonable pack for the want list that was already sent on the connection. Upon receiving "ACK %s ready" there is no point in looking at the remaining commits inside of rev_list. Sending additional "have %s" lines to the remote will not construct a smaller pack. It is unlikely a commit older than the current cut point will have a better delta base than the cut point itself has. The original design of this code had fetch-pack empty rev_list by marking a commit and its transitive ancestors COMMON whenever the remote side said "ACK %s {continue,common}" and skipping over any already COMMON commits during get_rev(). This approach does not work when most of rev_list is actually COMMON_REF, commits that are pointed to by a reference on the remote, which exist locally, and which have not yet been sent to the remote as a "have %s" line. Most of the common references are tags in the ref/tags namespace, using points in the commit graph that are more than 1 commit apart. In git.git itself, this is currently 340 tags, 339 of which point to commits in the commit graph. fetch-pack pushes all of these into rev_list, but is unable to mark them COMMON and discard during a remote's "ACK %s {continue,common}" because it does not parse through the entire parent chain. Not parsing the entire parent chain is an optimization to avoid walking back to the roots of the repository. Assuming the client is only following the remote (and does not make its own local commits), the client needs 11 rounds to spin through the entire list of tags (32 commits per round, ceil(339/32) == 11). Unfortunately the server knows on the first "have %s" line that it can produce a good pack, and does not need to see the remaining 320 tags in the other 10 rounds. Over git:// and ssh:// this isn't as bad as it sounds, the client is only transmitting an extra 16,000 bytes that it doesn't need to send. Over smart HTTP, the client must do an additional 10 HTTP POST requests, each of which incurs round-trip latency, and must upload the entire state vector of all known common objects. On the final POST request, this is 16 KiB worth of data. Fix all of this by clearing rev_list as soon as the remote side says it can construct a pack. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-03-15 07:48:38 +08:00
rev_list = NULL;
got_ready = 1;
}
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
break;
}
}
} while (ack);
flushes--;
if (got_continue && MAX_IN_VAIN < in_vain) {
if (args.verbose)
fprintf(stderr, "giving up\n");
break; /* give up */
}
}
}
done:
if (!got_ready || !no_done) {
packet_buf_write(&req_buf, "done\n");
send_request(fd[1], &req_buf);
}
if (args.verbose)
fprintf(stderr, "done\n");
if (retval != 0) {
multi_ack = 0;
flushes++;
}
strbuf_release(&req_buf);
consume_shallow_list(fd[0]);
while (flushes || multi_ack) {
int ack = get_ack(fd[0], result_sha1);
if (ack) {
if (args.verbose)
fprintf(stderr, "got ack (%d) %s\n", ack,
sha1_to_hex(result_sha1));
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
if (ack == ACK)
return 0;
multi_ack = 1;
continue;
}
flushes--;
}
/* it is no error to fetch into a completely empty repo */
return count ? retval : 0;
}
static struct commit_list *complete;
static int mark_complete(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
{
struct object *o = parse_object(sha1);
while (o && o->type == OBJ_TAG) {
struct tag *t = (struct tag *) o;
if (!t->tagged)
break; /* broken repository */
o->flags |= COMPLETE;
o = parse_object(t->tagged->sha1);
}
if (o && o->type == OBJ_COMMIT) {
struct commit *commit = (struct commit *)o;
fetch: avoid repeated commits in mark_complete We add every local ref to a list so that we can mark them and all of their ancestors back to a certain cutoff point. However, if some refs point to the same commit, we will end up adding them to the list many times. Furthermore, since commit_lists are stored as linked lists, we must do an O(n) traversal of the list in order to find the right place to insert each commit. This makes building the list O(n^2) in the number of refs. For normal repositories, this isn't a big deal. We have a few hundreds refs at most, and most of them are unique. But consider an "alternates" repo that serves as an object database for many other similar repos. For reachability, it needs to keep a copy of the refs in each child repo. This means it may have a large number of refs, many of which point to the same commits. By noting commits we have already added to the list, we can shrink the size of "n" in such a repo to the number of unique commits, which is on the order of what a normal repo would contain (it's actually more than a normal repo, since child repos may have branches at different states, but in practice it tends to be much smaller than the list with duplicates). Here are the results on one particular giant repo (containing objects for all Rails forks on GitHub): $ git for-each-ref | wc -l 112514 [before] $ git fetch --no-tags ../remote.git 63.52user 0.12system 1:03.68elapsed 99%CPU (0avgtext+0avgdata 137648maxresident)k 1856inputs+48outputs (11major+19603minor)pagefaults 0swaps $ git fetch --no-tags ../remote.git 6.15user 0.08system 0:06.25elapsed 99%CPU (0avgtext+0avgdata 123856maxresident)k 0inputs+40outputs (0major+18872minor)pagefaults 0swaps Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-05-20 04:48:51 +08:00
if (!(commit->object.flags & COMPLETE)) {
commit->object.flags |= COMPLETE;
commit_list_insert_by_date(commit, &complete);
}
}
return 0;
}
static void mark_recent_complete_commits(unsigned long cutoff)
{
while (complete && cutoff <= complete->item->date) {
if (args.verbose)
fprintf(stderr, "Marking %s as complete\n",
sha1_to_hex(complete->item->object.sha1));
pop_most_recent_commit(&complete, COMPLETE);
}
}
static void filter_refs(struct ref **refs, struct string_list *sought)
{
struct ref **return_refs;
struct ref *newlist = NULL;
struct ref **newtail = &newlist;
struct ref *ref, *next;
struct ref *fastarray[32];
int sought_pos;
if (sought->nr && !args.fetch_all) {
if (ARRAY_SIZE(fastarray) < sought->nr)
return_refs = xcalloc(sought->nr, sizeof(struct ref *));
else {
return_refs = fastarray;
memset(return_refs, 0, sizeof(struct ref *) * sought->nr);
}
}
else
return_refs = NULL;
sought_pos = 0;
for (ref = *refs; ref; ref = next) {
next = ref->next;
if (!memcmp(ref->name, "refs/", 5) &&
check_refname_format(ref->name + 5, 0))
; /* trash */
else if (args.fetch_all &&
(!args.depth || prefixcmp(ref->name, "refs/tags/") )) {
*newtail = ref;
ref->next = NULL;
newtail = &ref->next;
continue;
}
else {
int cmp = -1;
while (sought_pos < sought->nr) {
cmp = strcmp(ref->name, sought->items[sought_pos].string);
if (cmp < 0) /* definitely do not have it */
break;
else if (cmp == 0) { /* definitely have it */
return_refs[sought_pos] = ref;
sought->items[sought_pos++].string[0] = '\0';
fetch-pack: match refs exactly When we are determining the list of refs to fetch via fetch-pack, we have two sets of refs to compare: those on the remote side, and a "match" list of things we want to fetch. We iterate through the remote refs alphabetically, seeing if each one is wanted by the "match" list. Since def88e9 (Commit first cut at "git-fetch-pack", 2005-07-04), we have used the "path_match" function to do a suffix match, where a remote ref is considered wanted if any of the "match" elements is a suffix of the remote refname. This enables callers of fetch-pack to specify unqualified refs and have them matched up with remote refs (e.g., ask for "A" and get remote's "refs/heads/A"). However, if you provide a fully qualified ref, then there are corner cases where we provide the wrong answer. For example, given a remote with two refs: refs/foo/refs/heads/master refs/heads/master asking for "refs/heads/master" will first match "refs/foo/refs/heads/master" by the suffix rule, and we will erroneously fetch it instead of refs/heads/master. As it turns out, all callers of fetch_pack do provide fully-qualified refs for the match list. There are two ways fetch_pack can get match lists: 1. Through the transport code (i.e., via git-fetch) 2. On the command-line of git-fetch-pack In the first case, we will always be providing the names of fully-qualified refs from "struct ref" objects. We will have pre-matched those ref objects already (since we have to handle more advanced matching, like wildcard refspecs), and are just providing a list of the refs whose objects we need. In the second case, users could in theory be providing non-qualified refs on the command-line. However, the fetch-pack documentation claims that refs should be fully qualified (and has always done so since it was written in 2005). Let's change this path_match call to simply check for string equality, matching what the callers of fetch_pack are expecting. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-12-13 08:48:08 +08:00
break;
}
else /* might have it; keep looking */
sought_pos++;
}
if (!cmp)
fetch-pack: match refs exactly When we are determining the list of refs to fetch via fetch-pack, we have two sets of refs to compare: those on the remote side, and a "match" list of things we want to fetch. We iterate through the remote refs alphabetically, seeing if each one is wanted by the "match" list. Since def88e9 (Commit first cut at "git-fetch-pack", 2005-07-04), we have used the "path_match" function to do a suffix match, where a remote ref is considered wanted if any of the "match" elements is a suffix of the remote refname. This enables callers of fetch-pack to specify unqualified refs and have them matched up with remote refs (e.g., ask for "A" and get remote's "refs/heads/A"). However, if you provide a fully qualified ref, then there are corner cases where we provide the wrong answer. For example, given a remote with two refs: refs/foo/refs/heads/master refs/heads/master asking for "refs/heads/master" will first match "refs/foo/refs/heads/master" by the suffix rule, and we will erroneously fetch it instead of refs/heads/master. As it turns out, all callers of fetch_pack do provide fully-qualified refs for the match list. There are two ways fetch_pack can get match lists: 1. Through the transport code (i.e., via git-fetch) 2. On the command-line of git-fetch-pack In the first case, we will always be providing the names of fully-qualified refs from "struct ref" objects. We will have pre-matched those ref objects already (since we have to handle more advanced matching, like wildcard refspecs), and are just providing a list of the refs whose objects we need. In the second case, users could in theory be providing non-qualified refs on the command-line. However, the fetch-pack documentation claims that refs should be fully qualified (and has always done so since it was written in 2005). Let's change this path_match call to simply check for string equality, matching what the callers of fetch_pack are expecting. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-12-13 08:48:08 +08:00
continue; /* we will link it later */
}
free(ref);
}
if (!args.fetch_all) {
int i;
for (i = 0; i < sought->nr; i++) {
ref = return_refs[i];
if (ref) {
*newtail = ref;
ref->next = NULL;
newtail = &ref->next;
}
}
if (return_refs != fastarray)
free(return_refs);
}
*refs = newlist;
}
static void mark_alternate_complete(const struct ref *ref, void *unused)
{
mark_complete(NULL, ref->old_sha1, 0, NULL);
}
static int everything_local(struct ref **refs, struct string_list *sought)
{
struct ref *ref;
int retval;
unsigned long cutoff = 0;
save_commit_buffer = 0;
for (ref = *refs; ref; ref = ref->next) {
struct object *o;
o = parse_object(ref->old_sha1);
if (!o)
continue;
/* We already have it -- which may mean that we were
* in sync with the other side at some time after
* that (it is OK if we guess wrong here).
*/
if (o->type == OBJ_COMMIT) {
struct commit *commit = (struct commit *)o;
if (!cutoff || cutoff < commit->date)
cutoff = commit->date;
}
}
if (!args.depth) {
for_each_ref(mark_complete, NULL);
for_each_alternate_ref(mark_alternate_complete, NULL);
if (cutoff)
mark_recent_complete_commits(cutoff);
}
/*
* Mark all complete remote refs as common refs.
* Don't mark them common yet; the server has to be told so first.
*/
for (ref = *refs; ref; ref = ref->next) {
struct object *o = deref_tag(lookup_object(ref->old_sha1),
NULL, 0);
if (!o || o->type != OBJ_COMMIT || !(o->flags & COMPLETE))
continue;
if (!(o->flags & SEEN)) {
rev_list_push((struct commit *)o, COMMON_REF | SEEN);
mark_common((struct commit *)o, 1, 1);
}
}
filter_refs(refs, sought);
for (retval = 1, ref = *refs; ref ; ref = ref->next) {
const unsigned char *remote = ref->old_sha1;
unsigned char local[20];
struct object *o;
o = lookup_object(remote);
if (!o || !(o->flags & COMPLETE)) {
retval = 0;
if (!args.verbose)
continue;
fprintf(stderr,
"want %s (%s)\n", sha1_to_hex(remote),
ref->name);
continue;
}
hashcpy(ref->new_sha1, local);
if (!args.verbose)
continue;
fprintf(stderr,
"already have %s (%s)\n", sha1_to_hex(remote),
ref->name);
}
return retval;
}
static int sideband_demux(int in, int out, void *data)
{
int *xd = data;
int ret = recv_sideband("fetch-pack", xd[0], out);
close(out);
return ret;
}
static int get_pack(int xd[2], char **pack_lockfile)
{
struct async demux;
const char *argv[20];
char keep_arg[256];
char hdr_arg[256];
const char **av;
int do_keep = args.keep_pack;
struct child_process cmd;
memset(&demux, 0, sizeof(demux));
if (use_sideband) {
/* xd[] is talking with upload-pack; subprocess reads from
* xd[0], spits out band#2 to stderr, and feeds us band#1
* through demux->out.
*/
demux.proc = sideband_demux;
demux.data = xd;
demux.out = -1;
if (start_async(&demux))
die("fetch-pack: unable to fork off sideband"
" demultiplexer");
}
else
demux.out = xd[0];
memset(&cmd, 0, sizeof(cmd));
cmd.argv = argv;
av = argv;
*hdr_arg = 0;
if (!args.keep_pack && unpack_limit) {
struct pack_header header;
if (read_pack_header(demux.out, &header))
die("protocol error: bad pack header");
snprintf(hdr_arg, sizeof(hdr_arg),
"--pack_header=%"PRIu32",%"PRIu32,
ntohl(header.hdr_version), ntohl(header.hdr_entries));
if (ntohl(header.hdr_entries) < unpack_limit)
do_keep = 0;
else
do_keep = 1;
}
if (do_keep) {
if (pack_lockfile)
cmd.out = -1;
*av++ = "index-pack";
*av++ = "--stdin";
if (!args.quiet && !args.no_progress)
*av++ = "-v";
if (args.use_thin_pack)
*av++ = "--fix-thin";
if (args.lock_pack || unpack_limit) {
int s = sprintf(keep_arg,
"--keep=fetch-pack %"PRIuMAX " on ", (uintmax_t) getpid());
if (gethostname(keep_arg + s, sizeof(keep_arg) - s))
strcpy(keep_arg + s, "localhost");
*av++ = keep_arg;
}
}
else {
*av++ = "unpack-objects";
if (args.quiet || args.no_progress)
*av++ = "-q";
}
if (*hdr_arg)
*av++ = hdr_arg;
if (fetch_fsck_objects >= 0
? fetch_fsck_objects
: transfer_fsck_objects >= 0
? transfer_fsck_objects
: 0)
*av++ = "--strict";
*av++ = NULL;
cmd.in = demux.out;
cmd.git_cmd = 1;
if (start_command(&cmd))
die("fetch-pack: unable to fork off %s", argv[0]);
if (do_keep && pack_lockfile) {
*pack_lockfile = index_pack_lockfile(cmd.out);
close(cmd.out);
}
if (finish_command(&cmd))
die("%s failed", argv[0]);
if (use_sideband && finish_async(&demux))
die("error in sideband demultiplexer");
return 0;
}
static struct ref *do_fetch_pack(int fd[2],
const struct ref *orig_ref,
struct string_list *sought,
char **pack_lockfile)
{
struct ref *ref = copy_ref_list(orig_ref);
unsigned char sha1[20];
const char *agent_feature;
int agent_len;
sort_ref_list(&ref, ref_compare_name);
if (is_repository_shallow() && !server_supports("shallow"))
die("Server does not support shallow clients");
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
if (server_supports("multi_ack_detailed")) {
if (args.verbose)
fprintf(stderr, "Server supports multi_ack_detailed\n");
multi_ack = 2;
if (server_supports("no-done")) {
if (args.verbose)
fprintf(stderr, "Server supports no-done\n");
if (args.stateless_rpc)
no_done = 1;
}
Add multi_ack_detailed capability to fetch-pack/upload-pack When multi_ack_detailed is enabled the ACK continue messages returned by the remote upload-pack are broken out to describe the different states within the peer. This permits the client to better understand the server's in-memory state. The fetch-pack/upload-pack protocol now looks like: NAK --------------------------------- Always sent in response to "done" if there was no common base selected from the "have" lines (or no have lines were sent). * no multi_ack or multi_ack_detailed: Sent when the client has sent a pkt-line flush ("0000") and the server has not yet found a common base object. * either multi_ack or multi_ack_detailed: Always sent in response to a pkt-line flush. ACK %s ----------------------------------- * no multi_ack or multi_ack_detailed: Sent in response to "have" when the object exists on the remote side and is therefore an object in common between the peers. The argument is the SHA-1 of the common object. * either multi_ack or multi_ack_detailed: Sent in response to "done" if there are common objects. The argument is the last SHA-1 determined to be common. ACK %s continue ----------------------------------- * multi_ack only: Sent in response to "have". The remote side wants the client to consider this object as common, and immediately stop transmitting additional "have" lines for objects that are reachable from it. The reason the client should stop is not given, but is one of the two cases below available under multi_ack_detailed. ACK %s common ----------------------------------- * multi_ack_detailed only: Sent in response to "have". Both sides have this object. Like with "ACK %s continue" above the client should stop sending have lines reachable for objects from the argument. ACK %s ready ----------------------------------- * multi_ack_detailed only: Sent in response to "have". The client should stop transmitting objects which are reachable from the argument, and send "done" soon to get the objects. If the remote side has the specified object, it should first send an "ACK %s common" message prior to sending "ACK %s ready". Clients may still submit additional "have" lines if there are more side branches for the client to explore that might be added to the common set and reduce the number of objects to transfer. Signed-off-by: Shawn O. Pearce <spearce@spearce.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2009-10-31 08:47:25 +08:00
}
else if (server_supports("multi_ack")) {
if (args.verbose)
fprintf(stderr, "Server supports multi_ack\n");
multi_ack = 1;
}
if (server_supports("side-band-64k")) {
if (args.verbose)
fprintf(stderr, "Server supports side-band-64k\n");
use_sideband = 2;
}
else if (server_supports("side-band")) {
if (args.verbose)
fprintf(stderr, "Server supports side-band\n");
use_sideband = 1;
}
if (!server_supports("thin-pack"))
args.use_thin_pack = 0;
if (!server_supports("no-progress"))
args.no_progress = 0;
if (!server_supports("include-tag"))
args.include_tag = 0;
if (server_supports("ofs-delta")) {
if (args.verbose)
fprintf(stderr, "Server supports ofs-delta\n");
} else
prefer_ofs_delta = 0;
if ((agent_feature = server_feature_value("agent", &agent_len))) {
agent_supported = 1;
if (args.verbose && agent_len)
fprintf(stderr, "Server version is %.*s\n",
agent_len, agent_feature);
}
if (everything_local(&ref, sought)) {
packet_flush(fd[1]);
goto all_done;
}
if (find_common(fd, sha1, ref) < 0)
if (!args.keep_pack)
/* When cloning, it is not unusual to have
* no common commit.
*/
warning("no common commits");
if (args.stateless_rpc)
packet_flush(fd[1]);
if (get_pack(fd, pack_lockfile))
die("git fetch-pack: fetch failed.");
all_done:
return ref;
}
static int remove_duplicates(struct string_list *sought)
{
int src, dst;
if (!sought->nr)
return 0;
for (src = dst = 1; src < sought->nr; src++)
if (strcmp(sought->items[src].string, sought->items[dst-1].string))
sought->items[dst++] = sought->items[src];
return dst;
}
static int fetch_pack_config(const char *var, const char *value, void *cb)
{
if (strcmp(var, "fetch.unpacklimit") == 0) {
fetch_unpack_limit = git_config_int(var, value);
return 0;
}
if (strcmp(var, "transfer.unpacklimit") == 0) {
transfer_unpack_limit = git_config_int(var, value);
return 0;
}
if (strcmp(var, "repack.usedeltabaseoffset") == 0) {
prefer_ofs_delta = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "fetch.fsckobjects")) {
fetch_fsck_objects = git_config_bool(var, value);
return 0;
}
if (!strcmp(var, "transfer.fsckobjects")) {
transfer_fsck_objects = git_config_bool(var, value);
return 0;
}
return git_default_config(var, value, cb);
}
static struct lock_file lock;
static void fetch_pack_setup(void)
{
static int did_setup;
if (did_setup)
return;
git_config(fetch_pack_config, NULL);
if (0 <= transfer_unpack_limit)
unpack_limit = transfer_unpack_limit;
else if (0 <= fetch_unpack_limit)
unpack_limit = fetch_unpack_limit;
did_setup = 1;
}
int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
{
int i, ret;
struct ref *ref = NULL;
const char *dest = NULL;
struct string_list sought = STRING_LIST_INIT_DUP;
int fd[2];
char *pack_lockfile = NULL;
char **pack_lockfile_ptr = NULL;
struct child_process *conn;
packet_trace_identity("fetch-pack");
for (i = 1; i < argc && *argv[i] == '-'; i++) {
const char *arg = argv[i];
if (!prefixcmp(arg, "--upload-pack=")) {
args.uploadpack = arg + 14;
continue;
}
if (!prefixcmp(arg, "--exec=")) {
args.uploadpack = arg + 7;
continue;
}
if (!strcmp("--quiet", arg) || !strcmp("-q", arg)) {
args.quiet = 1;
continue;
}
if (!strcmp("--keep", arg) || !strcmp("-k", arg)) {
args.lock_pack = args.keep_pack;
args.keep_pack = 1;
continue;
}
if (!strcmp("--thin", arg)) {
args.use_thin_pack = 1;
continue;
}
if (!strcmp("--include-tag", arg)) {
args.include_tag = 1;
continue;
}
if (!strcmp("--all", arg)) {
args.fetch_all = 1;
continue;
}
if (!strcmp("--stdin", arg)) {
args.stdin_refs = 1;
continue;
}
if (!strcmp("-v", arg)) {
args.verbose = 1;
continue;
}
if (!prefixcmp(arg, "--depth=")) {
args.depth = strtol(arg + 8, NULL, 0);
continue;
}
if (!strcmp("--no-progress", arg)) {
args.no_progress = 1;
continue;
}
if (!strcmp("--stateless-rpc", arg)) {
args.stateless_rpc = 1;
continue;
}
if (!strcmp("--lock-pack", arg)) {
args.lock_pack = 1;
pack_lockfile_ptr = &pack_lockfile;
continue;
}
usage(fetch_pack_usage);
}
if (i < argc)
dest = argv[i++];
else
usage(fetch_pack_usage);
/*
* Copy refs from cmdline to growable list, then append any
* refs from the standard input:
*/
for (; i < argc; i++)
string_list_append(&sought, xstrdup(argv[i]));
fetch-pack: new --stdin option to read refs from stdin If a remote repo has too many tags (or branches), cloning it over the smart HTTP transport can fail because remote-curl.c puts all the refs from the remote repo on the fetch-pack command line. This can make the command line longer than the global OS command line limit, causing fetch-pack to fail. This is especially a problem on Windows where the command line limit is orders of magnitude shorter than Linux. There are already real repos out there that msysGit cannot clone over smart HTTP due to this problem. Here is an easy way to trigger this problem: git init too-many-refs cd too-many-refs echo bla > bla.txt git add . git commit -m test sha=$(git rev-parse HEAD) tag=$(perl -e 'print "bla" x 30') for i in `seq 50000`; do echo $sha refs/tags/$tag-$i >> .git/packed-refs done Then share this repo over the smart HTTP protocol and try cloning it: $ git clone http://localhost/.../too-many-refs/.git Cloning into 'too-many-refs'... fatal: cannot exec 'fetch-pack': Argument list too long 50k tags is obviously an absurd number, but it is required to demonstrate the problem on Linux because it has a much more generous command line limit. On Windows the clone fails with as little as 500 tags in the above loop, which is getting uncomfortably close to the number of tags you might see in real long lived repos. This is not just theoretical, msysGit is already failing to clone our company repo due to this. It's a large repo converted from CVS, nearly 10 years of history. Four possible solutions were discussed on the Git mailing list (in no particular order): 1) Call fetch-pack multiple times with smaller batches of refs. This was dismissed as inefficient and inelegant. 2) Add option --refs-fd=$n to pass a an fd from where to read the refs. This was rejected because inheriting descriptors other than stdin/stdout/stderr through exec() is apparently problematic on Windows, plus it would require changes to the run-command API to open extra pipes. 3) Add option --refs-from=$tmpfile to pass the refs using a temp file. This was not favored because of the temp file requirement. 4) Add option --stdin to pass the refs on stdin, one per line. In the end this option was chosen as the most efficient and most desirable from scripting perspective. There was however a small complication when using stdin to pass refs to fetch-pack. The --stateless-rpc option to fetch-pack also uses stdin for communication with the remote server. If we are going to sneak refs on stdin line by line, it would have to be done very carefully in the presence of --stateless-rpc, because when reading refs line by line we might read ahead too much data into our buffer and eat some of the remote protocol data which is also coming on stdin. One way to solve this would be to refactor get_remote_heads() in fetch-pack.c to accept a residual buffer from our stdin line parsing above, but this function is used in several places so other callers would be burdened by this residual buffer interface even when most of them don't need it. In the end we settled on the following solution: If --stdin is specified without --stateless-rpc, fetch-pack would read the refs from stdin one per line, in a script friendly format. However if --stdin is specified together with --stateless-rpc, fetch-pack would read the refs from stdin in packetized format (pkt-line) with a flush packet terminating the list of refs. This way we can read the exact number of bytes that we need from stdin, and then get_remote_heads() can continue reading from the same fd without losing a single byte of remote protocol data. This way the --stdin option only loses generality and scriptability when used together with --stateless-rpc, which is not easily scriptable anyway because it also uses pkt-line when talking to the remote server. Signed-off-by: Ivan Todoroski <grnch@gmx.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-04-02 23:13:48 +08:00
if (args.stdin_refs) {
if (args.stateless_rpc) {
/* in stateless RPC mode we use pkt-line to read
* from stdin, until we get a flush packet
*/
static char line[1000];
for (;;) {
int n = packet_read_line(0, line, sizeof(line));
if (!n)
break;
if (line[n-1] == '\n')
n--;
string_list_append(&sought, xmemdupz(line, n));
fetch-pack: new --stdin option to read refs from stdin If a remote repo has too many tags (or branches), cloning it over the smart HTTP transport can fail because remote-curl.c puts all the refs from the remote repo on the fetch-pack command line. This can make the command line longer than the global OS command line limit, causing fetch-pack to fail. This is especially a problem on Windows where the command line limit is orders of magnitude shorter than Linux. There are already real repos out there that msysGit cannot clone over smart HTTP due to this problem. Here is an easy way to trigger this problem: git init too-many-refs cd too-many-refs echo bla > bla.txt git add . git commit -m test sha=$(git rev-parse HEAD) tag=$(perl -e 'print "bla" x 30') for i in `seq 50000`; do echo $sha refs/tags/$tag-$i >> .git/packed-refs done Then share this repo over the smart HTTP protocol and try cloning it: $ git clone http://localhost/.../too-many-refs/.git Cloning into 'too-many-refs'... fatal: cannot exec 'fetch-pack': Argument list too long 50k tags is obviously an absurd number, but it is required to demonstrate the problem on Linux because it has a much more generous command line limit. On Windows the clone fails with as little as 500 tags in the above loop, which is getting uncomfortably close to the number of tags you might see in real long lived repos. This is not just theoretical, msysGit is already failing to clone our company repo due to this. It's a large repo converted from CVS, nearly 10 years of history. Four possible solutions were discussed on the Git mailing list (in no particular order): 1) Call fetch-pack multiple times with smaller batches of refs. This was dismissed as inefficient and inelegant. 2) Add option --refs-fd=$n to pass a an fd from where to read the refs. This was rejected because inheriting descriptors other than stdin/stdout/stderr through exec() is apparently problematic on Windows, plus it would require changes to the run-command API to open extra pipes. 3) Add option --refs-from=$tmpfile to pass the refs using a temp file. This was not favored because of the temp file requirement. 4) Add option --stdin to pass the refs on stdin, one per line. In the end this option was chosen as the most efficient and most desirable from scripting perspective. There was however a small complication when using stdin to pass refs to fetch-pack. The --stateless-rpc option to fetch-pack also uses stdin for communication with the remote server. If we are going to sneak refs on stdin line by line, it would have to be done very carefully in the presence of --stateless-rpc, because when reading refs line by line we might read ahead too much data into our buffer and eat some of the remote protocol data which is also coming on stdin. One way to solve this would be to refactor get_remote_heads() in fetch-pack.c to accept a residual buffer from our stdin line parsing above, but this function is used in several places so other callers would be burdened by this residual buffer interface even when most of them don't need it. In the end we settled on the following solution: If --stdin is specified without --stateless-rpc, fetch-pack would read the refs from stdin one per line, in a script friendly format. However if --stdin is specified together with --stateless-rpc, fetch-pack would read the refs from stdin in packetized format (pkt-line) with a flush packet terminating the list of refs. This way we can read the exact number of bytes that we need from stdin, and then get_remote_heads() can continue reading from the same fd without losing a single byte of remote protocol data. This way the --stdin option only loses generality and scriptability when used together with --stateless-rpc, which is not easily scriptable anyway because it also uses pkt-line when talking to the remote server. Signed-off-by: Ivan Todoroski <grnch@gmx.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-04-02 23:13:48 +08:00
}
}
else {
/* read from stdin one ref per line, until EOF */
struct strbuf line = STRBUF_INIT;
while (strbuf_getline(&line, stdin, '\n') != EOF)
string_list_append(&sought, strbuf_detach(&line, NULL));
fetch-pack: new --stdin option to read refs from stdin If a remote repo has too many tags (or branches), cloning it over the smart HTTP transport can fail because remote-curl.c puts all the refs from the remote repo on the fetch-pack command line. This can make the command line longer than the global OS command line limit, causing fetch-pack to fail. This is especially a problem on Windows where the command line limit is orders of magnitude shorter than Linux. There are already real repos out there that msysGit cannot clone over smart HTTP due to this problem. Here is an easy way to trigger this problem: git init too-many-refs cd too-many-refs echo bla > bla.txt git add . git commit -m test sha=$(git rev-parse HEAD) tag=$(perl -e 'print "bla" x 30') for i in `seq 50000`; do echo $sha refs/tags/$tag-$i >> .git/packed-refs done Then share this repo over the smart HTTP protocol and try cloning it: $ git clone http://localhost/.../too-many-refs/.git Cloning into 'too-many-refs'... fatal: cannot exec 'fetch-pack': Argument list too long 50k tags is obviously an absurd number, but it is required to demonstrate the problem on Linux because it has a much more generous command line limit. On Windows the clone fails with as little as 500 tags in the above loop, which is getting uncomfortably close to the number of tags you might see in real long lived repos. This is not just theoretical, msysGit is already failing to clone our company repo due to this. It's a large repo converted from CVS, nearly 10 years of history. Four possible solutions were discussed on the Git mailing list (in no particular order): 1) Call fetch-pack multiple times with smaller batches of refs. This was dismissed as inefficient and inelegant. 2) Add option --refs-fd=$n to pass a an fd from where to read the refs. This was rejected because inheriting descriptors other than stdin/stdout/stderr through exec() is apparently problematic on Windows, plus it would require changes to the run-command API to open extra pipes. 3) Add option --refs-from=$tmpfile to pass the refs using a temp file. This was not favored because of the temp file requirement. 4) Add option --stdin to pass the refs on stdin, one per line. In the end this option was chosen as the most efficient and most desirable from scripting perspective. There was however a small complication when using stdin to pass refs to fetch-pack. The --stateless-rpc option to fetch-pack also uses stdin for communication with the remote server. If we are going to sneak refs on stdin line by line, it would have to be done very carefully in the presence of --stateless-rpc, because when reading refs line by line we might read ahead too much data into our buffer and eat some of the remote protocol data which is also coming on stdin. One way to solve this would be to refactor get_remote_heads() in fetch-pack.c to accept a residual buffer from our stdin line parsing above, but this function is used in several places so other callers would be burdened by this residual buffer interface even when most of them don't need it. In the end we settled on the following solution: If --stdin is specified without --stateless-rpc, fetch-pack would read the refs from stdin one per line, in a script friendly format. However if --stdin is specified together with --stateless-rpc, fetch-pack would read the refs from stdin in packetized format (pkt-line) with a flush packet terminating the list of refs. This way we can read the exact number of bytes that we need from stdin, and then get_remote_heads() can continue reading from the same fd without losing a single byte of remote protocol data. This way the --stdin option only loses generality and scriptability when used together with --stateless-rpc, which is not easily scriptable anyway because it also uses pkt-line when talking to the remote server. Signed-off-by: Ivan Todoroski <grnch@gmx.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2012-04-02 23:13:48 +08:00
strbuf_release(&line);
}
}
if (args.stateless_rpc) {
conn = NULL;
fd[0] = 0;
fd[1] = 1;
} else {
conn = git_connect(fd, dest, args.uploadpack,
args.verbose ? CONNECT_VERBOSE : 0);
}
get_remote_heads(fd[0], &ref, 0, NULL);
ref = fetch_pack(&args, fd, conn, ref, dest,
&sought, pack_lockfile_ptr);
if (pack_lockfile) {
printf("lock %s\n", pack_lockfile);
fflush(stdout);
}
close(fd[0]);
close(fd[1]);
if (finish_connect(conn))
ref = NULL;
ret = !ref;
if (!ret && sought.nr) {
/* If the heads to pull were given, we should have
* consumed all of them by matching the remote.
* Otherwise, 'git fetch remote no-such-ref' would
* silently succeed without issuing an error.
*/
for (i = 0; i < sought.nr; i++) {
char *s = sought.items[i].string;
if (s && s[0]) {
error("no such remote ref %s", s);
ret = 1;
}
}
}
while (ref) {
printf("%s %s\n",
sha1_to_hex(ref->old_sha1), ref->name);
ref = ref->next;
}
return ret;
}
struct ref *fetch_pack(struct fetch_pack_args *my_args,
int fd[], struct child_process *conn,
const struct ref *ref,
const char *dest,
struct string_list *sought,
char **pack_lockfile)
{
struct stat st;
struct ref *ref_cpy;
fetch_pack_setup();
if (&args != my_args)
memcpy(&args, my_args, sizeof(args));
if (args.depth > 0) {
if (stat(git_path("shallow"), &st))
st.st_mtime = 0;
}
if (sought->nr) {
sort_string_list(sought);
remove_duplicates(sought);
}
if (!ref) {
packet_flush(fd[1]);
die("no matching remote head");
}
ref_cpy = do_fetch_pack(fd, ref, sought, pack_lockfile);
if (args.depth > 0) {
struct cache_time mtime;
struct strbuf sb = STRBUF_INIT;
char *shallow = git_path("shallow");
int fd;
mtime.sec = st.st_mtime;
mtime.nsec = ST_MTIME_NSEC(st);
if (stat(shallow, &st)) {
if (mtime.sec)
die("shallow file was removed during fetch");
} else if (st.st_mtime != mtime.sec
#ifdef USE_NSEC
|| ST_MTIME_NSEC(st) != mtime.nsec
#endif
)
die("shallow file was changed during fetch");
fd = hold_lock_file_for_update(&lock, shallow,
LOCK_DIE_ON_ERROR);
if (!write_shallow_commits(&sb, 0)
|| write_in_full(fd, sb.buf, sb.len) != sb.len) {
unlink_or_warn(shallow);
rollback_lock_file(&lock);
} else {
commit_lock_file(&lock);
}
strbuf_release(&sb);
}
reprepare_packed_git();
return ref_cpy;
}