1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-10 23:36:20 +02:00
git/builtin/fetch-pack.c

280 lines
6.6 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 08:51:05 +01:00
#include "builtin.h"
#include "alloc.h"
#include "hex.h"
#include "pkt-line.h"
#include "fetch-pack.h"
#include "remote.h"
#include "connect.h"
#include "oid-array.h"
#include "protocol.h"
static const char fetch_pack_usage[] =
"git fetch-pack [--all] [--stdin] [--quiet | -q] [--keep | -k] [--thin] "
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 17:13:48 +02:00
"[--include-tag] [--upload-pack=<git-upload-pack>] [--depth=<n>] "
"[--no-progress] [--diag-url] [-v] [<host>:]<directory> [<refs>...]";
static void add_sought_entry(struct ref ***sought, int *nr, int *alloc,
const char *name)
{
struct ref *ref;
struct object_id oid;
const char *p;
if (!parse_oid_hex(name, &oid, &p)) {
if (*p == ' ') {
/* <oid> <ref>, find refname */
name = p + 1;
} else if (*p == '\0') {
; /* <oid>, leave oid as name */
} else {
/* <ref>, clear cruft from oid */
oidclr(&oid);
}
} else {
/* <ref>, clear cruft from get_oid_hex */
oidclr(&oid);
}
ref = alloc_ref(name);
oidcpy(&ref->old_oid, &oid);
(*nr)++;
ALLOC_GROW(*sought, *nr, *alloc);
(*sought)[*nr - 1] = ref;
}
int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
{
int i, ret;
struct ref *ref = NULL;
const char *dest = NULL;
struct ref **sought = NULL;
int nr_sought = 0, alloc_sought = 0;
int fd[2];
struct string_list pack_lockfiles = STRING_LIST_INIT_DUP;
struct string_list *pack_lockfiles_ptr = NULL;
struct child_process *conn;
struct fetch_pack_args args;
struct oid_array shallow = OID_ARRAY_INIT;
struct string_list deepen_not = STRING_LIST_INIT_DUP;
struct packet_reader reader;
enum protocol_version version;
sha1_file: support lazily fetching missing objects Teach sha1_file to fetch objects from the remote configured in extensions.partialclone whenever an object is requested but missing. The fetching of objects can be suppressed through a global variable. This is used by fsck and index-pack. However, by default, such fetching is not suppressed. This is meant as a temporary measure to ensure that all Git commands work in such a situation. Future patches will update some commands to either tolerate missing objects (without fetching them) or be more efficient in fetching them. In order to determine the code changes in sha1_file.c necessary, I investigated the following: (1) functions in sha1_file.c that take in a hash, without the user regarding how the object is stored (loose or packed) (2) functions in packfile.c (because I need to check callers that know about the loose/packed distinction and operate on both differently, and ensure that they can handle the concept of objects that are neither loose nor packed) (1) is handled by the modification to sha1_object_info_extended(). For (2), I looked at for_each_packed_object and others. For for_each_packed_object, the callers either already work or are fixed in this patch: - reachable - only to find recent objects - builtin/fsck - already knows about missing objects - builtin/cat-file - warning message added in this commit Callers of the other functions do not need to be changed: - parse_pack_index - http - indirectly from http_get_info_packs - find_pack_entry_one - this searches a single pack that is provided as an argument; the caller already knows (through other means) that the sought object is in a specific pack - find_sha1_pack - fast-import - appears to be an optimization to not store a file if it is already in a pack - http-walker - to search through a struct alt_base - http-push - to search through remote packs - has_sha1_pack - builtin/fsck - already knows about promisor objects - builtin/count-objects - informational purposes only (check if loose object is also packed) - builtin/prune-packed - check if object to be pruned is packed (if not, don't prune it) - revision - used to exclude packed objects if requested by user - diff - just for optimization Signed-off-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-12-08 16:27:14 +01:00
fetch_if_missing = 0;
packet_trace_identity("fetch-pack");
memset(&args, 0, sizeof(args));
list-objects-filter: add and use initializers In 7e2619d8ff (list_objects_filter_options: plug leak of filter_spec strings, 2022-09-08), we noted that the filter_spec string_list was inconsistent in how it handled memory ownership of strings stored in the list. The fix there was a bit of a band-aid to set the "strdup_strings" variable right before adding anything. That works OK, and it lets the users of the API continue to zero-initialize the struct. But it makes the code a bit hard to follow and accident-prone, as any other spots appending the filter_spec need to think about whether to set the strdup_strings value, too (there's one such spot in partial_clone_get_default_filter_spec(), which is probably a possible memory leak). So let's do that full cleanup now. We'll introduce a LIST_OBJECTS_FILTER_INIT macro and matching function, and use them as appropriate (though it is for the "_options" struct, this matches the corresponding list_objects_filter_release() function). This is harder than it seems! Many other structs, like git_transport_data, embed the filter struct. So they need to initialize it themselves even if the rest of the enclosing struct is OK with zero-initialization. I found all of the relevant spots by grepping manually for declarations of list_objects_filter_options. And then doing so recursively for structs which embed it, and ones which embed those, and so on. I'm pretty sure I got everything, but there's no change that would alert the compiler if any topics in flight added new declarations. To catch this case, we now double-check in the parsing function that things were initialized as expected and BUG() if appropriate. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2022-09-11 07:03:07 +02:00
list_objects_filter_init(&args.filter_options);
args.uploadpack = "git-upload-pack";
for (i = 1; i < argc && *argv[i] == '-'; i++) {
const char *arg = argv[i];
if (skip_prefix(arg, "--upload-pack=", &arg)) {
args.uploadpack = arg;
continue;
}
if (skip_prefix(arg, "--exec=", &arg)) {
args.uploadpack = arg;
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("--diag-url", arg)) {
args.diag_url = 1;
continue;
}
if (!strcmp("-v", arg)) {
args.verbose = 1;
continue;
}
if (skip_prefix(arg, "--depth=", &arg)) {
args.depth = strtol(arg, NULL, 0);
continue;
}
if (skip_prefix(arg, "--shallow-since=", &arg)) {
args.deepen_since = xstrdup(arg);
continue;
}
if (skip_prefix(arg, "--shallow-exclude=", &arg)) {
string_list_append(&deepen_not, arg);
continue;
}
fetch, upload-pack: --deepen=N extends shallow boundary by N commits In git-fetch, --depth argument is always relative with the latest remote refs. This makes it a bit difficult to cover this use case, where the user wants to make the shallow history, say 3 levels deeper. It would work if remote refs have not moved yet, but nobody can guarantee that, especially when that use case is performed a couple months after the last clone or "git fetch --depth". Also, modifying shallow boundary using --depth does not work well with clones created by --since or --not. This patch fixes that. A new argument --deepen=<N> will add <N> more (*) parent commits to the current history regardless of where remote refs are. Have/Want negotiation is still respected. So if remote refs move, the server will send two chunks: one between "have" and "want" and another to extend shallow history. In theory, the client could send no "want"s in order to get the second chunk only. But the protocol does not allow that. Either you send no want lines, which means ls-remote; or you have to send at least one want line that carries deep-relative to the server.. The main work was done by Dongcan Jiang. I fixed it up here and there. And of course all the bugs belong to me. (*) We could even support --deepen=<N> where <N> is negative. In that case we can cut some history from the shallow clone. This operation (and --depth=<shorter depth>) does not require interaction with remote side (and more complicated to implement as a result). Helped-by: Duy Nguyen <pclouds@gmail.com> Helped-by: Eric Sunshine <sunshine@sunshineco.com> Helped-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Dongcan Jiang <dongcan.jiang@gmail.com> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-12 12:54:09 +02:00
if (!strcmp(arg, "--deepen-relative")) {
args.deepen_relative = 1;
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_lockfiles_ptr = &pack_lockfiles;
continue;
}
if (!strcmp("--check-self-contained-and-connected", arg)) {
args.check_self_contained_and_connected = 1;
continue;
}
if (!strcmp("--cloning", arg)) {
args.cloning = 1;
continue;
}
if (!strcmp("--update-shallow", arg)) {
args.update_shallow = 1;
continue;
}
if (!strcmp("--from-promisor", arg)) {
args.from_promisor = 1;
continue;
}
if (!strcmp("--refetch", arg)) {
args.refetch = 1;
continue;
}
if (skip_prefix(arg, ("--filter="), &arg)) {
parse_list_objects_filter(&args.filter_options, arg);
continue;
}
if (!strcmp(arg, ("--no-filter"))) {
list_objects_filter_set_no_filter(&args.filter_options);
continue;
}
usage(fetch_pack_usage);
}
if (deepen_not.nr)
args.deepen_not = &deepen_not;
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++)
add_sought_entry(&sought, &nr_sought, &alloc_sought, 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 17:13:48 +02:00
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
*/
for (;;) {
pkt-line: provide a LARGE_PACKET_MAX static buffer Most of the callers of packet_read_line just read into a static 1000-byte buffer (callers which handle arbitrary binary data already use LARGE_PACKET_MAX). This works fine in practice, because: 1. The only variable-sized data in these lines is a ref name, and refs tend to be a lot shorter than 1000 characters. 2. When sending ref lines, git-core always limits itself to 1000 byte packets. However, the only limit given in the protocol specification in Documentation/technical/protocol-common.txt is LARGE_PACKET_MAX; the 1000 byte limit is mentioned only in pack-protocol.txt, and then only describing what we write, not as a specific limit for readers. This patch lets us bump the 1000-byte limit to LARGE_PACKET_MAX. Even though git-core will never write a packet where this makes a difference, there are two good reasons to do this: 1. Other git implementations may have followed protocol-common.txt and used a larger maximum size. We don't bump into it in practice because it would involve very long ref names. 2. We may want to increase the 1000-byte limit one day. Since packets are transferred before any capabilities, it's difficult to do this in a backwards-compatible way. But if we bump the size of buffer the readers can handle, eventually older versions of git will be obsolete enough that we can justify bumping the writers, as well. We don't have plans to do this anytime soon, but there is no reason not to start the clock ticking now. Just bumping all of the reading bufs to LARGE_PACKET_MAX would waste memory. Instead, since most readers just read into a temporary buffer anyway, let's provide a single static buffer that all callers can use. We can further wrap this detail away by having the packet_read_line wrapper just use the buffer transparently and return a pointer to the static storage. That covers most of the cases, and the remaining ones already read into their own LARGE_PACKET_MAX buffers. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-02-20 21:02:57 +01:00
char *line = packet_read_line(0, NULL);
if (!line)
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 17:13:48 +02:00
break;
add_sought_entry(&sought, &nr_sought, &alloc_sought, line);
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 17:13:48 +02:00
}
}
else {
/* read from stdin one ref per line, until EOF */
struct strbuf line = STRBUF_INIT;
while (strbuf_getline_lf(&line, stdin) != EOF)
add_sought_entry(&sought, &nr_sought, &alloc_sought, line.buf);
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 17:13:48 +02:00
strbuf_release(&line);
}
}
if (args.stateless_rpc) {
conn = NULL;
fd[0] = 0;
fd[1] = 1;
} else {
int flags = args.verbose ? CONNECT_VERBOSE : 0;
if (args.diag_url)
flags |= CONNECT_DIAG_URL;
conn = git_connect(fd, dest, args.uploadpack,
flags);
if (!conn)
return args.diag_url ? 0 : 1;
}
packet_reader_init(&reader, fd[0], NULL, 0,
PACKET_READ_CHOMP_NEWLINE |
PACKET_READ_GENTLE_ON_EOF |
PACKET_READ_DIE_ON_ERR_PACKET);
version = discover_version(&reader);
switch (version) {
case protocol_v2:
get_remote_refs(fd[1], &reader, &ref, 0, NULL, NULL,
args.stateless_rpc);
break;
case protocol_v1:
case protocol_v0:
get_remote_heads(&reader, &ref, 0, NULL, &shallow);
break;
case protocol_unknown_version:
BUG("unknown protocol version");
}
ref = fetch_pack(&args, fd, ref, sought, nr_sought,
&shallow, pack_lockfiles_ptr, version);
if (pack_lockfiles.nr) {
int i;
printf("lock %s\n", pack_lockfiles.items[0].string);
fflush(stdout);
for (i = 1; i < pack_lockfiles.nr; i++)
warning(_("Lockfile created but not reported: %s"),
pack_lockfiles.items[i].string);
}
if (args.check_self_contained_and_connected &&
args.self_contained_and_connected) {
printf("connectivity-ok\n");
fflush(stdout);
}
close(fd[0]);
close(fd[1]);
if (finish_connect(conn))
return 1;
ret = !ref;
/*
* 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.
*/
ret |= report_unmatched_refs(sought, nr_sought);
while (ref) {
printf("%s %s\n",
oid_to_hex(&ref->old_oid), ref->name);
ref = ref->next;
}
return ret;
}