clone: add --bundle-uri option

Cloning a remote repository is one of the most expensive operations in
Git. The server can spend a lot of CPU time generating a pack-file for
the client's request. The amount of data can clog the network for a long
time, and the Git protocol is not resumable. For users with poor network
connections or are located far away from the origin server, this can be
especially painful.

Add a new '--bundle-uri' option to 'git clone' to bootstrap a clone from
a bundle. If the user is aware of a bundle server, then they can tell
Git to bootstrap the new repository with these bundles before fetching
the remaining objects from the origin server.

Reviewed-by: Josh Steadmon <[email protected]>
Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: derrickstolee

Documentation/git-clone.txt

@@ -323,6 +323,12 @@ or `--mirror` is given)
 	for `host.xz:foo/.git`).  Cloning into an existing directory
 	is only allowed if the directory is empty.
 
+--bundle-uri=<uri>::
+	Before fetching from the remote, fetch a bundle from the given
+	`<uri>` and unbundle the data into the local repository. The refs
+	in the bundle will be stored under the hidden `refs/bundle/*`
+	namespace.
+
 :git-clone: 1
 include::urls.txt[]
 

builtin/clone.c

@@ -34,6 +34,7 @@
 #include "list-objects-filter-options.h"
 #include "hook.h"
 #include "bundle.h"
+#include "bundle-uri.h"
 
 /*
  * Overall FIXMEs:
@@ -77,6 +78,7 @@ static int option_filter_submodules = -1;    /* unspecified */
 static int config_filter_submodules = -1;    /* unspecified */
 static struct string_list server_options = STRING_LIST_INIT_NODUP;
 static int option_remote_submodules;
+static const char *bundle_uri;
 
 static int recurse_submodules_cb(const struct option *opt,
 				 const char *arg, int unset)
@@ -160,6 +162,8 @@ static struct option builtin_clone_options[] = {
 		    N_("any cloned submodules will use their remote-tracking branch")),
 	OPT_BOOL(0, "sparse", &option_sparse_checkout,
 		    N_("initialize sparse-checkout file to include only files at root")),
+	OPT_STRING(0, "bundle-uri", &bundle_uri,
+		   N_("uri"), N_("a URI for downloading bundles before fetching from origin remote")),
 	OPT_END()
 };
 
@@ -1232,6 +1236,17 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	if (transport->smart_options && !deepen && !filter_options.choice)
 		transport->smart_options->check_self_contained_and_connected = 1;
 
+	/*
+	 * Before fetching from the remote, download and install bundle
+	 * data from the --bundle-uri option.
+	 */
+	if (bundle_uri) {
+		/* At this point, we need the_repository to match the cloned repo. */
+		repo_init(the_repository, git_dir, work_tree);
+		if (fetch_bundle_uri(the_repository, bundle_uri))
+			warning(_("failed to fetch objects from bundle URI '%s'"),
+				bundle_uri);
+	}
 
 	strvec_push(&transport_ls_refs_options.ref_prefixes, "HEAD");
 	refspec_ref_prefixes(&remote->fetch,

t/t5558-clone-bundle-uri.sh

@@ -0,0 +1,36 @@
+#!/bin/sh
+
+test_description='test fetching bundles with --bundle-uri'
+
+. ./test-lib.sh
+
+test_expect_success 'fail to clone from non-existent file' '
+	test_when_finished rm -rf test &&
+	git clone --bundle-uri="$(pwd)/does-not-exist" . test 2>err &&
+	grep "failed to download bundle from URI" err
+'
+
+test_expect_success 'fail to clone from non-bundle file' '
+	test_when_finished rm -rf test &&
+	echo bogus >bogus &&
+	git clone --bundle-uri="$(pwd)/bogus" . test 2>err &&
+	grep "is not a bundle" err
+'
+
+test_expect_success 'create bundle' '
+	git init clone-from &&
+	git -C clone-from checkout -b topic &&
+	test_commit -C clone-from A &&
+	test_commit -C clone-from B &&
+	git -C clone-from bundle create B.bundle topic
+'
+
+test_expect_success 'clone with path bundle' '
+	git clone --bundle-uri="clone-from/B.bundle" \
+		clone-from clone-path &&
+	git -C clone-path rev-parse refs/bundles/topic >actual &&
+	git -C clone-from rev-parse topic >expect &&
+	test_cmp expect actual
+'
+
+test_done