git@vger.kernel.org mailing list mirror (one of many)
 help / Atom feed
From: Jonathan Tan <jonathantanmy@google.com>
To: git@vger.kernel.org
Cc: Jonathan Tan <jonathantanmy@google.com>,
	gitster@pobox.com, git@jeffhostetler.com, peartben@gmail.com,
	christian.couder@gmail.com
Subject: [PATCH 15/18] clone: support excluding large blobs
Date: Fri, 29 Sep 2017 13:11:51 -0700
Message-ID: <9f0c6eb5aea49a5620de8e56fab2065805570f0e.1506714999.git.jonathantanmy@google.com> (raw)
In-Reply-To: <cover.1506714999.git.jonathantanmy@google.com>

Teach clone to support excluding large blobs through a blob-max-bytes
parameter.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 builtin/clone.c  | 23 +++++++++++++++++++++--
 t/t5601-clone.sh | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/builtin/clone.c b/builtin/clone.c
index dbddd98f8..4c2193dc4 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -60,6 +60,7 @@ static struct string_list option_optional_reference = STRING_LIST_INIT_NODUP;
 static int option_dissociate;
 static int max_jobs = -1;
 static struct string_list option_recurse_submodules = STRING_LIST_INIT_NODUP;
+static char *blob_max_bytes;
 
 static int recurse_submodules_cb(const struct option *opt,
 				 const char *arg, int unset)
@@ -135,6 +136,8 @@ static struct option builtin_clone_options[] = {
 			TRANSPORT_FAMILY_IPV4),
 	OPT_SET_INT('6', "ipv6", &family, N_("use IPv6 addresses only"),
 			TRANSPORT_FAMILY_IPV6),
+	OPT_STRING(0, "blob-max-bytes", &blob_max_bytes, N_("bytes"),
+		   N_("do not fetch blobs above this size")),
 	OPT_END()
 };
 
@@ -886,6 +889,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	struct refspec *refspec;
 	const char *fetch_pattern;
 
+	fetch_if_missing = 0;
+
 	packet_trace_identity("clone");
 	argc = parse_options(argc, argv, prefix, builtin_clone_options,
 			     builtin_clone_usage, 0);
@@ -1104,7 +1109,13 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		transport_set_option(transport, TRANS_OPT_UPLOADPACK,
 				     option_upload_pack);
 
-	if (transport->smart_options && !deepen)
+	if (blob_max_bytes) {
+		transport_set_option(transport, TRANS_OPT_BLOB_MAX_BYTES,
+				     blob_max_bytes);
+		transport_set_option(transport, TRANS_OPT_FROM_PROMISOR, "1");
+	}
+
+	if (transport->smart_options && !deepen && !blob_max_bytes)
 		transport->smart_options->check_self_contained_and_connected = 1;
 
 	refs = transport_get_remote_refs(transport);
@@ -1164,13 +1175,20 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	write_refspec_config(src_ref_prefix, our_head_points_at,
 			remote_head_points_at, &branch_top);
 
+	if (blob_max_bytes) {
+		git_config_set("core.repositoryformatversion", "1");
+		git_config_set("extensions.partialclone", "origin");
+		repository_format_partial_clone = "origin";
+	}
+
 	if (is_local)
 		clone_local(path, git_dir);
 	else if (refs && complete_refs_before_fetch)
 		transport_fetch_refs(transport, mapped_refs);
 
 	update_remote_refs(refs, mapped_refs, remote_head_points_at,
-			   branch_top.buf, reflog_msg.buf, transport, !is_local);
+			   branch_top.buf, reflog_msg.buf, transport,
+			   !is_local && !blob_max_bytes);
 
 	update_head(our_head_points_at, remote_head, reflog_msg.buf);
 
@@ -1191,6 +1209,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	}
 
 	junk_mode = JUNK_LEAVE_REPO;
+	fetch_if_missing = 1;
 	err = checkout(submodule_progress);
 
 	strbuf_release(&reflog_msg);
diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh
index 9c56f771b..951b1ffa8 100755
--- a/t/t5601-clone.sh
+++ b/t/t5601-clone.sh
@@ -571,4 +571,53 @@ test_expect_success 'GIT_TRACE_PACKFILE produces a usable pack' '
 	git -C replay.git index-pack -v --stdin <tmp.pack
 '
 
+partial_clone () {
+	SERVER="$1" &&
+	URL="$2" &&
+
+	rm -rf "$SERVER" client &&
+	test_create_repo "$SERVER" &&
+	test_commit -C "$SERVER" one &&
+	HASH1=$(git hash-object "$SERVER/one.t") &&
+	git -C "$SERVER" revert HEAD &&
+	test_commit -C "$SERVER" two &&
+	HASH2=$(git hash-object "$SERVER/two.t") &&
+	test_config -C "$SERVER" uploadpack.advertiseblobmaxbytes 1 &&
+	test_config -C "$SERVER" uploadpack.allowanysha1inwant 1 &&
+
+	git clone --blob-max-bytes=0 "$URL" client &&
+
+	git -C client fsck &&
+
+	# Ensure that unneeded blobs are not inadvertently fetched.
+	test_config -C client extensions.partialclone "not a remote" &&
+	test_must_fail git -C client cat-file -e "$HASH1" &&
+
+	# But this blob was fetched, because clone performs an initial checkout
+	git -C client cat-file -e "$HASH2"
+}
+
+test_expect_success 'partial clone' '
+	partial_clone server "file://$(pwd)/server"
+'
+
+test_expect_success 'partial clone: warn if server does not support blob-max-bytes' '
+	rm -rf server client &&
+	test_create_repo server &&
+	test_commit -C server one &&
+
+	git clone --blob-max-bytes=0 "file://$(pwd)/server" client 2> err &&
+
+	test_i18ngrep "blob-max-bytes not recognized by server" err
+'
+
+. "$TEST_DIRECTORY"/lib-httpd.sh
+start_httpd
+
+test_expect_success 'partial clone using HTTP' '
+	partial_clone "$HTTPD_DOCUMENT_ROOT_PATH/server" "$HTTPD_URL/smart/server"
+'
+
+stop_httpd
+
 test_done
-- 
2.14.2.822.g60be5d43e6-goog


  parent reply index

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-29 20:11 [PATCH 00/18] Partial clone (from clone to lazy fetch in 18 patches) Jonathan Tan
2017-09-29 20:11 ` [PATCH 01/18] fsck: introduce partialclone extension Jonathan Tan
2017-09-29 20:11 ` [PATCH 02/18] fsck: support refs pointing to promisor objects Jonathan Tan
2017-09-29 20:11 ` [PATCH 03/18] fsck: support referenced " Jonathan Tan
2017-09-29 20:11 ` [PATCH 04/18] fsck: support promisor objects as CLI argument Jonathan Tan
2017-09-29 20:11 ` [PATCH 05/18] index-pack: refactor writing of .keep files Jonathan Tan
2017-09-29 20:11 ` [PATCH 06/18] introduce fetch-object: fetch one promisor object Jonathan Tan
2017-09-29 20:11 ` [PATCH 07/18] sha1_file: support lazily fetching missing objects Jonathan Tan
2017-10-12 14:42   ` Christian Couder
2017-10-12 15:45     ` Christian Couder
2017-09-29 20:11 ` [PATCH 08/18] rev-list: support termination at promisor objects Jonathan Tan
2017-09-29 20:11 ` [PATCH 09/18] gc: do not repack promisor packfiles Jonathan Tan
2017-09-29 20:11 ` [PATCH 10/18] pack-objects: rename want_.* to ignore_.* Jonathan Tan
2017-09-29 20:11 ` [PATCH 11/18] pack-objects: support --blob-max-bytes Jonathan Tan
2017-09-29 20:11 ` [PATCH 12/18] fetch-pack: support excluding large blobs Jonathan Tan
2017-09-29 20:11 ` [PATCH 13/18] fetch: refactor calculation of remote list Jonathan Tan
2017-09-29 20:11 ` [PATCH 14/18] fetch: support excluding large blobs Jonathan Tan
2017-09-29 20:11 ` Jonathan Tan [this message]
2017-09-29 20:11 ` [PATCH 16/18] clone: configure blobmaxbytes in created repos Jonathan Tan
2017-09-29 20:11 ` [PATCH 17/18] unpack-trees: batch fetching of missing blobs Jonathan Tan
2017-09-29 20:11 ` [PATCH 18/18] fetch-pack: restore save_commit_buffer after use Jonathan Tan
2017-09-29 21:08 ` [PATCH 00/18] Partial clone (from clone to lazy fetch in 18 patches) Johannes Schindelin
2017-10-02  4:23 ` Junio C Hamano
2017-10-03  6:15 ` Christian Couder
2017-10-03  8:50   ` Junio C Hamano
2017-10-03 14:39     ` Jeff Hostetler
2017-10-03 23:42       ` Jonathan Tan
2017-10-04 13:30         ` Jeff Hostetler

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=9f0c6eb5aea49a5620de8e56fab2065805570f0e.1506714999.git.jonathantanmy@google.com \
    --to=jonathantanmy@google.com \
    --cc=christian.couder@gmail.com \
    --cc=git@jeffhostetler.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=peartben@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org mailing list mirror (one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/
       or Tor2web: https://www.tor2web.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox