upload-pack: add object filtering for partial clone

Teach upload-pack to negotiate object filtering over the protocol and
to send filter parameters to pack-objects.  This is intended for partial
clone and fetch.

The idea to make upload-pack configurable using uploadpack.allowFilter
comes from Jonathan Tan's work in [1].

[1] https://public-inbox.org/git/f211093280b422c32cc1b7034130072f35c5ed51.1506714999.git.jonathantanmy@google.com/

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 1ac0ae6adb0460a3460084aef2302434e24ee6de..e528210c67a4c66bef22e560b425d3bb3bb9f2e6 100644 (file)
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -3268,6 +3268,10 @@ uploadpack.packObjectsHook::
        was run. I.e., `upload-pack` will feed input intended for
        `pack-objects` to the hook, and expects a completed packfile on
        stdout.
+
+uploadpack.allowFilter::
+       If this option is set, `upload-pack` will advertise partial
+       clone and partial fetch object filtering.
 +
 Note that this configuration variable is ignored if it is seen in the
 repository-level config (this is a safety measure against fetching from

diff --git a/Documentation/technical/pack-protocol.txt b/Documentation/technical/pack-protocol.txt
index ed1eae8b83a651d34f9ce2488f58d02a763fbfd4..a43a113e44f3d959f2a527a7039c28199d12be25 100644 (file)
--- a/Documentation/technical/pack-protocol.txt
+++ b/Documentation/technical/pack-protocol.txt
@@ -212,6 +212,7 @@ out of what the server said it could do with the first 'want' line.
   upload-request    =  want-list
                       *shallow-line
                       *1depth-request
+                      [filter-request]
                       flush-pkt
 
   want-list         =  first-want
@@ -227,6 +228,8 @@ out of what the server said it could do with the first 'want' line.
   additional-want   =  PKT-LINE("want" SP obj-id)
 
   depth             =  1*DIGIT
+
+  filter-request    =  PKT-LINE("filter" SP filter-spec)
 ----
 
 Clients MUST send all the obj-ids it wants from the reference
@@ -249,6 +252,11 @@ complete those commits. Commits whose parents are not received as a
 result are defined as shallow and marked as such in the server. This
 information is sent back to the client in the next step.
 
+The client can optionally request that pack-objects omit various
+objects from the packfile using one of several filtering techniques.
+These are intended for use with partial clone and partial fetch
+operations.  See `rev-list` for possible "filter-spec" values.
+
 Once all the 'want's and 'shallow's (and optional 'deepen') are
 transferred, clients MUST send a flush-pkt, to tell the server side
 that it is done sending the list.

diff --git a/Documentation/technical/protocol-capabilities.txt b/Documentation/technical/protocol-capabilities.txt
index 26dcc6f502020da5214f1e161f1678813dd24059..332d209b58ca42dc303c757f2b31f7a4f3d033f4 100644 (file)
--- a/Documentation/technical/protocol-capabilities.txt
+++ b/Documentation/technical/protocol-capabilities.txt
@@ -309,3 +309,11 @@ to accept a signed push certificate, and asks the <nonce> to be
 included in the push certificate.  A send-pack client MUST NOT
 send a push-cert packet unless the receive-pack server advertises
 this capability.
+
+filter
+------
+
+If the upload-pack server advertises the 'filter' capability,
+fetch-pack may send "filter" commands to request a partial clone
+or partial fetch and request that the server omit various objects
+from the packfile.

diff --git a/upload-pack.c b/upload-pack.c
index e25f725c0feaa57c9a09c976628217c99dfb5652..e6d38b9ca06797ab369b0f583a79ced3ecdbf128 100644 (file)
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -10,6 +10,8 @@
 #include "diff.h"
 #include "revision.h"
 #include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
 #include "run-command.h"
 #include "connect.h"
 #include "sigchain.h"
@@ -18,6 +20,7 @@
 #include "parse-options.h"
 #include "argv-array.h"
 #include "prio-queue.h"
+#include "quote.h"
 
 static const char * const upload_pack_usage[] = {
        N_("git upload-pack [<options>] <dir>"),
@@ -64,6 +67,10 @@ static int advertise_refs;
 static int stateless_rpc;
 static const char *pack_objects_hook;
 
+static int filter_capability_requested;
+static int filter_advertise;
+static struct list_objects_filter_options filter_options;
+
 static void reset_timeout(void)
 {
        alarm(timeout);
@@ -131,6 +138,12 @@ static void create_pack_file(void)
                argv_array_push(&pack_objects.args, "--delta-base-offset");
        if (use_include_tag)
                argv_array_push(&pack_objects.args, "--include-tag");
+       if (filter_options.filter_spec) {
+               struct strbuf buf = STRBUF_INIT;
+               sq_quote_buf(&buf, filter_options.filter_spec);
+               argv_array_pushf(&pack_objects.args, "--filter=%s", buf.buf);
+               strbuf_release(&buf);
+       }
 
        pack_objects.in = -1;
        pack_objects.out = -1;
@@ -794,6 +807,12 @@ static void receive_needs(void)
                        deepen_rev_list = 1;
                        continue;
                }
+               if (skip_prefix(line, "filter ", &arg)) {
+                       if (!filter_capability_requested)
+                               die("git upload-pack: filtering capability not negotiated");
+                       parse_list_objects_filter(&filter_options, arg);
+                       continue;
+               }
                if (!skip_prefix(line, "want ", &arg) ||
                    get_oid_hex(arg, &oid_buf))
                        die("git upload-pack: protocol error, "
@@ -821,6 +840,8 @@ static void receive_needs(void)
                        no_progress = 1;
                if (parse_feature_request(features, "include-tag"))
                        use_include_tag = 1;
+               if (parse_feature_request(features, "filter"))
+                       filter_capability_requested = 1;
 
                o = parse_object(&oid_buf);
                if (!o) {
@@ -940,7 +961,7 @@ static int send_ref(const char *refname, const struct object_id *oid,
                struct strbuf symref_info = STRBUF_INIT;
 
                format_symref_info(&symref_info, cb_data);
-               packet_write_fmt(1, "%s %s%c%s%s%s%s%s agent=%s\n",
+               packet_write_fmt(1, "%s %s%c%s%s%s%s%s%s agent=%s\n",
                             oid_to_hex(oid), refname_nons,
                             0, capabilities,
                             (allow_unadvertised_object_request & ALLOW_TIP_SHA1) ?
@@ -949,6 +970,7 @@ static int send_ref(const char *refname, const struct object_id *oid,
                                     " allow-reachable-sha1-in-want" : "",
                             stateless_rpc ? " no-done" : "",
                             symref_info.buf,
+                            filter_advertise ? " filter" : "",
                             git_user_agent_sanitized());
                strbuf_release(&symref_info);
        } else {
@@ -1027,6 +1049,8 @@ static int upload_pack_config(const char *var, const char *value, void *unused)
        } else if (current_config_scope() != CONFIG_SCOPE_REPO) {
                if (!strcmp("uploadpack.packobjectshook", var))
                        return git_config_string(&pack_objects_hook, var, value);
+       } else if (!strcmp("uploadpack.allowfilter", var)) {
+               filter_advertise = git_config_bool(var, value);
        }
        return parse_hide_refs_config(var, value, "uploadpack");
 }