Merge branch 'rc/fetch-refetch'

gitster · gitster · commit 0f5e88517372 · 2022-04-04T10:56:23.000-07:00
"git fetch --refetch" learned to fetch everything without telling
the other side what we already have, which is useful when you
cannot trust what you have in the local object store.

* rc/fetch-refetch:
  docs: mention --refetch fetch option
  fetch: after refetch, encourage auto gc repacking
  t5615-partial-clone: add test for fetch --refetch
  fetch: add --refetch option
  builtin/fetch-pack: add --refetch option
  fetch-pack: add refetch
  fetch-negotiator: add specific noop initializer
diff --git a/Documentation/config/remote.txt b/Documentation/config/remote.txt
@@ -82,5 +82,7 @@ remote.<name>.promisor::
 	objects.
 
 remote.<name>.partialclonefilter::
-	The filter that will be applied when fetching from this
-	promisor remote.
+	The filter that will be applied when fetching from this	promisor remote.
+	Changing or clearing this value will only affect fetches for new commits.
+	To fetch associated objects for commits already present in the local object
+	database, use the `--refetch` option of linkgit:git-fetch[1].
diff --git a/Documentation/fetch-options.txt b/Documentation/fetch-options.txt
@@ -163,6 +163,16 @@ endif::git-pull[]
 	behavior for a remote may be specified with the remote.<name>.tagOpt
 	setting. See linkgit:git-config[1].
 
+ifndef::git-pull[]
+--refetch::
+	Instead of negotiating with the server to avoid transferring commits and
+	associated objects that are already present locally, this option fetches
+	all objects as a fresh clone would. Use this to reapply a partial clone
+	filter from configuration or using `--filter=` when the filter
+	definition has changed. Automatic post-fetch maintenance will perform
+	object database pack consolidation to remove any duplicate objects.
+endif::git-pull[]
+
 --refmap=<refspec>::
 	When fetching refs listed on the command line, use the
 	specified refspec (can be given more than once) to map the
diff --git a/Documentation/git-fetch-pack.txt b/Documentation/git-fetch-pack.txt
@@ -101,6 +101,10 @@ be in a separate packet, and the list must end with a flush packet.
 	current shallow boundary instead of from the tip of each
 	remote branch history.
 
+--refetch::
+	Skips negotiating commits with the server in order to fetch all matching
+	objects. Use to reapply a new partial clone blob/tree filter.
+
 --no-progress::
 	Do not show the progress.
 
diff --git a/Documentation/technical/partial-clone.txt b/Documentation/technical/partial-clone.txt
@@ -181,6 +181,9 @@ Fetching Missing Objects
   currently fetches all objects referred to by the requested objects, even
   though they are not necessary.
 
+- Fetching with `--refetch` will request a complete new filtered packfile from
+  the remote, which can be used to change a filter without needing to
+  dynamically fetch missing objects.
 
 Using many promisor remotes
 ---------------------------
diff --git a/builtin/fetch-pack.c b/builtin/fetch-pack.c
@@ -153,6 +153,10 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
 			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;
diff --git a/builtin/fetch.c b/builtin/fetch.c
@@ -59,7 +59,7 @@ static int prune_tags = -1; /* unspecified */
 
 static int all, append, dry_run, force, keep, multiple, update_head_ok;
 static int write_fetch_head = 1;
-static int verbosity, deepen_relative, set_upstream;
+static int verbosity, deepen_relative, set_upstream, refetch;
 static int progress = -1;
 static int enable_auto_gc = 1;
 static int tags = TAGS_DEFAULT, unshallow, update_shallow, deepen;
@@ -190,6 +190,9 @@ static struct option builtin_fetch_options[] = {
 	OPT_SET_INT_F(0, "unshallow", &unshallow,
 		      N_("convert to a complete repository"),
 		      1, PARSE_OPT_NONEG),
+	OPT_SET_INT_F(0, "refetch", &refetch,
+		      N_("re-fetch without negotiating common commits"),
+		      1, PARSE_OPT_NONEG),
 	{ OPTION_STRING, 0, "submodule-prefix", &submodule_prefix, N_("dir"),
 		   N_("prepend this to submodule path output"), PARSE_OPT_HIDDEN },
 	OPT_CALLBACK_F(0, "recurse-submodules-default",
@@ -1304,6 +1307,14 @@ static int check_exist_and_connected(struct ref *ref_map)
 	if (deepen)
 		return -1;
 
+	/*
+	 * Similarly, if we need to refetch, we always want to perform a full
+	 * fetch ignoring existing objects.
+	 */
+	if (refetch)
+		return -1;
+
+
 	/*
 	 * check_connected() allows objects to merely be promised, but
 	 * we need all direct targets to exist.
@@ -1517,6 +1528,8 @@ static struct transport *prepare_transport(struct remote *remote, int deepen)
 		set_option(transport, TRANS_OPT_DEEPEN_RELATIVE, "yes");
 	if (update_shallow)
 		set_option(transport, TRANS_OPT_UPDATE_SHALLOW, "yes");
+	if (refetch)
+		set_option(transport, TRANS_OPT_REFETCH, "yes");
 	if (filter_options.choice) {
 		const char *spec =
 			expand_list_objects_filter_spec(&filter_options);
@@ -2293,8 +2306,25 @@ int cmd_fetch(int argc, const char **argv, const char *prefix)
 					     NULL);
 	}
 
-	if (enable_auto_gc)
+	if (enable_auto_gc) {
+		if (refetch) {
+			/*
+			 * Hint auto-maintenance strongly to encourage repacking,
+			 * but respect config settings disabling it.
+			 */
+			int opt_val;
+			if (git_config_get_int("gc.autopacklimit", &opt_val))
+				opt_val = -1;
+			if (opt_val != 0)
+				git_config_push_parameter("gc.autoPackLimit=1");
+
+			if (git_config_get_int("maintenance.incremental-repack.auto", &opt_val))
+				opt_val = -1;
+			if (opt_val != 0)
+				git_config_push_parameter("maintenance.incremental-repack.auto=-1");
+		}
 		run_auto_maintenance(verbosity < 0);
+	}
 
  cleanup:
 	string_list_clear(&list, 0);
diff --git a/fetch-negotiator.c b/fetch-negotiator.c
@@ -23,3 +23,8 @@ void fetch_negotiator_init(struct repository *r,
 		return;
 	}
 }
+
+void fetch_negotiator_init_noop(struct fetch_negotiator *negotiator)
+{
+	noop_negotiator_init(negotiator);
+}
diff --git a/fetch-negotiator.h b/fetch-negotiator.h
@@ -53,7 +53,15 @@ struct fetch_negotiator {
 	void *data;
 };
 
+/*
+ * Initialize a negotiator based on the repository settings.
+ */
 void fetch_negotiator_init(struct repository *r,
 			   struct fetch_negotiator *negotiator);
 
+/*
+ * Initialize a noop negotiator.
+ */
+void fetch_negotiator_init_noop(struct fetch_negotiator *negotiator);
+
 #endif
diff --git a/fetch-pack.c b/fetch-pack.c
@@ -312,19 +312,21 @@ static int find_common(struct fetch_negotiator *negotiator,
 		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(the_repository, remote)) != NULL) &&
-				(o->flags & COMPLETE)) {
-			continue;
+		if (!args->refetch) {
+			/*
+			* 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(the_repository, remote)) != NULL) &&
+					(o->flags & COMPLETE)) {
+				continue;
+			}
 		}
 
 		remote_hex = oid_to_hex(remote);
@@ -692,6 +694,9 @@ static void mark_complete_and_common_ref(struct fetch_negotiator *negotiator,
 	int old_save_commit_buffer = save_commit_buffer;
 	timestamp_t cutoff = 0;
 
+	if (args->refetch)
+		return;
+
 	save_commit_buffer = 0;
 
 	trace2_region_enter("fetch-pack", "parse_remote_refs_and_find_cutoff", NULL);
@@ -1028,7 +1033,11 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 	struct fetch_negotiator *negotiator;
 
 	negotiator = &negotiator_alloc;
-	fetch_negotiator_init(r, negotiator);
+	if (args->refetch) {
+		fetch_negotiator_init_noop(negotiator);
+	} else {
+		fetch_negotiator_init(r, negotiator);
+	}
 
 	sort_ref_list(&ref, ref_compare_name);
 	QSORT(sought, nr_sought, cmp_ref_by_name);
@@ -1121,7 +1130,7 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 
 	mark_complete_and_common_ref(negotiator, args, &ref);
 	filter_refs(args, &ref, sought, nr_sought);
-	if (everything_local(args, &ref)) {
+	if (!args->refetch && everything_local(args, &ref)) {
 		packet_flush(fd[1]);
 		goto all_done;
 	}
@@ -1587,7 +1596,10 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 	struct strvec index_pack_args = STRVEC_INIT;
 
 	negotiator = &negotiator_alloc;
-	fetch_negotiator_init(r, negotiator);
+	if (args->refetch)
+		fetch_negotiator_init_noop(negotiator);
+	else
+		fetch_negotiator_init(r, negotiator);
 
 	packet_reader_init(&reader, fd[0], NULL, 0,
 			   PACKET_READ_CHOMP_NEWLINE |
@@ -1613,7 +1625,7 @@ static struct ref *do_fetch_pack_v2(struct fetch_pack_args *args,
 			/* Filter 'ref' by 'sought' and those that aren't local */
 			mark_complete_and_common_ref(negotiator, args, &ref);
 			filter_refs(args, &ref, sought, nr_sought);
-			if (everything_local(args, &ref))
+			if (!args->refetch && everything_local(args, &ref))
 				state = FETCH_DONE;
 			else
 				state = FETCH_SEND_REQUEST;
diff --git a/fetch-pack.h b/fetch-pack.h
@@ -42,6 +42,7 @@ struct fetch_pack_args {
 	unsigned update_shallow:1;
 	unsigned reject_shallow_remote:1;
 	unsigned deepen:1;
+	unsigned refetch:1;
 
 	/*
 	 * Indicate that the remote of this request is a promisor remote. The
diff --git a/remote-curl.c b/remote-curl.c
@@ -43,6 +43,7 @@ struct options {
 		/* see documentation of corresponding flag in fetch-pack.h */
 		from_promisor : 1,
 
+		refetch : 1,
 		atomic : 1,
 		object_format : 1,
 		force_if_includes : 1;
@@ -198,6 +199,9 @@ static int set_option(const char *name, const char *value)
 	} else if (!strcmp(name, "from-promisor")) {
 		options.from_promisor = 1;
 		return 0;
+	} else if (!strcmp(name, "refetch")) {
+		options.refetch = 1;
+		return 0;
 	} else if (!strcmp(name, "filter")) {
 		options.filter = xstrdup(value);
 		return 0;
@@ -1182,6 +1186,8 @@ static int fetch_git(struct discovery *heads,
 		strvec_push(&args, "--deepen-relative");
 	if (options.from_promisor)
 		strvec_push(&args, "--from-promisor");
+	if (options.refetch)
+		strvec_push(&args, "--refetch");
 	if (options.filter)
 		strvec_pushf(&args, "--filter=%s", options.filter);
 	strvec_push(&args, url.buf);
diff --git a/t/t5616-partial-clone.sh b/t/t5616-partial-clone.sh
@@ -166,6 +166,85 @@ test_expect_success 'manual prefetch of missing objects' '
 	test_line_count = 0 observed.oids
 '
 
+# create new commits in "src" repo to establish a history on file.4.txt
+# and push to "srv.bare".
+test_expect_success 'push new commits to server for file.4.txt' '
+	for x in a b c d e f
+	do
+		echo "Mod file.4.txt $x" >src/file.4.txt &&
+		if list_contains "a,b" "$x"; then
+			printf "%10000s" X >>src/file.4.txt
+		fi &&
+		if list_contains "c,d" "$x"; then
+			printf "%20000s" X >>src/file.4.txt
+		fi &&
+		git -C src add file.4.txt &&
+		git -C src commit -m "mod $x" || return 1
+	done &&
+	git -C src push -u srv main
+'
+
+# Do partial fetch to fetch smaller files; then verify that without --refetch
+# applying a new filter does not refetch missing large objects. Then use
+# --refetch to apply the new filter on existing commits. Test it under both
+# protocol v2 & v0.
+test_expect_success 'apply a different filter using --refetch' '
+	git -C pc1 fetch --filter=blob:limit=999 origin &&
+	git -C pc1 rev-list --quiet --objects --missing=print \
+		main..origin/main >observed &&
+	test_line_count = 4 observed &&
+
+	git -C pc1 fetch --filter=blob:limit=19999 --refetch origin &&
+	git -C pc1 rev-list --quiet --objects --missing=print \
+		main..origin/main >observed &&
+	test_line_count = 2 observed &&
+
+	git -c protocol.version=0 -C pc1 fetch --filter=blob:limit=29999 \
+		--refetch origin &&
+	git -C pc1 rev-list --quiet --objects --missing=print \
+		main..origin/main >observed &&
+	test_line_count = 0 observed
+'
+
+test_expect_success 'fetch --refetch works with a shallow clone' '
+	git clone --no-checkout --depth=1 --filter=blob:none "file://$(pwd)/srv.bare" pc1s &&
+	git -C pc1s rev-list --objects --missing=print HEAD >observed &&
+	test_line_count = 6 observed &&
+
+	GIT_TRACE=1 git -C pc1s fetch --filter=blob:limit=999 --refetch origin &&
+	git -C pc1s rev-list --objects --missing=print HEAD >observed &&
+	test_line_count = 6 observed
+'
+
+test_expect_success 'fetch --refetch triggers repacking' '
+	GIT_TRACE2_CONFIG_PARAMS=gc.autoPackLimit,maintenance.incremental-repack.auto &&
+	export GIT_TRACE2_CONFIG_PARAMS &&
+
+	GIT_TRACE2_EVENT="$PWD/trace1.event" \
+	git -C pc1 fetch --refetch origin &&
+	test_subcommand git maintenance run --auto --no-quiet <trace1.event &&
+	grep \"param\":\"gc.autopacklimit\",\"value\":\"1\" trace1.event &&
+	grep \"param\":\"maintenance.incremental-repack.auto\",\"value\":\"-1\" trace1.event &&
+
+	GIT_TRACE2_EVENT="$PWD/trace2.event" \
+	git -c protocol.version=0 \
+		-c gc.autoPackLimit=0 \
+		-c maintenance.incremental-repack.auto=1234 \
+		-C pc1 fetch --refetch origin &&
+	test_subcommand git maintenance run --auto --no-quiet <trace2.event &&
+	grep \"param\":\"gc.autopacklimit\",\"value\":\"0\" trace2.event &&
+	grep \"param\":\"maintenance.incremental-repack.auto\",\"value\":\"-1\" trace2.event &&
+
+	GIT_TRACE2_EVENT="$PWD/trace3.event" \
+	git -c protocol.version=0 \
+		-c gc.autoPackLimit=1234 \
+		-c maintenance.incremental-repack.auto=0 \
+		-C pc1 fetch --refetch origin &&
+	test_subcommand git maintenance run --auto --no-quiet <trace3.event &&
+	grep \"param\":\"gc.autopacklimit\",\"value\":\"1\" trace3.event &&
+	grep \"param\":\"maintenance.incremental-repack.auto\",\"value\":\"0\" trace3.event
+'
+
 test_expect_success 'partial clone with transfer.fsckobjects=1 works with submodules' '
 	test_create_repo submodule &&
 	test_commit -C submodule mycommit &&
@@ -225,7 +304,7 @@ test_expect_success 'use fsck before and after manually fetching a missing subtr
 
 	# Auto-fetch all remaining trees and blobs with --missing=error
 	git -C dst rev-list --missing=error --objects main >fetched_objects &&
-	test_line_count = 70 fetched_objects &&
+	test_line_count = 88 fetched_objects &&
 
 	awk -f print_1.awk fetched_objects |
 	xargs -n1 git -C dst cat-file -t >fetched_types &&
diff --git a/transport-helper.c b/transport-helper.c
@@ -715,6 +715,9 @@ static int fetch_refs(struct transport *transport,
 	if (data->transport_options.update_shallow)
 		set_helper_option(transport, "update-shallow", "true");
 
+	if (data->transport_options.refetch)
+		set_helper_option(transport, "refetch", "true");
+
 	if (data->transport_options.filter_options.choice) {
 		const char *spec = expand_list_objects_filter_spec(
 			&data->transport_options.filter_options);
diff --git a/transport.c b/transport.c
@@ -250,6 +250,9 @@ static int set_git_option(struct git_transport_options *opts,
 		list_objects_filter_die_if_populated(&opts->filter_options);
 		parse_list_objects_filter(&opts->filter_options, value);
 		return 0;
+	} else if (!strcmp(name, TRANS_OPT_REFETCH)) {
+		opts->refetch = !!value;
+		return 0;
 	} else if (!strcmp(name, TRANS_OPT_REJECT_SHALLOW)) {
 		opts->reject_shallow = !!value;
 		return 0;
@@ -384,6 +387,7 @@ static int fetch_refs_via_pack(struct transport *transport,
 	args.update_shallow = data->options.update_shallow;
 	args.from_promisor = data->options.from_promisor;
 	args.filter_options = data->options.filter_options;
+	args.refetch = data->options.refetch;
 	args.stateless_rpc = transport->stateless_rpc;
 	args.server_options = transport->server_options;
 	args.negotiation_tips = data->options.negotiation_tips;
diff --git a/transport.h b/transport.h

Original file line number	Diff line number	Diff line change
`@@ -23,3 +23,8 @@ void fetch_negotiator_init(struct repository *r,`
`23`	`23`	`return;`
`24`	`24`	`}`
`25`	`25`	`}`
	`26`	`+`
	`27`	`+void fetch_negotiator_init_noop(struct fetch_negotiator *negotiator)`
	`28`	`+{`
	`29`	`+ noop_negotiator_init(negotiator);`
	`30`	`+}`