convert: add "status=delayed" to filter process protocol

Some `clean` / `smudge` filters may require a significant amount of
time to process a single blob (e.g. the Git LFS smudge filter might
perform network requests). During this process the Git checkout
operation is blocked and Git needs to wait until the filter is done to
continue with the checkout.

Teach the filter process protocol, introduced in edcc8581 ("convert: add
filter.<driver>.process option", 2016-10-16), to accept the status
"delayed" as response to a filter request. Upon this response Git
continues with the checkout operation. After the checkout operation Git
calls "finish_delayed_checkout" which queries the filter for remaining
blobs. If the filter is still working on the completion, then the filter
is expected to block. If the filter has completed all remaining blobs
then an empty response is expected.

Git has a multiple code paths that checkout a blob. Support delayed
checkouts only in `clone` (in unpack-trees.c) and `checkout` operations
for now. The optimization is most effective in these code paths as all
files of the tree are processed.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 94 insertions, 16 deletions

diff --git a/convert.c b/convert.c
index d13e505df..12a0b3eaf 100644
--- a/convert.c
+++ b/convert.c
@@ -496,6 +496,7 @@ static int apply_single_file_filter(const char *path, const char *src, size_t le
 
 #define CAP_CLEAN    (1u<<0)
 #define CAP_SMUDGE   (1u<<1)
+#define CAP_DELAY    (1u<<2)
 
 struct cmd2process {
 	struct subprocess_entry subprocess; /* must be the first member! */
@@ -521,6 +522,7 @@ static int start_multi_file_filter_fn(struct subprocess_entry *subprocess)
 	} known_caps[] = {
 		{ "clean",  CAP_CLEAN  },
 		{ "smudge", CAP_SMUDGE },
+		{ "delay",  CAP_DELAY  },
 	};
 
 	sigchain_push(SIGPIPE, SIG_IGN);
@@ -605,9 +607,11 @@ static void handle_filter_error(const struct strbuf *filter_status,
 
 static int apply_multi_file_filter(const char *path, const char *src, size_t len,
 				   int fd, struct strbuf *dst, const char *cmd,
-				   const unsigned int wanted_capability)
+				   const unsigned int wanted_capability,
+				   struct delayed_checkout *dco)
 {
 	int err;
+	int can_delay = 0;
 	struct cmd2process *entry;
 	struct child_process *process;
 	struct strbuf nbuf = STRBUF_INIT;
@@ -662,6 +666,14 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 	if (err)
 		goto done;
 
+	if ((entry->supported_capabilities & CAP_DELAY) &&
+	    dco && dco->state == CE_CAN_DELAY) {
+		can_delay = 1;
+		err = packet_write_fmt_gently(process->in, "can-delay=1\n");
+		if (err)
+			goto done;
+	}
+
 	err = packet_flush_gently(process->in);
 	if (err)
 		goto done;
@@ -677,14 +689,73 @@ static int apply_multi_file_filter(const char *path, const char *src, size_t len
 	if (err)
 		goto done;
 
-	err = strcmp(filter_status.buf, "success");
+	if (can_delay && !strcmp(filter_status.buf, "delayed")) {
+		string_list_insert(&dco->filters, cmd);
+		string_list_insert(&dco->paths, path);
+	} else {
+		/* The filter got the blob and wants to send us a response. */
+		err = strcmp(filter_status.buf, "success");
+		if (err)
+			goto done;
+
+		err = read_packetized_to_strbuf(process->out, &nbuf) < 0;
+		if (err)
+			goto done;
+
+		err = subprocess_read_status(process->out, &filter_status);
+		if (err)
+			goto done;
+
+		err = strcmp(filter_status.buf, "success");
+	}
+
+done:
+	sigchain_pop(SIGPIPE);
+
+	if (err)
+		handle_filter_error(&filter_status, entry, wanted_capability);
+	else
+		strbuf_swap(dst, &nbuf);
+	strbuf_release(&nbuf);
+	return !err;
+}
+
+
+int async_query_available_blobs(const char *cmd, struct string_list *available_paths)
+{
+	int err;
+	char *line;
+	struct cmd2process *entry;
+	struct child_process *process;
+	struct strbuf filter_status = STRBUF_INIT;
+
+	assert(subprocess_map_initialized);
+	entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd);
+	if (!entry) {
+		error("external filter '%s' is not available anymore although "
+		      "not all paths have been filtered", cmd);
+		return 0;
+	}
+	process = &entry->subprocess.process;
+	sigchain_push(SIGPIPE, SIG_IGN);
+
+	err = packet_write_fmt_gently(
+		process->in, "command=list_available_blobs\n");
 	if (err)
 		goto done;
 
-	err = read_packetized_to_strbuf(process->out, &nbuf) < 0;
+	err = packet_flush_gently(process->in);
 	if (err)
 		goto done;
 
+	while ((line = packet_read_line(process->out, NULL))) {
+		const char *path;
+		if (skip_prefix(line, "pathname=", &path))
+			string_list_insert(available_paths, xstrdup(path));
+		else
+			; /* ignore unknown keys */
+	}
+
 	err = subprocess_read_status(process->out, &filter_status);
 	if (err)
 		goto done;
@@ -695,10 +766,7 @@ done:
 	sigchain_pop(SIGPIPE);
 
 	if (err)
-		handle_filter_error(&filter_status, entry, wanted_capability);
-	else
-		strbuf_swap(dst, &nbuf);
-	strbuf_release(&nbuf);
+		handle_filter_error(&filter_status, entry, 0);
 	return !err;
 }
 
@@ -713,7 +781,8 @@ static struct convert_driver {
 
 static int apply_filter(const char *path, const char *src, size_t len,
 			int fd, struct strbuf *dst, struct convert_driver *drv,
-			const unsigned int wanted_capability)
+			const unsigned int wanted_capability,
+			struct delayed_checkout *dco)
 {
 	const char *cmd = NULL;
 
@@ -731,7 +800,8 @@ static int apply_filter(const char *path, const char *src, size_t len,
 	if (cmd && *cmd)
 		return apply_single_file_filter(path, src, len, fd, dst, cmd);
 	else if (drv->process && *drv->process)
-		return apply_multi_file_filter(path, src, len, fd, dst, drv->process, wanted_capability);
+		return apply_multi_file_filter(path, src, len, fd, dst,
+			drv->process, wanted_capability, dco);
 
 	return 0;
 }
@@ -1072,7 +1142,7 @@ int would_convert_to_git_filter_fd(const char *path)
 	if (!ca.drv->required)
 		return 0;
 
-	return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN);
+	return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN, NULL);
 }
 
 const char *get_convert_attr_ascii(const char *path)
@@ -1109,7 +1179,7 @@ int convert_to_git(const char *path, const char *src, size_t len,
 
 	convert_attrs(&ca, path);
 
-	ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN);
+	ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN, NULL);
 	if (!ret && ca.drv && ca.drv->required)
 		die("%s: clean filter '%s' failed", path, ca.drv->name);
 
@@ -1134,7 +1204,7 @@ void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
 	assert(ca.drv);
 	assert(ca.drv->clean || ca.drv->process);
 
-	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN))
+	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL))
 		die("%s: clean filter '%s' failed", path, ca.drv->name);
 
 	crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
@@ -1143,7 +1213,7 @@ void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
 
 static int convert_to_working_tree_internal(const char *path, const char *src,
 					    size_t len, struct strbuf *dst,
-					    int normalizing)
+					    int normalizing, struct delayed_checkout *dco)
 {
 	int ret = 0, ret_filter = 0;
 	struct conv_attrs ca;
@@ -1168,21 +1238,29 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
 		}
 	}
 
-	ret_filter = apply_filter(path, src, len, -1, dst, ca.drv, CAP_SMUDGE);
+	ret_filter = apply_filter(
+		path, src, len, -1, dst, ca.drv, CAP_SMUDGE, dco);
 	if (!ret_filter && ca.drv && ca.drv->required)
 		die("%s: smudge filter %s failed", path, ca.drv->name);
 
 	return ret | ret_filter;
 }
 
+int async_convert_to_working_tree(const char *path, const char *src,
+				  size_t len, struct strbuf *dst,
+				  void *dco)
+{
+	return convert_to_working_tree_internal(path, src, len, dst, 0, dco);
+}
+
 int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst)
 {
-	return convert_to_working_tree_internal(path, src, len, dst, 0);
+	return convert_to_working_tree_internal(path, src, len, dst, 0, NULL);
 }
 
 int renormalize_buffer(const char *path, const char *src, size_t len, struct strbuf *dst)
 {
-	int ret = convert_to_working_tree_internal(path, src, len, dst, 1);
+	int ret = convert_to_working_tree_internal(path, src, len, dst, 1, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;