convert: stream from fd to required clean filter to reduce used address space

The data is streamed to the filter process anyway.  Better avoid mapping
the file if possible.  This is especially useful if a clean filter
reduces the size, for example if it computes a sha1 for binary data,
like git media.  The file size that the previous implementation could
handle was limited by the available address space; large files for
example could not be handled with (32-bit) msysgit.  The new
implementation can filter files of any size as long as the filter output
is small enough.

The new code path is only taken if the filter is required.  The filter
consumes data directly from the fd.  If it fails, the original data is
not immediately available.  The condition can easily be handled as
a fatal error, which is expected for a required filter anyway.

If the filter was not required, the condition would need to be handled
in a different way, like seeking to 0 and reading the data.  But this
would require more restructuring of the code and is probably not worth
it.  The obvious approach of falling back to reading all data would not
help achieving the main purpose of this patch, which is to handle large
files with limited address space.  If reading all data is an option, we
can simply take the old code path right away and mmap the entire file.

The environment variable GIT_MMAP_LIMIT, which has been introduced in
a previous commit is used to test that the expected code path is taken.
A related test that exercises required filters is modified to verify
that the data actually has been modified on its way from the file system
to the object store.

Signed-off-by: Steffen Prohaska <prohaska@zib.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 49 insertions, 6 deletions

diff --git a/convert.c b/convert.c
index cb5fbb45ea..677d339a8b 100644
--- a/convert.c
+++ b/convert.c
@@ -312,11 +312,12 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 struct filter_params {
 	const char *src;
 	unsigned long size;
+	int fd;
 	const char *cmd;
 	const char *path;
 };
 
-static int filter_buffer(int in, int out, void *data)
+static int filter_buffer_or_fd(int in, int out, void *data)
 {
 	/*
 	 * Spawn cmd and feed the buffer contents through its stdin.
@@ -355,7 +356,12 @@ static int filter_buffer(int in, int out, void *data)
 
 	sigchain_push(SIGPIPE, SIG_IGN);
 
-	write_err = (write_in_full(child_process.in, params->src, params->size) < 0);
+	if (params->src) {
+		write_err = (write_in_full(child_process.in, params->src, params->size) < 0);
+	} else {
+		write_err = copy_fd(params->fd, child_process.in);
+	}
+
 	if (close(child_process.in))
 		write_err = 1;
 	if (write_err)
@@ -371,7 +377,7 @@ static int filter_buffer(int in, int out, void *data)
 	return (write_err || status);
 }
 
-static int apply_filter(const char *path, const char *src, size_t len,
+static int apply_filter(const char *path, const char *src, size_t len, int fd,
                         struct strbuf *dst, const char *cmd)
 {
 	/*
@@ -392,11 +398,12 @@ static int apply_filter(const char *path, const char *src, size_t len,
 		return 1;
 
 	memset(&async, 0, sizeof(async));
-	async.proc = filter_buffer;
+	async.proc = filter_buffer_or_fd;
 	async.data = &params;
 	async.out = -1;
 	params.src = src;
 	params.size = len;
+	params.fd = fd;
 	params.cmd = cmd;
 	params.path = path;
 
@@ -747,6 +754,25 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
 	}
 }
 
+int would_convert_to_git_filter_fd(const char *path)
+{
+	struct conv_attrs ca;
+
+	convert_attrs(&ca, path);
+	if (!ca.drv)
+		return 0;
+
+	/*
+	 * Apply a filter to an fd only if the filter is required to succeed.
+	 * We must die if the filter fails, because the original data before
+	 * filtering is not available.
+	 */
+	if (!ca.drv->required)
+		return 0;
+
+	return apply_filter(path, NULL, 0, -1, NULL, ca.drv->clean);
+}
+
 int convert_to_git(const char *path, const char *src, size_t len,
                    struct strbuf *dst, enum safe_crlf checksafe)
 {
@@ -761,7 +787,7 @@ int convert_to_git(const char *path, const char *src, size_t len,
 		required = ca.drv->required;
 	}
 
-	ret |= apply_filter(path, src, len, dst, filter);
+	ret |= apply_filter(path, src, len, -1, dst, filter);
 	if (!ret && required)
 		die("%s: clean filter '%s' failed", path, ca.drv->name);
 
@@ -778,6 +804,23 @@ int convert_to_git(const char *path, const char *src, size_t len,
 	return ret | ident_to_git(path, src, len, dst, ca.ident);
 }
 
+void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
+			      enum safe_crlf checksafe)
+{
+	struct conv_attrs ca;
+	convert_attrs(&ca, path);
+
+	assert(ca.drv);
+	assert(ca.drv->clean);
+
+	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean))
+		die("%s: clean filter '%s' failed", path, ca.drv->name);
+
+	ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
+	crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
+	ident_to_git(path, dst->buf, dst->len, dst, ca.ident);
+}
+
 static int convert_to_working_tree_internal(const char *path, const char *src,
 					    size_t len, struct strbuf *dst,
 					    int normalizing)
@@ -811,7 +854,7 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
 		}
 	}
 
-	ret_filter = apply_filter(path, src, len, dst, filter);
+	ret_filter = apply_filter(path, src, len, -1, dst, filter);
 	if (!ret_filter && required)
 		die("%s: smudge filter %s failed", path, ca.drv->name);