git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[WIP RFC 3/5] upload-pack: refactor reading of pack-objects out

From
JTJonathan Tan <jonathantanmy@google.com>
Date
Dec 3, 2018, 23:37 UTC
Message-ID
<e19f294df9ff999d30a47339a7848c7104bfae7d.1543879256.git.jonathantanmy@google.com>
In-Reply-To
<cover.1543879256.git.jonathantanmy@google.com>

Subsequent patches will change how the output of pack-objects is processed, so extract that processing into its own function.

Currently, at most 1 character can be buffered (in the "buffered" local variable). One of those patches will require a larger buffer, so replace that "buffered" local variable with a buffer array.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 upload-pack.c | 80 +++++++++++++++++++++++++++++----------------------
 1 file changed, 46 insertions(+), 34 deletions(-)
diff --git a/upload-pack.c b/upload-pack.c
index 5e81f1ff24..cec43e0a46 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -101,14 +101,51 @@ static int write_one_shallow(const struct commit_graft *graft, void *cb_data)
 	return 0;
 }
 
+struct output_state {
+	char buffer[8193];
+	int used;
+};
+
+static int read_pack_objects_stdout(int outfd, struct output_state *os)
+{
+	/* Data ready; we keep the last byte to ourselves
+	 * in case we detect broken rev-list, so that we
+	 * can leave the stream corrupted.  This is
+	 * unfortunate -- unpack-objects would happily
+	 * accept a valid packdata with trailing garbage,
+	 * so appending garbage after we pass all the
+	 * pack data is not good enough to signal
+	 * breakage to downstream.
+	 */
+	ssize_t readsz;
+
+	readsz = xread(outfd, os->buffer + os->used,
+		       sizeof(os->buffer) - os->used);
+	if (readsz < 0) {
+		return readsz;
+	}
+	os->used += readsz;
+
+	if (os->used > 1) {
+		send_client_data(1, os->buffer, os->used - 1);
+		os->buffer[0] = os->buffer[os->used - 1];
+		os->used = 1;
+	} else {
+		send_client_data(1, os->buffer, os->used);
+		os->used = 0;
+	}
+
+	return readsz;
+}
+
 static void create_pack_file(const struct object_array *have_obj,
 			     const struct object_array *want_obj)
 {
 	struct child_process pack_objects = CHILD_PROCESS_INIT;
-	char data[8193], progress[128];
+	struct output_state output_state = {0};
+	char progress[128];
 	char abort_msg[] = "aborting due to possible repository "
 		"corruption on the remote side.";
-	int buffered = -1;
 	ssize_t sz;
 	int i;
 	FILE *pipe_fd;
@@ -235,39 +272,15 @@ static void create_pack_file(const struct object_array *have_obj,
 			continue;
 		}
 		if (0 <= pu && (pfd[pu].revents & (POLLIN|POLLHUP))) {
-			/* Data ready; we keep the last byte to ourselves
-			 * in case we detect broken rev-list, so that we
-			 * can leave the stream corrupted.  This is
-			 * unfortunate -- unpack-objects would happily
-			 * accept a valid packdata with trailing garbage,
-			 * so appending garbage after we pass all the
-			 * pack data is not good enough to signal
-			 * breakage to downstream.
-			 */
-			char *cp = data;
-			ssize_t outsz = 0;
-			if (0 <= buffered) {
-				*cp++ = buffered;
-				outsz++;
-			}
-			sz = xread(pack_objects.out, cp,
-				  sizeof(data) - outsz);
-			if (0 < sz)
-				;
-			else if (sz == 0) {
+			int result = read_pack_objects_stdout(pack_objects.out,
+							      &output_state);
+
+			if (result == 0) {
 				close(pack_objects.out);
 				pack_objects.out = -1;
-			}
-			else
+			} else if (result < 0) {
 				goto fail;
-			sz += outsz;
-			if (1 < sz) {
-				buffered = data[sz-1] & 0xFF;
-				sz--;
 			}
-			else
-				buffered = -1;
-			send_client_data(1, data, sz);
 		}
 
 		/*
@@ -292,9 +305,8 @@ static void create_pack_file(const struct object_array *have_obj,
 	}
 
 	/* flush the data */
-	if (0 <= buffered) {
-		data[0] = buffered;
-		send_client_data(1, data, 1);
+	if (output_state.used > 0) {
+		send_client_data(1, output_state.buffer, output_state.used);
 		fprintf(stderr, "flushed.\n");
 	}
 	if (use_sideband)
-- 
2.19.0.271.gfe8321ec05.dirty
Previous: Jonathan TanNext: Stefan Beller
Message 21 of 30 in “[WIP RFC 0/5] Design for offloading part of packfile response to CDN”
  1. Jonathan TanDec 3, 2018
  2. 1/5 Documentation: order protocol v2 sectionsJonathan Tan, Dec 3, 2018
  3. Junio C HamanoDec 5, 2018
  4. Jonathan TanDec 6, 2018
  5. Junio C HamanoDec 9, 2018
  6. 2/5 Documentation: add Packfile URIs design docJonathan Tan, Dec 3, 2018
  7. Stefan BellerDec 4, 2018
  8. brian m. carlsonDec 4, 2018
  9. Jonathan TanDec 4, 2018
  10. Christian CouderFeb 19, 2019
  11. Jonathan TanFeb 19, 2019
  12. Christian CouderFeb 22, 2019
  13. Ævar Arnfjörð BjarmasonFeb 19, 2019
  14. brian m. carlsonFeb 21, 2019
  15. Ævar Arnfjörð BjarmasonFeb 22, 2019
  16. Junio C HamanoDec 5, 2018
  17. Junio C HamanoDec 5, 2018
  18. Jonathan TanDec 6, 2018
  19. Ævar Arnfjörð BjarmasonFeb 19, 2019
  20. Jonathan TanFeb 19, 2019
  21. 3/5 upload-pack: refactor reading of pack-objects outJonathan Tan, Dec 3, 2018
  22. Stefan BellerDec 4, 2018
  23. Junio C HamanoDec 5, 2018
  24. 4/5 upload-pack: refactor writing of "packfile" lineJonathan Tan, Dec 3, 2018
  25. Junio C HamanoDec 6, 2018
  26. Jonathan TanDec 6, 2018
  27. Junio C HamanoDec 7, 2018
  28. 5/5 upload-pack: send part of packfile response as uriJonathan Tan, Dec 3, 2018
  29. Stefan BellerDec 4, 2018
  30. Stefan BellerDec 4, 2018

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.