pkt-line: support tracing verbatim pack contents

When debugging the pack protocol, it is sometimes useful to
store the verbatim pack that we sent or received on the
wire. Looking at the on-disk result is often not helpful for
a few reasons:

  1. If the operation is a clone, we destroy the repo on
     failure, leaving nothing on disk.

  2. If the pack is small, we unpack it immediately, and the
     full pack never hits the disk.

  3. If we feed the pack to "index-pack --fix-thin", the
     resulting pack has the extra delta bases added to it.

We already have a GIT_TRACE_PACKET mechanism for tracing
packets. Let's extend it with GIT_TRACE_PACKFILE to dump the
verbatim packfile.

There are a few other positive fallouts that come from
rearranging this code:

 - We currently disable the packet trace after seeing the
   PACK header, even though we may get human-readable lines
   on other sidebands; now we include them in the trace.

 - We currently try to print "PACK ..." in the trace to
   indicate that the packfile has started. But because we
   disable packet tracing, we never printed this line. We
   will now do so.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git.txt

@@ -1000,9 +1000,20 @@ Unsetting the variable, or setting it to empty, "0" or
 	Enables trace messages for all packets coming in or out of a
 	given program. This can help with debugging object negotiation
 	or other protocol issues. Tracing is turned off at a packet
-	starting with "PACK".
+	starting with "PACK" (but see 'GIT_TRACE_PACKFILE' below).
 	See 'GIT_TRACE' for available trace output options.
 
+'GIT_TRACE_PACKFILE'::
+	Enables tracing of packfiles sent or received by a
+	given program. Unlike other trace output, this trace is
+	verbatim: no headers, and no quoting of binary data. You almost
+	certainly want to direct into a file (e.g.,
+	`GIT_TRACE_PACKFILE=/tmp/my.pack`) rather than displaying it on
+	the terminal or mixing it with other trace output.
++
+Note that this is currently only implemented for the client side
+of clones and fetches.
+
 'GIT_TRACE_PERFORMANCE'::
 	Enables performance related trace messages, e.g. total execution
 	time of each Git command.

pkt-line.c

@@ -4,16 +4,51 @@
 char packet_buffer[LARGE_PACKET_MAX];
 static const char *packet_trace_prefix = "git";
 static struct trace_key trace_packet = TRACE_KEY_INIT(PACKET);
+static struct trace_key trace_pack = TRACE_KEY_INIT(PACKFILE);
 
 void packet_trace_identity(const char *prog)
 {
 	packet_trace_prefix = xstrdup(prog);
 }
 
+static int packet_trace_pack(const char *buf, unsigned int len, int sideband)
+{
+	if (!sideband) {
+		trace_verbatim(&trace_pack, buf, len);
+		return 1;
+	} else if (len && *buf == '\1') {
+		trace_verbatim(&trace_pack, buf + 1, len - 1);
+		return 1;
+	} else {
+		/* it's another non-pack sideband */
+		return 0;
+	}
+}
+
 static void packet_trace(const char *buf, unsigned int len, int write)
 {
 	int i;
 	struct strbuf out;
+	static int in_pack, sideband;
+
+	if (!trace_want(&trace_packet) && !trace_want(&trace_pack))
+		return;
+
+	if (in_pack) {
+		if (packet_trace_pack(buf, len, sideband))
+			return;
+	} else if (starts_with(buf, "PACK") || starts_with(buf, "\1PACK")) {
+		in_pack = 1;
+		sideband = *buf == '\1';
+		packet_trace_pack(buf, len, sideband);
+
+		/*
+		 * Make a note in the human-readable trace that the pack data
+		 * started.
+		 */
+		buf = "PACK ...";
+		len = strlen(buf);
+	}
 
 	if (!trace_want(&trace_packet))
 		return;
@@ -24,21 +59,15 @@ static void packet_trace(const char *buf, unsigned int len, int write)
 	strbuf_addf(&out, "packet: %12s%c ",
 		    packet_trace_prefix, write ? '>' : '<');
 
-	if (starts_with(buf, "PACK") || starts_with(buf, "\1PACK")) {
-		strbuf_addstr(&out, "PACK ...");
-		trace_disable(&trace_packet);
-	}
-	else {
-		/* XXX we should really handle printable utf8 */
-		for (i = 0; i < len; i++) {
-			/* suppress newlines */
-			if (buf[i] == '\n')
-				continue;
-			if (buf[i] >= 0x20 && buf[i] <= 0x7e)
-				strbuf_addch(&out, buf[i]);
-			else
-				strbuf_addf(&out, "\\%o", buf[i]);
-		}
+	/* XXX we should really handle printable utf8 */
+	for (i = 0; i < len; i++) {
+		/* suppress newlines */
+		if (buf[i] == '\n')
+			continue;
+		if (buf[i] >= 0x20 && buf[i] <= 0x7e)
+			strbuf_addch(&out, buf[i]);
+		else
+			strbuf_addf(&out, "\\%o", buf[i]);
 	}
 
 	strbuf_addch(&out, '\n');

t/t5601-clone.sh

@@ -496,4 +496,11 @@ test_expect_success 'shallow clone locally' '
 	( cd ddsstt && git fsck )
 '
 
+test_expect_success 'GIT_TRACE_PACKFILE produces a usable pack' '
+	rm -rf dst.git &&
+	GIT_TRACE_PACKFILE=$PWD/tmp.pack git clone --no-local --bare src dst.git &&
+	git init --bare replay.git &&
+	git -C replay.git index-pack -v --stdin <tmp.pack
+'
+
 test_done

trace.c

@@ -120,6 +120,13 @@ static int prepare_trace_line(const char *file, int line,
 	return 1;
 }
 
+void trace_verbatim(struct trace_key *key, const void *buf, unsigned len)
+{
+	if (!trace_want(key))
+		return;
+	write_or_whine_pipe(get_trace_fd(key), buf, len, err_msg);
+}
+
 static void print_trace_line(struct trace_key *key, struct strbuf *buf)
 {
 	strbuf_complete_line(buf);

trace.h

@@ -18,6 +18,7 @@ extern int trace_want(struct trace_key *key);
 extern void trace_disable(struct trace_key *key);
 extern uint64_t getnanotime(void);
 extern void trace_command_performance(const char **argv);
+extern void trace_verbatim(struct trace_key *key, const void *buf, unsigned len);
 
 #ifndef HAVE_VARIADIC_MACROS