Teach receive-pack how to keep pack files based on object count.

Since keeping a pushed pack or exploding it into loose objects
should be a local repository decision this teaches receive-pack
to decide if it should call unpack-objects or index-pack --stdin
--fix-thin based on the setting of receive.unpackLimit and the
number of objects contained in the received pack.

If the number of objects (hdr_entries) in the received pack is
below the value of receive.unpackLimit (which is 5000 by default)
then we unpack-objects as we have in the past.

If the hdr_entries >= receive.unpackLimit then we call index-pack and
ask it to include our pid and hostname in the .keep file to make it
easier to identify why a given pack has been kept in the repository.

Currently this leaves every received pack as a kept pack.  We really
don't want that as received packs will tend to be small.  Instead we
want to delete the .keep file automatically after all refs have
been updated.  That is being left as room for future improvement.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

1 files changed, 79 insertions, 19 deletions

diff --git a/receive-pack.c b/receive-pack.c
index ed08660da4..b8d12700d8 100644
--- a/receive-pack.c
+++ b/receive-pack.c
@@ -1,4 +1,5 @@
 #include "cache.h"
+#include "pack.h"
 #include "refs.h"
 #include "pkt-line.h"
 #include "run-command.h"
@@ -7,9 +8,8 @@
 
 static const char receive_pack_usage[] = "git-receive-pack <git-dir>";
 
-static const char *unpacker[] = { "unpack-objects", NULL };
-
 static int deny_non_fast_forwards = 0;
+static int unpack_limit = 5000;
 static int report_status;
 
 static char capabilities[] = "report-status";
@@ -25,6 +25,12 @@ static int receive_pack_config(const char *var, const char *value)
 		return 0;
 	}
 
+	if (strcmp(var, "receive.unpacklimit") == 0)
+	{
+		unpack_limit = git_config_int(var, value);
+		return 0;
+	}
+
 	return 0;
 }
 
@@ -227,27 +233,81 @@ static void read_head_info(void)
 	}
 }
 
+static const char *parse_pack_header(struct pack_header *hdr)
+{
+	char *c = (char*)hdr;
+	ssize_t remaining = sizeof(struct pack_header);
+	do {
+		ssize_t r = xread(0, c, remaining);
+		if (r <= 0)
+			return "eof before pack header was fully read";
+		remaining -= r;
+		c += r;
+	} while (remaining > 0);
+	if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
+		return "protocol error (pack signature mismatch detected)";
+	if (!pack_version_ok(hdr->hdr_version))
+		return "protocol error (pack version unsupported)";
+	return NULL;
+}
+
 static const char *unpack(void)
 {
-	int code = run_command_v_opt(1, unpacker, RUN_GIT_CMD);
+	struct pack_header hdr;
+	const char *hdr_err;
+	char hdr_arg[38];
+	int code;
+
+	hdr_err = parse_pack_header(&hdr);
+	if (hdr_err)
+		return hdr_err;
+	snprintf(hdr_arg, sizeof(hdr_arg), "--pack_header=%u,%u",
+			ntohl(hdr.hdr_version), ntohl(hdr.hdr_entries));
+
+	if (ntohl(hdr.hdr_entries) < unpack_limit) {
+		const char *unpacker[3];
+		unpacker[0] = "unpack-objects";
+		unpacker[1] = hdr_arg;
+		unpacker[2] = NULL;
+		code = run_command_v_opt(1, unpacker, RUN_GIT_CMD);
+	} else {
+		const char *keeper[6];
+		char my_host[255], keep_arg[128 + 255];
+
+		if (gethostname(my_host, sizeof(my_host)))
+			strcpy(my_host, "localhost");
+		snprintf(keep_arg, sizeof(keep_arg),
+				"--keep=receive-pack %i on %s",
+				getpid(), my_host);
+
+		keeper[0] = "index-pack";
+		keeper[1] = "--stdin";
+		keeper[2] = "--fix-thin";
+		keeper[3] = hdr_arg;
+		keeper[4] = keep_arg;
+		keeper[5] = NULL;
+		code = run_command_v_opt(1, keeper, RUN_GIT_CMD);
+		if (!code)
+			reprepare_packed_git();
+	}
 
 	switch (code) {
-	case 0:
-		return NULL;
-	case -ERR_RUN_COMMAND_FORK:
-		return "unpack fork failed";
-	case -ERR_RUN_COMMAND_EXEC:
-		return "unpack execute failed";
-	case -ERR_RUN_COMMAND_WAITPID:
-		return "waitpid failed";
-	case -ERR_RUN_COMMAND_WAITPID_WRONG_PID:
-		return "waitpid is confused";
-	case -ERR_RUN_COMMAND_WAITPID_SIGNAL:
-		return "unpacker died of signal";
-	case -ERR_RUN_COMMAND_WAITPID_NOEXIT:
-		return "unpacker died strangely";
-	default:
-		return "unpacker exited with error code";
+		case 0:
+			return NULL;
+		case -ERR_RUN_COMMAND_FORK:
+			return "unpack fork failed";
+		case -ERR_RUN_COMMAND_EXEC:
+			return "unpack execute failed";
+		case -ERR_RUN_COMMAND_WAITPID:
+			return "waitpid failed";
+		case -ERR_RUN_COMMAND_WAITPID_WRONG_PID:
+			return "waitpid is confused";
+		case -ERR_RUN_COMMAND_WAITPID_SIGNAL:
+			return "unpacker died of signal";
+		case -ERR_RUN_COMMAND_WAITPID_NOEXIT:
+			return "unpacker died strangely";
+		default:
+			return "unpacker exited with error code";
 	}
 }