pack-mtimes: support reading .mtimes files

To store the individual mtimes of objects in a cruft pack, introduce a
new `.mtimes` format that can optionally accompany a single pack in the
repository.

The format is defined in Documentation/technical/pack-format.txt, and
stores a 4-byte network order timestamp for each object in name (index)
order.

This patch prepares for cruft packs by defining the `.mtimes` format,
and introducing a basic API that callers can use to read out individual
mtimes.

Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

Documentation/technical/pack-format.txt

@@ -294,6 +294,25 @@ Pack file entry: <+
 
 All 4-byte numbers are in network order.
 
+== pack-*.mtimes files have the format:
+
+All 4-byte numbers are in network byte order.
+
+  - A 4-byte magic number '0x4d544d45' ('MTME').
+
+  - A 4-byte version identifier (= 1).
+
+  - A 4-byte hash function identifier (= 1 for SHA-1, 2 for SHA-256).
+
+  - A table of 4-byte unsigned integers. The ith value is the
+    modification time (mtime) of the ith object in the corresponding
+    pack by lexicographic (index) order. The mtimes count standard
+    epoch seconds.
+
+  - A trailer, containing a checksum of the corresponding packfile,
+    and a checksum of all of the above (each having length according
+    to the specified hash function).
+
 == multi-pack-index (MIDX) files have the following format:
 
 The multi-pack-index files refer to multiple pack-files and loose objects.

Makefile

@@ -993,6 +993,7 @@ LIB_OBJS += oidtree.o
 LIB_OBJS += pack-bitmap-write.o
 LIB_OBJS += pack-bitmap.o
 LIB_OBJS += pack-check.o
+LIB_OBJS += pack-mtimes.o
 LIB_OBJS += pack-objects.o
 LIB_OBJS += pack-revindex.o
 LIB_OBJS += pack-write.o

builtin/repack.c

@@ -217,6 +217,7 @@ static struct {
 } exts[] = {
 	{".pack"},
 	{".rev", 1},
+	{".mtimes", 1},
 	{".bitmap", 1},
 	{".promisor", 1},
 	{".idx"},

object-store.h

@@ -115,12 +115,20 @@ struct packed_git {
 		 freshened:1,
 		 do_not_close:1,
 		 pack_promisor:1,
-		 multi_pack_index:1;
+		 multi_pack_index:1,
+		 is_cruft:1;
 	unsigned char hash[GIT_MAX_RAWSZ];
 	struct revindex_entry *revindex;
 	const uint32_t *revindex_data;
 	const uint32_t *revindex_map;
 	size_t revindex_size;
+	/*
+	 * mtimes_map points at the beginning of the memory mapped region of
+	 * this pack's corresponding .mtimes file, and mtimes_size is the size
+	 * of that .mtimes file
+	 */
+	const uint32_t *mtimes_map;
+	size_t mtimes_size;
 	/* something like ".git/objects/pack/xxxxx.pack" */
 	char pack_name[FLEX_ARRAY]; /* more */
 };

pack-mtimes.c

@@ -0,0 +1,129 @@
+#include "git-compat-util.h"
+#include "pack-mtimes.h"
+#include "object-store.h"
+#include "packfile.h"
+
+static char *pack_mtimes_filename(struct packed_git *p)
+{
+	size_t len;
+	if (!strip_suffix(p->pack_name, ".pack", &len))
+		BUG("pack_name does not end in .pack");
+	return xstrfmt("%.*s.mtimes", (int)len, p->pack_name);
+}
+
+#define MTIMES_HEADER_SIZE (12)
+
+struct mtimes_header {
+	uint32_t signature;
+	uint32_t version;
+	uint32_t hash_id;
+};
+
+static int load_pack_mtimes_file(char *mtimes_file,
+				 uint32_t num_objects,
+				 const uint32_t **data_p, size_t *len_p)
+{
+	int fd, ret = 0;
+	struct stat st;
+	uint32_t *data = NULL;
+	size_t mtimes_size, expected_size;
+	struct mtimes_header header;
+
+	fd = git_open(mtimes_file);
+
+	if (fd < 0) {
+		ret = -1;
+		goto cleanup;
+	}
+	if (fstat(fd, &st)) {
+		ret = error_errno(_("failed to read %s"), mtimes_file);
+		goto cleanup;
+	}
+
+	mtimes_size = xsize_t(st.st_size);
+
+	if (mtimes_size < MTIMES_HEADER_SIZE) {
+		ret = error(_("mtimes file %s is too small"), mtimes_file);
+		goto cleanup;
+	}
+
+	data = xmmap(NULL, mtimes_size, PROT_READ, MAP_PRIVATE, fd, 0);
+
+	header.signature = ntohl(data[0]);
+	header.version = ntohl(data[1]);
+	header.hash_id = ntohl(data[2]);
+
+	if (header.signature != MTIMES_SIGNATURE) {
+		ret = error(_("mtimes file %s has unknown signature"), mtimes_file);
+		goto cleanup;
+	}
+
+	if (header.version != 1) {
+		ret = error(_("mtimes file %s has unsupported version %"PRIu32),
+			    mtimes_file, header.version);
+		goto cleanup;
+	}
+
+	if (!(header.hash_id == 1 || header.hash_id == 2)) {
+		ret = error(_("mtimes file %s has unsupported hash id %"PRIu32),
+			    mtimes_file, header.hash_id);
+		goto cleanup;
+	}
+
+
+	expected_size = MTIMES_HEADER_SIZE;
+	expected_size = st_add(expected_size, st_mult(sizeof(uint32_t), num_objects));
+	expected_size = st_add(expected_size, 2 * (header.hash_id == 1 ? GIT_SHA1_RAWSZ : GIT_SHA256_RAWSZ));
+
+	if (mtimes_size != expected_size) {
+		ret = error(_("mtimes file %s is corrupt"), mtimes_file);
+		goto cleanup;
+	}
+
+cleanup:
+	if (ret) {
+		if (data)
+			munmap(data, mtimes_size);
+	} else {
+		*len_p = mtimes_size;
+		*data_p = data;
+	}
+
+	close(fd);
+	return ret;
+}
+
+int load_pack_mtimes(struct packed_git *p)
+{
+	char *mtimes_name = NULL;
+	int ret = 0;
+
+	if (!p->is_cruft)
+		return ret; /* not a cruft pack */
+	if (p->mtimes_map)
+		return ret; /* already loaded */
+
+	ret = open_pack_index(p);
+	if (ret < 0)
+		goto cleanup;
+
+	mtimes_name = pack_mtimes_filename(p);
+	ret = load_pack_mtimes_file(mtimes_name,
+				    p->num_objects,
+				    &p->mtimes_map,
+				    &p->mtimes_size);
+cleanup:
+	free(mtimes_name);
+	return ret;
+}
+
+uint32_t nth_packed_mtime(struct packed_git *p, uint32_t pos)
+{
+	if (!p->mtimes_map)
+		BUG("pack .mtimes file not loaded for %s", p->pack_name);
+	if (p->num_objects <= pos)
+		BUG("pack .mtimes out-of-bounds (%"PRIu32" vs %"PRIu32")",
+		    pos, p->num_objects);
+
+	return get_be32(p->mtimes_map + pos + 3);
+}

pack-mtimes.h

@@ -0,0 +1,26 @@
+#ifndef PACK_MTIMES_H
+#define PACK_MTIMES_H
+
+#include "git-compat-util.h"
+
+#define MTIMES_SIGNATURE 0x4d544d45 /* "MTME" */
+#define MTIMES_VERSION 1
+
+struct packed_git;
+
+/*
+ * Loads the .mtimes file corresponding to "p", if any, returning zero
+ * on success.
+ */
+int load_pack_mtimes(struct packed_git *p);
+
+/* Returns the mtime associated with the object at position "pos" (in
+ * lexicographic/index order) in pack "p".
+ *
+ * Note that it is a BUG() to call this function if either (a) "p" does
+ * not have a corresponding .mtimes file, or (b) it does, but it hasn't
+ * been loaded
+ */
+uint32_t nth_packed_mtime(struct packed_git *p, uint32_t pos);
+
+#endif

packfile.c

@@ -334,12 +334,22 @@ static void close_pack_revindex(struct packed_git *p)
 	p->revindex_data = NULL;
 }
 
+static void close_pack_mtimes(struct packed_git *p)
+{
+	if (!p->mtimes_map)
+		return;
+
+	munmap((void *)p->mtimes_map, p->mtimes_size);
+	p->mtimes_map = NULL;
+}
+
 void close_pack(struct packed_git *p)
 {
 	close_pack_windows(p);
 	close_pack_fd(p);
 	close_pack_index(p);
 	close_pack_revindex(p);
+	close_pack_mtimes(p);
 	oidset_clear(&p->bad_objects);
 }
 
@@ -363,7 +373,7 @@ void close_object_store(struct raw_object_store *o)
 
 void unlink_pack_path(const char *pack_name, int force_delete)
 {
-	static const char *exts[] = {".pack", ".idx", ".rev", ".keep", ".bitmap", ".promisor"};
+	static const char *exts[] = {".pack", ".idx", ".rev", ".keep", ".bitmap", ".promisor", ".mtimes"};
 	int i;
 	struct strbuf buf = STRBUF_INIT;
 	size_t plen;
@@ -718,6 +728,10 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
 	if (!access(p->pack_name, F_OK))
 		p->pack_promisor = 1;
 
+	xsnprintf(p->pack_name + path_len, alloc - path_len, ".mtimes");
+	if (!access(p->pack_name, F_OK))
+		p->is_cruft = 1;
+
 	xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack");
 	if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
 		free(p);
@@ -869,7 +883,8 @@ static void prepare_pack(const char *full_name, size_t full_name_len,
 	    ends_with(file_name, ".pack") ||
 	    ends_with(file_name, ".bitmap") ||
 	    ends_with(file_name, ".keep") ||
-	    ends_with(file_name, ".promisor"))
+	    ends_with(file_name, ".promisor") ||
+	    ends_with(file_name, ".mtimes"))
 		string_list_append(data->garbage, full_name);
 	else
 		report_garbage(PACKDIR_FILE_GARBAGE, full_name);