}
}
-static int unuse_one_window(struct packed_git *current, int keep_fd)
+static int unuse_one_window(struct packed_git *current)
{
struct packed_git *p, *lru_p = NULL;
struct pack_window *lru_w = NULL, *lru_l = NULL;
pack_mapped -= lru_w->len;
if (lru_l)
lru_l->next = lru_w->next;
- else {
+ else
lru_p->windows = lru_w->next;
- if (!lru_p->windows && lru_p->pack_fd != -1
- && lru_p->pack_fd != keep_fd) {
- close(lru_p->pack_fd);
- pack_open_fds--;
- lru_p->pack_fd = -1;
- }
- }
free(lru_w);
pack_open_windows--;
return 1;
return 0;
}
-void release_pack_memory(size_t need, int fd)
+void release_pack_memory(size_t need)
{
size_t cur = pack_mapped;
- while (need >= (cur - pack_mapped) && unuse_one_window(NULL, fd))
+ while (need >= (cur - pack_mapped) && unuse_one_window(NULL))
; /* nothing */
}
if (ret == MAP_FAILED) {
if (!length)
return NULL;
- release_pack_memory(length, fd);
+ release_pack_memory(length);
ret = mmap(start, length, prot, flags, fd, offset);
if (ret == MAP_FAILED)
die_errno("Out of memory? mmap failed");
}
}
+/*
+ * The LRU pack is the one with the oldest MRU window, preferring packs
+ * with no used windows, or the oldest mtime if it has no windows allocated.
+ */
+static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struct pack_window **mru_w, int *accept_windows_inuse)
+{
+ struct pack_window *w, *this_mru_w;
+ int has_windows_inuse = 0;
+
+ /*
+ * Reject this pack if it has windows and the previously selected
+ * one does not. If this pack does not have windows, reject
+ * it if the pack file is newer than the previously selected one.
+ */
+ if (*lru_p && !*mru_w && (p->windows || p->mtime > (*lru_p)->mtime))
+ return;
+
+ for (w = this_mru_w = p->windows; w; w = w->next) {
+ /*
+ * Reject this pack if any of its windows are in use,
+ * but the previously selected pack did not have any
+ * inuse windows. Otherwise, record that this pack
+ * has windows in use.
+ */
+ if (w->inuse_cnt) {
+ if (*accept_windows_inuse)
+ has_windows_inuse = 1;
+ else
+ return;
+ }
+
+ if (w->last_used > this_mru_w->last_used)
+ this_mru_w = w;
+
+ /*
+ * Reject this pack if it has windows that have been
+ * used more recently than the previously selected pack.
+ * If the previously selected pack had windows inuse and
+ * we have not encountered a window in this pack that is
+ * inuse, skip this check since we prefer a pack with no
+ * inuse windows to one that has inuse windows.
+ */
+ if (*mru_w && *accept_windows_inuse == has_windows_inuse &&
+ this_mru_w->last_used > (*mru_w)->last_used)
+ return;
+ }
+
+ /*
+ * Select this pack.
+ */
+ *mru_w = this_mru_w;
+ *lru_p = p;
+ *accept_windows_inuse = has_windows_inuse;
+}
+
+static int close_one_pack(void)
+{
+ struct packed_git *p, *lru_p = NULL;
+ struct pack_window *mru_w = NULL;
+ int accept_windows_inuse = 1;
+
+ for (p = packed_git; p; p = p->next) {
+ if (p->pack_fd == -1)
+ continue;
+ find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse);
+ }
+
+ if (lru_p) {
+ close(lru_p->pack_fd);
+ pack_open_fds--;
+ lru_p->pack_fd = -1;
+ return 1;
+ }
+
+ return 0;
+}
+
void unuse_pack(struct pack_window **w_cursor)
{
struct pack_window *w = *w_cursor;
static unsigned int get_max_fd_limit(void)
{
#ifdef RLIMIT_NOFILE
- struct rlimit lim;
+ {
+ struct rlimit lim;
- if (getrlimit(RLIMIT_NOFILE, &lim))
- die_errno("cannot get RLIMIT_NOFILE");
+ if (!getrlimit(RLIMIT_NOFILE, &lim))
+ return lim.rlim_cur;
+ }
+#endif
- return lim.rlim_cur;
-#elif defined(_SC_OPEN_MAX)
- return sysconf(_SC_OPEN_MAX);
-#elif defined(OPEN_MAX)
+#ifdef _SC_OPEN_MAX
+ {
+ long open_max = sysconf(_SC_OPEN_MAX);
+ if (0 < open_max)
+ return open_max;
+ /*
+ * Otherwise, we got -1 for one of the two
+ * reasons:
+ *
+ * (1) sysconf() did not understand _SC_OPEN_MAX
+ * and signaled an error with -1; or
+ * (2) sysconf() said there is no limit.
+ *
+ * We _could_ clear errno before calling sysconf() to
+ * tell these two cases apart and return a huge number
+ * in the latter case to let the caller cap it to a
+ * value that is not so selfish, but letting the
+ * fallback OPEN_MAX codepath take care of these cases
+ * is a lot simpler.
+ */
+ }
+#endif
+
+#ifdef OPEN_MAX
return OPEN_MAX;
#else
return 1; /* see the caller ;-) */
pack_max_fds = 1;
}
- while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1))
+ while (pack_max_fds <= pack_open_fds && close_one_pack())
; /* nothing */
p->pack_fd = git_open_noatime(p->pack_name);
win->len = (size_t)len;
pack_mapped += win->len;
while (packed_git_limit < pack_mapped
- && unuse_one_window(p, p->pack_fd))
+ && unuse_one_window(p))
; /* nothing */
win->base = xmmap(NULL, win->len,
PROT_READ, MAP_PRIVATE,
static void try_to_free_pack_memory(size_t size)
{
- release_pack_memory(size, -1);
+ release_pack_memory(size);
}
struct packed_git *add_packed_git(const char *path, int path_len, int local)
return map;
}
-/*
- * There used to be a second loose object header format which
- * was meant to mimic the in-pack format, allowing for direct
- * copy of the object data. This format turned up not to be
- * really worth it and we no longer write loose objects in that
- * format.
- */
-static int experimental_loose_object(unsigned char *map)
-{
- unsigned int word;
-
- /*
- * We must determine if the buffer contains the standard
- * zlib-deflated stream or the experimental format based
- * on the in-pack object format. Compare the header byte
- * for each format:
- *
- * RFC1950 zlib w/ deflate : 0www1000 : 0 <= www <= 7
- * Experimental pack-based : Stttssss : ttt = 1,2,3,4
- *
- * If bit 7 is clear and bits 0-3 equal 8, the buffer MUST be
- * in standard loose-object format, UNLESS it is a Git-pack
- * format object *exactly* 8 bytes in size when inflated.
- *
- * However, RFC1950 also specifies that the 1st 16-bit word
- * must be divisible by 31 - this checksum tells us our buffer
- * is in the standard format, giving a false positive only if
- * the 1st word of the Git-pack format object happens to be
- * divisible by 31, ie:
- * ((byte0 * 256) + byte1) % 31 = 0
- * => 0ttt10000www1000 % 31 = 0
- *
- * As it happens, this case can only arise for www=3 & ttt=1
- * - ie, a Commit object, which would have to be 8 bytes in
- * size. As no Commit can be that small, we find that the
- * combination of these two criteria (bitmask & checksum)
- * can always correctly determine the buffer format.
- */
- word = (map[0] << 8) + map[1];
- if ((map[0] & 0x8F) == 0x08 && !(word % 31))
- return 0;
- else
- return 1;
-}
-
unsigned long unpack_object_header_buffer(const unsigned char *buf,
unsigned long len, enum object_type *type, unsigned long *sizep)
{
int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
{
- unsigned long size, used;
- static const char valid_loose_object_type[8] = {
- 0, /* OBJ_EXT */
- 1, 1, 1, 1, /* "commit", "tree", "blob", "tag" */
- 0, /* "delta" and others are invalid in a loose object */
- };
- enum object_type type;
-
/* Get the data stream */
memset(stream, 0, sizeof(*stream));
stream->next_in = map;
stream->next_out = buffer;
stream->avail_out = bufsiz;
- if (experimental_loose_object(map)) {
- /*
- * The old experimental format we no longer produce;
- * we can still read it.
- */
- used = unpack_object_header_buffer(map, mapsize, &type, &size);
- if (!used || !valid_loose_object_type[type])
- return -1;
- map += used;
- mapsize -= used;
-
- /* Set up the stream for the rest.. */
- stream->next_in = map;
- stream->avail_in = mapsize;
- git_inflate_init(stream);
-
- /* And generate the fake traditional header */
- stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
- typename(type), size);
- return 0;
- }
git_inflate_init(stream);
return git_inflate(stream, 0);
}
return base_offset;
}
+/*
+ * Like get_delta_base above, but we return the sha1 instead of the pack
+ * offset. This means it is cheaper for REF deltas (we do not have to do
+ * the final object lookup), but more expensive for OFS deltas (we
+ * have to load the revidx to convert the offset back into a sha1).
+ */
+static const unsigned char *get_delta_base_sha1(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t curpos,
+ enum object_type type,
+ off_t delta_obj_offset)
+{
+ if (type == OBJ_REF_DELTA) {
+ unsigned char *base = use_pack(p, w_curs, curpos, NULL);
+ return base;
+ } else if (type == OBJ_OFS_DELTA) {
+ struct revindex_entry *revidx;
+ off_t base_offset = get_delta_base(p, w_curs, &curpos,
+ type, delta_obj_offset);
+
+ if (!base_offset)
+ return NULL;
+
+ revidx = find_pack_revindex(p, base_offset);
+ if (!revidx)
+ return NULL;
+
+ return nth_packed_object_sha1(p, revidx->nr);
+ } else
+ return NULL;
+}
+
int unpack_object_header(struct packed_git *p,
struct pack_window **w_curs,
off_t *curpos,
}
}
+ if (oi->delta_base_sha1) {
+ if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+ const unsigned char *base;
+
+ base = get_delta_base_sha1(p, &w_curs, curpos,
+ type, obj_offset);
+ if (!base) {
+ type = OBJ_BAD;
+ goto out;
+ }
+
+ hashcpy(oi->delta_base_sha1, base);
+ } else
+ hashclr(oi->delta_base_sha1);
+ }
+
out:
unuse_pack(&w_curs);
return type;
int i;
struct delta_base_cache_entry *ent;
+ ent = get_delta_base_cache_entry(p, curpos);
+ if (eq_delta_base_cache_entry(ent, p, curpos)) {
+ type = ent->type;
+ data = ent->data;
+ size = ent->size;
+ clear_delta_base_cache_entry(ent);
+ base_from_cache = 1;
+ break;
+ }
+
if (do_check_packed_object_crc && p->index_version > 1) {
struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
unsigned long len = revidx[1].offset - obj_offset;
}
}
- ent = get_delta_base_cache_entry(p, curpos);
- if (eq_delta_base_cache_entry(ent, p, curpos)) {
- type = ent->type;
- data = ent->data;
- size = ent->size;
- clear_delta_base_cache_entry(ent);
- base_from_cache = 1;
- break;
- }
-
type = unpack_object_header(p, &w_curs, &curpos, &size);
if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA)
break;
git_zstream stream;
char hdr[32];
+ if (oi->delta_base_sha1)
+ hashclr(oi->delta_base_sha1);
+
/*
* If we don't care about type or size, then we don't
- * need to look inside the object at all.
+ * need to look inside the object at all. Note that we
+ * do not optimize out the stat call, even if the
+ * caller doesn't care about the disk-size, since our
+ * return value implicitly indicates whether the
+ * object even exists.
*/
if (!oi->typep && !oi->sizep) {
- if (oi->disk_sizep) {
- struct stat st;
- if (stat_sha1_file(sha1, &st) < 0)
- return -1;
+ struct stat st;
+ if (stat_sha1_file(sha1, &st) < 0)
+ return -1;
+ if (oi->disk_sizep)
*oi->disk_sizep = st.st_size;
- }
return 0;
}
return 0;
}
-/* returns enum object_type or negative */
-int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi)
+int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi, unsigned flags)
{
struct cached_object *co;
struct pack_entry e;
int rtype;
+ const unsigned char *real = lookup_replace_object_extended(sha1, flags);
- co = find_cached_object(sha1);
+ co = find_cached_object(real);
if (co) {
if (oi->typep)
*(oi->typep) = co->type;
*(oi->sizep) = co->size;
if (oi->disk_sizep)
*(oi->disk_sizep) = 0;
+ if (oi->delta_base_sha1)
+ hashclr(oi->delta_base_sha1);
oi->whence = OI_CACHED;
return 0;
}
- if (!find_pack_entry(sha1, &e)) {
+ if (!find_pack_entry(real, &e)) {
/* Most likely it's a loose object. */
- if (!sha1_loose_object_info(sha1, oi)) {
+ if (!sha1_loose_object_info(real, oi)) {
oi->whence = OI_LOOSE;
return 0;
}
/* Not a loose object; someone else may have just packed it. */
reprepare_packed_git();
- if (!find_pack_entry(sha1, &e))
+ if (!find_pack_entry(real, &e))
return -1;
}
rtype = packed_object_info(e.p, e.offset, oi);
if (rtype < 0) {
- mark_bad_packed_object(e.p, sha1);
- return sha1_object_info_extended(sha1, oi);
+ mark_bad_packed_object(e.p, real);
+ return sha1_object_info_extended(real, oi, 0);
} else if (in_delta_base_cache(e.p, e.offset)) {
oi->whence = OI_DBCACHED;
} else {
return 0;
}
+/* returns enum object_type or negative */
int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
{
enum object_type type;
oi.typep = &type;
oi.sizep = sizep;
- if (sha1_object_info_extended(sha1, &oi) < 0)
+ if (sha1_object_info_extended(sha1, &oi, LOOKUP_REPLACE_OBJECT) < 0)
return -1;
return type;
}
void *data;
char *path;
const struct packed_git *p;
- const unsigned char *repl = (flag & READ_SHA1_FILE_REPLACE)
- ? lookup_replace_object(sha1) : sha1;
+ const unsigned char *repl = lookup_replace_object_extended(sha1, flag);
errno = 0;
data = read_object(repl, type, size);