#include "mergesort.h"
#include "packfile.h"
#include "delta.h"
-#include "list.h"
#include "streaming.h"
#include "sha1-lookup.h"
#include "commit.h"
#include "tree.h"
#include "object-store.h"
#include "midx.h"
+#include "commit-graph.h"
+#include "promisor-remote.h"
char *odb_pack_name(struct strbuf *buf,
- const unsigned char *sha1,
+ const unsigned char *hash,
const char *ext)
{
strbuf_reset(buf);
strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(),
- sha1_to_hex(sha1), ext);
+ hash_to_hex(hash), ext);
return buf->buf;
}
struct packed_git *p = alloc_packed_git(alloc);
memcpy(p->pack_name, path, alloc); /* includes NUL */
- hashcpy(p->sha1, sha1);
+ hashcpy(p->hash, sha1);
if (check_packed_git_idx(idx_path, p)) {
free(p);
return NULL;
return 0;
}
-void release_pack_memory(size_t need)
-{
- size_t cur = pack_mapped;
- while (need >= (cur - pack_mapped) && unuse_one_window(NULL))
- ; /* nothing */
-}
-
void close_pack_windows(struct packed_git *p)
{
while (p->windows) {
}
}
-static int close_pack_fd(struct packed_git *p)
+int close_pack_fd(struct packed_git *p)
{
if (p->pack_fd < 0)
return 0;
close_pack_index(p);
}
-void close_all_packs(struct raw_object_store *o)
+void close_object_store(struct raw_object_store *o)
{
struct packed_git *p;
close_midx(o->multi_pack_index);
o->multi_pack_index = NULL;
}
+
+ close_commit_graph(o);
+}
+
+void unlink_pack_path(const char *pack_name, int force_delete)
+{
+ static const char *exts[] = {".pack", ".idx", ".keep", ".bitmap", ".promisor"};
+ int i;
+ struct strbuf buf = STRBUF_INIT;
+ size_t plen;
+
+ strbuf_addstr(&buf, pack_name);
+ strip_suffix_mem(buf.buf, &buf.len, ".pack");
+ plen = buf.len;
+
+ if (!force_delete) {
+ strbuf_addstr(&buf, ".keep");
+ if (!access(buf.buf, F_OK)) {
+ strbuf_release(&buf);
+ return;
+ }
+ }
+
+ for (i = 0; i < ARRAY_SIZE(exts); i++) {
+ strbuf_setlen(&buf, plen);
+ strbuf_addstr(&buf, exts[i]);
+ unlink(buf.buf);
+ }
+
+ strbuf_release(&buf);
}
/*
#endif
}
+const char *pack_basename(struct packed_git *p)
+{
+ const char *ret = strrchr(p->pack_name, '/');
+ if (ret)
+ ret = ret + 1; /* skip past slash */
+ else
+ ret = p->pack_name; /* we only have a base */
+ return ret;
+}
+
/*
* Do not call this directly as this leaks p->pack_fd on error return;
* call open_packed_git() instead.
struct pack_header hdr;
unsigned char hash[GIT_MAX_RAWSZ];
unsigned char *idx_hash;
- long fd_flag;
ssize_t read_result;
const unsigned hashsz = the_hash_algo->rawsz;
if (!p->index_data) {
struct multi_pack_index *m;
- const char *pack_name = strrchr(p->pack_name, '/');
+ const char *pack_name = pack_basename(p);
for (m = the_repository->objects->multi_pack_index;
m; m = m->next) {
} else if (p->pack_size != st.st_size)
return error("packfile %s size changed", p->pack_name);
- /* We leave these file descriptors open with sliding mmap;
- * there is no point keeping them open across exec(), though.
- */
- fd_flag = fcntl(p->pack_fd, F_GETFD, 0);
- if (fd_flag < 0)
- return error("cannot determine file descriptor flags");
- fd_flag |= FD_CLOEXEC;
- if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1)
- return error("cannot set FD_CLOEXEC");
-
/* Verify we recognize this pack file format. */
read_result = read_in_full(p->pack_fd, &hdr, sizeof(hdr));
if (read_result < 0)
" while index indicates %"PRIu32" objects",
p->pack_name, ntohl(hdr.hdr_entries),
p->num_objects);
- if (lseek(p->pack_fd, p->pack_size - hashsz, SEEK_SET) == -1)
- return error("end of packfile %s is unavailable", p->pack_name);
- read_result = read_in_full(p->pack_fd, hash, hashsz);
+ read_result = pread_in_full(p->pack_fd, hash, hashsz,
+ p->pack_size - hashsz);
if (read_result < 0)
return error_errno("error reading from %s", p->pack_name);
if (read_result != hashsz)
while (packed_git_limit < pack_mapped
&& unuse_one_window(p))
; /* nothing */
- win->base = xmmap(NULL, win->len,
+ win->base = xmmap_gently(NULL, win->len,
PROT_READ, MAP_PRIVATE,
p->pack_fd, win->offset);
if (win->base == MAP_FAILED)
}
}
-static void try_to_free_pack_memory(size_t size)
-{
- release_pack_memory(size);
-}
-
struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
{
- static int have_set_try_to_free_routine;
struct stat st;
size_t alloc;
struct packed_git *p;
- if (!have_set_try_to_free_routine) {
- have_set_try_to_free_routine = 1;
- set_try_to_free_routine(try_to_free_pack_memory);
- }
-
/*
* Make sure a corresponding .pack file exists and that
* the index looks sane.
p->pack_local = local;
p->mtime = st.st_mtime;
if (path_len < the_hash_algo->hexsz ||
- get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->sha1))
- hashclr(p->sha1);
+ get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->hash))
+ hashclr(p->hash);
return p;
}
pack->next = r->objects->packed_git;
r->objects->packed_git = pack;
+
+ hashmap_entry_init(&pack->packmap_ent, strhash(pack->pack_name));
+ hashmap_add(&r->objects->pack_map, &pack->packmap_ent);
}
void (*report_garbage)(unsigned seen_bits, const char *path);
if (strip_suffix_mem(full_name, &base_len, ".idx") &&
!(data->m && midx_contains_pack(data->m, file_name))) {
- /* Don't reopen a pack we already have. */
- for (p = data->r->objects->packed_git; p; p = p->next) {
- size_t len;
- if (strip_suffix(p->pack_name, ".pack", &len) &&
- len == base_len &&
- !memcmp(p->pack_name, full_name, len))
- break;
- }
+ struct hashmap_entry hent;
+ char *pack_name = xstrfmt("%.*s.pack", (int)base_len, full_name);
+ unsigned int hash = strhash(pack_name);
+ hashmap_entry_init(&hent, hash);
- if (!p) {
+ /* Don't reopen a pack we already have. */
+ if (!hashmap_get(&data->r->objects->pack_map, &hent, pack_name)) {
p = add_packed_git(full_name, full_name_len, data->local);
if (p)
install_packed_git(data->r, p);
}
+ free(pack_name);
}
if (!report_garbage)
* all unreachable objects about to be pruned, in which case they're not really
* interesting as a measure of repo size in the first place.
*/
-unsigned long approximate_object_count(void)
+unsigned long repo_approximate_object_count(struct repository *r)
{
- if (!the_repository->objects->approximate_object_count_valid) {
+ if (!r->objects->approximate_object_count_valid) {
unsigned long count;
struct multi_pack_index *m;
struct packed_git *p;
- prepare_packed_git(the_repository);
+ prepare_packed_git(r);
count = 0;
- for (m = get_multi_pack_index(the_repository); m; m = m->next)
+ for (m = get_multi_pack_index(r); m; m = m->next)
count += m->num_objects;
- for (p = the_repository->objects->packed_git; p; p = p->next) {
+ for (p = r->objects->packed_git; p; p = p->next) {
if (open_pack_index(p))
continue;
count += p->num_objects;
}
- the_repository->objects->approximate_object_count = count;
+ r->objects->approximate_object_count = count;
}
- return the_repository->objects->approximate_object_count;
+ return r->objects->approximate_object_count;
}
static void *get_next_packed_git(const void *p)
}
rearrange_packed_git(r);
- r->objects->all_packs = NULL;
-
prepare_packed_git_mru(r);
r->objects->packed_git_initialized = 1;
}
{
struct object_directory *odb;
+ obj_read_lock();
for (odb = r->objects->odb; odb; odb = odb->next)
odb_clear_loose_cache(odb);
r->objects->approximate_object_count_valid = 0;
r->objects->packed_git_initialized = 0;
prepare_packed_git(r);
+ obj_read_unlock();
}
struct packed_git *get_packed_git(struct repository *r)
struct packed_git *get_all_packs(struct repository *r)
{
- prepare_packed_git(r);
-
- if (!r->objects->all_packs) {
- struct packed_git *p = r->objects->packed_git;
- struct multi_pack_index *m;
-
- for (m = r->objects->multi_pack_index; m; m = m->next) {
- uint32_t i;
- for (i = 0; i < m->num_packs; i++) {
- if (!prepare_midx_pack(m, i)) {
- m->packs[i]->next = p;
- p = m->packs[i];
- }
- }
- }
+ struct multi_pack_index *m;
- r->objects->all_packs = p;
+ prepare_packed_git(r);
+ for (m = r->objects->multi_pack_index; m; m = m->next) {
+ uint32_t i;
+ for (i = 0; i < m->num_packs; i++)
+ prepare_midx_pack(r, m, i);
}
- return r->objects->all_packs;
+ return r->objects->packed_git;
}
struct list_head *get_packed_git_mru(struct repository *r)
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
+ /*
+ * Note: the window section returned by use_pack() must be
+ * available throughout git_inflate()'s unlocked execution. To
+ * ensure no other thread will modify the window in the
+ * meantime, we rely on the packed_window.inuse_cnt. This
+ * counter is incremented before window reading and checked
+ * before window disposal.
+ *
+ * Other worrying sections could be the call to close_pack_fd(),
+ * which can close packs even with in-use windows, and to
+ * reprepare_packed_git(). Regarding the former, mmap doc says:
+ * "closing the file descriptor does not unmap the region". And
+ * for the latter, it won't re-open already available packs.
+ */
+ obj_read_unlock();
st = git_inflate(&stream, Z_FINISH);
+ obj_read_lock();
curpos += stream.next_in - in;
} while ((st == Z_OK || st == Z_BUF_ERROR) &&
stream.total_out < sizeof(delta_head));
return NULL;
}
-static off_t get_delta_base(struct packed_git *p,
- struct pack_window **w_curs,
- off_t *curpos,
- enum object_type type,
- off_t delta_obj_offset)
+off_t get_delta_base(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t *curpos,
+ enum object_type type,
+ off_t delta_obj_offset)
{
unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL);
off_t base_offset;
* 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)
+static int get_delta_base_oid(struct packed_git *p,
+ struct pack_window **w_curs,
+ off_t curpos,
+ struct object_id *oid,
+ 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;
+ oidread(oid, base);
+ return 0;
} 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;
+ return -1;
revidx = find_pack_revindex(p, base_offset);
if (!revidx)
- return NULL;
+ return -1;
- return nth_packed_object_sha1(p, revidx->nr);
+ return nth_packed_object_id(oid, p, revidx->nr);
} else
- return NULL;
+ return -1;
}
static int retry_bad_packed_offset(struct repository *r,
revidx = find_pack_revindex(p, obj_offset);
if (!revidx)
return OBJ_BAD;
- nth_packed_object_oid(&oid, p, revidx->nr);
+ nth_packed_object_id(&oid, p, revidx->nr);
mark_bad_packed_object(p, oid.hash);
type = oid_object_info(r, &oid, NULL);
if (type <= OBJ_NONE)
if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) {
poi_stack_alloc = alloc_nr(poi_stack_nr);
ALLOC_ARRAY(poi_stack, poi_stack_alloc);
- memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr);
+ COPY_ARRAY(poi_stack, small_poi_stack, poi_stack_nr);
} else {
ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc);
}
};
struct delta_base_cache_entry {
- struct hashmap hash;
+ struct hashmap_entry ent;
struct delta_base_cache_key key;
struct list_head lru;
void *data;
static struct delta_base_cache_entry *
get_delta_base_cache_entry(struct packed_git *p, off_t base_offset)
{
- struct hashmap_entry entry;
+ struct hashmap_entry entry, *e;
struct delta_base_cache_key key;
if (!delta_base_cache.cmpfn)
hashmap_entry_init(&entry, pack_entry_hash(p, base_offset));
key.p = p;
key.base_offset = base_offset;
- return hashmap_get(&delta_base_cache, &entry, &key);
+ e = hashmap_get(&delta_base_cache, &entry, &key);
+ return e ? container_of(e, struct delta_base_cache_entry, ent) : NULL;
}
static int delta_base_cache_key_eq(const struct delta_base_cache_key *a,
}
static int delta_base_cache_hash_cmp(const void *unused_cmp_data,
- const void *va, const void *vb,
+ const struct hashmap_entry *va,
+ const struct hashmap_entry *vb,
const void *vkey)
{
- const struct delta_base_cache_entry *a = va, *b = vb;
+ const struct delta_base_cache_entry *a, *b;
const struct delta_base_cache_key *key = vkey;
+
+ a = container_of(va, const struct delta_base_cache_entry, ent);
+ b = container_of(vb, const struct delta_base_cache_entry, ent);
+
if (key)
return !delta_base_cache_key_eq(&a->key, key);
else
*/
static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent)
{
- hashmap_remove(&delta_base_cache, ent, &ent->key);
+ hashmap_remove(&delta_base_cache, &ent->ent, &ent->key);
list_del(&ent->lru);
delta_base_cached -= ent->size;
free(ent);
struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent));
struct list_head *lru, *tmp;
+ /*
+ * Check required to avoid redundant entries when more than one thread
+ * is unpacking the same object, in unpack_entry() (since its phases I
+ * and III might run concurrently across multiple threads).
+ */
+ if (in_delta_base_cache(p, base_offset))
+ return;
+
delta_base_cached += base_size;
list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
if (!delta_base_cache.cmpfn)
hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0);
- hashmap_entry_init(ent, pack_entry_hash(p, base_offset));
- hashmap_add(&delta_base_cache, ent);
+ hashmap_entry_init(&ent->ent, pack_entry_hash(p, base_offset));
+ hashmap_add(&delta_base_cache, &ent->ent);
}
int packed_object_info(struct repository *r, struct packed_git *p,
}
}
- if (oi->delta_base_sha1) {
+ if (oi->delta_base_oid) {
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) {
+ if (get_delta_base_oid(p, &w_curs, curpos,
+ oi->delta_base_oid,
+ type, obj_offset) < 0) {
type = OBJ_BAD;
goto out;
}
-
- hashcpy(oi->delta_base_sha1, base);
} else
- hashclr(oi->delta_base_sha1);
+ oidclr(oi->delta_base_oid);
}
oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED :
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
+ /*
+ * Note: we must ensure the window section returned by
+ * use_pack() will be available throughout git_inflate()'s
+ * unlocked execution. Please refer to the comment at
+ * get_size_from_delta() to see how this is done.
+ */
+ obj_read_unlock();
st = git_inflate(&stream, Z_FINISH);
+ obj_read_lock();
if (!stream.avail_out)
break; /* the payload is larger than it should be */
curpos += stream.next_in - in;
off_t len = revidx[1].offset - obj_offset;
if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
struct object_id oid;
- nth_packed_object_oid(&oid, p, revidx->nr);
+ nth_packed_object_id(&oid, p, revidx->nr);
error("bad packed object CRC for %s",
oid_to_hex(&oid));
mark_bad_packed_object(p, oid.hash);
&& delta_stack == small_delta_stack) {
delta_stack_alloc = alloc_nr(delta_stack_nr);
ALLOC_ARRAY(delta_stack, delta_stack_alloc);
- memcpy(delta_stack, small_delta_stack,
- sizeof(*delta_stack)*delta_stack_nr);
+ COPY_ARRAY(delta_stack, small_delta_stack,
+ delta_stack_nr);
} else {
ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc);
}
struct object_id base_oid;
revidx = find_pack_revindex(p, obj_offset);
if (revidx) {
- nth_packed_object_oid(&base_oid, p, revidx->nr);
+ nth_packed_object_id(&base_oid, p, revidx->nr);
error("failed to read delta base object %s"
" at offset %"PRIuMAX" from %s",
oid_to_hex(&base_oid), (uintmax_t)obj_offset,
index_lookup, index_lookup_width, result);
}
-const unsigned char *nth_packed_object_sha1(struct packed_git *p,
- uint32_t n)
+int nth_packed_object_id(struct object_id *oid,
+ struct packed_git *p,
+ uint32_t n)
{
const unsigned char *index = p->index_data;
const unsigned int hashsz = the_hash_algo->rawsz;
if (!index) {
if (open_pack_index(p))
- return NULL;
+ return -1;
index = p->index_data;
}
if (n >= p->num_objects)
- return NULL;
+ return -1;
index += 4 * 256;
if (p->index_version == 1) {
- return index + (hashsz + 4) * n + 4;
+ oidread(oid, index + (hashsz + 4) * n + 4);
} else {
index += 8;
- return index + hashsz * n;
+ oidread(oid, index + hashsz * n);
}
-}
-
-const struct object_id *nth_packed_object_oid(struct object_id *oid,
- struct packed_git *p,
- uint32_t n)
-{
- const unsigned char *hash = nth_packed_object_sha1(p, n);
- if (!hash)
- return NULL;
- hashcpy(oid->hash, hash);
- return oid;
+ return 0;
}
void check_pack_index_ptr(const struct packed_git *p, const void *vptr)
return 0;
for (m = r->objects->multi_pack_index; m; m = m->next) {
- if (fill_midx_entry(oid, e, m))
+ if (fill_midx_entry(r, oid, e, m))
return 1;
}
list_for_each(pos, &r->objects->packed_git_mru) {
struct packed_git *p = list_entry(pos, struct packed_git, mru);
- if (fill_pack_entry(oid, e, p)) {
+ if (!p->multi_pack_index && fill_pack_entry(oid, e, p)) {
list_move(&p->mru, &r->objects->packed_git_mru);
return 1;
}
uint32_t i;
int r = 0;
- if (flags & FOR_EACH_OBJECT_PACK_ORDER)
- load_pack_revindex(p);
+ if (flags & FOR_EACH_OBJECT_PACK_ORDER) {
+ if (load_pack_revindex(p))
+ return -1;
+ }
for (i = 0; i < p->num_objects; i++) {
uint32_t pos;
else
pos = i;
- if (!nth_packed_object_oid(&oid, p, pos))
+ if (nth_packed_object_id(&oid, p, pos) < 0)
return error("unable to get sha1 of object %u in %s",
pos, p->pack_name);
oidset_insert(set, &parents->item->object.oid);
} else if (obj->type == OBJ_TAG) {
struct tag *tag = (struct tag *) obj;
- oidset_insert(set, &tag->tagged->oid);
+ oidset_insert(set, get_tagged_oid(tag));
}
return 0;
}
static int promisor_objects_prepared;
if (!promisor_objects_prepared) {
- if (repository_format_partial_clone) {
+ if (has_promisor_remote()) {
for_each_packed_object(add_promisor_object,
&promisor_objects,
FOR_EACH_OBJECT_PROMISOR_ONLY);