summaryrefslogtreecommitdiff
path: root/builtin/index-pack.c
diff options
context:
space:
mode:
Diffstat (limited to 'builtin/index-pack.c')
-rw-r--r--builtin/index-pack.c838
1 files changed, 645 insertions, 193 deletions
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index e40451ffb4..470547835c 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -9,9 +9,10 @@
#include "progress.h"
#include "fsck.h"
#include "exec_cmd.h"
+#include "thread-utils.h"
static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [ --keep | --keep=<msg> ] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
struct object_entry {
struct pack_idx_entry idx;
@@ -19,6 +20,8 @@ struct object_entry {
unsigned int hdr_size;
enum object_type type;
enum object_type real_type;
+ unsigned delta_depth;
+ int base_object_no;
};
union delta_base {
@@ -32,6 +35,21 @@ struct base_data {
struct object_entry *obj;
void *data;
unsigned long size;
+ int ref_first, ref_last;
+ int ofs_first, ofs_last;
+};
+
+#if !defined(NO_PTHREADS) && defined(NO_THREAD_SAFE_PREAD)
+/* pread() emulation is not thread-safe. Disable threading. */
+#define NO_PTHREADS
+#endif
+
+struct thread_local {
+#ifndef NO_PTHREADS
+ pthread_t thread;
+#endif
+ struct base_data *base_cache;
+ size_t base_cache_used;
};
/*
@@ -50,11 +68,11 @@ struct delta_entry {
static struct object_entry *objects;
static struct delta_entry *deltas;
-static struct base_data *base_cache;
-static size_t base_cache_used;
+static struct thread_local nothread_data;
static int nr_objects;
static int nr_deltas;
static int nr_resolved_deltas;
+static int nr_threads;
static int from_stdin;
static int strict;
@@ -66,17 +84,89 @@ static struct progress *progress;
static unsigned char input_buffer[4096];
static unsigned int input_offset, input_len;
static off_t consumed_bytes;
+static unsigned deepest_delta;
static git_SHA_CTX input_ctx;
static uint32_t input_crc32;
static int input_fd, output_fd, pack_fd;
+#ifndef NO_PTHREADS
+
+static struct thread_local *thread_data;
+static int nr_dispatched;
+static int threads_active;
+
+static pthread_mutex_t read_mutex;
+#define read_lock() lock_mutex(&read_mutex)
+#define read_unlock() unlock_mutex(&read_mutex)
+
+static pthread_mutex_t counter_mutex;
+#define counter_lock() lock_mutex(&counter_mutex)
+#define counter_unlock() unlock_mutex(&counter_mutex)
+
+static pthread_mutex_t work_mutex;
+#define work_lock() lock_mutex(&work_mutex)
+#define work_unlock() unlock_mutex(&work_mutex)
+
+static pthread_key_t key;
+
+static inline void lock_mutex(pthread_mutex_t *mutex)
+{
+ if (threads_active)
+ pthread_mutex_lock(mutex);
+}
+
+static inline void unlock_mutex(pthread_mutex_t *mutex)
+{
+ if (threads_active)
+ pthread_mutex_unlock(mutex);
+}
+
+/*
+ * Mutex and conditional variable can't be statically-initialized on Windows.
+ */
+static void init_thread(void)
+{
+ init_recursive_mutex(&read_mutex);
+ pthread_mutex_init(&counter_mutex, NULL);
+ pthread_mutex_init(&work_mutex, NULL);
+ pthread_key_create(&key, NULL);
+ thread_data = xcalloc(nr_threads, sizeof(*thread_data));
+ threads_active = 1;
+}
+
+static void cleanup_thread(void)
+{
+ if (!threads_active)
+ return;
+ threads_active = 0;
+ pthread_mutex_destroy(&read_mutex);
+ pthread_mutex_destroy(&counter_mutex);
+ pthread_mutex_destroy(&work_mutex);
+ pthread_key_delete(key);
+ free(thread_data);
+}
+
+#else
+
+#define read_lock()
+#define read_unlock()
+
+#define counter_lock()
+#define counter_unlock()
+
+#define work_lock()
+#define work_unlock()
+
+#endif
+
+
static int mark_link(struct object *obj, int type, void *data)
{
if (!obj)
return -1;
if (type != OBJ_ANY && obj->type != type)
- die("object type mismatch at %s", sha1_to_hex(obj->sha1));
+ die(_("object type mismatch at %s"), sha1_to_hex(obj->sha1));
obj->flags |= FLAG_LINK;
return 0;
@@ -96,7 +186,7 @@ static void check_object(struct object *obj)
unsigned long size;
int type = sha1_object_info(obj->sha1, &size);
if (type != obj->type || type <= 0)
- die("object of unexpected type");
+ die(_("object of unexpected type"));
obj->flags |= FLAG_CHECKED;
return;
}
@@ -133,15 +223,18 @@ static void *fill(int min)
if (min <= input_len)
return input_buffer + input_offset;
if (min > sizeof(input_buffer))
- die("cannot fill %d bytes", min);
+ die(Q_("cannot fill %d byte",
+ "cannot fill %d bytes",
+ min),
+ min);
flush();
do {
ssize_t ret = xread(input_fd, input_buffer + input_len,
sizeof(input_buffer) - input_len);
if (ret <= 0) {
if (!ret)
- die("early EOF");
- die_errno("read error on input");
+ die(_("early EOF"));
+ die_errno(_("read error on input"));
}
input_len += ret;
if (from_stdin)
@@ -153,14 +246,14 @@ static void *fill(int min)
static void use(int bytes)
{
if (bytes > input_len)
- die("used more bytes than were available");
+ die(_("used more bytes than were available"));
input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);
input_len -= bytes;
input_offset += bytes;
/* make sure off_t is sufficiently large not to wrap */
if (signed_add_overflows(consumed_bytes, bytes))
- die("pack too large for current definition of off_t");
+ die(_("pack too large for current definition of off_t"));
consumed_bytes += bytes;
}
@@ -169,19 +262,19 @@ static const char *open_pack_file(const char *pack_name)
if (from_stdin) {
input_fd = 0;
if (!pack_name) {
- static char tmpfile[PATH_MAX];
- output_fd = odb_mkstemp(tmpfile, sizeof(tmpfile),
+ static char tmp_file[PATH_MAX];
+ output_fd = odb_mkstemp(tmp_file, sizeof(tmp_file),
"pack/tmp_pack_XXXXXX");
- pack_name = xstrdup(tmpfile);
+ pack_name = xstrdup(tmp_file);
} else
output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
if (output_fd < 0)
- die_errno("unable to create '%s'", pack_name);
+ die_errno(_("unable to create '%s'"), pack_name);
pack_fd = output_fd;
} else {
input_fd = open(pack_name, O_RDONLY);
if (input_fd < 0)
- die_errno("cannot open packfile '%s'", pack_name);
+ die_errno(_("cannot open packfile '%s'"), pack_name);
output_fd = -1;
pack_fd = input_fd;
}
@@ -195,7 +288,7 @@ static void parse_pack_header(void)
/* Header consistency check */
if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
- die("pack signature mismatch");
+ die(_("pack signature mismatch"));
if (!pack_version_ok(hdr->hdr_version))
die("pack version %"PRIu32" unsupported",
ntohl(hdr->hdr_version));
@@ -215,7 +308,35 @@ static NORETURN void bad_object(unsigned long offset, const char *format, ...)
va_start(params, format);
vsnprintf(buf, sizeof(buf), format, params);
va_end(params);
- die("pack has bad object at offset %lu: %s", offset, buf);
+ die(_("pack has bad object at offset %lu: %s"), offset, buf);
+}
+
+static inline struct thread_local *get_thread_data(void)
+{
+#ifndef NO_PTHREADS
+ if (threads_active)
+ return pthread_getspecific(key);
+ assert(!threads_active &&
+ "This should only be reached when all threads are gone");
+#endif
+ return &nothread_data;
+}
+
+#ifndef NO_PTHREADS
+static void set_thread_data(struct thread_local *data)
+{
+ if (threads_active)
+ pthread_setspecific(key, data);
+}
+#endif
+
+static struct base_data *alloc_base_data(void)
+{
+ struct base_data *base = xmalloc(sizeof(struct base_data));
+ memset(base, 0, sizeof(*base));
+ base->ref_last = -1;
+ base->ofs_last = -1;
+ return base;
}
static void free_base_data(struct base_data *c)
@@ -223,15 +344,16 @@ static void free_base_data(struct base_data *c)
if (c->data) {
free(c->data);
c->data = NULL;
- base_cache_used -= c->size;
+ get_thread_data()->base_cache_used -= c->size;
}
}
static void prune_base_data(struct base_data *retain)
{
struct base_data *b;
- for (b = base_cache;
- base_cache_used > delta_base_cache_limit && b;
+ struct thread_local *data = get_thread_data();
+ for (b = data->base_cache;
+ data->base_cache_used > delta_base_cache_limit && b;
b = b->child) {
if (b->data && b != retain)
free_base_data(b);
@@ -243,12 +365,12 @@ static void link_base_data(struct base_data *base, struct base_data *c)
if (base)
base->child = c;
else
- base_cache = c;
+ get_thread_data()->base_cache = c;
c->base = base;
c->child = NULL;
if (c->data)
- base_cache_used += c->size;
+ get_thread_data()->base_cache_used += c->size;
prune_base_data(c);
}
@@ -258,14 +380,14 @@ static void unlink_base_data(struct base_data *c)
if (base)
base->child = NULL;
else
- base_cache = NULL;
+ get_thread_data()->base_cache = NULL;
free_base_data(c);
}
static void *unpack_entry_data(unsigned long offset, unsigned long size)
{
int status;
- z_stream stream;
+ git_zstream stream;
void *buf = xmalloc(size);
memset(&stream, 0, sizeof(stream));
@@ -280,7 +402,7 @@ static void *unpack_entry_data(unsigned long offset, unsigned long size)
use(input_len - stream.avail_in);
} while (status == Z_OK);
if (stream.total_out != size || status != Z_STREAM_END)
- bad_object(offset, "inflate returned %d", status);
+ bad_object(offset, _("inflate returned %d"), status);
git_inflate_end(&stream);
return buf;
}
@@ -325,7 +447,7 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
while (c & 128) {
base_offset += 1;
if (!base_offset || MSB(base_offset, 7))
- bad_object(obj->idx.offset, "offset value overflow for delta base object");
+ bad_object(obj->idx.offset, _("offset value overflow for delta base object"));
p = fill(1);
c = *p;
use(1);
@@ -333,7 +455,7 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
}
delta_base->offset = obj->idx.offset - base_offset;
if (delta_base->offset <= 0 || delta_base->offset >= obj->idx.offset)
- bad_object(obj->idx.offset, "delta base offset is out of bound");
+ bad_object(obj->idx.offset, _("delta base offset is out of bound"));
break;
case OBJ_COMMIT:
case OBJ_TREE:
@@ -341,7 +463,7 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
case OBJ_TAG:
break;
default:
- bad_object(obj->idx.offset, "unknown object type %d", obj->type);
+ bad_object(obj->idx.offset, _("unknown object type %d"), obj->type);
}
obj->hdr_size = consumed_bytes - obj->idx.offset;
@@ -355,7 +477,7 @@ static void *get_data_from_pack(struct object_entry *obj)
off_t from = obj[0].idx.offset + obj[0].hdr_size;
unsigned long len = obj[1].idx.offset - from;
unsigned char *data, *inbuf;
- z_stream stream;
+ git_zstream stream;
int status;
data = xmalloc(obj->size);
@@ -370,9 +492,12 @@ static void *get_data_from_pack(struct object_entry *obj)
ssize_t n = (len < 64*1024) ? len : 64*1024;
n = pread(pack_fd, inbuf, n, from);
if (n < 0)
- die_errno("cannot pread pack file");
+ die_errno(_("cannot pread pack file"));
if (!n)
- die("premature end of pack file, %lu bytes missing", len);
+ die(Q_("premature end of pack file, %lu byte missing",
+ "premature end of pack file, %lu bytes missing",
+ len),
+ len);
from += n;
len -= n;
stream.next_in = inbuf;
@@ -382,14 +507,25 @@ static void *get_data_from_pack(struct object_entry *obj)
/* This has been inflated OK when first encountered, so... */
if (status != Z_STREAM_END || stream.total_out != obj->size)
- die("serious inflate inconsistency");
+ die(_("serious inflate inconsistency"));
git_inflate_end(&stream);
free(inbuf);
return data;
}
-static int find_delta(const union delta_base *base)
+static int compare_delta_bases(const union delta_base *base1,
+ const union delta_base *base2,
+ enum object_type type1,
+ enum object_type type2)
+{
+ int cmp = type1 - type2;
+ if (cmp)
+ return cmp;
+ return memcmp(base1, base2, UNION_BASE_SZ);
+}
+
+static int find_delta(const union delta_base *base, enum object_type type)
{
int first = 0, last = nr_deltas;
@@ -398,7 +534,8 @@ static int find_delta(const union delta_base *base)
struct delta_entry *delta = &deltas[next];
int cmp;
- cmp = memcmp(base, &delta->base, UNION_BASE_SZ);
+ cmp = compare_delta_bases(base, &delta->base,
+ type, objects[delta->obj_no].type);
if (!cmp)
return next;
if (cmp < 0) {
@@ -411,9 +548,10 @@ static int find_delta(const union delta_base *base)
}
static void find_delta_children(const union delta_base *base,
- int *first_index, int *last_index)
+ int *first_index, int *last_index,
+ enum object_type type)
{
- int first = find_delta(base);
+ int first = find_delta(base, type);
int last = first;
int end = nr_deltas - 1;
@@ -434,25 +572,30 @@ static void sha1_object(const void *data, unsigned long size,
enum object_type type, unsigned char *sha1)
{
hash_sha1_file(data, size, typename(type), sha1);
+ read_lock();
if (has_sha1_file(sha1)) {
void *has_data;
enum object_type has_type;
unsigned long has_size;
has_data = read_sha1_file(sha1, &has_type, &has_size);
+ read_unlock();
if (!has_data)
- die("cannot read existing object %s", sha1_to_hex(sha1));
+ die(_("cannot read existing object %s"), sha1_to_hex(sha1));
if (size != has_size || type != has_type ||
memcmp(data, has_data, size) != 0)
- die("SHA1 COLLISION FOUND WITH %s !", sha1_to_hex(sha1));
+ die(_("SHA1 COLLISION FOUND WITH %s !"), sha1_to_hex(sha1));
free(has_data);
- }
+ } else
+ read_unlock();
+
if (strict) {
+ read_lock();
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(sha1);
if (blob)
blob->object.flags |= FLAG_CHECKED;
else
- die("invalid blob object %s", sha1_to_hex(sha1));
+ die(_("invalid blob object %s"), sha1_to_hex(sha1));
} else {
struct object *obj;
int eaten;
@@ -464,11 +607,11 @@ static void sha1_object(const void *data, unsigned long size,
*/
obj = parse_object_buffer(sha1, type, size, buf, &eaten);
if (!obj)
- die("invalid %s", typename(type));
+ die(_("invalid %s"), typename(type));
if (fsck_object(obj, 1, fsck_error_function))
- die("Error in object");
+ die(_("Error in object"));
if (fsck_walk(obj, mark_link, NULL))
- die("Not all child objects of %s are reachable", sha1_to_hex(obj->sha1));
+ die(_("Not all child objects of %s are reachable"), sha1_to_hex(obj->sha1));
if (obj->type == OBJ_TREE) {
struct tree *item = (struct tree *) obj;
@@ -480,31 +623,72 @@ static void sha1_object(const void *data, unsigned long size,
}
obj->flags |= FLAG_CHECKED;
}
+ read_unlock();
}
}
+static int is_delta_type(enum object_type type)
+{
+ return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
+}
+
+/*
+ * This function is part of find_unresolved_deltas(). There are two
+ * walkers going in the opposite ways.
+ *
+ * The first one in find_unresolved_deltas() traverses down from
+ * parent node to children, deflating nodes along the way. However,
+ * memory for deflated nodes is limited by delta_base_cache_limit, so
+ * at some point parent node's deflated content may be freed.
+ *
+ * The second walker is this function, which goes from current node up
+ * to top parent if necessary to deflate the node. In normal
+ * situation, its parent node would be already deflated, so it just
+ * needs to apply delta.
+ *
+ * In the worst case scenario, parent node is no longer deflated because
+ * we're running out of delta_base_cache_limit; we need to re-deflate
+ * parents, possibly up to the top base.
+ *
+ * All deflated objects here are subject to be freed if we exceed
+ * delta_base_cache_limit, just like in find_unresolved_deltas(), we
+ * just need to make sure the last node is not freed.
+ */
static void *get_base_data(struct base_data *c)
{
if (!c->data) {
struct object_entry *obj = c->obj;
+ struct base_data **delta = NULL;
+ int delta_nr = 0, delta_alloc = 0;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
- void *base = get_base_data(c->base);
- void *raw = get_data_from_pack(obj);
+ while (is_delta_type(c->obj->type) && !c->data) {
+ ALLOC_GROW(delta, delta_nr + 1, delta_alloc);
+ delta[delta_nr++] = c;
+ c = c->base;
+ }
+ if (!delta_nr) {
+ c->data = get_data_from_pack(obj);
+ c->size = obj->size;
+ get_thread_data()->base_cache_used += c->size;
+ prune_base_data(c);
+ }
+ for (; delta_nr > 0; delta_nr--) {
+ void *base, *raw;
+ c = delta[delta_nr - 1];
+ obj = c->obj;
+ base = get_base_data(c->base);
+ raw = get_data_from_pack(obj);
c->data = patch_delta(
base, c->base->size,
raw, obj->size,
&c->size);
free(raw);
if (!c->data)
- bad_object(obj->idx.offset, "failed to apply delta");
- } else {
- c->data = get_data_from_pack(obj);
- c->size = obj->size;
+ bad_object(obj->idx.offset, _("failed to apply delta"));
+ get_thread_data()->base_cache_used += c->size;
+ prune_base_data(c);
}
-
- base_cache_used += c->size;
- prune_base_data(c);
+ free(delta);
}
return c->data;
}
@@ -515,6 +699,10 @@ static void resolve_delta(struct object_entry *delta_obj,
void *base_data, *delta_data;
delta_obj->real_type = base->obj->real_type;
+ delta_obj->delta_depth = base->obj->delta_depth + 1;
+ if (deepest_delta < delta_obj->delta_depth)
+ deepest_delta = delta_obj->delta_depth;
+ delta_obj->base_object_no = base->obj - objects;
delta_data = get_data_from_pack(delta_obj);
base_data = get_base_data(base);
result->obj = delta_obj;
@@ -522,93 +710,150 @@ static void resolve_delta(struct object_entry *delta_obj,
delta_data, delta_obj->size, &result->size);
free(delta_data);
if (!result->data)
- bad_object(delta_obj->idx.offset, "failed to apply delta");
+ bad_object(delta_obj->idx.offset, _("failed to apply delta"));
sha1_object(result->data, result->size, delta_obj->real_type,
delta_obj->idx.sha1);
+ counter_lock();
nr_resolved_deltas++;
+ counter_unlock();
}
-static void find_unresolved_deltas(struct base_data *base,
- struct base_data *prev_base)
+static struct base_data *find_unresolved_deltas_1(struct base_data *base,
+ struct base_data *prev_base)
{
- int i, ref_first, ref_last, ofs_first, ofs_last;
-
- /*
- * This is a recursive function. Those brackets should help reducing
- * stack usage by limiting the scope of the delta_base union.
- */
- {
+ if (base->ref_last == -1 && base->ofs_last == -1) {
union delta_base base_spec;
hashcpy(base_spec.sha1, base->obj->idx.sha1);
- find_delta_children(&base_spec, &ref_first, &ref_last);
+ find_delta_children(&base_spec,
+ &base->ref_first, &base->ref_last, OBJ_REF_DELTA);
memset(&base_spec, 0, sizeof(base_spec));
base_spec.offset = base->obj->idx.offset;
- find_delta_children(&base_spec, &ofs_first, &ofs_last);
- }
+ find_delta_children(&base_spec,
+ &base->ofs_first, &base->ofs_last, OBJ_OFS_DELTA);
- if (ref_last == -1 && ofs_last == -1) {
- free(base->data);
- return;
+ if (base->ref_last == -1 && base->ofs_last == -1) {
+ free(base->data);
+ return NULL;
+ }
+
+ link_base_data(prev_base, base);
}
- link_base_data(prev_base, base);
+ if (base->ref_first <= base->ref_last) {
+ struct object_entry *child = objects + deltas[base->ref_first].obj_no;
+ struct base_data *result = alloc_base_data();
- for (i = ref_first; i <= ref_last; i++) {
- struct object_entry *child = objects + deltas[i].obj_no;
- if (child->real_type == OBJ_REF_DELTA) {
- struct base_data result;
- resolve_delta(child, base, &result);
- if (i == ref_last && ofs_last == -1)
- free_base_data(base);
- find_unresolved_deltas(&result, base);
- }
+ assert(child->real_type == OBJ_REF_DELTA);
+ resolve_delta(child, base, result);
+ if (base->ref_first == base->ref_last && base->ofs_last == -1)
+ free_base_data(base);
+
+ base->ref_first++;
+ return result;
}
- for (i = ofs_first; i <= ofs_last; i++) {
- struct object_entry *child = objects + deltas[i].obj_no;
- if (child->real_type == OBJ_OFS_DELTA) {
- struct base_data result;
- resolve_delta(child, base, &result);
- if (i == ofs_last)
- free_base_data(base);
- find_unresolved_deltas(&result, base);
- }
+ if (base->ofs_first <= base->ofs_last) {
+ struct object_entry *child = objects + deltas[base->ofs_first].obj_no;
+ struct base_data *result = alloc_base_data();
+
+ assert(child->real_type == OBJ_OFS_DELTA);
+ resolve_delta(child, base, result);
+ if (base->ofs_first == base->ofs_last)
+ free_base_data(base);
+
+ base->ofs_first++;
+ return result;
}
unlink_base_data(base);
+ return NULL;
+}
+
+static void find_unresolved_deltas(struct base_data *base)
+{
+ struct base_data *new_base, *prev_base = NULL;
+ for (;;) {
+ new_base = find_unresolved_deltas_1(base, prev_base);
+
+ if (new_base) {
+ prev_base = base;
+ base = new_base;
+ } else {
+ free(base);
+ base = prev_base;
+ if (!base)
+ return;
+ prev_base = base->base;
+ }
+ }
}
static int compare_delta_entry(const void *a, const void *b)
{
const struct delta_entry *delta_a = a;
const struct delta_entry *delta_b = b;
- return memcmp(&delta_a->base, &delta_b->base, UNION_BASE_SZ);
+
+ /* group by type (ref vs ofs) and then by value (sha-1 or offset) */
+ return compare_delta_bases(&delta_a->base, &delta_b->base,
+ objects[delta_a->obj_no].type,
+ objects[delta_b->obj_no].type);
+}
+
+static void resolve_base(struct object_entry *obj)
+{
+ struct base_data *base_obj = alloc_base_data();
+ base_obj->obj = obj;
+ base_obj->data = NULL;
+ find_unresolved_deltas(base_obj);
}
-/* Parse all objects and return the pack content SHA1 hash */
+#ifndef NO_PTHREADS
+static void *threaded_second_pass(void *data)
+{
+ set_thread_data(data);
+ for (;;) {
+ int i;
+ work_lock();
+ display_progress(progress, nr_resolved_deltas);
+ while (nr_dispatched < nr_objects &&
+ is_delta_type(objects[nr_dispatched].type))
+ nr_dispatched++;
+ if (nr_dispatched >= nr_objects) {
+ work_unlock();
+ break;
+ }
+ i = nr_dispatched++;
+ work_unlock();
+
+ resolve_base(&objects[i]);
+ }
+ return NULL;
+}
+#endif
+
+/*
+ * First pass:
+ * - find locations of all objects;
+ * - calculate SHA1 of all non-delta objects;
+ * - remember base (SHA1 or offset) for all deltas.
+ */
static void parse_pack_objects(unsigned char *sha1)
{
int i;
struct delta_entry *delta = deltas;
struct stat st;
- /*
- * First pass:
- * - find locations of all objects;
- * - calculate SHA1 of all non-delta objects;
- * - remember base (SHA1 or offset) for all deltas.
- */
if (verbose)
progress = start_progress(
- from_stdin ? "Receiving objects" : "Indexing objects",
+ from_stdin ? _("Receiving objects") : _("Indexing objects"),
nr_objects);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
void *data = unpack_raw_entry(obj, &delta->base);
obj->real_type = obj->type;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA) {
+ if (is_delta_type(obj->type)) {
nr_deltas++;
delta->obj_no = i;
delta++;
@@ -624,15 +869,28 @@ static void parse_pack_objects(unsigned char *sha1)
flush();
git_SHA1_Final(sha1, &input_ctx);
if (hashcmp(fill(20), sha1))
- die("pack is corrupted (SHA1 mismatch)");
+ die(_("pack is corrupted (SHA1 mismatch)"));
use(20);
/* If input_fd is a file, we should have reached its end now. */
if (fstat(input_fd, &st))
- die_errno("cannot fstat packfile");
+ die_errno(_("cannot fstat packfile"));
if (S_ISREG(st.st_mode) &&
lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size)
- die("pack has junk at the end");
+ die(_("pack has junk at the end"));
+}
+
+/*
+ * Second pass:
+ * - for all non-delta objects, look if it is used as a base for
+ * deltas;
+ * - if used as a base, uncompress the object and apply all deltas,
+ * recursively checking if the resulting object is used as a base
+ * for some more deltas.
+ */
+static void resolve_deltas(void)
+{
+ int i;
if (!nr_deltas)
return;
@@ -641,51 +899,105 @@ static void parse_pack_objects(unsigned char *sha1)
qsort(deltas, nr_deltas, sizeof(struct delta_entry),
compare_delta_entry);
- /*
- * Second pass:
- * - for all non-delta objects, look if it is used as a base for
- * deltas;
- * - if used as a base, uncompress the object and apply all deltas,
- * recursively checking if the resulting object is used as a base
- * for some more deltas.
- */
if (verbose)
- progress = start_progress("Resolving deltas", nr_deltas);
+ progress = start_progress(_("Resolving deltas"), nr_deltas);
+
+#ifndef NO_PTHREADS
+ nr_dispatched = 0;
+ if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) {
+ init_thread();
+ for (i = 0; i < nr_threads; i++) {
+ int ret = pthread_create(&thread_data[i].thread, NULL,
+ threaded_second_pass, thread_data + i);
+ if (ret)
+ die("unable to create thread: %s", strerror(ret));
+ }
+ for (i = 0; i < nr_threads; i++)
+ pthread_join(thread_data[i].thread, NULL);
+ cleanup_thread();
+ return;
+ }
+#endif
+
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
- struct base_data base_obj;
- if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
+ if (is_delta_type(obj->type))
continue;
- base_obj.obj = obj;
- base_obj.data = NULL;
- find_unresolved_deltas(&base_obj, NULL);
+ resolve_base(obj);
display_progress(progress, nr_resolved_deltas);
}
}
+/*
+ * Third pass:
+ * - append objects to convert thin pack to full pack if required
+ * - write the final 20-byte SHA-1
+ */
+static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved);
+static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_sha1)
+{
+ if (nr_deltas == nr_resolved_deltas) {
+ stop_progress(&progress);
+ /* Flush remaining pack final 20-byte SHA1. */
+ flush();
+ return;
+ }
+
+ if (fix_thin_pack) {
+ struct sha1file *f;
+ unsigned char read_sha1[20], tail_sha1[20];
+ char msg[48];
+ int nr_unresolved = nr_deltas - nr_resolved_deltas;
+ int nr_objects_initial = nr_objects;
+ if (nr_unresolved <= 0)
+ die(_("confusion beyond insanity"));
+ objects = xrealloc(objects,
+ (nr_objects + nr_unresolved + 1)
+ * sizeof(*objects));
+ f = sha1fd(output_fd, curr_pack);
+ fix_unresolved_deltas(f, nr_unresolved);
+ sprintf(msg, "completed with %d local objects",
+ nr_objects - nr_objects_initial);
+ stop_progress_msg(&progress, msg);
+ sha1close(f, tail_sha1, 0);
+ hashcpy(read_sha1, pack_sha1);
+ fixup_pack_header_footer(output_fd, pack_sha1,
+ curr_pack, nr_objects,
+ read_sha1, consumed_bytes-20);
+ if (hashcmp(read_sha1, tail_sha1) != 0)
+ die("Unexpected tail checksum for %s "
+ "(disk corruption?)", curr_pack);
+ }
+ if (nr_deltas != nr_resolved_deltas)
+ die(Q_("pack has %d unresolved delta",
+ "pack has %d unresolved deltas",
+ nr_deltas - nr_resolved_deltas),
+ nr_deltas - nr_resolved_deltas);
+}
+
static int write_compressed(struct sha1file *f, void *in, unsigned int size)
{
- z_stream stream;
+ git_zstream stream;
int status;
unsigned char outbuf[4096];
memset(&stream, 0, sizeof(stream));
- deflateInit(&stream, zlib_compression_level);
+ git_deflate_init(&stream, zlib_compression_level);
stream.next_in = in;
stream.avail_in = size;
do {
stream.next_out = outbuf;
stream.avail_out = sizeof(outbuf);
- status = deflate(&stream, Z_FINISH);
+ status = git_deflate(&stream, Z_FINISH);
sha1write(f, outbuf, sizeof(outbuf) - stream.avail_out);
} while (status == Z_OK);
if (status != Z_STREAM_END)
- die("unable to deflate appended object (%d)", status);
+ die(_("unable to deflate appended object (%d)"), status);
size = stream.total_out;
- deflateEnd(&stream);
+ git_deflate_end(&stream);
return size;
}
@@ -752,20 +1064,20 @@ static void fix_unresolved_deltas(struct sha1file *f, int nr_unresolved)
for (i = 0; i < n; i++) {
struct delta_entry *d = sorted_by_pos[i];
enum object_type type;
- struct base_data base_obj;
+ struct base_data *base_obj = alloc_base_data();
if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
continue;
- base_obj.data = read_sha1_file(d->base.sha1, &type, &base_obj.size);
- if (!base_obj.data)
+ base_obj->data = read_sha1_file(d->base.sha1, &type, &base_obj->size);
+ if (!base_obj->data)
continue;
- if (check_sha1_signature(d->base.sha1, base_obj.data,
- base_obj.size, typename(type)))
- die("local object %s is corrupt", sha1_to_hex(d->base.sha1));
- base_obj.obj = append_obj_to_pack(f, d->base.sha1,
- base_obj.data, base_obj.size, type);
- find_unresolved_deltas(&base_obj, NULL);
+ if (check_sha1_signature(d->base.sha1, base_obj->data,
+ base_obj->size, typename(type)))
+ die(_("local object %s is corrupt"), sha1_to_hex(d->base.sha1));
+ base_obj->obj = append_obj_to_pack(f, d->base.sha1,
+ base_obj->data, base_obj->size, type);
+ find_unresolved_deltas(base_obj);
display_progress(progress, nr_resolved_deltas);
}
free(sorted_by_pos);
@@ -786,7 +1098,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
fsync_or_die(output_fd, curr_pack_name);
err = close(output_fd);
if (err)
- die_errno("error while closing pack file");
+ die_errno(_("error while closing pack file"));
}
if (keep_msg) {
@@ -799,7 +1111,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
if (keep_fd < 0) {
if (errno != EEXIST)
- die_errno("cannot write keep file '%s'",
+ die_errno(_("cannot write keep file '%s'"),
keep_name);
} else {
if (keep_msg_len > 0) {
@@ -807,7 +1119,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
write_or_die(keep_fd, "\n", 1);
}
if (close(keep_fd) != 0)
- die_errno("cannot close written keep file '%s'",
+ die_errno(_("cannot close written keep file '%s'"),
keep_name);
report = "keep";
}
@@ -820,7 +1132,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
final_pack_name = name;
}
if (move_temp_to_file(curr_pack_name, final_pack_name))
- die("cannot store pack file");
+ die(_("cannot store pack file"));
} else if (from_stdin)
chmod(final_pack_name, 0444);
@@ -831,7 +1143,7 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
final_index_name = name;
}
if (move_temp_to_file(curr_index_name, final_index_name))
- die("cannot store index file");
+ die(_("cannot store index file"));
} else
chmod(final_index_name, 0444);
@@ -859,24 +1171,152 @@ static void final(const char *final_pack_name, const char *curr_pack_name,
static int git_index_pack_config(const char *k, const char *v, void *cb)
{
+ struct pack_idx_option *opts = cb;
+
if (!strcmp(k, "pack.indexversion")) {
- pack_idx_default_version = git_config_int(k, v);
- if (pack_idx_default_version > 2)
- die("bad pack.indexversion=%"PRIu32,
- pack_idx_default_version);
+ opts->version = git_config_int(k, v);
+ if (opts->version > 2)
+ die("bad pack.indexversion=%"PRIu32, opts->version);
+ return 0;
+ }
+ if (!strcmp(k, "pack.threads")) {
+ nr_threads = git_config_int(k, v);
+ if (nr_threads < 0)
+ die("invalid number of threads specified (%d)",
+ nr_threads);
+#ifdef NO_PTHREADS
+ if (nr_threads != 1)
+ warning("no threads support, ignoring %s", k);
+ nr_threads = 1;
+#endif
return 0;
}
return git_default_config(k, v, cb);
}
+static int cmp_uint32(const void *a_, const void *b_)
+{
+ uint32_t a = *((uint32_t *)a_);
+ uint32_t b = *((uint32_t *)b_);
+
+ return (a < b) ? -1 : (a != b);
+}
+
+static void read_v2_anomalous_offsets(struct packed_git *p,
+ struct pack_idx_option *opts)
+{
+ const uint32_t *idx1, *idx2;
+ uint32_t i;
+
+ /* The address of the 4-byte offset table */
+ idx1 = (((const uint32_t *)p->index_data)
+ + 2 /* 8-byte header */
+ + 256 /* fan out */
+ + 5 * p->num_objects /* 20-byte SHA-1 table */
+ + p->num_objects /* CRC32 table */
+ );
+
+ /* The address of the 8-byte offset table */
+ idx2 = idx1 + p->num_objects;
+
+ for (i = 0; i < p->num_objects; i++) {
+ uint32_t off = ntohl(idx1[i]);
+ if (!(off & 0x80000000))
+ continue;
+ off = off & 0x7fffffff;
+ if (idx2[off * 2])
+ continue;
+ /*
+ * The real offset is ntohl(idx2[off * 2]) in high 4
+ * octets, and ntohl(idx2[off * 2 + 1]) in low 4
+ * octets. But idx2[off * 2] is Zero!!!
+ */
+ ALLOC_GROW(opts->anomaly, opts->anomaly_nr + 1, opts->anomaly_alloc);
+ opts->anomaly[opts->anomaly_nr++] = ntohl(idx2[off * 2 + 1]);
+ }
+
+ if (1 < opts->anomaly_nr)
+ qsort(opts->anomaly, opts->anomaly_nr, sizeof(uint32_t), cmp_uint32);
+}
+
+static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
+{
+ struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);
+
+ if (!p)
+ die(_("Cannot open existing pack file '%s'"), pack_name);
+ if (open_pack_index(p))
+ die(_("Cannot open existing pack idx file for '%s'"), pack_name);
+
+ /* Read the attributes from the existing idx file */
+ opts->version = p->index_version;
+
+ if (opts->version == 2)
+ read_v2_anomalous_offsets(p, opts);
+
+ /*
+ * Get rid of the idx file as we do not need it anymore.
+ * NEEDSWORK: extract this bit from free_pack_by_name() in
+ * sha1_file.c, perhaps? It shouldn't matter very much as we
+ * know we haven't installed this pack (hence we never have
+ * read anything from it).
+ */
+ close_pack_index(p);
+ free(p);
+}
+
+static void show_pack_info(int stat_only)
+{
+ int i, baseobjects = nr_objects - nr_deltas;
+ unsigned long *chain_histogram = NULL;
+
+ if (deepest_delta)
+ chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long));
+
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = &objects[i];
+
+ if (is_delta_type(obj->type))
+ chain_histogram[obj->delta_depth - 1]++;
+ if (stat_only)
+ continue;
+ printf("%s %-6s %lu %lu %"PRIuMAX,
+ sha1_to_hex(obj->idx.sha1),
+ typename(obj->real_type), obj->size,
+ (unsigned long)(obj[1].idx.offset - obj->idx.offset),
+ (uintmax_t)obj->idx.offset);
+ if (is_delta_type(obj->type)) {
+ struct object_entry *bobj = &objects[obj->base_object_no];
+ printf(" %u %s", obj->delta_depth, sha1_to_hex(bobj->idx.sha1));
+ }
+ putchar('\n');
+ }
+
+ if (baseobjects)
+ printf_ln(Q_("non delta: %d object",
+ "non delta: %d objects",
+ baseobjects),
+ baseobjects);
+ for (i = 0; i < deepest_delta; i++) {
+ if (!chain_histogram[i])
+ continue;
+ printf_ln(Q_("chain length = %d: %lu object",
+ "chain length = %d: %lu objects",
+ chain_histogram[i]),
+ i + 1,
+ chain_histogram[i]);
+ }
+}
+
int cmd_index_pack(int argc, const char **argv, const char *prefix)
{
- int i, fix_thin_pack = 0;
+ int i, fix_thin_pack = 0, verify = 0, stat_only = 0, stat = 0;
const char *curr_pack, *curr_index;
const char *index_name = NULL, *pack_name = NULL;
const char *keep_name = NULL, *keep_msg = NULL;
char *index_name_buf = NULL, *keep_name_buf = NULL;
struct pack_idx_entry **idx_objects;
+ struct pack_idx_option opts;
unsigned char pack_sha1[20];
if (argc == 2 && !strcmp(argv[1], "-h"))
@@ -884,9 +1324,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
read_replace_refs = 0;
- git_config(git_index_pack_config, NULL);
+ reset_pack_idx_option(&opts);
+ git_config(git_index_pack_config, &opts);
if (prefix && chdir(prefix))
- die("Cannot come back to cwd");
+ die(_("Cannot come back to cwd"));
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
@@ -898,10 +1339,30 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
fix_thin_pack = 1;
} else if (!strcmp(arg, "--strict")) {
strict = 1;
+ } else if (!strcmp(arg, "--verify")) {
+ verify = 1;
+ } else if (!strcmp(arg, "--verify-stat")) {
+ verify = 1;
+ stat = 1;
+ } else if (!strcmp(arg, "--verify-stat-only")) {
+ verify = 1;
+ stat = 1;
+ stat_only = 1;
} else if (!strcmp(arg, "--keep")) {
keep_msg = "";
} else if (!prefixcmp(arg, "--keep=")) {
keep_msg = arg + 7;
+ } else if (!prefixcmp(arg, "--threads=")) {
+ char *end;
+ nr_threads = strtoul(arg+10, &end, 0);
+ if (!arg[10] || *end || nr_threads < 0)
+ usage(index_pack_usage);
+#ifdef NO_PTHREADS
+ if (nr_threads != 1)
+ warning("no threads support, "
+ "ignoring %s", arg);
+ nr_threads = 1;
+#endif
} else if (!prefixcmp(arg, "--pack_header=")) {
struct pack_header *hdr;
char *c;
@@ -910,10 +1371,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
hdr->hdr_signature = htonl(PACK_SIGNATURE);
hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));
if (*c != ',')
- die("bad %s", arg);
+ die(_("bad %s"), arg);
hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));
if (*c)
- die("bad %s", arg);
+ die(_("bad %s"), arg);
input_len = sizeof(*hdr);
} else if (!strcmp(arg, "-v")) {
verbose = 1;
@@ -923,13 +1384,13 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
index_name = argv[++i];
} else if (!prefixcmp(arg, "--index-version=")) {
char *c;
- pack_idx_default_version = strtoul(arg + 16, &c, 10);
- if (pack_idx_default_version > 2)
- die("bad %s", arg);
+ opts.version = strtoul(arg + 16, &c, 10);
+ if (opts.version > 2)
+ die(_("bad %s"), arg);
if (*c == ',')
- pack_idx_off32_limit = strtoul(c+1, &c, 0);
- if (*c || pack_idx_off32_limit & 0x80000000)
- die("bad %s", arg);
+ opts.off32_limit = strtoul(c+1, &c, 0);
+ if (*c || opts.off32_limit & 0x80000000)
+ die(_("bad %s"), arg);
} else
usage(index_pack_usage);
continue;
@@ -943,11 +1404,11 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
if (!pack_name && !from_stdin)
usage(index_pack_usage);
if (fix_thin_pack && !from_stdin)
- die("--fix-thin cannot be used without --stdin");
+ die(_("--fix-thin cannot be used without --stdin"));
if (!index_name && pack_name) {
int len = strlen(pack_name);
if (!has_extension(pack_name, ".pack"))
- die("packfile name '%s' does not end with '.pack'",
+ die(_("packfile name '%s' does not end with '.pack'"),
pack_name);
index_name_buf = xmalloc(len);
memcpy(index_name_buf, pack_name, len - 5);
@@ -957,67 +1418,58 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
if (keep_msg && !keep_name && pack_name) {
int len = strlen(pack_name);
if (!has_extension(pack_name, ".pack"))
- die("packfile name '%s' does not end with '.pack'",
+ die(_("packfile name '%s' does not end with '.pack'"),
pack_name);
keep_name_buf = xmalloc(len);
memcpy(keep_name_buf, pack_name, len - 5);
strcpy(keep_name_buf + len - 5, ".keep");
keep_name = keep_name_buf;
}
+ if (verify) {
+ if (!index_name)
+ die(_("--verify with no packfile name given"));
+ read_idx_option(&opts, index_name);
+ opts.flags |= WRITE_IDX_VERIFY | WRITE_IDX_STRICT;
+ }
+ if (strict)
+ opts.flags |= WRITE_IDX_STRICT;
+
+#ifndef NO_PTHREADS
+ if (!nr_threads) {
+ nr_threads = online_cpus();
+ /* An experiment showed that more threads does not mean faster */
+ if (nr_threads > 3)
+ nr_threads = 3;
+ }
+#endif
curr_pack = open_pack_file(pack_name);
parse_pack_header();
- objects = xmalloc((nr_objects + 1) * sizeof(struct object_entry));
- deltas = xmalloc(nr_objects * sizeof(struct delta_entry));
+ objects = xcalloc(nr_objects + 1, sizeof(struct object_entry));
+ deltas = xcalloc(nr_objects, sizeof(struct delta_entry));
parse_pack_objects(pack_sha1);
- if (nr_deltas == nr_resolved_deltas) {
- stop_progress(&progress);
- /* Flush remaining pack final 20-byte SHA1. */
- flush();
- } else {
- if (fix_thin_pack) {
- struct sha1file *f;
- unsigned char read_sha1[20], tail_sha1[20];
- char msg[48];
- int nr_unresolved = nr_deltas - nr_resolved_deltas;
- int nr_objects_initial = nr_objects;
- if (nr_unresolved <= 0)
- die("confusion beyond insanity");
- objects = xrealloc(objects,
- (nr_objects + nr_unresolved + 1)
- * sizeof(*objects));
- f = sha1fd(output_fd, curr_pack);
- fix_unresolved_deltas(f, nr_unresolved);
- sprintf(msg, "completed with %d local objects",
- nr_objects - nr_objects_initial);
- stop_progress_msg(&progress, msg);
- sha1close(f, tail_sha1, 0);
- hashcpy(read_sha1, pack_sha1);
- fixup_pack_header_footer(output_fd, pack_sha1,
- curr_pack, nr_objects,
- read_sha1, consumed_bytes-20);
- if (hashcmp(read_sha1, tail_sha1) != 0)
- die("Unexpected tail checksum for %s "
- "(disk corruption?)", curr_pack);
- }
- if (nr_deltas != nr_resolved_deltas)
- die("pack has %d unresolved deltas",
- nr_deltas - nr_resolved_deltas);
- }
+ resolve_deltas();
+ conclude_pack(fix_thin_pack, curr_pack, pack_sha1);
free(deltas);
if (strict)
check_objects();
+ if (stat)
+ show_pack_info(stat_only);
+
idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
for (i = 0; i < nr_objects; i++)
idx_objects[i] = &objects[i].idx;
- curr_index = write_idx_file(index_name, idx_objects, nr_objects, pack_sha1);
+ curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_sha1);
free(idx_objects);
- final(pack_name, curr_pack,
- index_name, curr_index,
- keep_name, keep_msg,
- pack_sha1);
+ if (!verify)
+ final(pack_name, curr_pack,
+ index_name, curr_index,
+ keep_name, keep_msg,
+ pack_sha1);
+ else
+ close(input_fd);
free(objects);
free(index_name_buf);
free(keep_name_buf);
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-18 06:01:25 +0000