#include "progress.h"
#include "fsck.h"
#include "exec_cmd.h"
+#include "streaming.h"
+#include "thread-utils.h"
static const char index_pack_usage[] =
"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
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;
+};
+
/*
* Even if sizeof(union delta_base) == 24 on 64-bit archs, we really want
* to memcmp() only the first 20 bytes.
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;
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)
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 ¬hread_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));
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);
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);
}
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)
+static int is_delta_type(enum object_type type)
{
+ return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
+}
+
+static void *unpack_entry_data(unsigned long offset, unsigned long size,
+ enum object_type type, unsigned char *sha1)
+{
+ static char fixed_buf[8192];
int status;
git_zstream stream;
- void *buf = xmalloc(size);
+ void *buf;
+ git_SHA_CTX c;
+ char hdr[32];
+ int hdrlen;
+
+ if (!is_delta_type(type)) {
+ hdrlen = sprintf(hdr, "%s %lu", typename(type), size) + 1;
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, hdr, hdrlen);
+ } else
+ sha1 = NULL;
+ if (type == OBJ_BLOB && size > big_file_threshold)
+ buf = fixed_buf;
+ else
+ buf = xmalloc(size);
memset(&stream, 0, sizeof(stream));
git_inflate_init(&stream);
stream.next_out = buf;
- stream.avail_out = size;
+ stream.avail_out = buf == fixed_buf ? sizeof(fixed_buf) : size;
do {
+ unsigned char *last_out = stream.next_out;
stream.next_in = fill(1);
stream.avail_in = input_len;
status = git_inflate(&stream, 0);
use(input_len - stream.avail_in);
+ if (sha1)
+ git_SHA1_Update(&c, last_out, stream.next_out - last_out);
+ if (buf == fixed_buf) {
+ stream.next_out = buf;
+ stream.avail_out = sizeof(fixed_buf);
+ }
} while (status == Z_OK);
if (stream.total_out != size || status != Z_STREAM_END)
bad_object(offset, _("inflate returned %d"), status);
git_inflate_end(&stream);
- return buf;
+ if (sha1)
+ git_SHA1_Final(sha1, &c);
+ return buf == fixed_buf ? NULL : buf;
}
-static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_base)
+static void *unpack_raw_entry(struct object_entry *obj,
+ union delta_base *delta_base,
+ unsigned char *sha1)
{
unsigned char *p;
unsigned long size, c;
}
obj->hdr_size = consumed_bytes - obj->idx.offset;
- data = unpack_entry_data(obj->idx.offset, obj->size);
+ data = unpack_entry_data(obj->idx.offset, obj->size, obj->type, sha1);
obj->idx.crc32 = input_crc32;
return data;
}
-static void *get_data_from_pack(struct object_entry *obj)
+static void *unpack_data(struct object_entry *obj,
+ int (*consume)(const unsigned char *, unsigned long, void *),
+ void *cb_data)
{
off_t from = obj[0].idx.offset + obj[0].hdr_size;
unsigned long len = obj[1].idx.offset - from;
git_zstream stream;
int status;
- data = xmalloc(obj->size);
+ data = xmalloc(consume ? 64*1024 : obj->size);
inbuf = xmalloc((len < 64*1024) ? len : 64*1024);
memset(&stream, 0, sizeof(stream));
git_inflate_init(&stream);
stream.next_out = data;
- stream.avail_out = obj->size;
+ stream.avail_out = consume ? 64*1024 : obj->size;
do {
ssize_t n = (len < 64*1024) ? len : 64*1024;
len -= n;
stream.next_in = inbuf;
stream.avail_in = n;
- status = git_inflate(&stream, 0);
+ if (!consume)
+ status = git_inflate(&stream, 0);
+ else {
+ do {
+ status = git_inflate(&stream, 0);
+ if (consume(data, stream.next_out - data, cb_data)) {
+ free(inbuf);
+ free(data);
+ return NULL;
+ }
+ stream.next_out = data;
+ stream.avail_out = 64*1024;
+ } while (status == Z_OK && stream.avail_in);
+ }
} while (len && status == Z_OK && !stream.avail_in);
/* This has been inflated OK when first encountered, so... */
git_inflate_end(&stream);
free(inbuf);
+ if (consume) {
+ free(data);
+ data = NULL;
+ }
return data;
}
+static void *get_data_from_pack(struct object_entry *obj)
+{
+ return unpack_data(obj, NULL, NULL);
+}
+
static int compare_delta_bases(const union delta_base *base1,
const union delta_base *base2,
enum object_type type1,
*last_index = last;
}
-static void sha1_object(const void *data, unsigned long size,
- enum object_type type, unsigned char *sha1)
+struct compare_data {
+ struct object_entry *entry;
+ struct git_istream *st;
+ unsigned char *buf;
+ unsigned long buf_size;
+};
+
+static int compare_objects(const unsigned char *buf, unsigned long size,
+ void *cb_data)
+{
+ struct compare_data *data = cb_data;
+
+ if (data->buf_size < size) {
+ free(data->buf);
+ data->buf = xmalloc(size);
+ data->buf_size = size;
+ }
+
+ while (size) {
+ ssize_t len = read_istream(data->st, data->buf, size);
+ if (len == 0)
+ die(_("SHA1 COLLISION FOUND WITH %s !"),
+ sha1_to_hex(data->entry->idx.sha1));
+ if (len < 0)
+ die(_("unable to read %s"),
+ sha1_to_hex(data->entry->idx.sha1));
+ if (memcmp(buf, data->buf, len))
+ die(_("SHA1 COLLISION FOUND WITH %s !"),
+ sha1_to_hex(data->entry->idx.sha1));
+ size -= len;
+ buf += len;
+ }
+ return 0;
+}
+
+static int check_collison(struct object_entry *entry)
+{
+ struct compare_data data;
+ enum object_type type;
+ unsigned long size;
+
+ if (entry->size <= big_file_threshold || entry->type != OBJ_BLOB)
+ return -1;
+
+ memset(&data, 0, sizeof(data));
+ data.entry = entry;
+ data.st = open_istream(entry->idx.sha1, &type, &size, NULL);
+ if (!data.st)
+ return -1;
+ if (size != entry->size || type != entry->type)
+ die(_("SHA1 COLLISION FOUND WITH %s !"),
+ sha1_to_hex(entry->idx.sha1));
+ unpack_data(entry, compare_objects, &data);
+ close_istream(data.st);
+ free(data.buf);
+ return 0;
+}
+
+static void sha1_object(const void *data, struct object_entry *obj_entry,
+ unsigned long size, enum object_type type,
+ const unsigned char *sha1)
{
- hash_sha1_file(data, size, typename(type), sha1);
- if (has_sha1_file(sha1)) {
+ void *new_data = NULL;
+ int collision_test_needed;
+
+ assert(data || obj_entry);
+
+ read_lock();
+ collision_test_needed = has_sha1_file(sha1);
+ read_unlock();
+
+ if (collision_test_needed && !data) {
+ read_lock();
+ if (!check_collison(obj_entry))
+ collision_test_needed = 0;
+ read_unlock();
+ }
+ if (collision_test_needed) {
void *has_data;
enum object_type has_type;
unsigned long has_size;
+ read_lock();
+ has_type = sha1_object_info(sha1, &has_size);
+ if (has_type != type || has_size != size)
+ die(_("SHA1 COLLISION FOUND WITH %s !"), sha1_to_hex(sha1));
has_data = read_sha1_file(sha1, &has_type, &has_size);
+ read_unlock();
+ if (!data)
+ data = new_data = get_data_from_pack(obj_entry);
if (!has_data)
die(_("cannot read existing object %s"), sha1_to_hex(sha1));
if (size != has_size || type != has_type ||
die(_("SHA1 COLLISION FOUND WITH %s !"), sha1_to_hex(sha1));
free(has_data);
}
+
if (strict) {
+ read_lock();
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(sha1);
if (blob)
int eaten;
void *buf = (void *) data;
+ if (!buf)
+ buf = new_data = get_data_from_pack(obj_entry);
+
/*
* we do not need to free the memory here, as the
* buf is deleted by the caller.
}
obj->flags |= FLAG_CHECKED;
}
+ read_unlock();
}
-}
-static int is_delta_type(enum object_type type)
-{
- return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
+ free(new_data);
}
/*
if (!delta_nr) {
c->data = get_data_from_pack(obj);
c->size = obj->size;
- base_cache_used += c->size;
+ get_thread_data()->base_cache_used += c->size;
prune_base_data(c);
}
for (; delta_nr > 0; delta_nr--) {
free(raw);
if (!c->data)
bad_object(obj->idx.offset, _("failed to apply delta"));
- base_cache_used += c->size;
+ get_thread_data()->base_cache_used += c->size;
prune_base_data(c);
}
free(delta);
free(delta_data);
if (!result->data)
bad_object(delta_obj->idx.offset, _("failed to apply delta"));
- sha1_object(result->data, result->size, delta_obj->real_type,
+ hash_sha1_file(result->data, result->size,
+ typename(delta_obj->real_type), delta_obj->idx.sha1);
+ sha1_object(result->data, NULL, result->size, delta_obj->real_type,
delta_obj->idx.sha1);
+ counter_lock();
nr_resolved_deltas++;
+ counter_unlock();
}
static struct base_data *find_unresolved_deltas_1(struct base_data *base,
objects[delta_b->obj_no].type);
}
-/* Parse all objects and return the pack content SHA1 hash */
+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);
+}
+
+#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;
+ int i, nr_delays = 0;
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"),
nr_objects);
for (i = 0; i < nr_objects; i++) {
struct object_entry *obj = &objects[i];
- void *data = unpack_raw_entry(obj, &delta->base);
+ void *data = unpack_raw_entry(obj, &delta->base, obj->idx.sha1);
obj->real_type = obj->type;
if (is_delta_type(obj->type)) {
nr_deltas++;
delta->obj_no = i;
delta++;
+ } else if (!data) {
+ /* large blobs, check later */
+ obj->real_type = OBJ_BAD;
+ nr_delays++;
} else
- sha1_object(data, obj->size, obj->type, obj->idx.sha1);
+ sha1_object(data, NULL, obj->size, obj->type, obj->idx.sha1);
free(data);
display_progress(progress, i+1);
}
lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size)
die(_("pack has junk at the end"));
+ for (i = 0; i < nr_objects; i++) {
+ struct object_entry *obj = &objects[i];
+ if (obj->real_type != OBJ_BAD)
+ continue;
+ obj->real_type = obj->type;
+ sha1_object(NULL, obj, obj->size, obj->type, obj->idx.sha1);
+ nr_delays--;
+ }
+ if (nr_delays)
+ die(_("confusion beyond insanity in parse_pack_objects()"));
+}
+
+/*
+ * 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;
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);
+
+#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 = alloc_base_data();
if (is_delta_type(obj->type))
continue;
- base_obj->obj = obj;
- base_obj->data = NULL;
- find_unresolved_deltas(base_obj);
+ 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)
{
git_zstream stream;
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);
}
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;
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 = 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(Q_("pack has %d unresolved delta",
- "pack has %d unresolved deltas",
- nr_deltas - nr_resolved_deltas),
- nr_deltas - nr_resolved_deltas);
- }
+ resolve_deltas();
+ conclude_pack(fix_thin_pack, curr_pack, pack_sha1);
free(deltas);
if (strict)
check_objects();