[PATCH v2 0/2] Multithread index-pack

@@ -682,6 +682,23 @@ static int compare_delta_entry(const void *a, const void *b)
 				   objects[delta_b->obj_no].type);
 }
 
+/*
+ * 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 second_pass(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);
+	display_progress(progress, nr_resolved_deltas);
+}
+
 /* Parse all objects and return the pack content SHA1 hash */
 static void parse_pack_objects(unsigned char *sha1)
 {

@@ -736,26 +753,14 @@ 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);
 	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);
-		display_progress(progress, nr_resolved_deltas);
+		second_pass(obj);
 	}
 }
 

@@ -74,6 +74,16 @@ OPTIONS
 --strict::
 	Die, if the pack contains broken objects or links.
 
+--threads=<n>::
+	Specifies the number of threads to spawn when resolving
+	deltas. This requires that index-pack be compiled with
+	pthreads otherwise this option is ignored with a warning.
+	This is meant to reduce packing time on multiprocessor
+	machines. The required amount of memory for the delta search
+	window is however multiplied by the number of threads.
+	Specifying 0 will cause git to auto-detect the number of CPU's
+	and use maximum 3 threads.
+
 
 Note
 ----

@@ -2159,7 +2159,7 @@ builtin/branch.o builtin/checkout.o builtin/clone.o builtin/reset.o branch.o tra
 builtin/bundle.o bundle.o transport.o: bundle.h
 builtin/bisect--helper.o builtin/rev-list.o bisect.o: bisect.h
 builtin/clone.o builtin/fetch-pack.o transport.o: fetch-pack.h
-builtin/grep.o builtin/pack-objects.o transport-helper.o thread-utils.o: thread-utils.h
+builtin/index-pack.o builtin/grep.o builtin/pack-objects.o transport-helper.o thread-utils.o: thread-utils.h
 builtin/send-pack.o transport.o: send-pack.h
 builtin/log.o builtin/shortlog.o: shortlog.h
 builtin/prune.o builtin/reflog.o reachable.o: reachable.h

@@ -9,6 +9,7 @@
 #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>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";

@@ -38,6 +39,14 @@ struct base_data {
 	int ofs_first, ofs_last;
 };
 
+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.

@@ -54,11 +63,12 @@ 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_processed;
 static int nr_deltas;
 static int nr_resolved_deltas;
+static int nr_threads;
 
 static int from_stdin;
 static int strict;

@@ -75,6 +85,72 @@ 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 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 (nr_threads > 1)
+		pthread_mutex_lock(mutex);
+}
+
+static inline void unlock_mutex(pthread_mutex_t *mutex)
+{
+	if (nr_threads > 1)
+		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));
+}
+
+static void cleanup_thread(void)
+{
+	pthread_mutex_destroy(&read_mutex);
+	pthread_mutex_destroy(&counter_mutex);
+	pthread_mutex_destroy(&work_mutex);
+	pthread_key_delete(key);
+	nr_threads = 1;
+	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)

@@ -223,6 +299,17 @@ static NORETURN void bad_object(unsigned long offset, const char *format, ...)
 	die("pack has bad object at offset %lu: %s", offset, buf);
 }
 
+static struct thread_local *get_thread_data()
+{
+#ifndef NO_PTHREADS
+	if (nr_threads > 1)
+		return pthread_getspecific(key);
+#endif
+	assert(nr_threads == 1 &&
+	       "This should only be reached when all threads are gone");
+	return &nothread_data;
+}
+
 static struct base_data *alloc_base_data(void)
 {
 	struct base_data *base = xmalloc(sizeof(struct base_data));

@@ -237,15 +324,16 @@ 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);

@@ -257,12 +345,12 @@ 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);
 }
 

@@ -272,7 +360,7 @@ 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);
 }
 

@@ -461,19 +549,24 @@ 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));
 		if (size != has_size || type != has_type ||
 		    memcmp(data, has_data, size) != 0)
 			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)

@@ -507,6 +600,7 @@ static void sha1_object(const void *data, unsigned long size,
 			}
 			obj->flags |= FLAG_CHECKED;
 		}
+		read_unlock();
 	}
 }
 

@@ -552,7 +646,7 @@ static void *get_base_data(struct base_data *c)
 		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--) {

@@ -568,7 +662,7 @@ static void *get_base_data(struct base_data *c)
 			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);

@@ -596,7 +690,9 @@ static void resolve_delta(struct object_entry *delta_obj,
 		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 struct base_data *find_unresolved_deltas_1(struct base_data *base,

@@ -696,7 +792,31 @@ static void second_pass(struct object_entry *obj)
 	base_obj->obj = obj;
 	base_obj->data = NULL;
 	find_unresolved_deltas(base_obj);
-	display_progress(progress, nr_resolved_deltas);
+}
+
+static void *threaded_second_pass(void *arg)
+{
+#ifndef NO_PTHREADS
+	if (nr_threads > 1)
+		pthread_setspecific(key, arg);
+#endif
+	for (;;) {
+		int i;
+		work_lock();
+		display_progress(progress, nr_resolved_deltas);
+		while (nr_processed < nr_objects &&
+		       is_delta_type(objects[nr_processed].type))
+			nr_processed++;
+		if (nr_processed >= nr_objects) {
+			work_unlock();
+			break;
+		}
+		i = nr_processed++;
+		work_unlock();
+
+		second_pass(&objects[i]);
+	}
+	return NULL;
 }
 
 /* Parse all objects and return the pack content SHA1 hash */

@@ -755,13 +875,25 @@ static void parse_pack_objects(unsigned char *sha1)
 
 	if (verbose)
 		progress = start_progress("Resolving deltas", nr_deltas);
-	for (i = 0; i < nr_objects; i++) {
-		struct object_entry *obj = &objects[i];
 
-		if (is_delta_type(obj->type))
-			continue;
-		second_pass(obj);
+	nr_processed = 0;
+#ifndef NO_PTHREADS
+	if (nr_threads > 1) {
+		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
+	threaded_second_pass(NULL);
 }
 
 static int write_compressed(struct sha1file *f, void *in, unsigned int size)

@@ -967,6 +1099,18 @@ static int git_index_pack_config(const char *k, const char *v, void *cb)
 			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);
 }
 

@@ -1125,6 +1269,17 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				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;

@@ -1196,6 +1351,15 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	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));

@@ -69,6 +69,7 @@ static int nr_processed;
 static int nr_deltas;
 static int nr_resolved_deltas;
 static int nr_threads;
+static int threads_active;
 
 static int from_stdin;
 static int strict;

@@ -105,13 +106,13 @@ static pthread_key_t key;
 
 static inline void lock_mutex(pthread_mutex_t *mutex)
 {
-	if (nr_threads > 1)
+	if (threads_active)
 		pthread_mutex_lock(mutex);
 }
 
 static inline void unlock_mutex(pthread_mutex_t *mutex)
 {
-	if (nr_threads > 1)
+	if (threads_active)
 		pthread_mutex_unlock(mutex);
 }
 

@@ -125,14 +126,16 @@ static void init_thread(void)
 	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)
 {
+	threads_active = 0;
 	pthread_mutex_destroy(&read_mutex);
 	pthread_mutex_destroy(&counter_mutex);
 	pthread_mutex_destroy(&work_mutex);
-	pthread_key_delete(key);
+	/*pthread_key_delete(key);*/
 	nr_threads = 1;
 	free(thread_data);
 }
-- 8< --