[PATCH] straighten the list of objects to deltify

@@ -1313,12 +1313,6 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	if (trg_entry->type != src_entry->type)
 		return -1;
 
-	/* We do not compute delta to *create* objects we are not
-	 * going to pack.
-	 */
-	if (trg_entry->preferred_base)
-		return -1;
-
 	/*
 	 * We do not bother to try a delta that we discarded
 	 * on an earlier try, but only when reusing delta data.

@@ -1443,43 +1437,24 @@ static void free_unpacked(struct unpacked *n)
 	n->depth = 0;
 }
 
-static void find_deltas(struct object_entry **list, int window, int depth)
+static void find_deltas(struct object_entry **list, unsigned list_size,
+			unsigned nr_deltas, int window, int depth)
 {
-	uint32_t i = nr_objects, idx = 0, count = 0, processed = 0;
+	uint32_t i = list_size, idx = 0, count = 0, processed = 0;
 	unsigned int array_size = window * sizeof(struct unpacked);
 	struct unpacked *array;
 	int max_depth;
 
-	if (!nr_objects)
-		return;
 	array = xmalloc(array_size);
 	memset(array, 0, array_size);
 	if (progress)
-		start_progress(&progress_state, "Deltifying %u objects...", "", nr_result);
+		start_progress(&progress_state, "Deltifying %u objects...", "", nr_deltas);
 
 	do {
 		struct object_entry *entry = list[--i];
 		struct unpacked *n = array + idx;
 		int j, best_base = -1;
 
-		if (!entry->preferred_base)
-			processed++;
-
-		if (progress)
-			display_progress(&progress_state, processed);
-
-		if (entry->delta)
-			/* This happens if we decided to reuse existing
-			 * delta from a pack.  "!no_reuse_delta &&" is implied.
-			 */
-			continue;
-
-		if (entry->size < 50)
-			continue;
-
-		if (entry->no_try_delta)
-			continue;
-
 		free_unpacked(n);
 		n->entry = entry;
 

@@ -1491,6 +1466,15 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 			count--;
 		}
 
+		/* We do not compute delta to *create* objects we are not
+		 * going to pack.
+		 */
+		if (entry->preferred_base)
+			goto next;
+
+		if (progress)
+			display_progress(&progress_state, ++processed);
+
 		/*
 		 * If the current object is at pack edge, take the depth the
 		 * objects that depend on the current object into account

@@ -1565,18 +1549,41 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 static void prepare_pack(int window, int depth)
 {
 	struct object_entry **delta_list;
-	uint32_t i;
+	uint32_t i, n, nr_deltas;
 
 	get_object_details();
 
-	if (!window || !depth)
+	if (!nr_objects || !window || !depth)
 		return;
 
 	delta_list = xmalloc(nr_objects * sizeof(*delta_list));
-	for (i = 0; i < nr_objects; i++)
-		delta_list[i] = objects + i;
-	qsort(delta_list, nr_objects, sizeof(*delta_list), type_size_sort);
-	find_deltas(delta_list, window+1, depth);
+	nr_deltas = n = 0;
+
+	for (i = 0; i < nr_objects; i++) {
+		struct object_entry *entry = objects + i;
+
+		if (entry->delta)
+			/* This happens if we decided to reuse existing
+			 * delta from a pack.  "!no_reuse_delta &&" is implied.
+			 */
+			continue;
+
+		if (entry->size < 50)
+			continue;
+
+		if (entry->no_try_delta)
+			continue;
+
+		if (!entry->preferred_base)
+			nr_deltas++;
+
+		delta_list[n++] = entry;
+	}
+
+	if (nr_deltas) {
+		qsort(delta_list, n, sizeof(*delta_list), type_size_sort);
+		find_deltas(delta_list, n, nr_deltas, window+1, depth);
+	}
 	free(delta_list);
 }
 

@@ -78,7 +78,6 @@ static unsigned long delta_cache_size = 0;
 static unsigned long max_delta_cache_size = 0;
 static unsigned long cache_max_small_delta_size = 1000;
 
-static unsigned long window_memory_usage = 0;
 static unsigned long window_memory_limit = 0;
 
 /*

@@ -1300,7 +1299,7 @@ static int delta_cacheable(unsigned long src_size, unsigned long trg_size,
  * one.
  */
 static int try_delta(struct unpacked *trg, struct unpacked *src,
-		     unsigned max_depth)
+		     unsigned max_depth, unsigned long *mem_usage)
 {
 	struct object_entry *trg_entry = trg->entry;
 	struct object_entry *src_entry = src->entry;

@@ -1356,7 +1355,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 		if (sz != trg_size)
 			die("object %s inconsistent object length (%lu vs %lu)",
 			    sha1_to_hex(trg_entry->idx.sha1), sz, trg_size);
-		window_memory_usage += sz;
+		*mem_usage += sz;
 	}
 	if (!src->data) {
 		src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz);

@@ -1366,7 +1365,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 		if (sz != src_size)
 			die("object %s inconsistent object length (%lu vs %lu)",
 			    sha1_to_hex(src_entry->idx.sha1), sz, src_size);
-		window_memory_usage += sz;
+		*mem_usage += sz;
 	}
 	if (!src->index) {
 		src->index = create_delta_index(src->data, src_size);

@@ -1376,7 +1375,7 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 				warning("suboptimal pack - out of memory");
 			return 0;
 		}
-		window_memory_usage += sizeof_delta_index(src->index);
+		*mem_usage += sizeof_delta_index(src->index);
 	}
 
 	delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);

@@ -1423,18 +1422,19 @@ static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
 	return m;
 }
 
-static void free_unpacked(struct unpacked *n)
+static unsigned long free_unpacked(struct unpacked *n)
 {
-	window_memory_usage -= sizeof_delta_index(n->index);
+	unsigned long freed_mem = sizeof_delta_index(n->index);
 	free_delta_index(n->index);
 	n->index = NULL;
 	if (n->data) {
+		freed_mem += n->entry->size;
 		free(n->data);
 		n->data = NULL;
-		window_memory_usage -= n->entry->size;
 	}
 	n->entry = NULL;
 	n->depth = 0;
+	return freed_mem;
 }
 
 static void find_deltas(struct object_entry **list, unsigned list_size,

@@ -1443,7 +1443,7 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 	uint32_t i = list_size, idx = 0, count = 0, processed = 0;
 	unsigned int array_size = window * sizeof(struct unpacked);
 	struct unpacked *array;
-	int max_depth;
+	unsigned long mem_usage = 0;
 
 	array = xmalloc(array_size);
 	memset(array, 0, array_size);

@@ -1453,16 +1453,16 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 	do {
 		struct object_entry *entry = list[--i];
 		struct unpacked *n = array + idx;
-		int j, best_base = -1;
+		int j, max_depth, best_base = -1;
 
-		free_unpacked(n);
+		mem_usage -= free_unpacked(n);
 		n->entry = entry;
 
 		while (window_memory_limit &&
-		       window_memory_usage > window_memory_limit &&
+		       mem_usage > window_memory_limit &&
 		       count > 1) {
 			uint32_t tail = (idx + window - count) % window;
-			free_unpacked(array + tail);
+			mem_usage -= free_unpacked(array + tail);
 			count--;
 		}
 

@@ -1497,7 +1497,7 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 			m = array + other_idx;
 			if (!m->entry)
 				break;
-			ret = try_delta(n, m, max_depth);
+			ret = try_delta(n, m, max_depth, &mem_usage);
 			if (ret < 0)
 				break;
 			else if (ret > 0)

@@ -1438,17 +1438,15 @@ static unsigned long free_unpacked(struct unpacked *n)
 }
 
 static void find_deltas(struct object_entry **list, unsigned list_size,
-			unsigned nr_deltas, int window, int depth)
+			int window, int depth, unsigned *processed)
 {
-	uint32_t i = list_size, idx = 0, count = 0, processed = 0;
+	uint32_t i = list_size, idx = 0, count = 0;
 	unsigned int array_size = window * sizeof(struct unpacked);
 	struct unpacked *array;
 	unsigned long mem_usage = 0;
 
 	array = xmalloc(array_size);
 	memset(array, 0, array_size);
-	if (progress)
-		start_progress(&progress_state, "Deltifying %u objects...", "", nr_deltas);
 
 	do {
 		struct object_entry *entry = list[--i];

@@ -1472,8 +1470,9 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 		if (entry->preferred_base)
 			goto next;
 
+		(*processed)++;
 		if (progress)
-			display_progress(&progress_state, ++processed);
+			display_progress(&progress_state, *processed);
 
 		/*
 		 * If the current object is at pack edge, take the depth the

@@ -1536,9 +1535,6 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 			idx = 0;
 	} while (i > 0);
 
-	if (progress)
-		stop_progress(&progress_state);
-
 	for (i = 0; i < window; ++i) {
 		free_delta_index(array[i].index);
 		free(array[i].data);

@@ -1581,8 +1577,17 @@ static void prepare_pack(int window, int depth)
 	}
 
 	if (nr_deltas) {
+		unsigned nr_done = 0;
+		if (progress)
+			start_progress(&progress_state,
+				       "Deltifying %u objects...", "",
+				       nr_deltas);
 		qsort(delta_list, n, sizeof(*delta_list), type_size_sort);
-		find_deltas(delta_list, n, nr_deltas, window+1, depth);
+		find_deltas(delta_list, n, window+1, depth, &nr_done);
+		if (progress)
+			stop_progress(&progress_state);
+		if (nr_done != nr_deltas)
+			die("inconsistency with delta count");
 	}
 	free(delta_list);
 }

@@ -122,6 +122,9 @@ all::
 # If not set it defaults to the bare 'wish'. If it is set to the empty
 # string then NO_TCLTK will be forced (this is used by configure script).
 #
+# Define THREADED_DELTA_SEARCH if you have pthreads and wish to exploit
+# parallel delta searching when packing objects.
+#
 
 GIT-VERSION-FILE: .FORCE-GIT-VERSION-FILE
 	@$(SHELL_PATH) ./GIT-VERSION-GEN

@@ -662,6 +665,11 @@ ifdef NO_HSTRERROR
 	COMPAT_OBJS += compat/hstrerror.o
 endif
 
+ifdef THREADED_DELTA_SEARCH
+	BASIC_CFLAGS += -DTHREADED_DELTA_SEARCH
+	EXTLIBS += -lpthread
+endif
+
 ifeq ($(TCLTK_PATH),)
 NO_TCLTK=NoThanks
 endif

@@ -15,6 +15,10 @@
 #include "list-objects.h"
 #include "progress.h"
 
+#ifdef THREADED_DELTA_SEARCH
+#include <pthread.h>
+#endif
+
 static const char pack_usage[] = "\
 git-pack-objects [{ -q | --progress | --all-progress }] \n\
 	[--max-pack-size=N] [--local] [--incremental] \n\

@@ -1290,6 +1294,25 @@ static int delta_cacheable(unsigned long src_size, unsigned long trg_size,
 	return 0;
 }
 
+#ifdef THREADED_DELTA_SEARCH
+
+static pthread_mutex_t read_mutex = PTHREAD_MUTEX_INITIALIZER;
+#define read_lock()		pthread_mutex_lock(&read_mutex)
+#define read_unlock()		pthread_mutex_unlock(&read_mutex)
+
+static pthread_mutex_t progress_mutex = PTHREAD_MUTEX_INITIALIZER;
+#define progress_lock()		pthread_mutex_lock(&progress_mutex)
+#define progress_unlock()	pthread_mutex_unlock(&progress_mutex)
+
+#else
+
+#define read_lock()		0
+#define read_unlock()		0
+#define progress_lock()		0
+#define progress_unlock()	0
+
+#endif
+
 /*
  * We search for deltas _backwards_ in a list sorted by type and
  * by size, so that we see progressively smaller and smaller files.

@@ -1348,7 +1371,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 
 	/* Load data if not already done */
 	if (!trg->data) {
+		read_lock();
 		trg->data = read_sha1_file(trg_entry->idx.sha1, &type, &sz);
+		read_unlock();
 		if (!trg->data)
 			die("object %s cannot be read",
 			    sha1_to_hex(trg_entry->idx.sha1));

@@ -1358,7 +1383,9 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 		*mem_usage += sz;
 	}
 	if (!src->data) {
+		read_lock();
 		src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz);
+		read_unlock();
 		if (!src->data)
 			die("object %s cannot be read",
 			    sha1_to_hex(src_entry->idx.sha1));

@@ -1470,9 +1497,11 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 		if (entry->preferred_base)
 			goto next;
 
+		progress_lock();
 		(*processed)++;
 		if (progress)
 			display_progress(&progress_state, *processed);
+		progress_unlock();
 
 		/*
 		 * If the current object is at pack edge, take the depth the

@@ -1542,6 +1571,58 @@ static void find_deltas(struct object_entry **list, unsigned list_size,
 	free(array);
 }
 
+#ifdef THREADED_DELTA_SEARCH
+
+struct thread_params {
+	pthread_t thread;
+	struct object_entry **list;
+	unsigned list_size;
+	int window;
+	int depth;
+	unsigned *processed;
+};
+
+static void *threaded_find_deltas(void *arg)
+{
+	struct thread_params *p = arg;
+	if (p->list_size)
+		find_deltas(p->list, p->list_size,
+			    p->window, p->depth, p->processed);
+	return NULL;
+}
+
+#define NR_THREADS	8
+
+static void ll_find_deltas(struct object_entry **list, unsigned list_size,
+			   int window, int depth, unsigned *processed)
+{
+	struct thread_params p[NR_THREADS];
+	int i, ret;
+
+	for (i = 0; i < NR_THREADS; i++) {
+		unsigned sublist_size = list_size / (NR_THREADS - i);
+		p[i].list = list;
+		p[i].list_size = sublist_size;
+		p[i].window = window;
+		p[i].depth = depth;
+		p[i].processed = processed;
+		ret = pthread_create(&p[i].thread, NULL,
+				     threaded_find_deltas, &p[i]);
+		if (ret)
+			die("unable to create thread: %s", strerror(ret));
+		list += sublist_size;
+		list_size -= sublist_size;
+	}
+
+	for (i = 0; i < NR_THREADS; i++) {
+		pthread_join(p[i].thread, NULL);
+	}
+}
+
+#else
+#define ll_find_deltas find_deltas
+#endif
+
 static void prepare_pack(int window, int depth)
 {
 	struct object_entry **delta_list;

@@ -1583,7 +1664,7 @@ static void prepare_pack(int window, int depth)
 				       "Deltifying %u objects...", "",
 				       nr_deltas);
 		qsort(delta_list, n, sizeof(*delta_list), type_size_sort);
-		find_deltas(delta_list, n, window+1, depth, &nr_done);
+		ll_find_deltas(delta_list, n, window+1, depth, &nr_done);
 		if (progress)
 			stop_progress(&progress_state);
 		if (nr_done != nr_deltas)