Merge branch 'nd/pack-deltify-regression-fix'

In a recent update in 2.18 era, "git pack-objects" started
producing a larger than necessary packfiles by missing
opportunities to use large deltas.

* nd/pack-deltify-regression-fix:
  pack-objects: fix performance issues on packing large deltas

5 files changed, 58 insertions, 15 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 0d80dee2ba..d1144a8f7e 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -2041,10 +2041,6 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 	delta_buf = create_delta(src->index, trg->data, trg_size, &delta_size, max_size);
 	if (!delta_buf)
 		return 0;
-	if (delta_size >= (1U << OE_DELTA_SIZE_BITS)) {
-		free(delta_buf);
-		return 0;
-	}
 
 	if (DELTA(trg_entry)) {
 		/* Prefer only shallower same-sized deltas. */
@@ -2303,6 +2299,7 @@ static void init_threaded_search(void)
 	pthread_mutex_init(&cache_mutex, NULL);
 	pthread_mutex_init(&progress_mutex, NULL);
 	pthread_cond_init(&progress_cond, NULL);
+	pthread_mutex_init(&to_pack.lock, NULL);
 	old_try_to_free_routine = set_try_to_free_routine(try_to_free_from_threads);
 }
 
diff --git a/ci/run-build-and-tests.sh b/ci/run-build-and-tests.sh
index 4b04c75b7f..2a5bff4a1c 100755
--- a/ci/run-build-and-tests.sh
+++ b/ci/run-build-and-tests.sh
@@ -14,6 +14,7 @@ then
 	export GIT_TEST_SPLIT_INDEX=yes
 	export GIT_TEST_FULL_IN_PACK_ARRAY=true
 	export GIT_TEST_OE_SIZE=10
+	export GIT_TEST_OE_DELTA_SIZE=5
 	make --quiet test
 fi
 
diff --git a/pack-objects.c b/pack-objects.c
index 92708522e7..6ef87e5683 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -146,6 +146,8 @@ void prepare_packing_data(struct packing_data *pdata)
 
 	pdata->oe_size_limit = git_env_ulong("GIT_TEST_OE_SIZE",
 					     1U << OE_SIZE_BITS);
+	pdata->oe_delta_size_limit = git_env_ulong("GIT_TEST_OE_DELTA_SIZE",
+						   1UL << OE_DELTA_SIZE_BITS);
 }
 
 struct object_entry *packlist_alloc(struct packing_data *pdata,
@@ -160,6 +162,8 @@ struct object_entry *packlist_alloc(struct packing_data *pdata,
 
 		if (!pdata->in_pack_by_idx)
 			REALLOC_ARRAY(pdata->in_pack, pdata->nr_alloc);
+		if (pdata->delta_size)
+			REALLOC_ARRAY(pdata->delta_size, pdata->nr_alloc);
 	}
 
 	new_entry = pdata->objects + pdata->nr_objects++;
diff --git a/pack-objects.h b/pack-objects.h
index 08c6b57d49..62806ccc39 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -2,6 +2,7 @@
 #define PACK_OBJECTS_H
 
 #include "object-store.h"
+#include "thread-utils.h"
 #include "pack.h"
 
 #define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024)
@@ -15,7 +16,7 @@
  * above this limit. Don't lower it too much.
  */
 #define OE_SIZE_BITS		31
-#define OE_DELTA_SIZE_BITS	20
+#define OE_DELTA_SIZE_BITS	23
 
 /*
  * State flags for depth-first search used for analyzing delta cycles.
@@ -95,11 +96,12 @@ struct object_entry {
 				     */
 	unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
 	unsigned delta_size_valid:1;
+	unsigned char in_pack_header_size;
 	unsigned in_pack_idx:OE_IN_PACK_BITS;	/* already in pack */
 	unsigned z_delta_size:OE_Z_DELTA_BITS;
 	unsigned type_valid:1;
-	unsigned type_:TYPE_BITS;
 	unsigned no_try_delta:1;
+	unsigned type_:TYPE_BITS;
 	unsigned in_pack_type:TYPE_BITS; /* could be delta */
 	unsigned preferred_base:1; /*
 				    * we do not pack this, but is available
@@ -109,17 +111,16 @@ struct object_entry {
 	unsigned tagged:1; /* near the very tip of refs */
 	unsigned filled:1; /* assigned write-order */
 	unsigned dfs_state:OE_DFS_STATE_BITS;
-	unsigned char in_pack_header_size;
 	unsigned depth:OE_DEPTH_BITS;
 
 	/*
 	 * pahole results on 64-bit linux (gcc and clang)
 	 *
-	 *   size: 80, bit_padding: 20 bits, holes: 8 bits
+	 *   size: 80, bit_padding: 9 bits
 	 *
 	 * and on 32-bit (gcc)
 	 *
-	 *   size: 76, bit_padding: 20 bits, holes: 8 bits
+	 *   size: 76, bit_padding: 9 bits
 	 */
 };
 
@@ -131,6 +132,7 @@ struct packing_data {
 	uint32_t index_size;
 
 	unsigned int *in_pack_pos;
+	unsigned long *delta_size;
 
 	/*
 	 * Only one of these can be non-NULL and they have different
@@ -141,10 +143,29 @@ struct packing_data {
 	struct packed_git **in_pack_by_idx;
 	struct packed_git **in_pack;
 
+#ifndef NO_PTHREADS
+	pthread_mutex_t lock;
+#endif
+
 	uintmax_t oe_size_limit;
+	uintmax_t oe_delta_size_limit;
 };
 
 void prepare_packing_data(struct packing_data *pdata);
+
+static inline void packing_data_lock(struct packing_data *pdata)
+{
+#ifndef NO_PTHREADS
+	pthread_mutex_lock(&pdata->lock);
+#endif
+}
+static inline void packing_data_unlock(struct packing_data *pdata)
+{
+#ifndef NO_PTHREADS
+	pthread_mutex_unlock(&pdata->lock);
+#endif
+}
+
 struct object_entry *packlist_alloc(struct packing_data *pdata,
 				    const unsigned char *sha1,
 				    uint32_t index_pos);
@@ -333,18 +354,34 @@ static inline unsigned long oe_delta_size(struct packing_data *pack,
 {
 	if (e->delta_size_valid)
 		return e->delta_size_;
-	return oe_size(pack, e);
+
+	/*
+	 * pack->detla_size[] can't be NULL because oe_set_delta_size()
+	 * must have been called when a new delta is saved with
+	 * oe_set_delta().
+	 * If oe_delta() returns NULL (i.e. default state, which means
+	 * delta_size_valid is also false), then the caller must never
+	 * call oe_delta_size().
+	 */
+	return pack->delta_size[e - pack->objects];
 }
 
 static inline void oe_set_delta_size(struct packing_data *pack,
 				     struct object_entry *e,
 				     unsigned long size)
 {
-	e->delta_size_ = size;
-	e->delta_size_valid = e->delta_size_ == size;
-	if (!e->delta_size_valid && size != oe_size(pack, e))
-		BUG("this can only happen in check_object() "
-		    "where delta size is the same as entry size");
+	if (size < pack->oe_delta_size_limit) {
+		e->delta_size_ = size;
+		e->delta_size_valid = 1;
+	} else {
+		packing_data_lock(pack);
+		if (!pack->delta_size)
+			ALLOC_ARRAY(pack->delta_size, pack->nr_alloc);
+		packing_data_unlock(pack);
+
+		pack->delta_size[e - pack->objects] = size;
+		e->delta_size_valid = 0;
+	}
 }
 
 #endif
diff --git a/t/README b/t/README
index 8373a27fea..9028b47d92 100644
--- a/t/README
+++ b/t/README
@@ -315,6 +315,10 @@ packs on demand. This normally only happens when the object size is
 over 2GB. This variable forces the code path on any object larger than
 <n> bytes.
 
+GIT_TEST_OE_DELTA_SIZE=<n> exercises the uncomon pack-objects code
+path where deltas larger than this limit require extra memory
+allocation for bookkeeping.
+
 Naming Tests
 ------------