pack-objects: move in_pack out of struct object_entry

Instead of using 8 bytes (on 64 bit arch) to store a pointer to a
pack. Use an index instead since the number of packs should be
relatively small.

This limits the number of packs we can handle to 1k. Since we can't be
sure people can never run into the situation where they have more than
1k pack files. Provide a fall back route for it.

If we find out they have too many packs, the new in_pack_by_idx[]
array (which has at most 1k elements) will not be used. Instead we
allocate in_pack[] array that holds nr_objects elements. This is
similar to how the optional in_pack_pos field is handled.

The new simple test is just to make sure the too-many-packs code path
is at least executed. The true test is running

    make test GIT_TEST_FULL_IN_PACK_ARRAY=1

to take advantage of other special case tests.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 65 insertions, 0 deletions

diff --git a/pack-objects.c b/pack-objects.c
index 9558d13834..08cfe68b6b 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -2,6 +2,8 @@
 #include "object.h"
 #include "pack.h"
 #include "pack-objects.h"
+#include "packfile.h"
+#include "config.h"
 
 static uint32_t locate_object_entry_hash(struct packing_data *pdata,
 					 const unsigned char *sha1,
@@ -86,6 +88,63 @@ struct object_entry *packlist_find(struct packing_data *pdata,
 	return &pdata->objects[pdata->index[i] - 1];
 }
 
+static void prepare_in_pack_by_idx(struct packing_data *pdata)
+{
+	struct packed_git **mapping, *p;
+	int cnt = 0, nr = 1U << OE_IN_PACK_BITS;
+
+	ALLOC_ARRAY(mapping, nr);
+	/*
+	 * oe_in_pack() on an all-zero'd object_entry
+	 * (i.e. in_pack_idx also zero) should return NULL.
+	 */
+	mapping[cnt++] = NULL;
+	for (p = get_packed_git(the_repository); p; p = p->next, cnt++) {
+		if (cnt == nr) {
+			free(mapping);
+			return;
+		}
+		p->index = cnt;
+		mapping[cnt] = p;
+	}
+	pdata->in_pack_by_idx = mapping;
+}
+
+/*
+ * A new pack appears after prepare_in_pack_by_idx() has been
+ * run. This is likely a race.
+ *
+ * We could map this new pack to in_pack_by_idx[] array, but then we
+ * have to deal with full array anyway. And since it's hard to test
+ * this fall back code, just stay simple and fall back to using
+ * in_pack[] array.
+ */
+void oe_map_new_pack(struct packing_data *pack,
+		     struct packed_git *p)
+{
+	uint32_t i;
+
+	REALLOC_ARRAY(pack->in_pack, pack->nr_alloc);
+
+	for (i = 0; i < pack->nr_objects; i++)
+		pack->in_pack[i] = oe_in_pack(pack, pack->objects + i);
+
+	FREE_AND_NULL(pack->in_pack_by_idx);
+}
+
+/* assume pdata is already zero'd by caller */
+void prepare_packing_data(struct packing_data *pdata)
+{
+	if (git_env_bool("GIT_TEST_FULL_IN_PACK_ARRAY", 0)) {
+		/*
+		 * do not initialize in_pack_by_idx[] to force the
+		 * slow path in oe_in_pack()
+		 */
+	} else {
+		prepare_in_pack_by_idx(pdata);
+	}
+}
+
 struct object_entry *packlist_alloc(struct packing_data *pdata,
 				    const unsigned char *sha1,
 				    uint32_t index_pos)
@@ -95,6 +154,9 @@ struct object_entry *packlist_alloc(struct packing_data *pdata,
 	if (pdata->nr_objects >= pdata->nr_alloc) {
 		pdata->nr_alloc = (pdata->nr_alloc  + 1024) * 3 / 2;
 		REALLOC_ARRAY(pdata->objects, pdata->nr_alloc);
+
+		if (!pdata->in_pack_by_idx)
+			REALLOC_ARRAY(pdata->in_pack, pdata->nr_alloc);
 	}
 
 	new_entry = pdata->objects + pdata->nr_objects++;
@@ -107,5 +169,8 @@ struct object_entry *packlist_alloc(struct packing_data *pdata,
 	else
 		pdata->index[index_pos] = pdata->nr_objects;
 
+	if (pdata->in_pack)
+		pdata->in_pack[pdata->nr_objects - 1] = NULL;
+
 	return new_entry;
 }