Web lists-archives.com

[PATCH 14/15] pack-objects: reorder members to shrink struct object_entry




Previous patches leave lots of holes and padding in this struct. This
patch reorders the members and shrinks the struct down to 80 bytes
(from 136 bytes on 64-bit systems, before any field shrinking is done)
with 16 bits to spare (and a couple more in in_pack_header_size when
we really run out of bits).

This is the last in a series of memory reduction patches (see
"pack-objects: a bit of document about struct object_entry" for the
first one).

Overall they've reduced repack memory size on linux-2.6.git from
3.747G to 3.424G, or by around 320M, a decrease of 8.5%. The runtime
of repack has stayed the same throughout this series. Ævar's testing
on a big monorepo he has access to (bigger than linux-2.6.git) has
shown a 7.9% reduction, so the overall expected improvement should be
somewhere around 8%.

See 87po42cwql.fsf@xxxxxxxxxxxxxxxxxxx on-list
(https://public-inbox.org/git/87po42cwql.fsf@xxxxxxxxxxxxxxxxxxx/) for
more detailed numbers and a test script used to produce the numbers
cited above.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@xxxxxxxxx>
---
 pack-objects.h | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/pack-objects.h b/pack-objects.h
index 1c588184b2..e5456c6c89 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -28,6 +28,10 @@ enum dfs_state {
 };
 
 /*
+ * The size of struct nearly determines pack-objects's memory
+ * consumption. This struct is packed tight for that reason. When you
+ * add or reorder something in this struct, think a bit about this.
+ *
  * basic object info
  * -----------------
  * idx.oid is filled up before delta searching starts. idx.crc32 is
@@ -76,34 +80,44 @@ enum dfs_state {
  */
 struct object_entry {
 	struct pack_idx_entry idx;
+	void *delta_data;	/* cached delta (uncompressed) */
+	off_t in_pack_offset;
+	uint32_t hash;			/* name hint hash */
 	unsigned size_:OE_SIZE_BITS;
 	unsigned size_valid:1;
-	unsigned in_pack_idx:OE_IN_PACK_BITS;	/* already in pack */
-	off_t in_pack_offset;
 	uint32_t delta_idx;	/* delta base object */
 	uint32_t delta_child_idx; /* deltified objects who bases me */
 	uint32_t delta_sibling_idx; /* other deltified objects who
 				     * uses the same base as me
 				     */
-	void *delta_data;	/* cached delta (uncompressed) */
 	unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
 	unsigned delta_size_valid:1;
+	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 in_pack_type:TYPE_BITS; /* could be delta */
-	unsigned type_valid:1;
-	uint32_t hash;			/* name hint hash */
-	unsigned char in_pack_header_size;
 	unsigned preferred_base:1; /*
 				    * we do not pack this, but is available
 				    * to be used as the base object to delta
 				    * objects against.
 				    */
-	unsigned no_try_delta:1;
 	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
+	 *
+	 * and on 32-bit (gcc)
+	 *
+	 *   size: 76, bit_padding: 20 bits, holes: 8 bits
+	 */
 };
 
 struct packing_data {
-- 
2.17.0.367.g5dd2e386c3