Implement a simple delta_base cache

This trivial 256-entry delta_base cache improves performance for some
loads by a factor of 2.5 or so.

Instead of always re-generating the delta bases (possibly over and over
and over again), just cache the last few ones. They often can get re-used.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/sha1_file.c b/sha1_file.c
index f11ca3fbacd5de159129c3311d7915d56aff79e4..a7e3a2a9f963ce1bee1f54f05eaa8852b2bd2347 100644 (file)
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1352,16 +1352,57 @@ static void *unpack_compressed_entry(struct packed_git *p,
        return buffer;
 }
 
        return buffer;
 }
 

+#define MAX_DELTA_CACHE (256)
+
+static struct delta_base_cache_entry {
+       struct packed_git *p;
+       off_t base_offset;
+       unsigned long size;
+       void *data;
+       enum object_type type;
+} delta_base_cache[MAX_DELTA_CACHE];
+
+static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
+{
+       unsigned long hash;
+
+       hash = (unsigned long)p + (unsigned long)base_offset;
+       hash += (hash >> 8) + (hash >> 16);
+       return hash & 0xff;
+}
+

 static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
        unsigned long *base_size, enum object_type *type)
 {
 static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
        unsigned long *base_size, enum object_type *type)
 {

+       void *ret;
+       unsigned long hash = pack_entry_hash(p, base_offset);
+       struct delta_base_cache_entry *ent = delta_base_cache + hash;
+
+       ret = ent->data;
+       if (ret && ent->p == p && ent->base_offset == base_offset)
+               goto found_cache_entry;

        return unpack_entry(p, base_offset, type, base_size);
        return unpack_entry(p, base_offset, type, base_size);

+
+found_cache_entry:
+       ent->data = NULL;
+       *type = ent->type;
+       *base_size = ent->size;
+       return ret;

 }
 
 static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
        void *base, unsigned long base_size, enum object_type type)
 {
 }
 
 static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
        void *base, unsigned long base_size, enum object_type type)
 {

-       free(base);
+       unsigned long hash = pack_entry_hash(p, base_offset);
+       struct delta_base_cache_entry *ent = delta_base_cache + hash;
+
+       if (ent->data)
+               free(ent->data);
+       ent->p = p;
+       ent->base_offset = base_offset;
+       ent->type = type;
+       ent->data = base;
+       ent->size = base_size;

 }
 
 static void *unpack_delta_entry(struct packed_git *p,
 }
 
 static void *unpack_delta_entry(struct packed_git *p,