[PATCH 4/4] pack v4: make use of cached v4 trees when unpacking

From

Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

Date

Sep 12, 2013, 10:38 UTC

Message-ID

<1378982284-7848-4-git-send-email-pclouds@gmail.com>

In-Reply-To

<1378982284-7848-1-git-send-email-pclouds@gmail.com>

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 The problem I see with decode_entries() is that given n copy
 sequences, it re-reads the same base n times. 30+ copy sequences are
 not unusual at all with git.git.

 I'm thinking of adding a cache to deal with one-base trees, which is
 all we have now. If we know in advance what base a tree needs without
 parsing the tree, we could unpack from base up like we do with
 ref-deltas. Because in this case we know the base is always flat, we
 could have a more efficient decode_entries that only goes through the
 base once. I want to get the timing down to as close as possible to
 v2 before adding v4-aware interface.

 Pack cache is an idea being cooked for a while by Jeff. Maybe we
 could merge his work to pack v4 or require it when pack v4 is finally
 merged to 'next'.

 packv4-parse.c | 17 +++++++++++++++--
 packv4-parse.h |  2 ++
 sha1_file.c    | 14 ++++++++++++++
 3 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/packv4-parse.c b/packv4-parse.c
index 5002f42..b8855b0 100644
--- a/packv4-parse.c
+++ b/packv4-parse.c
@@ -415,8 +415,20 @@ static int decode_entries(struct packed_git *p, struct pack_window **w_curs,
 	unsigned int nb_entries;
 	const unsigned char *src, *scp;
 	off_t copy_objoffset = 0;
+	const void *cached = NULL;
+	unsigned long cached_size, cached_v4_size;
+
+	if (hdr)	      /* we need offset point at obj header */
+		cached = get_cached_v4_tree(p, offset,
+					    &cached_size, &cached_v4_size);
+
+	if (cached) {
+		src = cached;
+		avail = cached_v4_size;
+		hdr = 0;
+	} else
+		src = use_pack(p, w_curs, offset, &avail);
 
-	src = use_pack(p, w_curs, offset, &avail);
 	scp = src;
 
 	if (hdr) {
@@ -452,7 +464,8 @@ static int decode_entries(struct packed_git *p, struct pack_window **w_curs,
 	while (count) {
 		unsigned int what;
 
-		if (avail < 20) {
+		/* fixme: need to put bach the out-of-bound check when cached == 1 */
+		if (!cached && avail < 20) {
 			src = use_pack(p, w_curs, offset, &avail);
 			if (avail < 20)
 				return -1;
diff --git a/packv4-parse.h b/packv4-parse.h
index 647b73c..f584c31 100644
--- a/packv4-parse.h
+++ b/packv4-parse.h
@@ -16,6 +16,8 @@ unsigned long pv4_unpack_object_header_buffer(const unsigned char *base,
 					      unsigned long *sizep);
 const unsigned char *get_sha1ref(struct packed_git *p,
 				 const unsigned char **bufp);
+const void *get_cached_v4_tree(struct packed_git *p, off_t base_offset,
+			 unsigned long *size, unsigned long *v4_size);
 
 void *pv4_get_commit(struct packed_git *p, struct pack_window **w_curs,
 		     off_t offset, unsigned long size);
diff --git a/sha1_file.c b/sha1_file.c
index b176316..82570be 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1967,6 +1967,20 @@ static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
 	return eq_delta_base_cache_entry(ent, p, base_offset);
 }
 
+const void *get_cached_v4_tree(struct packed_git *p, off_t base_offset,
+			 unsigned long *size, unsigned long *v4_size)
+{
+	struct delta_base_cache_entry *ent;
+	ent = get_delta_base_cache_entry(p, base_offset);
+
+	if (!eq_delta_base_cache_entry(ent, p, base_offset) ||
+	    ent->type != OBJ_PV4_TREE)
+		return NULL;
+	*size = ent->size;
+	*v4_size = ent->v4_size;
+	return ent->data;
+}
+
 static void clear_delta_base_cache_entry(struct delta_base_cache_entry *ent)
 {
 	ent->data = NULL;

-- 
1.8.2.83.gc99314b