for_each_packed_object: support iterating in pack-order

peff · gitster · commit 736eb88fdc8a · 2018-08-13T13:48:28.000-07:00
We currently iterate over objects within a pack in .idx order, which uses the object hashes. That means that it is effectively random with respect to the location of the object within the pack. If you're going to access the actual object data, there are two reasons to move linearly through the pack itself: 1. It improves the locality of access in the packfile. In the cold-cache case, this may mean fewer disk seeks, or better usage of disk cache. 2. We store related deltas together in the packfile. Which means that the delta base cache can operate much more efficiently if we visit all of those related deltas in sequence, as the earlier items are likely to still be in the cache. Whereas if we visit the objects in random order, our cache entries are much more likely to have been evicted by unrelated deltas in the meantime. So in general, if you're going to access the object contents pack order is generally going to end up more efficient. But if you're simply generating a list of object names, or if you're going to end up sorting the result anyway, you're better off just using the .idx order, as finding the pack order means generating the in-memory pack-revindex. According to the numbers in 8b8dfd5 (pack-revindex: radix-sort the revindex, 2013-07-11), that takes about 200ms for linux.git, and 20ms for git.git (those numbers are a few years old but are still a good ballpark). That makes it a good optimization for some cases (we can save tens of seconds in git.git by having good locality of delta access, for a 20ms cost), but a bad one for others (e.g., right now "cat-file --batch-all-objects --batch-check="%(objectname)" is 170ms in git.git, so adding 20ms to that is noticeable). Hence this patch makes it an optional flag. You can't actually do any interesting timings yet, as it's not plumbed through to any user-facing tools like cat-file. That will come in a later patch. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/cache.h b/cache.h
@@ -1633,6 +1633,11 @@ enum for_each_object_flags {
 
 	/* Only iterate over packs obtained from the promisor remote. */
 	FOR_EACH_OBJECT_PROMISOR_ONLY = (1<<1),
+
+	/*
+	 * Visit objects within a pack in packfile order rather than .idx order
+	 */
+	FOR_EACH_OBJECT_PACK_ORDER = (1<<2),
 };
 
 /*
diff --git a/commit-graph.c b/commit-graph.c
@@ -730,7 +730,7 @@ void write_commit_graph(const char *obj_dir,
 				die("error adding pack %s", packname.buf);
 			if (open_pack_index(p))
 				die("error opening index for %s", packname.buf);
-			for_each_object_in_pack(p, add_packed_commits, &oids);
+			for_each_object_in_pack(p, add_packed_commits, &oids, 0);
 			close_pack(p);
 		}
 		strbuf_release(&packname);
diff --git a/packfile.c b/packfile.c
@@ -1885,19 +1885,30 @@ int has_pack_index(const unsigned char *sha1)
 	return 1;
 }
 
-int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn cb, void *data)
+int for_each_object_in_pack(struct packed_git *p,
+			    each_packed_object_fn cb, void *data,
+			    enum for_each_object_flags flags)
 {
 	uint32_t i;
 	int r = 0;
 
+	if (flags & FOR_EACH_OBJECT_PACK_ORDER)
+		load_pack_revindex(p);
+
 	for (i = 0; i < p->num_objects; i++) {
+		uint32_t pos;
 		struct object_id oid;
 
-		if (!nth_packed_object_oid(&oid, p, i))
+		if (flags & FOR_EACH_OBJECT_PACK_ORDER)
+			pos = p->revindex[i].nr;
+		else
+			pos = i;
+
+		if (!nth_packed_object_oid(&oid, p, pos))
 			return error("unable to get sha1 of object %u in %s",
-				     i, p->pack_name);
+				     pos, p->pack_name);
 
-		r = cb(&oid, p, i, data);
+		r = cb(&oid, p, pos, data);
 		if (r)
 			break;
 	}
@@ -1922,7 +1933,7 @@ int for_each_packed_object(each_packed_object_fn cb, void *data,
 			pack_errors = 1;
 			continue;
 		}
-		r = for_each_object_in_pack(p, cb, data);
+		r = for_each_object_in_pack(p, cb, data, flags);
 		if (r)
 			break;
 	}
diff --git a/packfile.h b/packfile.h
@@ -153,16 +153,18 @@ extern int has_pack_index(const unsigned char *sha1);
  * By default, this includes both local and alternate packs.
  *
  * Note that some objects may appear twice if they are found in multiple packs.
- * Each pack is visited in an unspecified order. Objects within a pack are
- * visited in pack-idx order (i.e., sorted by oid).
+ * Each pack is visited in an unspecified order. By default, objects within a
+ * pack are visited in pack-idx order (i.e., sorted by oid).
  *
  * The list of flags can be found in cache.h.
  */
 typedef int each_packed_object_fn(const struct object_id *oid,
 				  struct packed_git *pack,
 				  uint32_t pos,
 				  void *data);
-int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn, void *data);
+int for_each_object_in_pack(struct packed_git *p,
+			    each_packed_object_fn, void *data,
+			    enum for_each_object_flags flags);
 int for_each_packed_object(each_packed_object_fn, void *,
 			   enum for_each_object_flags flags);
 

Original file line number	Diff line number	Diff line change
`@@ -730,7 +730,7 @@ void write_commit_graph(const char *obj_dir,`
`730`	`730`	`die("error adding pack %s", packname.buf);`
`731`	`731`	`if (open_pack_index(p))`
`732`	`732`	`die("error opening index for %s", packname.buf);`
`733`		`- for_each_object_in_pack(p, add_packed_commits, &oids);`
	`733`	`+ for_each_object_in_pack(p, add_packed_commits, &oids, 0);`
`734`	`734`	`close_pack(p);`
`735`	`735`	`}`
`736`	`736`	`strbuf_release(&packname);`