Re: [RFC PATCH] index-pack: improve performance on NFS

@@ -135,6 +135,18 @@ struct raw_object_store {
 	 */
 	struct packed_git *all_packs;
 
+	/*
+	 * A set of all loose objects we have. This probably ought to be split
+	 * into a set of 256 caches so that we can fault in one directory at a
+	 * time.
+	 */
+	struct oid_array loose_cache;
+	enum {
+		LOOSE_CACHE_UNFILLED = 0,
+		LOOSE_CACHE_INVALID,
+		LOOSE_CACHE_VALID
+	} loose_cache_status;
+
 	/*
 	 * A fast, rough count of the number of objects in the repository.
 	 * These two fields are not meant for direct access. Use

@@ -990,6 +990,8 @@ void reprepare_packed_git(struct repository *r)
 	r->objects->approximate_object_count_valid = 0;
 	r->objects->packed_git_initialized = 0;
 	prepare_packed_git(r);
+	oid_array_clear(&r->objects->loose_cache);
+	r->objects->loose_cache_status = LOOSE_CACHE_UNFILLED;
 }
 
 struct packed_git *get_packed_git(struct repository *r)

@@ -1172,6 +1172,40 @@ int parse_sha1_header(const char *hdr, unsigned long *sizep)
 	return parse_sha1_header_extended(hdr, &oi, 0);
 }
 
+/* probably should be configurable? */
+#define LOOSE_OBJECT_CACHE_MAX 65536
+
+static int fill_loose_cache(const struct object_id *oid,
+			    const char *path,
+			    void *data)
+{
+	struct oid_array *cache = data;
+
+	if (cache->nr == LOOSE_OBJECT_CACHE_MAX)
+		return -1;
+
+	oid_array_append(data, oid);
+	return 0;
+}
+
+static int quick_has_loose(struct raw_object_store *r,
+			   struct object_id *oid)
+{
+	struct oid_array *cache = &r->loose_cache;
+
+	if (r->loose_cache_status == LOOSE_CACHE_UNFILLED) {
+		if (for_each_loose_object(fill_loose_cache, cache, 0) < 0)
+			r->loose_cache_status = LOOSE_CACHE_INVALID;
+		else
+			r->loose_cache_status = LOOSE_CACHE_VALID;
+	}
+
+	if (r->loose_cache_status == LOOSE_CACHE_INVALID)
+		return -1;
+
+	return oid_array_lookup(cache, oid) >= 0;
+}
+
 static int sha1_loose_object_info(struct repository *r,
 				  const unsigned char *sha1,
 				  struct object_info *oi, int flags)

@@ -1198,6 +1232,19 @@ static int sha1_loose_object_info(struct repository *r,
 	if (!oi->typep && !oi->type_name && !oi->sizep && !oi->contentp) {
 		const char *path;
 		struct stat st;
+		if (!oi->disk_sizep && (flags & OBJECT_INFO_QUICK)) {
+			struct object_id oid;
+			hashcpy(oid.hash, sha1);
+			switch (quick_has_loose(r->objects, &oid)) {
+			case 0:
+				return -1; /* missing: error */
+			case 1:
+				return 0; /* have: 0 == success */
+			default:
+				/* unknown; fall back to stat */
+				break;
+			}
+		}
 		if (stat_sha1_file(r, sha1, &st, &path) < 0)
 			return -1;
 		if (oi->disk_sizep)