提交 dd5a1843 编写于 作者: E Eric Dumazet 提交者: David S. Miller

[IPSEC] flow: reorder "struct flow_cache_entry" and remove SLAB_HWCACHE_ALIGN

1) We can shrink sizeof(struct flow_cache_entry) by 8 bytes on 64bit arches.
2) No need to align these structures to hardware cache lines, this only waste 
   ram for very litle gain.
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 fca09fb7
......@@ -30,8 +30,8 @@ struct flow_cache_entry {
struct flow_cache_entry *next;
u16 family;
u8 dir;
struct flowi key;
u32 genid;
struct flowi key;
void *object;
atomic_t *object_ref;
};
......@@ -346,7 +346,7 @@ static int __init flow_cache_init(void)
flow_cachep = kmem_cache_create("flow_cache",
sizeof(struct flow_cache_entry),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
0, SLAB_PANIC,
NULL);
flow_hash_shift = 10;
flow_lwm = 2 * flow_hash_size;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册