Re: [PATCH] net/udp: do not touch skb->peeked unless really needed

On Wed, Dec 7, 2016, at 18:32, Eric Dumazet wrote:

On Wed, 2016-12-07 at 17:09 +0000, David Laight wrote:

quoted

From: Paolo Abeni

quoted

Sent: 06 December 2016 17:08

...

quoted

@@ -79,6 +82,9 @@ struct udp_sock {
 	int			(*gro_complete)(struct sock *sk,
 						struct sk_buff *skb,
 						int nhoff);
+
+	/* since we are prone to drops, avoid dirtying any sk cacheline */
+	atomic_t		drops ____cacheline_aligned_in_smp;
 };

Isn't that likely to create a large hole on systems with large cache lines.
(Same as any other use of ____cacheline_aligned_in_smp.)

Yes, I would like to avoid that, unless we come to the conclusion it is
absolutely needed.

I feel that we could simply use a pointer, and allocate memory on
demand, since many sockets do not ever experience a drop.

The pointer could stay in a read mostly section.

We even could use per cpu or node counter for some heavy drop cases. 

I had the same idea while discussing that with Paolo, merely using an
*atomic_t = kmalloc(sizeof(atomic_t)) out of band of the socket.

My fear was that those could be aggregated by the slab cache into one
cache line, causing even more heating on cachelines.

Bye,
Hannes