From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eliezer Tamir Subject: Re: [PATCH v2 net-next] net: Add low-latency/polling support for UDP multicast Date: Thu, 08 Aug 2013 11:46:17 +0300 Message-ID: <52035AD9.30703@linux.intel.com> References: <5200A203.2090306@linux.intel.com> <1375818663-12318-1-git-send-email-sbohrer@rgmadvisors.com> <1375906946.4004.45.camel@edumazet-glaptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Cc: Shawn Bohrer , davem@davemloft.net, netdev@vger.kernel.org, Amir Vadai , tomk@rgmadvisors.com To: Eric Dumazet Return-path: Received: from mga02.intel.com ([134.134.136.20]:52074 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933813Ab3HHIqV (ORCPT ); Thu, 8 Aug 2013 04:46:21 -0400 In-Reply-To: <1375906946.4004.45.camel@edumazet-glaptop> Sender: netdev-owner@vger.kernel.org List-ID: On 07/08/2013 23:22, Eric Dumazet wrote: > On Tue, 2013-08-06 at 14:51 -0500, Shawn Bohrer wrote: >> Set the napi id for each socket in the multicast path to enable >> low-latency/polling support. >> >> Signed-off-by: Shawn Bohrer >> --- >> v2 include ipv6 support > > This might help your workload, but I doubt it is generic enough. > > One UDP socket is supposed to receive traffic from many endpoints, > so we have no guarantee all the received traffic will end on a single RX > queue on the NIC. > > That's the same logic than RFS here. > > sk_mark_napi_id() in UDP are wrong IMHO. > > It should be guarded by the following test in > __udp_queue_rcv_skb() > > if (inet_sk(sk)->inet_daddr) { > sock_rps_save_rxhash(sk, skb); > sk_mark_napi_id(sk, skb); > } > > (To occur only for connected UDP sockets, where we are 100% sure all > packets will use this same rxhash/rx queue) This would also be safe if there is only one NIC and said NIC was programmed to always place this socket's data on the same queue. I don't have a good suggestion on how to detect this.