From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [PATCH] irq: Add node_affinity CPU masks for smarter irqbalance hints Date: Tue, 24 Nov 2009 21:35:41 +0100 Message-ID: <87iqczwtia.fsf@basil.nowhere.org> References: <20091124.093956.247147202.davem@davemloft.net> <1259085412.2631.48.camel@ppwaskie-mobl2> <4B0C2547.8030408@gmail.com> <20091124.105442.06273019.davem@davemloft.net> <4B0C2CCA.6030006@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: David Miller , peter.p.waskiewicz.jr@intel.com, peterz@infradead.org, arjan@linux.intel.com, yong.zhang0@gmail.com, linux-kernel@vger.kernel.org, arjan@linux.jf.intel.com, netdev@vger.kernel.org To: Eric Dumazet Return-path: Received: from one.firstfloor.org ([213.235.205.2]:51737 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757572AbZKXUfg (ORCPT ); Tue, 24 Nov 2009 15:35:36 -0500 In-Reply-To: <4B0C2CCA.6030006@gmail.com> (Eric Dumazet's message of "Tue, 24 Nov 2009 19:58:18 +0100") Sender: netdev-owner@vger.kernel.org List-ID: Eric Dumazet writes: > David Miller a =E9crit : >> From: Eric Dumazet >> Date: Tue, 24 Nov 2009 19:26:15 +0100 >>=20 >>> It seems complex to me, maybe optimal thing would be to use a NUMA = policy to >>> spread vmalloc() allocations to all nodes to get a good bandwidth..= =2E >>=20 >> vmalloc() and sk_buff's don't currently mix and I really don't see u= s >> every allowing them to :-) > > I think Peter was referring to tx/rx rings buffers, not sk_buffs. > > They (ring buffers) are allocated with vmalloc() at driver init time. They are typically allocated with dma_alloc_coherent(), which does allocate a continuous area. In theory you could do interleaving with IOMMus, but just putting it on the same node as the device is probably better. -Andi --=20 ak@linux.intel.com -- Speaking for myself only.