From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753162AbZBDIJN (ORCPT ); Wed, 4 Feb 2009 03:09:13 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751589AbZBDIIy (ORCPT ); Wed, 4 Feb 2009 03:08:54 -0500 Received: from kandzendo.ru ([195.178.208.66]:59125 "EHLO tservice.net.ru" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751423AbZBDIIy (ORCPT ); Wed, 4 Feb 2009 03:08:54 -0500 Date: Wed, 4 Feb 2009 11:08:51 +0300 From: Evgeniy Polyakov To: David Miller Cc: jarkao2@gmail.com, herbert@gondor.apana.org.au, w@1wt.eu, dada1@cosmosbay.com, ben@zeus.com, mingo@elte.hu, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, jens.axboe@oracle.com Subject: Re: [PATCH v2] tcp: splice as many packets as possible at once Message-ID: <20090204080851.GA10445@ioremap.net> References: <20090202.235017.253437221.davem@davemloft.net> <20090203094108.GA4639@ff.dom.local> <20090203111012.GA16878@ioremap.net> <20090203.164609.160183741.davem@davemloft.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090203.164609.160183741.davem@davemloft.net> User-Agent: Mutt/1.5.13 (2006-08-11) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Feb 03, 2009 at 04:46:09PM -0800, David Miller (davem@davemloft.net) wrote: > > NTA tried to solve this by not allowing to free the data allocated on > > the different CPU, contrary to what SLAB does. Modulo cache coherency > > improvements, > > This could kill performance on NUMA systems if we are not careful. > > If we ever consider NTA seriously, these issues would need to > be performance tested. Quite contrary I think. Memory is allocated and freed on the same CPU, which means on the same memory domain, closest to the CPU in question. I did not test NUMA though, but NTA performance on the usual CPU (it is 2.5 years old already :) was noticebly good. -- Evgeniy Polyakov