From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S261937AbUB1WhJ (ORCPT ); Sat, 28 Feb 2004 17:37:09 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S261939AbUB1WhJ (ORCPT ); Sat, 28 Feb 2004 17:37:09 -0500 Received: from gprs147-251.eurotel.cz ([160.218.147.251]:5504 "EHLO amd.ucw.cz") by vger.kernel.org with ESMTP id S261937AbUB1WhH (ORCPT ); Sat, 28 Feb 2004 17:37:07 -0500 Date: Sat, 28 Feb 2004 23:36:54 +0100 From: Pavel Machek To: discuss@x86-64.org, kernel list Subject: Re: [discuss] scp running too slow Message-ID: <20040228223654.GA800@elf.ucw.cz> References: <20040228222942.GA736@elf.ucw.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20040228222942.GA736@elf.ucw.cz> X-Warning: Reading this can be dangerous to your mental health. User-Agent: Mutt/1.5.4i Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Hi! > I'm copying huge file from x86-64 machine to i386. > > x86-64 is running 2.6.3-bk, today from Linus' cvs. tg3 driver. It > shows pretty high CPU load (like 98% CPU), and is not even able to > reach 1MB/sec. When x86-64 machine was running 2.4, I was able to get > >4MB/sec... > > Any ideas? Okay, probably my fault. That machine is running in PIO mode, and log was full of hda: lost interrupt; which explains poor performance. I need to enable chipset-specific dma support in kernel config. Pavel -- When do you have a heart between your knees? [Johanka's followup: and *two* hearts?]