From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joris Subject: Re: ICH7: ata_piix twice as fast as ahci? Date: Sun, 17 Feb 2008 17:39:41 +0100 Message-ID: <6b9952490802170839m4456353ejfd5a68d0aaccdf88@mail.gmail.com> References: <6b9952490802170741h1de9be53nefccea3775f7de00@mail.gmail.com> <20080217161033.3bb420fd@core> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: Received: from an-out-0708.google.com ([209.85.132.244]:10429 "EHLO an-out-0708.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755571AbYBQQjl (ORCPT ); Sun, 17 Feb 2008 11:39:41 -0500 Received: by an-out-0708.google.com with SMTP id d31so309110and.103 for ; Sun, 17 Feb 2008 08:39:41 -0800 (PST) In-Reply-To: <20080217161033.3bb420fd@core> Content-Disposition: inline Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Alan Cox Cc: Linux IDE 2008/2/17, Alan Cox : > On Sun, 17 Feb 2008 16:41:42 +0100 > Joris wrote: > > > Hello List, > > > > Odd problem on my machines: the sata disks appear to be a lot slower > > when used via ata_piix vs the ahci driver. > > I would expect that. AHCI allows the use of NCQ and unloads a ton of work > from the processor. It also means you pretty much avoid the inter command > latency that limits standard IDE performance. Alan, >>From your response I'm not sure if I made clear that ata_piix was faster, and ahci slower? Am I interpreting this correctly as having to choose between fast iops with low cpu (+ hotplug) with ahci and twice the linear read speed with ata_piix? Kind regards, Joris