From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Garzik Subject: Re: [PATCH] libata: write cache and read ahead Date: Wed, 24 Aug 2005 06:04:00 -0400 Message-ID: <430C4610.3080205@pobox.com> References: <43085209.50405@torque.net> <430914C2.8030301@pobox.com> <43095EB3.2020202@torque.net> <430BAFD3.9000702@adaptec.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mail.dvmed.net ([216.237.124.58]:29586 "EHLO mail.dvmed.net") by vger.kernel.org with ESMTP id S1750849AbVHXKEP (ORCPT ); Wed, 24 Aug 2005 06:04:15 -0400 In-Reply-To: <430BAFD3.9000702@adaptec.com> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Luben Tuikov Cc: dougg@torque.net, linux-scsi@vger.kernel.org, Tejun Heo Luben Tuikov wrote: > On 08/22/05 01:12, Douglas Gilbert wrote: > >>I was surprised how much code needed changing. >>With MODE SELECT's issues with libata addressed >>various other SAT "extras" should be much easier >>to implement. That should make libata more attractive >>as a SAT layer for SAS LLDDs (that don't do it already >>in firmware). > > > Doug, how about never needing a SAT layer for SAS LLDDs > for ATA/ATAPI devices. > > Would you object if I "give" you a "domain device" to which > you can send FISes (+ the packet if ATAPI) through > a SAM-4 intefrace: Execute Task + TMFs? > > Jeff? SAT is the useful piece of libata that makes everything work. You can't rip out it and still expect to do anything useful ;-) libata relies on SCSI's device class drivers -- sd, sr, st, sg -- to manage devices and generate commands to service. And in turn, we rely on SAT (libata-scsi.c) to translate device class commands into ATA commands. If the SAT layer went away, then nothing would exist to generate commands for libata to service. Jeff