From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:58490) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1a9YMx-00016U-7E for qemu-devel@nongnu.org; Thu, 17 Dec 2015 08:13:23 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1a9YMs-0002T3-F1 for qemu-devel@nongnu.org; Thu, 17 Dec 2015 08:13:19 -0500 Received: from mx1.redhat.com ([209.132.183.28]:42845) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1a9YMs-0002Sh-Ao for qemu-devel@nongnu.org; Thu, 17 Dec 2015 08:13:14 -0500 References: <1450284917-10508-1-git-send-email-apyrgio@arrikto.com> <5671AA78.8050603@redhat.com> <5672768E.70101@arrikto.com> <56728F08.7070702@redhat.com> <5672B451.1050302@arrikto.com> From: Paolo Bonzini Message-ID: <5672B4E6.8000504@redhat.com> Date: Thu, 17 Dec 2015 14:13:10 +0100 MIME-Version: 1.0 In-Reply-To: <5672B451.1050302@arrikto.com> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 0/9] Add full scatter-gather support for SCSI generic devices List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Alex Pyrgiotis Cc: qemu-devel@nongnu.org On 17/12/2015 14:10, Alex Pyrgiotis wrote: >>>>> Which commands have large payloads and are on the data path, for >>>>> scsi-block? Or is the use case just scsi-generic (e.g. tape devices?)? > > If I understand correctly, what you're saying is that if "scsi-block" is > started with "cache=writeback" and internally uses ioctl()s to bypass > the page cache, why not set "cache=none" beforehand and use > readv()/writev()? > > This is a valid suggestion, but this patch does not target only the > "scsi-block" device type. Its purpose is to allow faster read/writes via > ioctl()s, either to a "scsi-block" device or to a "scsi-generic" device. > Note that the latter device type can only use ioctl()s, so it cannot > benefit from the readv()/writev() DMA interface and currently has to use > a bounce buffer. Okay, so that answers my questions; there is still a valid use case for e.g. tape devices, and of course for when someone forgets to use scsi-block. Paolo >> We can improve the code to print a warning if you don't. (It needs some >> care: iscsi never caches, independent of the cache= argument, so we >> don't want to warn for it. But it can be done). > > I wasn't particularly concerned about that issue. I'd may prefer if this > was explicitly addressed in the QEMU doc, under the "cache=" section, > but that's a different discussion. > > Thanks, > Alex >