From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Garzik Subject: Re: Implementing NVMHCI... Date: Sat, 11 Apr 2009 19:51:31 -0400 Message-ID: <49E12D03.5070906@garzik.org> References: <49E0D47B.9070205@garzik.org> <20090411203246.513a0892@lxorguk.ukuu.org.uk> <20090412002527.631a5a89@lxorguk.ukuu.org.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from srv5.dvmed.net ([207.36.208.214]:43590 "EHLO mail.dvmed.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750779AbZDKXvo (ORCPT ); Sat, 11 Apr 2009 19:51:44 -0400 In-Reply-To: <20090412002527.631a5a89@lxorguk.ukuu.org.uk> Sender: linux-ide-owner@vger.kernel.org List-Id: linux-ide@vger.kernel.org To: Alan Cox Cc: Grant Grundler , Linus Torvalds , Linux IDE mailing list , LKML , Jens Axboe , Arjan van de Ven Alan Cox wrote: >> We've abstract the DMA mapping/SG list handling enough that the >> block size should make no more difference than it does for the >> MTU size of a network. > > You need to start managing groups of pages in the vm and keeping them > together and writing them out together and paging them together even if > one of them is dirty and the other isn't. You have to deal with cases > where a process forks and the two pages are dirtied one in each but still > have to be written together. > > Alternatively you go for read-modify-write (nasty performance hit > especially for RAID or a log structured fs). Or just ignore the extra length, thereby excising the 'read-modify' step... Total storage is halved or worse, but you don't take as much of a performance hit. Jeff