From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37727) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Ys7ln-0005pl-59 for qemu-devel@nongnu.org; Tue, 12 May 2015 06:50:40 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Ys7lm-0001gj-AD for qemu-devel@nongnu.org; Tue, 12 May 2015 06:50:39 -0400 Message-ID: <5551DAF1.1010009@redhat.com> Date: Tue, 12 May 2015 12:50:25 +0200 From: Paolo Bonzini MIME-Version: 1.0 References: <1431409679-16077-1-git-send-email-den@openvz.org> <1431409679-16077-3-git-send-email-den@openvz.org> <20150512102709.GB3696@noname.str.redhat.com> In-Reply-To: <20150512102709.GB3696@noname.str.redhat.com> Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCH 2/2] block: align bounce buffers to page List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Kevin Wolf , "Denis V. Lunev" Cc: Stefan Hajnoczi , qemu-devel@nongnu.org, qemu-block@nongnu.org On 12/05/2015 12:27, Kevin Wolf wrote: > I think it would make more sense to keep this specific to the raw-posix > driver. After all, it's only the kernel page cache that we optimise > here. Other backends probably don't take advantage of page alignment. I don't think it makes sense to keep it raw-posix-specific, though. It's not the page cache that we optimize for, because this is with O_DIRECT. If anything, making it page aligned means that the buffer spans one fewer physical page and thus it may economize a bit on TLB misses. Paolo