From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751969Ab1G2PZr (ORCPT ); Fri, 29 Jul 2011 11:25:47 -0400 Received: from mail-wy0-f174.google.com ([74.125.82.174]:45147 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751600Ab1G2PZq (ORCPT ); Fri, 29 Jul 2011 11:25:46 -0400 Subject: Re: [RFC PATCH]vhost-blk: In-kernel accelerator for virtio block device From: Sasha Levin To: Liu Yuan Cc: Stefan Hajnoczi , "Michael S. Tsirkin" , Rusty Russell , Avi Kivity , kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Khoa Huynh , Badari Pulavarty , Christoph Hellwig In-Reply-To: <4E32A105.6080509@gmail.com> References: <1311863346-4338-1-git-send-email-namei.unix@gmail.com> <4E325F98.5090308@gmail.com> <4E32A105.6080509@gmail.com> Content-Type: text/plain; charset="us-ascii" Date: Fri, 29 Jul 2011 18:25:04 +0300 Message-ID: <1311953104.30835.15.camel@lappy> Mime-Version: 1.0 X-Mailer: Evolution 2.32.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2011-07-29 at 20:01 +0800, Liu Yuan wrote: > Looking at this long list,most are function pointers that can not be > inlined, and the internal data structures used by these functions are > dozons. Leave aside code complexity, this long code path would really > need retrofit. As Christoph simply put, this kind of mess is inherent > all over the qemu code. So I am afraid, the 'retrofit' would end up to > be a re-write the entire (sub)system. I have to admit that, I am > inclined to the MST's vhost approach, that write a new subsystem other > than tedious profiling and fixing, that would possibly goes as far as > actually re-writing it. I don't think the fix for problematic userspace is to write more kernel code. vhost-net improved throughput and latency by several factors, allowing to achieve much more than was possible at userspace alone. With vhost-blk we see an improvement of ~15% - which I assume by your and Christoph's comments can be mostly attributed to QEMU. Merging a module which won't improve performance dramatically compared to what is possible to achieve in userspace (even if it would require a code rewrite) sounds a bit wrong to me. -- Sasha.