From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752000AbaIJPVX (ORCPT ); Wed, 10 Sep 2014 11:21:23 -0400 Received: from mail-vc0-f172.google.com ([209.85.220.172]:34699 "EHLO mail-vc0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751916AbaIJPVV (ORCPT ); Wed, 10 Sep 2014 11:21:21 -0400 MIME-Version: 1.0 In-Reply-To: <54106BBF.7010907@redhat.com> References: <1410044994-14943-1-git-send-email-hch@lst.de> <54106BBF.7010907@redhat.com> Date: Wed, 10 Sep 2014 23:21:20 +0800 Message-ID: Subject: Re: [PATCH] virtio_blk: merge S/G list entries by default From: Ming Lei To: Paolo Bonzini Cc: Christoph Hellwig , Jens Axboe , Linux Virtualization , Linux Kernel Mailing List , "Michael S. Tsirkin" Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Sep 10, 2014 at 11:18 PM, Paolo Bonzini wrote: > Il 07/09/2014 12:32, Ming Lei ha scritto: >> It is a good idea to disable SG merge for vq incapable of indirect because >> there are very limited direct descriptors. > > I think you mean _enabling_ SG merge if indirect descriptors are not there. You are right, sorry for the typo. >> For vq capable of indirect, it should be better to not do SG merge at default >> because: >> >> - from hypervisor view, no matter how many segments one req has, all are >> submitted to host kernel by one syscall, such as readv/io_submit >> >> - host kernel still need to do the same merge again > > Here we agree. > > Paolo > >> From my test(virtio-blk over null_blk), looks enabling SG merge may cause >> throughput a little drop(~3%). > Thanks, -- Ming Lei