From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paolo Bonzini Subject: Re: [Qemu-devel] [question] virtio-blk performance degradationhappened with virito-serial Date: Mon, 01 Sep 2014 15:12:45 +0200 Message-ID: <540470CD.9060800@redhat.com> References: <201408291545282753855@sangfor.com>, <20140829143849.GA8909@grmbl.mre>, <201409012038178763909@sangfor.com> <201409012052442706397@sangfor.com> <5404701F.5070302@de.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=gbk Content-Transfer-Encoding: 7bit Cc: qemu-devel , kvm To: Christian Borntraeger , Zhang Haoyu , Amit Shah Return-path: Received: from mail-qa0-f50.google.com ([209.85.216.50]:51865 "EHLO mail-qa0-f50.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751449AbaIANMu (ORCPT ); Mon, 1 Sep 2014 09:12:50 -0400 Received: by mail-qa0-f50.google.com with SMTP id cm18so5022979qab.9 for ; Mon, 01 Sep 2014 06:12:50 -0700 (PDT) In-Reply-To: <5404701F.5070302@de.ibm.com> Sender: kvm-owner@vger.kernel.org List-ID: Il 01/09/2014 15:09, Christian Borntraeger ha scritto: > This is just wild guessing: > If virtio-blk and virtio-serial share an IRQ, the guest operating system has to check each virtqueue for activity. Maybe there is some inefficiency doing that. > AFAIK virtio-serial registers 64 virtqueues (on 31 ports + console) even if everything is unused. That could be the case if MSI is disabled. Paolo