From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Fjellstrom Subject: virtio disk host cpu overhead? Date: Fri, 03 Mar 2017 10:05:06 -0700 Message-ID: <4596416.eghLixMk0z@natasha> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7Bit To: kvm@vger.kernel.org Return-path: Received: from mail.tomasu.net ([192.241.222.217]:47908 "EHLO mail.tomasu.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751584AbdCCTAN (ORCPT ); Fri, 3 Mar 2017 14:00:13 -0500 Received: from localhost (amavis.tomasu.net [10.134.12.52]) by mail.tomasu.net (Postfix) with ESMTP id 2DE5F15495F for ; Fri, 3 Mar 2017 17:05:09 +0000 (UTC) Received: from mail.tomasu.net ([10.134.23.144]) by localhost (amavis.tomasu.net [10.134.12.52]) (amavisd-new, port 10024) with LMTP id nmCSx-309DdE for ; Fri, 3 Mar 2017 17:05:08 +0000 (UTC) Received: from natasha.localnet (S010652540017b116.ed.shawcable.net [174.3.107.104]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) (Authenticated sender: thomas@fjellstrom.ca) by mail.tomasu.net (Postfix) with ESMTPSA id 76AF0154865 for ; Fri, 3 Mar 2017 17:05:08 +0000 (UTC) Sender: kvm-owner@vger.kernel.org List-ID: I've been testing a new samsung 960 evo nvme drive i just got, and running tests on it in a guest shows a minimum of double the cpu time on the host as it does on the guest. Somehow a guest running a single thread iozone or fio test can use 4+ cores on the host side at 50-100%. I have debian's 4.9.13 kernel installed on the host (4.9.2 on the guest), and kvm/qemu 2.8.0. I'm using libvirt and virt-manager to set up the guest, with a lvm volume set up on the nvme drive, and exporting a couple volumes to the guest which it then either uses lvm on, or testing is done raw on a secondary volume. (I've tried both) Host is a consumer box with an AMD 970 board + FX-8320, and 32GB ram. Guest is currently allocated 8 threads, and 1GB ram which it is currently only using 111MB of while fio is running. I'm curious to know if this is expected behavior, misconfiguration on my end, or a misunderstanding of how things work? I'd appreciate any insight or help anyone is able and willing to provide. -- Thomas Fjellstrom thomas@fjellstrom.ca