From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934271AbZIDVS5 (ORCPT ); Fri, 4 Sep 2009 17:18:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S934025AbZIDVSz (ORCPT ); Fri, 4 Sep 2009 17:18:55 -0400 Received: from mx1.redhat.com ([209.132.183.28]:57208 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933855AbZIDVSz (ORCPT ); Fri, 4 Sep 2009 17:18:55 -0400 From: Jeff Moyer To: Christoph Hellwig Cc: Rusty Russell , kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Mark McLoughlin Subject: Re: [PATCH for-2.6.31] virtio_blk: revert QUEUE_FLAG_VIRT addition References: <20090904204442.GA30941@lst.de> X-PGP-KeyID: 1F78E1B4 X-PGP-CertKey: F6FE 280D 8293 F72C 65FD 5A58 1FF8 A7CA 1F78 E1B4 X-PCLoadLetter: What the f**k does that mean? Date: Fri, 04 Sep 2009 17:18:51 -0400 In-Reply-To: <20090904204442.GA30941@lst.de> (Christoph Hellwig's message of "Fri, 4 Sep 2009 22:44:42 +0200") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.0.60 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Christoph Hellwig writes: > It seems like the addition of QUEUE_FLAG_VIRT caueses major performance > regressions for Fedora users: > > https://bugzilla.redhat.com/show_bug.cgi?id=509383 > https://bugzilla.redhat.com/show_bug.cgi?id=505695 > > while I can't reproduce those extreme regressions myself I think the flag > is wrong. > > Rationale: > > QUEUE_FLAG_VIRT expands to QUEUE_FLAG_NONROT which casus the queue > unplugged immediately. This is not a good behaviour for at least > qemu and kvm where we do have significant overhead for every > I/O operations. Even with all the latested speeups (native AIO, > MSI support, zero copy) we can only get native speed for up to 128kb > I/O requests we already are down to 66% of native performance for 4kb > requests even on my laptop running the Intel X25-M SSD for which the > QUEUE_FLAG_NONROT was designed. > If we ever get virtio-blk overhead low enough that this flag makes > sense it should only be set based on a feature flag set by the host. I agree with that rationale. Acked-by: Jeff Moyer