From mboxrd@z Thu Jan 1 00:00:00 1970 From: Pekka Enberg Subject: Re: [PATCH 1/3] kvm tools: Make virtio-net kvm__irq_line thread safe Date: Fri, 29 Apr 2011 13:37:56 +0300 Message-ID: References: <1304058985-13833-1-git-send-email-asias.hejun@gmail.com> <4DBA6519.5070509@gmail.com> <1304063606.10069.7.camel@lappy> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: Sasha Levin , Asias He , Ingo Molnar , Prasad Joshi , kvm@vger.kernel.org To: Cyrill Gorcunov Return-path: Received: from mail-vw0-f46.google.com ([209.85.212.46]:38556 "EHLO mail-vw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751029Ab1D2Kh5 (ORCPT ); Fri, 29 Apr 2011 06:37:57 -0400 Received: by vws1 with SMTP id 1so2634731vws.19 for ; Fri, 29 Apr 2011 03:37:56 -0700 (PDT) In-Reply-To: Sender: kvm-owner@vger.kernel.org List-ID: On Fri, Apr 29, 2011 at 1:02 PM, Cyrill Gorcunov wrote: > So, if I understand all the things correct -- making virtio devices to > belong separated irqs > issued some race conditions on read\write operations between host and > guest and adding > thread pool revealed it, right? (because previously we were doing all > the work inside i/o > path on guest site). So does reverting commit a37089da817ce7aad9789aeb9fc09b68e088ad9a ("kvm tools: Use threadpool for virtio-net") fix things? I think the problem here is that now RX path relies on VIRTIO_PCI_QUEUE_NOTIFY to happen in order for it to trigger KVM_IRQ_LINE which is wrong. Using shared IRQs obviously masks the problem which is why reverting Cyrill's commit makes the problem go away. Pekka