From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rusty Russell Subject: Re: [PATCH 3/4] virtio_net: don't free buffers in xmit ring Date: Tue, 2 Jun 2009 23:13:52 +0930 Message-ID: <200906022313.52808.rusty@rustcorp.com.au> References: <200905292346.24141.rusty@rustcorp.com.au> <1243930422.9146.60.camel@blaa> Mime-Version: 1.0 Content-Type: Text/Plain; charset="utf-8" Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, virtualization@lists.linux-foundation.org To: Mark McLoughlin Return-path: Received: from ozlabs.org ([203.10.76.45]:53681 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752689AbZFBNn4 (ORCPT ); Tue, 2 Jun 2009 09:43:56 -0400 In-Reply-To: <1243930422.9146.60.camel@blaa> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 2 Jun 2009 05:43:42 pm Mark McLoughlin wrote: > On Fri, 2009-05-29 at 23:46 +0930, Rusty Russell wrote: > > The virtio_net driver is complicated by the two methods of freeing old > > xmit buffers (in addition to freeing old ones at the start of the xmit > > path). > > > > The original code used a 1/10 second timer attached to xmit_free(), > > reset on every xmit. Before we orphaned skbs on xmit, the > > transmitting userspace could block with a full socket until the timer > > fired, the skb destructor was called, and they were re-woken. > > The timer was actually added to solve a hang when trying to unload > nf_conntrack AFAIR - nf_conntrack was blocking on the skb being freed > and we never actually freed it. > > I think skb_orphan() is enough to prevent this, is it? Yep. > > Unfortunately, VIRTIO_F_NOTIFY_ON_EMPTY makes quite a lot of work: a > > host which is faster than the guest will fire the interrupt every xmit > > packet (slowing the guest down further). > > Ouch. So, does simply disabling host support for > VIRTIO_F_NOTIFY_ON_EMPTY speed up current guests? That was my original change. It cuts the interrupts, but there's enough else going on that there's not a reliably-measurable speedup (this is with lguest, haven't tested with kvm). Cheers, Rusty.