From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paul Brook Subject: Re: [Qemu-devel] [PATCH 4/6] virtio network driver Date: Sun, 30 Mar 2008 10:27:07 +0000 Message-ID: <200803301127.08620.paul@codesourcery.com> References: <1206827760-4566-1-git-send-email-aliguori@us.ibm.com> <1206827760-4566-4-git-send-email-aliguori@us.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Cc: kvm-devel@lists.sourceforge.net, Marcelo Tosatti , Aurelien Jarno To: qemu-devel@nongnu.org Return-path: In-Reply-To: <1206827760-4566-4-git-send-email-aliguori@us.ibm.com> Content-Disposition: inline List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kvm-devel-bounces@lists.sourceforge.net Errors-To: kvm-devel-bounces@lists.sourceforge.net List-Id: kvm.vger.kernel.org On Saturday 29 March 2008, Anthony Liguori wrote: > + =A0 =A0if ((elem =3D virtqueue_pop(n->rx_vq)) =3D=3D NULL) { > +=A0=A0=A0=A0=A0=A0=A0/* wait until the guest adds some rx bufs */ > +=A0=A0=A0=A0=A0=A0=A0n->can_receive =3D 0; > +=A0=A0=A0=A0=A0=A0=A0return; > + =A0 =A0} Setting can_receive to zero *after* dropping a packet is a bit late. Not a fatal flaw, but it does make can_receive fairly useless. The whole po= int = of can_receive is to workaround lack of proper TCP rate control in the slir= p = code. Paul ------------------------------------------------------------------------- Check out the new SourceForge.net Marketplace. It's the best place to buy or sell services for just about anything Open Source. http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace