From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sasha Levin Subject: Re: [RFC] kvm tools: Implement multiple VQ for virtio-net Date: Tue, 15 Nov 2011 17:30:29 +0200 Message-ID: <1321371029.3178.9.camel@lappy> References: <1321049521-26376-1-git-send-email-levinsasha928@gmail.com> <20111113102428.GD15322@redhat.com> <1321196430.2425.2.camel@sasha> <4EC07729.3050303@gmail.com> <1321265740.2425.7.camel@sasha> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Asias He , gorcunov@gmail.com, kvm@vger.kernel.org, mingo@elte.hu, "Michael S. Tsirkin" , netdev@vger.kernel.org, penberg@kernel.org, Rusty Russell , virtualization@lists.linux-foundation.org To: Krishna Kumar2 Return-path: In-Reply-To: Sender: kvm-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Tue, 2011-11-15 at 10:14 +0530, Krishna Kumar2 wrote: > Sasha Levin wrote on 11/14/2011 03:45:40 PM: > > > > Why both the bandwidth and latency performance are dropping so > > > dramatically with multiple VQ? > > > > It looks like theres no hash sync between host and guest, which makes > > the RX VQ change for every packet. This is my guess. > > Yes, I confirmed this happens for macvtap. I am > using ixgbe - it calls skb_record_rx_queue when > a skb is allocated, but sets rxhash when a packet > arrives. Macvtap is relying on record_rx_queue > first ahead of rxhash (as part of my patch making > macvtap multiqueue), hence different skbs result > in macvtap selecting different vq's. I'm seeing this behavior in non-macvtep related setup as well (simple tap <-> virtio-net). -- Sasha.