From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Lemoine Subject: Re: [RFC] netif_rx: receive path optimization Date: Thu, 31 Mar 2005 23:43:27 +0200 Message-ID: <5cac192f05033113434742aeb4@mail.gmail.com> References: <20050330132815.605c17d0@dxpl.pdx.osdl.net> <20050331120410.7effa94d@dxpl.pdx.osdl.net> <1112303431.1073.67.camel@jzny.localdomain> <20050331131707.69f451ea@dxpl.pdx.osdl.net> Reply-To: Eric Lemoine Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: hadi@znyx.com, "David S. Miller" , netdev Return-path: To: Stephen Hemminger In-Reply-To: <20050331131707.69f451ea@dxpl.pdx.osdl.net> Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org > > > Here is another alternative that seems better than the earlier posting. It uses > > > a per device receive queue for non-NAPI devices. The only issue is that then > > > we lose the per-cpu queue's and that could impact the loopback device performance. > > > If that is really an issue, then the per-cpu magic should be moved to the loopback > > > device. > > > > > > > The repurcassions of going from per-CPU-for-all-devices queue > > (introduced by softnet) to per-device-for-all-CPUs maybe huge in my > > opinion especially in SMP. A closer view of whats there now maybe > > per-device-per-CPU backlog queue. > > Any real hardware only has a single receive packet source (the interrupt routine), > and the only collision would be in the case of interrupt migration. So having > per-device-per-CPU queue's would be overkill and more complex because > the NAPI scheduling is per-netdevice rather than per-queue (though that > could be fixed). > > > I think performance will be impacted in all devices. imo, whatever needs > > to go in needs to have some experimental data to back it > > Experiment with what? Proving an absolute negative is impossible. > I will test loopback and non-NAPI version of a couple of gigabit drivers > to see. Just a naive question : why at all trying to accelerate netif_rx? Isn't NAPI the best choice for high performance rx anyway? -- Eric