From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965999Ab3E2TIv (ORCPT ); Wed, 29 May 2013 15:08:51 -0400 Received: from mail-pb0-f49.google.com ([209.85.160.49]:47080 "EHLO mail-pb0-f49.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759396Ab3E2TIm (ORCPT ); Wed, 29 May 2013 15:08:42 -0400 Message-ID: <1369854520.5109.79.camel@edumazet-glaptop> Subject: Re: [PATCH v6 net-next 2/5] net: implement support for low latency socket polling From: Eric Dumazet To: Or Gerlitz Cc: Eliezer Tamir , David Miller , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, Jesse Brandeburg , Don Skidmore , e1000-devel@lists.sourceforge.net, Willem de Bruijn , Andi Kleen , HPA , Eilon Greenstien , Alex Rosenbaum , Eliezer Tamir Date: Wed, 29 May 2013 12:08:40 -0700 In-Reply-To: References: <20130529063916.27486.3841.stgit@ladj378.jer.intel.com> <20130529063935.27486.18610.stgit@ladj378.jer.intel.com> <51A617D7.6000406@linux.intel.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.3-0ubuntu6 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2013-05-29 at 21:52 +0300, Or Gerlitz wrote: > Eliezer Tamir wrote: > > Or Gerlitz wrote: > > >> Unlike with TCP sockets, UDP sockets may receive packets from multiple > >> sources and hence the receiving context may be steered to be executed > >> on different cores through RSS or other Flow-Steering HW mechanisms > >> which could mean different napi contexts for the same socket, is that > >> a problem here? what's the severity? > > > Nothing will break if you poll on the wrong queue. > > Your data will come through normal NAPI processing of the right queue. > > Can you elaborate a little further, why you call this "wrong" and "right"? > -- This definitely need some documentation, because before llpoll, device RX path was serviced by the cpu receiving the harwdare interrupt. So the "wrong" queue could add false sharing, and wrong NUMA allocations. From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH v6 net-next 2/5] net: implement support for low latency socket polling Date: Wed, 29 May 2013 12:08:40 -0700 Message-ID: <1369854520.5109.79.camel@edumazet-glaptop> References: <20130529063916.27486.3841.stgit@ladj378.jer.intel.com> <20130529063935.27486.18610.stgit@ladj378.jer.intel.com> <51A617D7.6000406@linux.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Willem de Bruijn , Don, Eliezer Tamir , e1000-devel@lists.sourceforge.net, netdev@vger.kernel.org, HPA , Jesse Brandeburg , Alex Rosenbaum , linux-kernel@vger.kernel.org, Eliezer Tamir , Andi Kleen , Eilon Greenstien , David Miller To: Or Gerlitz Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: e1000-devel-bounces@lists.sourceforge.net List-Id: netdev.vger.kernel.org On Wed, 2013-05-29 at 21:52 +0300, Or Gerlitz wrote: > Eliezer Tamir wrote: > > Or Gerlitz wrote: > > >> Unlike with TCP sockets, UDP sockets may receive packets from multiple > >> sources and hence the receiving context may be steered to be executed > >> on different cores through RSS or other Flow-Steering HW mechanisms > >> which could mean different napi contexts for the same socket, is that > >> a problem here? what's the severity? > > > Nothing will break if you poll on the wrong queue. > > Your data will come through normal NAPI processing of the right queue. > > Can you elaborate a little further, why you call this "wrong" and "right"? > -- This definitely need some documentation, because before llpoll, device RX path was serviced by the cpu receiving the harwdare interrupt. So the "wrong" queue could add false sharing, and wrong NUMA allocations. ------------------------------------------------------------------------------ Introducing AppDynamics Lite, a free troubleshooting tool for Java/.NET Get 100% visibility into your production application - at no cost. Code-level diagnostics for performance bottlenecks with <2% overhead Download for free and get started troubleshooting in minutes. http://p.sf.net/sfu/appdyn_d2d_ap1 _______________________________________________ E1000-devel mailing list E1000-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/e1000-devel To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired