From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-1.0 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_PASS autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id E089DC282C7 for ; Sat, 26 Jan 2019 09:36:44 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id AD432218F0 for ; Sat, 26 Jan 2019 09:36:44 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726362AbfAZJgn (ORCPT ); Sat, 26 Jan 2019 04:36:43 -0500 Received: from mx1.redhat.com ([209.132.183.28]:33204 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726321AbfAZJgn (ORCPT ); Sat, 26 Jan 2019 04:36:43 -0500 Received: from smtp.corp.redhat.com (int-mx08.intmail.prod.int.phx2.redhat.com [10.5.11.23]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id E176D7F3EC; Sat, 26 Jan 2019 09:36:42 +0000 (UTC) Received: from ovpn-116-49.ams2.redhat.com (ovpn-116-49.ams2.redhat.com [10.36.116.49]) by smtp.corp.redhat.com (Postfix) with ESMTP id 9B77545BD; Sat, 26 Jan 2019 09:36:41 +0000 (UTC) Message-ID: <33fac48cd79c98b1da7af20f04c5acef9b740ce3.camel@redhat.com> Subject: Re: [PATCH RFC 3/3] udp: Support UDP fraglist GRO/GSO. From: Paolo Abeni To: Steffen Klassert Cc: netdev@vger.kernel.org, Willem de Bruijn , "Jason A. Donenfeld" Date: Sat, 26 Jan 2019 10:36:40 +0100 In-Reply-To: <20190125075855.GT3581@gauss3.secunet.de> References: <20181221075334.9000-1-steffen.klassert@secunet.com> <20181221075334.9000-4-steffen.klassert@secunet.com> <7e001c0f99f688da4be762528ddc9287f49797fc.camel@redhat.com> <20190125075855.GT3581@gauss3.secunet.de> Content-Type: text/plain; charset="UTF-8" User-Agent: Evolution 3.30.4 (3.30.4-1.fc29) Mime-Version: 1.0 Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.84 on 10.5.11.23 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.25]); Sat, 26 Jan 2019 09:36:43 +0000 (UTC) Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org On Fri, 2019-01-25 at 08:58 +0100, Steffen Klassert wrote: > > Finally this will cause GRO/GSO for local UDP packets delivery to non > > GSO_SEGMENT sockets. That could be possibly a win or a regression: we > > save on netfilter/IP stack traversal, but we add additional work, some > > performances figures would probably help. > > I did some tests for the local receive path with netperf and iperf, but > in this case the sender that generates the packets is the bottleneck. > So the benchmarks are not that meaningful for the receive path. I think we can use GSO on the sender if we add some additional code on the rx side - for testing purpose only - limiting the GRO aggregation to an (user controlled via sysfs) value. Beyond that, other options would be using multiple senders threads and a single rx queue and/or asymmetric CPUs. > Do you have some performance tests for UDP GRO receive? I have a bunch of ansible(!!!) scripts I can share, if you dare. They have a lot of hard-coded setting, so I'm not sure how much can be re- used outside my testbed. I also hope/wish/think/ I can allocate some time for benchmarking this on my own in the next week[s], so I'll try to post some results for the next iteration. Cheers, Paolo