[{"id":1759546,"web_url":"http://patchwork.ozlabs.org/comment/1759546/","msgid":"<20170829170249.yqfq3cvvnnncszf3@ast-mbp>","list_archive_url":null,"date":"2017-08-29T17:02:51","subject":"Re: [PATCH net-next 4/7] xdp: separate xdp_redirect tracepoint in\n\terror case","submitter":{"id":42586,"url":"http://patchwork.ozlabs.org/api/people/42586/","name":"Alexei Starovoitov","email":"alexei.starovoitov@gmail.com"},"content":"On Tue, Aug 29, 2017 at 04:37:56PM +0200, Jesper Dangaard Brouer wrote:\n> There is a need to separate the xdp_redirect tracepoint into two\n> tracepoints, for separating the error case from the normal forward\n> case.\n> \n> Due to the extreme speeds XDP is operating at, loading a tracepoint\n> have a measurable impact. Single core XDP REDIRECT (ethtool tuned\n> rx-usecs 25) can do 13.7 Mpps forwarding, but loading a simple\n> bpf_prog at the tracepoint (with a return 0) reduce perf to 10.2 Mpps\n> (CPU E5-1650 v4 @ 3.60GHz, driver: ixgbe)\n> \n> The overhead of loading a bpf-based tracepoint can be calculated to\n> cost 25 nanosec ((1/13782002-1/10267937)*10^9 = -24.83 ns).\n> \n> Using perf record on the tracepoint event, with a non-matching --filter\n> expression, the overhead is much larger. Performance drops to 8.3 Mpps,\n> cost 48 nanosec ((1/13782002-1/8312497)*10^9 = -47.74))\n> \n> Having a separate tracepoint for err cases, which should be less\n> frequent, allow running a continuous monitor for errors while not\n> affecting the redirect forward performance (this have also been\n> verified by measurements).\n> \n> Signed-off-by: Jesper Dangaard Brouer \n\nthanks for detailed analysis of performance impact of the changes.\nlooks great to me.\nAcked-by: Alexei Starovoitov ","headers":{"Return-Path":"","X-Original-To":"patchwork-incoming@ozlabs.org","Delivered-To":"patchwork-incoming@ozlabs.org","Authentication-Results":["ozlabs.org;\n\tspf=none (mailfrom) smtp.mailfrom=vger.kernel.org\n\t(client-ip=209.132.180.67; helo=vger.kernel.org;\n\tenvelope-from=netdev-owner@vger.kernel.org;\n\treceiver=)","ozlabs.org; dkim=pass (2048-bit key;\n\tunprotected) header.d=gmail.com header.i=@gmail.com\n\theader.b=\"tqIFNWhT\"; dkim-atps=neutral"],"Received":["from vger.kernel.org (vger.kernel.org [209.132.180.67])\n\tby ozlabs.org (Postfix) with ESMTP id 3xhZhL5NFpz9s76\n\tfor ;\n\tWed, 30 Aug 2017 03:02:58 +1000 (AEST)","(majordomo@vger.kernel.org) by vger.kernel.org via listexpand\n\tid S1751285AbdH2RC5 (ORCPT );\n\tTue, 29 Aug 2017 13:02:57 -0400","from mail-pg0-f68.google.com ([74.125.83.68]:35429 \"EHLO\n\tmail-pg0-f68.google.com\" rhost-flags-OK-OK-OK-OK) by vger.kernel.org\n\twith ESMTP id S1751275AbdH2RC4 (ORCPT\n\t); Tue, 29 Aug 2017 13:02:56 -0400","by mail-pg0-f68.google.com with SMTP id r133so3147352pgr.2\n\tfor ; Tue, 29 Aug 2017 10:02:55 -0700 (PDT)","from ast-mbp ([2620:10d:c090:180::1:18ee])\n\tby smtp.gmail.com with ESMTPSA id\n\tm8sm5935979pfj.35.2017.08.29.10.02.52\n\t(version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128);\n\tTue, 29 Aug 2017 10:02:52 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=gmail.com; s=20161025;\n\th=date:from:to:cc:subject:message-id:references:mime-version\n\t:content-disposition:in-reply-to:user-agent;\n\tbh=Z75XqiCo2Fl5Vo0r8m1KZEofjDw0nUilY24cnzOSciU=;\n\tb=tqIFNWhTYIGEjbS5r0QmvZE/OC6MURzdjT00bNgVksCiWWdpkpxg71ylE8vF7vEc5O\n\tQcBvC915j5cM8LoO8HooYRrUtCxyy2zV8xggVQnx3dzo/PLBPQeuXi152r8owY2iCIQ+\n\t+98lAHcp9fr0Twh95MCZxWBrmxTvnf5XOp61BXtzCFJ6X+WGQVTsYh7G9PwjrI3F0fvN\n\tRjEVtVSrHI+Wfo7p5s5/AkMq1gwuPoJ3reKy9s5fa2fFoDQD9zdZMX5ZDQtBWf3g+H82\n\tzJMIw88MocHS1dGtoIo3l4yD8ED8ZzeFfiZxALWuaq4uyfDXN6EREGpe2uFYnFdJEGqR\n\tiP6Q==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n\td=1e100.net; s=20161025;\n\th=x-gm-message-state:date:from:to:cc:subject:message-id:references\n\t:mime-version:content-disposition:in-reply-to:user-agent;\n\tbh=Z75XqiCo2Fl5Vo0r8m1KZEofjDw0nUilY24cnzOSciU=;\n\tb=g7D1rL+K2hIsLjktbZrAkpgZXP6g2IQ7/lotDsqwRFuYK9j8+BGuZ2A8Dhxj3ObF1K\n\tGcvquZYJISCpX12GMU+hUGA0BiLCUkEG/qW6QspIHwnVC6tbAEZcMMZQap2p+Rpn7jD2\n\tysdI+BNipKXGNRL6J8oDabQxMNtBlgxhoY3eLut/5t46RSNOAEKqZZuREVF1bASdPXkb\n\tqqsKwHElQsvpENYaUN/BXkBVRfG14aJa73YEWBAAdaSDMEjwQtfVwHGeOkVD33S48mmM\n\toe/MABGzxgKOkq3diVfUiOjZtXcbDut6a3Fy2Xsflk58OgJzq39lJ58vwlIeMx9GMnO8\n\tl6aA==","X-Gm-Message-State":"AHYfb5hogvfJrXuiR8hhFGyYA+KQUGz/aUD+eDC63CfH/Ps7ReoIPEC9\n\tvtYvqMf1kxtqvQ==","X-Received":"by 10.99.1.88 with SMTP id 85mr923189pgb.1.1504026173646;\n\tTue, 29 Aug 2017 10:02:53 -0700 (PDT)","Date":"Tue, 29 Aug 2017 10:02:51 -0700","From":"Alexei Starovoitov ","To":"Jesper Dangaard Brouer ","Cc":"netdev@vger.kernel.org, John Fastabend ","Subject":"Re: [PATCH net-next 4/7] xdp: separate xdp_redirect tracepoint in\n\terror case","Message-ID":"<20170829170249.yqfq3cvvnnncszf3@ast-mbp>","References":"<150401743083.16384.15778781741742858567.stgit@firesoul>\n\t<150401747611.16384.8021135230122395742.stgit@firesoul>","MIME-Version":"1.0","Content-Type":"text/plain; charset=us-ascii","Content-Disposition":"inline","In-Reply-To":"<150401747611.16384.8021135230122395742.stgit@firesoul>","User-Agent":"NeoMutt/20170421 (1.8.2)","Sender":"netdev-owner@vger.kernel.org","Precedence":"bulk","List-ID":"","X-Mailing-List":"netdev@vger.kernel.org"}}]