From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by dpdk.space (Postfix) with ESMTP id F089EA05D3 for ; Thu, 23 May 2019 19:54:32 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 1D4671B946; Thu, 23 May 2019 19:54:32 +0200 (CEST) Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) by dpdk.org (Postfix) with ESMTP id C64152B9E for ; Thu, 23 May 2019 19:54:30 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga008.fm.intel.com ([10.253.24.58]) by fmsmga105.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 23 May 2019 10:54:29 -0700 X-ExtLoop1: 1 Received: from orsmsx106.amr.corp.intel.com ([10.22.225.133]) by fmsmga008.fm.intel.com with ESMTP; 23 May 2019 10:54:29 -0700 Received: from orsmsx112.amr.corp.intel.com ([169.254.3.79]) by ORSMSX106.amr.corp.intel.com ([169.254.1.30]) with mapi id 14.03.0415.000; Thu, 23 May 2019 10:54:28 -0700 From: "Ergin, Mesut A" To: "Ananyev, Konstantin" , "Xing, Beilei" , "Zhang, Qi Z" CC: "dev@dpdk.org" , Thomas Monjalon , "Yigit, Ferruh" , Andrew Rybchenko Thread-Topic: [dpdk-dev] [PATCH 2/3] net/i40e: add runtime option to disable vector rx Thread-Index: AQHVDuYmoFW75bB560aVBXesmCM4TqZ0SVIAgADQ0YCAAKmAgIAAhvyA///CjVCAAWXXAIABj9KQ Date: Thu, 23 May 2019 17:54:27 +0000 Message-ID: <3615B82CA151CF42A86EDDD9846A8B38C7A8C36F@ORSMSX112.amr.corp.intel.com> References: <1557980885-183777-1-git-send-email-mesut.a.ergin@intel.com> <1557980885-183777-3-git-send-email-mesut.a.ergin@intel.com> <2601191342CEEE43887BDE71AB97725801616360D7@irsmsx105.ger.corp.intel.com> <3615B82CA151CF42A86EDDD9846A8B38C7A838E6@ORSMSX112.amr.corp.intel.com> <2601191342CEEE43887BDE71AB9772580161636445@irsmsx105.ger.corp.intel.com> <3615B82CA151CF42A86EDDD9846A8B38C7A86A60@ORSMSX112.amr.corp.intel.com> <2601191342CEEE43887BDE71AB9772580161636A0D@irsmsx105.ger.corp.intel.com> <3615B82CA151CF42A86EDDD9846A8B38C7A872FE@ORSMSX112.amr.corp.intel.com> <2601191342CEEE43887BDE71AB9772580161636EF4@irsmsx105.ger.corp.intel.com> In-Reply-To: <2601191342CEEE43887BDE71AB9772580161636EF4@irsmsx105.ger.corp.intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiNjVmMWJkZjMtYzVlNy00Nzg5LTliOWQtMWIxZDk2ZjQ2YTk5IiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX05UIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE3LjEwLjE4MDQuNDkiLCJUcnVzdGVkTGFiZWxIYXNoIjoiSHBtdnZvRXJjK3RNRUZoR0preldFbmpTOFArTTNlYkxHWllZN0xHWjlRVEpFT04zOFRVdnBMXC9GYVM5ajV0RXMifQ== x-ctpclassification: CTP_NT dlp-product: dlpe-windows dlp-version: 11.2.0.6 dlp-reaction: no-action x-originating-ip: [10.22.254.139] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH 2/3] net/i40e: add runtime option to disable vector rx X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" > > > > > If you plan to use FD mode on your device, why not enable it > > > > > at setup phase via rte_eth_dev_configure()? > > > > > Then proper rx function would be selected. > > > > > > > > > > > > > FDIR_MODE was designed to bind late automatically -- it is set when= the > first > > > > filter rule is parsed, and unset when the last rule is removed. > > > > > > Why is that, if you can define it at configuration stage, and RX func= tion > > > selection is based on it? > > > > I don't know why it was designed that way -- maybe maintainers know the > > historical context. >=20 > What I am trying to say - if particular feature (FD) enablement/disableme= nt > affects RX/TX function selection, then there should be an ability to > enable/disable > that feature at configuration state (dev_config/queue_setup). > Function to change value of that feature at runtime (after > dev_start/queue_start) > should return an error if new value can't be supported with already selec= ted > RX/TX > function. > If that's is not the case, then it sounds like a bug/gap in i40e driver t= hat needs to > be fixed. Will send a fix for that shortly.