From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by dpdk.org (Postfix) with ESMTP id 09EA85A50 for ; Fri, 29 May 2015 06:47:55 +0200 (CEST) Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga103.jf.intel.com with ESMTP; 28 May 2015 21:47:42 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.13,514,1427785200"; d="scan'208";a="701941571" Received: from pgsmsx103.gar.corp.intel.com ([10.221.44.82]) by orsmga001.jf.intel.com with ESMTP; 28 May 2015 21:47:41 -0700 Received: from bgsmsx104.gar.corp.intel.com (10.223.4.190) by PGSMSX103.gar.corp.intel.com (10.221.44.82) with Microsoft SMTP Server (TLS) id 14.3.224.2; Fri, 29 May 2015 12:47:40 +0800 Received: from bgsmsx102.gar.corp.intel.com ([169.254.2.87]) by BGSMSX104.gar.corp.intel.com ([169.254.5.28]) with mapi id 14.03.0224.002; Fri, 29 May 2015 10:17:39 +0530 From: "Ramia, Kannan Babu" To: "Dumitrescu, Cristian" , "Rajagopalan Sivaramakrishnan" , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [PATCH v3] pipeline: add statistics for librte_pipeline Thread-Index: AQHQmM652FttWDxm/02UWehTOpnofZ2RxAewgACdk0A= Date: Fri, 29 May 2015 04:47:38 +0000 Message-ID: <682698A055A0F44AA47192B2014114972AE90E0C@BGSMSX102.gar.corp.intel.com> References: <3EB4FA525960D640B5BDFFD6A3D891263236E6CA@IRSMSX108.ger.corp.intel.com> In-Reply-To: <3EB4FA525960D640B5BDFFD6A3D891263236E6CA@IRSMSX108.ger.corp.intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.223.10.10] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v3] pipeline: add statistics for librte_pipeline X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 29 May 2015 04:47:56 -0000 The confusion is due to whether you consider stats as a library feature or = Debug feature. Mostly log levels are considered as debug features in the pr= oduction system and controlled system wide flag not per library flags. Whil= e statistics could be considered as a library feature which could be turned= on and off depends on the application needs. I am with Cristian to have p= er library feature configuration flag for statistics.=20 Regards Kannan Babu -----Original Message----- From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Dumitrescu, Cristian Sent: Friday, May 29, 2015 12:56 AM To: Rajagopalan Sivaramakrishnan; dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH v3] pipeline: add statistics for librte_pipe= line Hi Raja, Thanks for your input. I think we have the following options identified so far for stats collectio= n configuration: 1. Stats configuration through the RTE_LOG_LEVEL 2. Single configuration fl= ag global for all DPDK libraries 3. Single configuration flag per DPDK libr= ary It would be good if Thomas and Stephen, as well as others, would reply with= their preference order. My personal preference order is: 3., 2., 1., but I can work with any of the= above that is identified by the majority of the replies. My goal right now= is reaching a conclusion on this item as soon as we can. Regards, Cristian > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Rajagopalan=20 > Sivaramakrishnan > Sent: Wednesday, May 27, 2015 11:45 PM > To: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3] pipeline: add statistics for=20 > librte_pipeline >=20 >=20 > > > You also reiterate that you would like to have the stats always enabl= ed. > You > > can definitely do this, it is one of the available choices, but why=20 > > not also accommodate the users that want to pick the opposite=20 > > choice? Why force apps to spend cycles on stats if the app either=20 > > does not want these > counters > > (library counters not relevant for that app, maybe the app is only > interested > > in maintaining some other stats that it implements itself) or do not=20 > > want them anymore (maybe they only needed them during debug phase), etc= ? > > Jay asked this question, and I did my best in my reply to describe=20 > > our motivation (http://www.dpdk.org/ml/archives/dev/2015- > May/017992.html). > > Maybe you missed that post, it would be good to get your reply on=20 > > this one too. > > > > I want to see DPDK get out of the config madness. > > This is real code, not an Intel benchmark special. >=20 >=20 > I agree that statistics will definitely be required in most real-world=20 > production environments and the overhead from per-core stats gathering=20 > will be minimal if the data structures are such that CPU cache=20 > thrashing is avoided. > However, if there are scenarios where it is desirable to turn stats=20 > off, I think we can live with a config option. > I am not comfortable with using the log level to enable/disable=20 > statistics as they are not really related. A separate config option=20 > for stats collection seems like a reasonable compromise. >=20 > Raja