From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga09.intel.com (mga09.intel.com [134.134.136.24]) by dpdk.org (Postfix) with ESMTP id 8335F5A36 for ; Thu, 21 May 2015 01:41:28 +0200 (CEST) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga102.jf.intel.com with ESMTP; 20 May 2015 16:41:27 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.13,466,1427785200"; d="scan'208";a="732752652" Received: from irsmsx105.ger.corp.intel.com ([163.33.3.28]) by orsmga002.jf.intel.com with ESMTP; 20 May 2015 16:41:26 -0700 Received: from irsmsx108.ger.corp.intel.com ([169.254.11.59]) by irsmsx105.ger.corp.intel.com ([169.254.7.73]) with mapi id 14.03.0224.002; Thu, 21 May 2015 00:41:25 +0100 From: "Dumitrescu, Cristian" To: Thomas Monjalon Thread-Topic: [dpdk-dev] [PATCH v2] pipeline: add statistics for librte_pipeline ports and tables Thread-Index: AQHQkWZQUPiGW1BlN0muPEnhvuILX52D/wVsgADlY3D///8CgIAAfaVw Date: Wed, 20 May 2015 23:41:25 +0000 Message-ID: <3EB4FA525960D640B5BDFFD6A3D891263236A93E@IRSMSX108.ger.corp.intel.com> References: <1430396143-10936-1-git-send-email-michalx.k.jastrzebski@intel.com> <43396928.Zqf8pLaHBD@xps13> <3EB4FA525960D640B5BDFFD6A3D891263236A65D@IRSMSX108.ger.corp.intel.com> <2017641.P0ts6fjbPO@xps13> In-Reply-To: <2017641.P0ts6fjbPO@xps13> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.182] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "dev@dpdk.org" Subject: Re: [dpdk-dev] [PATCH v2] pipeline: add statistics for librte_pipeline ports and tables 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: Wed, 20 May 2015 23:41:29 -0000 > -----Original Message----- > From: Thomas Monjalon [mailto:thomas.monjalon@6wind.com] > Sent: Wednesday, May 20, 2015 3:45 PM > To: Dumitrescu, Cristian > Cc: Wodkowski, PawelX; dev@dpdk.org; Jastrzebski, MichalX K > Subject: Re: [dpdk-dev] [PATCH v2] pipeline: add statistics for librte_pi= peline > ports and tables >=20 > Please Cristian, do not top post. > I'm replacing your comment in the right context. >=20 > 2015-05-20 13:57, Dumitrescu, Cristian: > > From: Thomas Monjalon [mailto:thomas.monjalon@6wind.com] > > > Thanks for the detailed explanation. > > > > > > You are raising a trade-off problem about > > > feature/maintenance/performance. > > > I think we must choose among 4 solutions: > > > 1/ always enabled > > > 2/ build-time log level > > > 3/ run-time option > > > 4/ build-time option > > > > > > It's good to have this discussion and let other contributors giving t= heir > > > opinion. > > > > > > 2015-05-19 22:41, Dumitrescu, Cristian: > > > > 1. What is the technical solution to avoid performance loss due to = stats > > > > support? > > > > Generally, I would agree with you that config options should be > avoided, > > > > especially those that alter the API (function prototypes, data stru= cture > > > > layouts, etc). Please note this is not the case for any of our patc= hes, > > > > as only the stats collection is enabled/disabled, while the data > > > > structures and functions are not changed by the build time option. > > > > > > > > But what can you do for statistics? We all know that collecting the= stats > > > > sucks up CPU cycles, especially due to memory accesses, so stats al= ways > > > > have a run-time cost. Traditionally, stats are typically enabled fo= r > > > > debugging purposes and then turned off for the release version when > > > > performance is required. How can this be done if build time flags a= re > not > > > > used? > > > > > > Statistics in drivers are always enabled (first solution). > > > If those statistics are only used for debugging, why not using the bu= ild- > time > > > option CONFIG_RTE_LOG_LEVEL? (second solution) > > > > Can you please describe what solution 2 on your list (build-time log > > level) consists of? > > > > I see log level useful for printing messages when an event takes place, > > but this is not what these stats patches are about. We want to poll > > for those counters on demand: if the build-time flag is off, then the > > value of those counters is 0; when the build-time is on, then the stats > > counters have the real value. Basically, the build-time flag only > > enables/disables the update of the counters at run-time, which is where > > CPU cycles are consumed. I am not sure how the log levels can help here= ? >=20 > I think that counting stats is a kind of logging. > Some stats are always counted (see drivers) and you want to use these one= s > only for debugging (after rebuilding DPDK with some debug options). > So I suggest, as second solution, to check CONFIG_RTE_LOG_LEVEL is at > debug > level instead of having one option per module. > It would be implemented with "#if RTE_LOG_LEVEL =3D=3D RTE_LOG_DEBUG" in > RTE_PIPELINE_STATS_ADD. The problem I see with this approach is that you cannot turn off debug mess= ages while still having the statistics collected. We should allow people t= o collects the stats without getting the debug messages. How do we do this? Although most people use the stats for debugging and then turn them off, so= me other people are OK with the stats related performance drop for the prod= uction code (e.g. they might want to log some stats periodically), but they= want to get rid of the debug messages.=20 Potential idea: Would it be acceptable to create a new log level that is dedicated to stats= ? This would have to be higher priority than all the present ones, so it ne= eds to be: #define RTE_LOG_STATS 1U. This way, we can get rid of all the= debug messages while still logging stats: #if ((RTE_LOG_STATS <=3D RTE_LOG_LEVEL) #define STATS_COUNTER_ADD(level, type, counter, val) counter +=3D val #else #define STATS_COUNTER_ADD(level, type, counter, val) #endif However, this won't allow getting the debug messages with stats collection = being suppressed. But probably this case is not relevant.