From mboxrd@z Thu Jan 1 00:00:00 1970 From: Olivier MATZ Subject: Re: Making space in mbuf data-structure Date: Wed, 16 Jul 2014 14:32:54 +0200 Message-ID: <53C670F6.8070007@6wind.com> References: <59AF69C657FD0841A61C55336867B5B02CF13E32@IRSMSX103.ger.corp.intel.com> <53BA7422.9080706@6wind.com> <2601191342CEEE43887BDE71AB97725821338121@IRSMSX105.ger.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit To: "Ananyev, Konstantin" , "Richardson, Bruce" , "dev-VfR2kkLFssw@public.gmane.org" Return-path: In-Reply-To: <2601191342CEEE43887BDE71AB97725821338121-kPTMFJFq+rEu0RiL9chJVbfspsVTdybXVpNB7YpNyf8@public.gmane.org> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" Hi Konstantin, On 07/15/2014 11:07 AM, Ananyev, Konstantin wrote: >> As this change would impact the core of DPDK, I think it would be >> interesting to list some representative use-cases in order to evaluate >> the cost of each solution. This will also help for future modifications, >> and could be included in a sort of non-regression test? >> > > I think this is a very good idea. > Let's create a list of such test-cases. > Two obvious apps from our side would probably be: > - test-pmd iofwd mode > - l3fwd > What else should we add here? I agree that test-pmd iofwd is a good reference to track regressions or analyze performance issues, but I'm not sure it's a real use-case. To me, it's more important to ensure that l3fwd performance stay stable compared to iofwd. I think l3fwd is the most representative of a DPDK application. Other use-case could include: - virtualization, maybe using ovdk? - ip fragmentation / reassembly - an application that encapsulate or decapsulate in a tunnel Regards, Olivier