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 06BED5A30 for ; Wed, 8 Jun 2016 12:25:58 +0200 (CEST) Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by orsmga103.jf.intel.com with ESMTP; 08 Jun 2016 03:25:57 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.26,438,1459839600"; d="scan'208";a="983264993" Received: from fmsmsx106.amr.corp.intel.com ([10.18.124.204]) by fmsmga001.fm.intel.com with ESMTP; 08 Jun 2016 03:25:29 -0700 Received: from fmsmsx155.amr.corp.intel.com (10.18.116.71) by FMSMSX106.amr.corp.intel.com (10.18.124.204) with Microsoft SMTP Server (TLS) id 14.3.248.2; Wed, 8 Jun 2016 03:25:28 -0700 Received: from shsmsx152.ccr.corp.intel.com (10.239.6.52) by FMSMSX155.amr.corp.intel.com (10.18.116.71) with Microsoft SMTP Server (TLS) id 14.3.248.2; Wed, 8 Jun 2016 03:25:28 -0700 Received: from shsmsx101.ccr.corp.intel.com ([169.254.1.24]) by SHSMSX152.ccr.corp.intel.com ([169.254.6.107]) with mapi id 14.03.0248.002; Wed, 8 Jun 2016 18:25:26 +0800 From: "Ye, ShushenX" To: "users@dpdk.org" Thread-Topic: suggest dpdk transplant to window NDIS6.4 platform Thread-Index: AdHBbbbXPfGe4B9YQ4eFev2+15Dbcg== Date: Wed, 8 Jun 2016 10:25:26 +0000 Message-ID: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: [dpdk-users] suggest dpdk transplant to window NDIS6.4 platform X-BeenThere: users@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: usage discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 08 Jun 2016 10:25:59 -0000 suggest dpdk transplant to window platform in windows platform 1G NIC only can use 10% line rate in small packet mode,= in big concurrent TCP link environment, It's too slow, I have high concurrent task system(in windows), Performance is very good, I= t's can solve c10k problem, in windows, It's can reach 10 million TCP link= , However iops only 100k, it's far from reaching 1G NIC's 1.4 million iops If dpdk can provide mul queue packet interface to Windows user mode , It = will be exciting. -----Original Message----- From: users [mailto:users-bounces@dpdk.org] On Behalf Of users-request@dpdk= .org Sent: Wednesday, June 8, 2016 6:00 PM To: users@dpdk.org Subject: users Digest, Vol 34, Issue 1 Send users mailing list submissions to users@dpdk.org To subscribe or unsubscribe via the World Wide Web, visit http://dpdk.org/ml/listinfo/users or, via email, send a message with subject or body 'help' to users-request@dpdk.org You can reach the person managing the list at users-owner@dpdk.org When replying, please edit your Subject line so it is more specific than "R= e: Contents of users digest..." Today's Topics: 1. KNI app random mac generation (SAKTHIVEL ANAND S) 2. Re: FW: Looking for packet forwarding of real traffic (Jean Tourrilhes) 3. A question about the function __mempool_get_bulk() of dpdk-16.04 (Wu, Xiaoban) 4. Re: A question about the function __mempool_get_bulk() of dpdk-16.04 (Wiles, Keith) 5. Re: A question about the function __mempool_get_bulk() of dpdk-16.04 (Wu, Xiaoban) ---------------------------------------------------------------------- Message: 1 Date: Tue, 7 Jun 2016 19:38:20 +0530 From: SAKTHIVEL ANAND S To: users@dpdk.org Subject: [dpdk-users] KNI app random mac generation Message-ID: Content-Type: text/plain; charset=3DUTF-8 Hi I have recently downloaded 16.04, in this version also i could see KNI rand= om mac generation behavior. Is there any plan to fix this or it is purposef= ully made like that? if i am wrongly understood this random generation, ple= ase explain its purpose. -- Thanks Sakthivel S OM ------------------------------ Message: 2 Date: Tue, 7 Jun 2016 11:35:20 -0700 From: Jean Tourrilhes To: users@dpdk.org, anand.sa88@gmail.com Subject: Re: [dpdk-users] FW: Looking for packet forwarding of real traffic Message-ID: <20160607183520.GB16956@labs.hpe.com> Content-Type: text/plain; charset=3Dus-ascii SAKTHIVEL ANAND S wrote: >=20 > you may try KNI app ,in the examples. > Thanks I may try that. Thanks ! Jean ------------------------------ Message: 3 Date: Tue, 7 Jun 2016 20:52:25 +0000 From: "Wu, Xiaoban" To: "users@dpdk.org" Subject: [dpdk-users] A question about the function __mempool_get_bulk() of dpdk-16.04 Message-ID: =09 Content-Type: text/plain; charset=3D"iso-8859-1" Dear DPDK Users, I have been reading the pktgen-3.0.02 source codes with dpdk-16.04. In the pktgen.c, function pktgen_send_pkts(), line 1098, it calls function = wr_pktmbuf_alloc_bulk_noreset(). Then it calls the function rte_mempool_ge= t_bulk() which calls the function __mempool_get_bulk(). Since in the function rte_pktmbuf_pool_create(), the "flags" is set to zero= in default, this leads to that when calling __mempool_get_bulk(), the inpu= t parameter"is_mc=3D=3D1". Hence the function __mempool_get_bulk() will exe= cute the line 961-992 except that when "ret" is less that 0. My question is why at line 992, this has to return 0? In the line 941, the = comment says that ">=3D0: Success; number of objects supplied." I am confu= sed by this comment, since in line 985-990, we can see that the input param= eter "obj_table" is supplied by new values and the number of the new values= is "n". Does this means that we need to "return n;" instead of "return 0;"= ? Am I missing something here? Thank you so much for your help. All the best, Xiaoban ------------------------------ Message: 4 Date: Tue, 7 Jun 2016 22:30:24 +0000 From: "Wiles, Keith" To: "Wu, Xiaoban" , "users@dpdk.org" Subject: Re: [dpdk-users] A question about the function __mempool_get_bulk() of dpdk-16.04 Message-ID: <506DDABB-6DFC-4FEB-8A8D-43B7AA2EE251@intel.com> Content-Type: text/plain; charset=3D"utf-8" On 6/7/16, 3:52 PM, "users on behalf of Wu, Xiaoban" wrote: >Dear DPDK Users, > > >I have been reading the pktgen-3.0.02 source codes with dpdk-16.04. > > >In the pktgen.c, function pktgen_send_pkts(), line 1098, it calls function= wr_pktmbuf_alloc_bulk_noreset(). Then it calls the function rte_mempool_g= et_bulk() which calls the function __mempool_get_bulk(). > > >Since in the function rte_pktmbuf_pool_create(), the "flags" is set to zer= o in default, this leads to that when calling __mempool_get_bulk(), the inp= ut parameter"is_mc=3D=3D1". Hence the function __mempool_get_bulk() will ex= ecute the line 961-992 except that when "ret" is less that 0. I checked out dpdk v16.04 and could not get your line numbers to workout, m= aybe you are on a slightly different version then release 16.04?? > > >My question is why at line 992, this has to return 0? In the line 941, the= comment says that ">=3D0: Success; number of objects supplied." I am conf= used by this comment, since in line 985-990, we can see that the input para= meter "obj_table" is supplied by new values and the number of the new value= s is "n". Does this means that we need to "return n;" instead of "return 0;= "? The statement ?>=3D0 number of objects supplied? also confused me some, but= routines rte_ring_mc/sc_dequeue_bulk() returns zero on success when all re= quested objects are return not the number of objects returned. It seems it = would be nice to have the number of objects returned, but as it is always ?= n? it is best to return < 0 on error. The _bulk allocate will not return a= les then ?n? objects, this is why the code in pktgen tests for zero and no= t something greater then zero. The code in pktgen could test for ret >=3D 0= but the results are the same.=20 > > >Am I missing something here? Thank you so much for your help. > > >All the best, > >Xiaoban > ------------------------------ Message: 5 Date: Wed, 8 Jun 2016 00:12:44 +0000 From: "Wu, Xiaoban" To: "Wiles, Keith" , "users@dpdk.org" Subject: Re: [dpdk-users] A question about the function __mempool_get_bulk() of dpdk-16.04 Message-ID: =09 Content-Type: text/plain; charset=3D"Windows-1252" Dear Keith, Yes, I see the checking for 0 in the pktgen codes. Maybe it is more clear i= f returns n like the wirte() in linux, but it also means a lot of codes nee= d to be rewritten. As long as it is consistent and we know how to work arou= nd it, it should be fine. Thanks so much for your reply. All the best, Xiaoban ________________________________________ From: Wiles, Keith Sent: Tuesday, June 7, 2016 6:30:24 PM To: Wu, Xiaoban; users@dpdk.org Subject: Re: [dpdk-users] A question about the function __mempool_get_bulk(= ) of dpdk-16.04 On 6/7/16, 3:52 PM, "users on behalf of Wu, Xiaoban" wrote: >Dear DPDK Users, > > >I have been reading the pktgen-3.0.02 source codes with dpdk-16.04. > > >In the pktgen.c, function pktgen_send_pkts(), line 1098, it calls function= wr_pktmbuf_alloc_bulk_noreset(). Then it calls the function rte_mempool_g= et_bulk() which calls the function __mempool_get_bulk(). > > >Since in the function rte_pktmbuf_pool_create(), the "flags" is set to zer= o in default, this leads to that when calling __mempool_get_bulk(), the inp= ut parameter"is_mc=3D=3D1". Hence the function __mempool_get_bulk() will ex= ecute the line 961-992 except that when "ret" is less that 0. I checked out dpdk v16.04 and could not get your line numbers to workout, m= aybe you are on a slightly different version then release 16.04?? > > >My question is why at line 992, this has to return 0? In the line 941, the= comment says that ">=3D0: Success; number of objects supplied." I am conf= used by this comment, since in line 985-990, we can see that the input para= meter "obj_table" is supplied by new values and the number of the new value= s is "n". Does this means that we need to "return n;" instead of "return 0;= "? The statement ?>=3D0 number of objects supplied? also confused me some, but= routines rte_ring_mc/sc_dequeue_bulk() returns zero on success when all re= quested objects are return not the number of objects returned. It seems it = would be nice to have the number of objects returned, but as it is always ?= n? it is best to return < 0 on error. The _bulk allocate will not return a= les then ?n? objects, this is why the code in pktgen tests for zero and no= t something greater then zero. The code in pktgen could test for ret >=3D 0= but the results are the same. > > >Am I missing something here? Thank you so much for your help. > > >All the best, > >Xiaoban > End of users Digest, Vol 34, Issue 1 ************************************