From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mailout1.radware.com (unknown [192.115.180.130]) by dpdk.org (Postfix) with ESMTP id D0D2991B7 for ; Thu, 15 Oct 2015 14:46:54 +0200 (CEST) Received: from ILMB2.corp.radware.com ([169.254.2.82]) by ILCAS2.corp.radware.com ([176.200.120.122]) with mapi id 14.03.0210.002; Thu, 15 Oct 2015 15:46:54 +0300 From: Nissim Nisimov To: "Burakov, Anatoly" , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [PATCH] eal:Map rte cfg and uio at the end of hugepage mem Thread-Index: AQHRB0WhW3ent9mlSkCyXiUSh1guLJ5sf1Jw Date: Thu, 15 Oct 2015 12:46:53 +0000 Message-ID: <94AA676E9B9A384A844E7692F3CAD906C54F8B6B@ILMB2.corp.radware.com> References: <1444911367-23738-1-git-send-email-nissimn@radware.com> In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [176.200.121.205] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH] eal:Map rte cfg and uio at the end of hugepage mem 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: Thu, 15 Oct 2015 12:46:55 -0000 Hi Anatoly, Actually the use of --base-virtaddr will be valuable only when user know in= advance the virtual addresses he wishes for huge pages in his application. We found out that in some of the cases we don't know it in advance and prop= ose a more generic solution which will solve the below issue without user i= nterfering. If user --base-virtaddr is not null (i.e user know the addresses he wants f= or the hugepages) our changes will be disabled and the code will act exactl= y as today without the patch. Pls let me know if u have any more doubts. Thx Nissim -----Original Message----- From: Burakov, Anatoly [mailto:anatoly.burakov@intel.com]=20 Sent: Thursday, October 15, 2015 3:33 PM To: Nissim Nisimov; dev@dpdk.org Subject: RE: [dpdk-dev] [PATCH] eal:Map rte cfg and uio at the end of hugep= age mem Hi > Problem: > In DPDK Primary/Secondary module we assume mapping same regions of=20 > virtual memory addresses for Primary process and Secondary. > An issue may occur when the Primary and secondary processes are not=20 > symmetric in such way that the code is not the same (for example,=20 > Primary process is a traffic distributer and secondary is a worker).=20 > The result may be that specific virtual address region in the first=20 > process won't be available in the second process. >=20 > Changes done at eal init: > map all related rte configuration and uio sections close to the end of=20 > huge pages memory (that mean rte_eal_memory_init() should be called=20 > before > rte_config_init() in primary process) > According to our observations there will be more probability to=20 > success when allocating rte_config and uio memzones after huge pages=20 > sections (actually uio is already allocated after the huge pages area) Not sure I understand the purpose of the patch. Doesn't --base-virtaddr fla= g solve your issues? Thanks, Anatoly