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 DCD24201 for ; Wed, 26 Jul 2017 16:55:56 +0200 (CEST) Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga103.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 26 Jul 2017 07:55:55 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.40,415,1496127600"; d="scan'208";a="883047490" Received: from fmsmsx105.amr.corp.intel.com ([10.18.124.203]) by FMSMGA003.fm.intel.com with ESMTP; 26 Jul 2017 07:55:55 -0700 Received: from fmsmsx158.amr.corp.intel.com (10.18.116.75) by FMSMSX105.amr.corp.intel.com (10.18.124.203) with Microsoft SMTP Server (TLS) id 14.3.319.2; Wed, 26 Jul 2017 07:55:54 -0700 Received: from fmsmsx113.amr.corp.intel.com ([169.254.13.214]) by fmsmsx158.amr.corp.intel.com ([169.254.15.172]) with mapi id 14.03.0319.002; Wed, 26 Jul 2017 07:55:55 -0700 From: "Wiles, Keith" To: Paul Tsvika CC: "users@dpdk.org" Thread-Topic: [dpdk-users] [pktgen] pktgen Tx/Rx rates are not the same in loopback testing case Thread-Index: AQHTAjO1rkKNoVHuA0KRl+W6vTqWpaJe4GEAgACqE4CABTCCAIAAVYsAgAE8WYCAAGKlgA== Date: Wed, 26 Jul 2017 14:55:53 +0000 Message-ID: References: <5ABE8F66-FD6B-424C-835C-74CB0CA4F8EE@intel.com> In-Reply-To: Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.254.49.103] Content-Type: text/plain; charset="us-ascii" Content-ID: <0F0935AA09F0CC40965A113426F8E600@intel.com> Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-users] [pktgen] pktgen Tx/Rx rates are not the same in loopback testing case X-BeenThere: users@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK usage discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Jul 2017 14:55:57 -0000 > On Jul 26, 2017, at 4:02 AM, Paul Tsvika wrote: >=20 > Hi Keith. >=20 > This is a loopback test and I think it somehow affects the performance si= nce there is only one NIC and phy on the mother board. >=20 > I tried two mother boards and the tx/rx ( 9611/9497 ) rates look more rea= sonable. >=20 > I can also set packet size in pktgen command line.=20 If Pktgen performance is OK in other motherboards, then the problem with th= is machine is most likely not a Pktgen problem. You did not answer my quest= ion about the PCIe slots in my previous email. >=20 > However, I still don't understand why RX Desc 512, TX Desc 1024 are not = the same. >=20 > Should the values suppose to be the same ? The increased TX ring size is to reduce the number of times a TX done clean= up occurs. >=20 >=20 >=20 > Regards- >=20 >=20 > P.T >=20 > =20 Regards, Keith