From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 29AEDA00E6 for ; Mon, 8 Jul 2019 11:14:52 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 6ACAC31FC; Mon, 8 Jul 2019 11:14:51 +0200 (CEST) Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by dpdk.org (Postfix) with ESMTP id 4611F3195 for ; Mon, 8 Jul 2019 11:14:48 +0200 (CEST) X-Amp-Result: UNKNOWN X-Amp-Original-Verdict: FILE UNKNOWN X-Amp-File-Uploaded: False Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga107.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 08 Jul 2019 02:14:47 -0700 X-IronPort-AV: E=Sophos;i="5.63,466,1557212400"; d="scan'208";a="159071475" Received: from bricha3-mobl.ger.corp.intel.com ([10.237.221.51]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 08 Jul 2019 02:14:45 -0700 Date: Mon, 8 Jul 2019 10:14:42 +0100 From: Bruce Richardson To: David Marchand Cc: Xiaolong Ye , Ferruh Yigit , Qi Zhang , dev Message-ID: <20190708091442.GA476@bricha3-MOBL.ger.corp.intel.com> References: <20190707155705.58515-1-xiaolong.ye@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.11.4 (2019-03-13) Subject: Re: [dpdk-dev] [PATCH] net/af_xdp: correct xdp frame size X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On Mon, Jul 08, 2019 at 10:26:18AM +0200, David Marchand wrote: > On Mon, Jul 8, 2019 at 10:03 AM Xiaolong Ye wrote: > > > XSK_UMEM__DEFAULT_FRAME_SIZE has been changed to 4096 in kernel commit > > 123e8da1d330 (xsk: Change the default frame size to 4096 and allow > > controlling it), but we still need to keep ETH_AF_XDP_FRAME_SIZE as 2048 to > > fit most dpdk apps. > > > > I might have missed something, but can't you use the mbuf size from the > packet mempool passed at rx_queue_setup? > Sadly not - but we are working on ways to allow that. Right now, the kernel only allows 2k aligned buffers of 2k or 4k in size for packet IO, which prevents regular mbuf pools from working. There is work in progress to relax those restrictions, but it's not yet ready for kernel acceptance. The V1 of the set can be seen at: https://www.spinics.net/lists/netdev/msg579786.html