From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <mhall@mhcomputing.net>
Received: from mail.mhcomputing.net (master.mhcomputing.net [74.208.46.186])
 by dpdk.org (Postfix) with ESMTP id 87A177F0C
 for <dev@dpdk.org>; Thu, 20 Nov 2014 22:43:29 +0100 (CET)
Received: by mail.mhcomputing.net (Postfix, from userid 1000)
 id E469180C00C; Thu, 20 Nov 2014 13:52:33 -0800 (PST)
Date: Thu, 20 Nov 2014 13:52:33 -0800
From: Matthew Hall <mhall@mhcomputing.net>
To: Newman Poborsky <newman555p@gmail.com>
Message-ID: <20141120215233.GA15551@mhcomputing.net>
References: <CAHW=9PuErCQW=PDFzMoQLyUhzif6xNsU_28UmiJC=895t8+62w@mail.gmail.com>
 <E115CCD9D858EF4F90C690B0DCB4D8972684D317@IRSMSX108.ger.corp.intel.com>
 <CAHW=9Pthh1-sHbpbjt9PvQcjZ_Tr_9EK+re7zkdmw=pFv0_Fbw@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAHW=9Pthh1-sHbpbjt9PvQcjZ_Tr_9EK+re7zkdmw=pFv0_Fbw@mail.gmail.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] one worker reading multiple ports
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
X-List-Received-Date: Thu, 20 Nov 2014 21:43:29 -0000

On Thu, Nov 20, 2014 at 05:10:51PM +0100, Newman Poborsky wrote:
> Thank you for your answer.
> 
> I just realized that the reason the rte_eth_rx_burst() returns 0 is because
> inside ixgbe_recv_pkts() this fails:
> nmb = rte_rxmbuf_alloc(rxq->mb_pool);  => nmb is NULL
> 
> Does this mean that every RX queue should have its own rte_mempool?  If so,
> are there any optimal values for: number of RX descriptors, per-queue
> rte_mempool size, number of hugepages (from what I understand, these 3 are
> correlated)?
> 
> If I'm wrong, please explain why.
> 
> Thanks!
> 
> BR,
> Newman

Newman,

Mempools are created per NUMA node (ordinarily this means per processor socket 
if sockets > 1).

When doing Tx / Rx Queue Setup, one should determine the socket which owns the 
given PCI NIC, and try to use memory on that same socket to handle traffic for 
that NIC and Queues.

So, for N cards with Q * N Tx / Rx queues, you only need S mempools.

Then each of the Q * N queues will use the mempool from the socket closest to 
the card.

Matthew.