From mboxrd@z Thu Jan  1 00:00:00 1970
From: =?UTF-8?Q?Mattias_R=c3=b6nnblom?= <mattias.ronnblom@ericsson.com>
Subject: Re: DSW eventdev and multi-process DPDK
Date: Fri, 18 Jan 2019 15:47:42 +0100
Message-ID: <b9c363d6-f64f-d9a3-8e25-3d06c80e1024@ericsson.com>
References: <2D68DFF2-08A3-403B-9570-43D4AD916FD2@paloaltonetworks.com>
 <e35340db-a364-4735-037d-c15220b3ecfe@ericsson.com>
 <8C05BF3C-5D90-4CD0-AA71-1B4C4324E53B@paloaltonetworks.com>
 <597ee5d1-6db1-54ee-36af-df28ef1654bb@ericsson.com>
 <2ED77A34-B171-49BF-966A-BAE6A9E1BC66@paloaltonetworks.com>
 <ff0ca613-8a3c-b1d9-8247-fedf31aab884@ericsson.com>
 <58E15395-2C48-49C0-B702-40F511E61E55@paloaltonetworks.com>
 <C87F4808-2A33-47E0-B959-B95895B19D2F@paloaltonetworks.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 8bit
To: Venky Venkatesh <vvenkatesh@paloaltonetworks.com>,
 "dev@dpdk.org" <dev@dpdk.org>
Return-path: <dev-bounces@dpdk.org>
Received: from mail.lysator.liu.se (mail.lysator.liu.se [130.236.254.3])
 by dpdk.org (Postfix) with ESMTP id BC10F28FD
 for <dev@dpdk.org>; Fri, 18 Jan 2019 15:47:43 +0100 (CET)
Received: from mail.lysator.liu.se (localhost [127.0.0.1])
 by mail.lysator.liu.se (Postfix) with ESMTP id 3B54A4001C
 for <dev@dpdk.org>; Fri, 18 Jan 2019 15:47:43 +0100 (CET)
In-Reply-To: <C87F4808-2A33-47E0-B959-B95895B19D2F@paloaltonetworks.com>
Content-Language: en-US
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <https://mails.dpdk.org/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://mails.dpdk.org/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <https://mails.dpdk.org/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

On 2019-01-18 07:36, Venky Venkatesh wrote:
> 
> [VV]: Some more information. I went with the assumption that I will call these APIs on both the PRIMARY and SECONDARY processes and that these APIs would do the right thing viz. on the PRIMARY it would allocate and initialize while in the SECONDARY it would attach to those memories and structures. However that doesn’t seem to be the case: rte_event_port_setup is trying to allocate a ring of the same name in both processes and is crashing in rte_memzone_reserve_thread_safe (specifically at if ((memzone_lookup_thread_unsafe(name)) != NULL)) which is called from rte_event_ring_create.

Ports etc need (and should) only be configured once.

> Can you pls advise if the DSW is multiprocess ready?

I've answered this question already.

>If not, are there any plans to do so?
> 

For all I know, it should work already. If not, maybe it's here Palo 
Alto Networks chips in.