From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <dev-bounces@dpdk.org>
Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124])
	by inbox.dpdk.org (Postfix) with ESMTP id 09EE84252F;
	Thu,  7 Sep 2023 04:09:49 +0200 (CEST)
Received: from mails.dpdk.org (localhost [127.0.0.1])
	by mails.dpdk.org (Postfix) with ESMTP id 9C2134029E;
	Thu,  7 Sep 2023 04:09:48 +0200 (CEST)
Received: from VLXDG1SPAM1.ramaxel.com (email.unionmem.com [221.4.138.186])
 by mails.dpdk.org (Postfix) with ESMTP id 503E94029D
 for <dev@dpdk.org>; Thu,  7 Sep 2023 04:09:45 +0200 (CEST)
Received: from V12DG1MBS03.ramaxel.local ([172.26.18.33])
 by VLXDG1SPAM1.ramaxel.com with ESMTP id 38729QtK028327;
 Thu, 7 Sep 2023 10:09:26 +0800 (GMT-8)
 (envelope-from wanry@3snic.com)
Received: from [10.64.136.151] (10.64.136.151) by V12DG1MBS03.ramaxel.local
 (172.26.18.33) with Microsoft SMTP Server (version=TLS1_2,
 cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id 15.1.2375.17; Thu, 7
 Sep 2023 10:09:25 +0800
Message-ID: <547ced53-b77e-494c-a849-bf954d44f60a@3snic.com>
Date: Thu, 7 Sep 2023 10:09:23 +0800
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH 08/32] net/sssnic/base: add work queue
To: Stephen Hemminger <stephen@networkplumber.org>
CC: <dev@dpdk.org>, <ferruh.yigit@amd.com>, Steven Song <steven.song@3snic.com>
References: <20230829075829.208413-1-wanry@3snic.com>
 <20230829075829.208413-9-wanry@3snic.com>
 <20230906080918.7c0545dd@hermes.local>
From: Renyong Wan <wanry@3snic.com>
In-Reply-To: <20230906080918.7c0545dd@hermes.local>
Content-Type: text/plain; charset="UTF-8"; format=flowed
Content-Transfer-Encoding: 8bit
X-Originating-IP: [10.64.136.151]
X-ClientProxiedBy: V12DG1MBS01.ramaxel.local (172.26.18.31) To
 V12DG1MBS03.ramaxel.local (172.26.18.33)
X-DNSRBL: 
X-SPAM-SOURCE-CHECK: pass
X-MAIL: VLXDG1SPAM1.ramaxel.com 38729QtK028327
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.29
Precedence: list
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

Hello Stephen,

Thanks for your kindly review.

sssnic_workq is quite different from rte_ring, it's used to maintain 
information of hardware work queue, like Rx work queue, Tx work queue 
etc. Unlike rte_ring the elements of sssnic_workq are organized in a 
blcok of contiguous DMA memory accessed by hardware work queue, in 
addition the sssnic_workq records CI(consumer index) and PI(producer 
index) that synchronize with hardware work queue, driver generally 
accesses element of sssnic_workq by PI or CI.  Therefore I don't think 
rte_ring is suitable for sssnic_workq.

On 2023/9/6 23:09, Stephen Hemminger wrote:
> On Tue, 29 Aug 2023 15:58:05 +0800w
> <wanry@3snic.com> wrote:
>
>> From: Renyong Wan <wanry@3snic.com>
>>
>> Work queue is used to maintain hardware queue information by
>> driver, it is usually used in control queue, rx queue
>> and tx queue.
>>
>> Signed-off-by: Steven Song <steven.song@3snic.com>
>> Signed-off-by: Renyong Wan <wanry@3snic.com>
> Looks like this driver is reinventing rte_ring.
> Please don't do this.

-- 
Regards,
Renyong Wan