From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <jinxiu.1006@163.com>
Received: from m13-71.163.com (m13-71.163.com [220.181.13.71])
 by dpdk.org (Postfix) with ESMTP id 609421F3
 for <dev@dpdk.org>; Tue, 13 Aug 2013 08:26:47 +0200 (CEST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=163.com;
 s=s110527; h=Received:Date:From:To:Subject:Content-Type:
 MIME-Version:Message-ID; bh=PDw2FBWSAMnY9q5pTDi5vAce5nTMy4GZCfaD
 sOBBBiM=; b=XSeOaUaS0iyPWiytZEgGWB4SaK2ok36qm3UARRDb7BLHwswSqoS9
 H5BRDmTvQFP7vyigWcUnD4w1fEhT0lHFx1rI1MtpQTp67dd0sGvpHa5SIB9tagLZ
 Ci05Ik8v16N8ISwOh692IZ+ugvZPVOicVOLiuRNz3mjXpfduDI49FDQ=
Received: from jinxiu.1006$163.com ( [211.162.75.108] ) by
 ajax-webmail-wmsvr71 (Coremail) ; Tue, 13 Aug 2013 14:27:11 +0800 (CST)
X-Originating-IP: [211.162.75.108]
Date: Tue, 13 Aug 2013 14:27:11 +0800 (CST)
From: dvr  <jinxiu.1006@163.com>
To: dev@dpdk.org
X-Priority: 3
X-Mailer: Coremail Webmail Server Version SP_ntes V3.5 build
 20130709(22708.5479.5480) Copyright (c) 2002-2013 www.mailtech.cn 163com
X-CM-CTRLDATA: AjDJYGZvb3Rlcl9odG09MzYxMDo4MQ==
Content-Type: multipart/alternative; 
 boundary="----=_Part_383295_844658498.1376375231182"
MIME-Version: 1.0
Message-ID: <48188b20.1c74c.140765b52ce.Coremail.jinxiu.1006@163.com>
X-CM-TRANSID: R8GowECJRkDA0QlSypj+AA--.1799W
X-CM-SenderInfo: xmlq5xbxoriiqw6rljoofrz/1tbiGgJ47FD+LPVu+wABsv
X-Coremail-Antispam: 1U5529EdanIXcx71UUUUU7vcSsGvfC2KfnxnUU==
Subject: [dpdk-dev] =?gbk?b?SXMgobFydGVfbWVtcG9vbF9tcF9wdXRfYnVsaygpobAg?=
 =?gbk?q?multi-producer_safe=3F?=
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: Tue, 13 Aug 2013 06:26:48 -0000

------=_Part_383295_844658498.1376375231182
Content-Type: text/plain; charset=GBK
Content-Transfer-Encoding: 7bit

hi,
    all
    I'm confused with some code about mempool:   
   
    rte_mempool.h   ( lib/ librte_mempool ,about line 668) 
    rte_mempool_mp_put_bulk();   //put serveral objects back in the mempool(multi-producers safe)
    rte_mempool_sp_put_bulk();   //put serveral objects back in the mempool(NOT multi-producers safe)
 
    rte_mempool.h   ( lib/ librte_mempool ,about line 563) 
    __mempool_put_bulk()
    {
         ......
         if(unlikely(cache_size==0 || is_mp==0))   
               goto ring_enqueue;
         ......
         //add in cache while there is enough room
        while(cache_add_count>0) {
             cache_objs[cache_len]=*obj_table;
             obj_table++;
             cache_len++;
             n--;
             cache_add_count--;
        }
             ......
       ring_enqueue:
        ......
       if(is_mp)
            rte_ring_mp_enqueue_bulk();
       else
            rte_ring_sp_enqueue_bulk();
        ......
    }
 
    My question is :rte_mempool_mp_put_bulk() and rte_mempool_sp_put_bulk() call the same function  __mempool_put_bulk() with different "is_mp" value. If is_mp=1, that is ,multi-producer, the code will add these objects in cache while there is enough room, when two thread enqueue objects at the same time, isn't it unsafe?but the annotation show this function is "multi-producer safe".
    Another question: how many thread we can have on a core? just one?
 
    Any help will be appreciate!
    Regards
Maria
------=_Part_383295_844658498.1376375231182
Content-Type: text/html; charset=GBK
Content-Transfer-Encoding: 7bit

<div style="line-height:1.7;color:#000000;font-size:14px;font-family:arial"><DIV style="LINE-HEIGHT: 1.7; FONT-FAMILY: arial; COLOR: #000000; FONT-SIZE: 14px">
<DIV>hi,</DIV>
<DIV>&nbsp;&nbsp;&nbsp; all</DIV>
<DIV>&nbsp;&nbsp;&nbsp; I'm confused with some code about mempool:&nbsp;&nbsp;&nbsp; </DIV>
<DIV>&nbsp;&nbsp;&nbsp; </DIV>
<DIV>&nbsp;&nbsp;&nbsp; <SPAN style="COLOR: #880000">rte_mempool.h&nbsp;&nbsp; ( lib/ librte_mempool ,about line 668)</SPAN>&nbsp;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;rte_mempool_mp_put_bulk();&nbsp;&nbsp; //put serveral objects back in the mempool(multi-producers safe)</DIV>
<DIV>
<DIV>&nbsp;&nbsp;&nbsp; rte_mempool_sp_put_bulk();&nbsp;&nbsp; //put serveral objects back in the mempool(NOT multi-producers safe)</DIV>
<DIV>&nbsp;</DIV>
<DIV>&nbsp;&nbsp;&nbsp; <SPAN style="COLOR: #880000">rte_mempool.h&nbsp;&nbsp; ( lib/ librte_mempool ,about line 563)&nbsp;</SPAN></DIV>
<DIV><SPAN style="COLOR: #880000"></SPAN>&nbsp;&nbsp;&nbsp; __mempool_put_bulk()</DIV>
<DIV>&nbsp;&nbsp;&nbsp; { </DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; ......</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; if(unlikely(cache_size==0 || is_mp==0))&nbsp;&nbsp;<SPAN style="COLOR: #880000">&nbsp;</SPAN></DIV>
<DIV><SPAN style="COLOR: #880000"></SPAN><SPAN style="COLOR: #880000"></SPAN>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; goto ring_enqueue;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;......</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; //add in cache while there is enough room</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; while(cache_add_count&gt;0) {</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; cache_objs[cache_len]=*obj_table;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;obj_table++;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;cache_len++;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;n--;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;cache_add_count--;</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; }</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;......</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; ring_enqueue:</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; ......</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; if(is_mp)</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; rte_ring_mp_enqueue_bulk();</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; else</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;rte_ring_sp_enqueue_bulk();</DIV>
<DIV>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; ......</DIV>
<DIV>&nbsp;&nbsp;&nbsp; }</DIV>
<DIV>&nbsp;</DIV>
<DIV>&nbsp;&nbsp;&nbsp; My question is :rte_mempool_mp_put_bulk() and rte_mempool_sp_put_bulk() call the same function&nbsp; __mempool_put_bulk() with different "is_mp" value. If is_mp=1, that is ,multi-producer,&nbsp;the code will add these objects&nbsp;in cache while there is enough room, when two thread enqueue objects at the same time, isn't it unsafe?but the annotation show this function is "multi-producer safe".</DIV>
<DIV>&nbsp;&nbsp;&nbsp; Another question: how many thread we can have&nbsp;on a core? just one?</DIV>
<DIV>&nbsp;</DIV>
<DIV>&nbsp;&nbsp;&nbsp; Any help will be appreciate!</DIV>
<DIV>&nbsp;&nbsp;&nbsp; Regards</DIV>
<DIV>Maria</DIV></DIV></DIV></div><br><br><span title="neteasefooter"><span id="netease_mail_footer"></span></span>
------=_Part_383295_844658498.1376375231182--