From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id 703B95A6B for ; Fri, 6 Nov 2015 06:33:33 +0100 (CET) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga101.jf.intel.com with ESMTP; 05 Nov 2015 21:33:32 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.20,250,1444719600"; d="scan'208";a="843841917" Received: from fmsmsx106.amr.corp.intel.com ([10.18.124.204]) by orsmga002.jf.intel.com with ESMTP; 05 Nov 2015 21:33:32 -0800 Received: from FMSMSX110.amr.corp.intel.com (10.18.116.10) by FMSMSX106.amr.corp.intel.com (10.18.124.204) with Microsoft SMTP Server (TLS) id 14.3.248.2; Thu, 5 Nov 2015 21:33:31 -0800 Received: from shsmsx102.ccr.corp.intel.com (10.239.4.154) by fmsmsx110.amr.corp.intel.com (10.18.116.10) with Microsoft SMTP Server (TLS) id 14.3.248.2; Thu, 5 Nov 2015 21:33:31 -0800 Received: from shsmsx101.ccr.corp.intel.com ([169.254.1.57]) by shsmsx102.ccr.corp.intel.com ([169.254.2.199]) with mapi id 14.03.0248.002; Fri, 6 Nov 2015 13:33:30 +0800 From: "Xie, Huawei" To: Tetsuya Mukawa , "dev@dpdk.org" Thread-Topic: [RFC PATCH] vhost: remove lockless enqueue to virt ring Thread-Index: AdEXs8MKEM4gvU7ETWOXGe7VBj3daA== Date: Fri, 6 Nov 2015 05:33:29 +0000 Message-ID: References: <1446658952-101192-1-git-send-email-huawei.xie@intel.com> <563C0598.1040205@igel.co.jp> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "ann.zhuangyanying@huawei.com" Subject: Re: [dpdk-dev] [RFC PATCH] vhost: remove lockless enqueue to virt ring X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 06 Nov 2015 05:33:33 -0000 On 11/6/2015 9:43 AM, Tetsuya Mukawa wrote:=0A= > On 2015/11/05 19:21, Xie, Huawei wrote:=0A= >> If no objections, would remove the internal cmpset enqueue, should get= =0A= >> some improved performance.=0A= >>=0A= >> No idea why commit message is lost:=0A= >> DPDK doesn't support receiving/transmitting packets from/to the same=0A= >> port/queue.=0A= >> Vhost pmd wraps vhost device as normal dpdk port. dpdkvhost based=0A= >> applications/switch=0A= >> also treate virtio port and physical port both as ports, and have=0A= >> their own=0A= >> lock implmentation when to enqueue packets to the same port. This patch= =0A= >> removes=0A= >> the internal lockless vhost enqueue implmentation.=0A= >> On 11/5/2015 5:38 PM, Huawei Xie wrote:=0A= >>> Signed-off-by: Huawei Xie =0A= > Hi Xie,=0A= >=0A= > I think it's a good optimization.=0A= > But I guess the patch will changes behavior of vhost library API.=0A= > For example, if someone has already implemented an application based on= =0A= > the assumption that vhost library has internal lock, I doubt their=0A= > application will face an issue with this patch.=0A= Yes, i understand. If we have an improper implementation, we fix it as=0A= early as possible. I prefer to remove the internal lock currently. The=0A= last thing i want to do is maintain two APIs.=0A= Would follow the ABI process.=0A= >=0A= > If it's correct, we might need to follow below steps.=0A= > http://dpdk.org/doc/guides/contributing/versioning.html=0A= >=0A= > Thanks,=0A= > Tetsuya=0A= >=0A= =0A=