From mboxrd@z Thu Jan  1 00:00:00 1970
From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Subject: Re: [PATCH] vhost: add back support for concurrent
	enqueue
Date: Tue, 16 Aug 2016 10:37:15 +0800
Message-ID: <20160816023715.GL30752@yliu-dev.sh.intel.com>
References: <1471291224-12755-1-git-send-email-rich.lane@bigswitch.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: dev@dpdk.org, Huawei Xie <huawei.xie@intel.com>
To: Rich Lane <rich.lane@bigswitch.com>
Return-path: <dev-bounces@dpdk.org>
Received: from mga04.intel.com (mga04.intel.com [192.55.52.120])
 by dpdk.org (Postfix) with ESMTP id F1AEC5A63
 for <dev@dpdk.org>; Tue, 16 Aug 2016 04:28:46 +0200 (CEST)
Content-Disposition: inline
In-Reply-To: <1471291224-12755-1-git-send-email-rich.lane@bigswitch.com>
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>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

On Mon, Aug 15, 2016 at 01:00:24PM -0700, Rich Lane wrote:
> Concurrent enqueue is an important performance optimization when the number
> of cores used for switching is different than the number of vhost queues.
> I've observed a 20% performance improvement compared to a strategy that
> binds queues to cores.
> 
> The atomic cmpset is only executed when the application calls
> rte_vhost_enqueue_burst_mp. Benchmarks show no performance impact
> when not using concurrent enqueue.
> 
> Mergeable RX buffers aren't supported by concurrent enqueue to minimize
> code complexity.

I think that would break things when Mergeable rx is enabled (which is
actually enabled by default).

Besides that, as mentioned in the last week f2f talk, do you think adding
a new flag RTE_VHOST_USER_CONCURRENT_ENQUEUE (for rte_vhost_driver_register())
__might__ be a better idea? That could save us a API, to which I don't object
though.

	--yliu