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 75CB8A054F;
	Wed,  7 Sep 2022 16:47:17 +0200 (CEST)
Received: from [217.70.189.124] (localhost [127.0.0.1])
	by mails.dpdk.org (Postfix) with ESMTP id 1ECD240143;
	Wed,  7 Sep 2022 16:47:17 +0200 (CEST)
Received: from smartserver.smartsharesystems.com
 (smartserver.smartsharesystems.com [77.243.40.215])
 by mails.dpdk.org (Postfix) with ESMTP id 2A71C400D6
 for <dev@dpdk.org>; Wed,  7 Sep 2022 16:47:15 +0200 (CEST)
Content-class: urn:content-classes:message
MIME-Version: 1.0
Content-Type: text/plain;
	charset="iso-8859-1"
Subject: RE: [PATCH v4] vhost: support CPU copy for small packets
Content-Transfer-Encoding: quoted-printable
X-MimeOLE: Produced By Microsoft Exchange V6.5
Date: Wed, 7 Sep 2022 16:47:13 +0200
Message-ID: <98CBD80474FA8B44BF855DF32C47DC35D87300@smartserver.smartshare.dk>
In-Reply-To: <20220829005658.84590-1-wenwux.ma@intel.com>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: [PATCH v4] vhost: support CPU copy for small packets
Thread-Index: Adi7QnZ/y5S9XdSNSAGDiB6Y+JwrbQHg/6Yw
References: <20220812064517.272530-1-wenwux.ma@intel.com>
 <20220829005658.84590-1-wenwux.ma@intel.com>
From: =?iso-8859-1?Q?Morten_Br=F8rup?= <mb@smartsharesystems.com>
To: "Wenwu Ma" <wenwux.ma@intel.com>, <maxime.coquelin@redhat.com>,
 <chenbo.xia@intel.com>, <dev@dpdk.org>,
 "Bruce Richardson" <bruce.richardson@intel.com>
Cc: <sunil.pai.g@intel.com>, <jiayu.hu@intel.com>, <yinan.wang@intel.com>,
 <xingguang.he@intel.com>, <xuan.ding@intel.com>, <cheng1.jiang@intel.com>,
 <yuanx.wang@intel.com>
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

> From: Wenwu Ma [mailto:wenwux.ma@intel.com]
> Sent: Monday, 29 August 2022 02.57
>=20
> Offloading small packets to DMA degrades throughput 10%~20%,
> and this is because DMA offloading is not free and DMA is not
> good at processing small packets. In addition, control plane
> packets are usually small, and assign those packets to DMA will
> significantly increase latency, which may cause timeout like
> TCP handshake packets. Therefore, this patch use CPU to perform
> small copies in vhost.
>=20
> Signed-off-by: Wenwu Ma <wenwux.ma@intel.com>
> ---

[...]

> diff --git a/lib/vhost/virtio_net.c b/lib/vhost/virtio_net.c
> index 35fa4670fd..cf796183a0 100644
> --- a/lib/vhost/virtio_net.c
> +++ b/lib/vhost/virtio_net.c
> @@ -26,6 +26,8 @@
>=20
>  #define MAX_BATCH_LEN 256
>=20
> +#define CPU_COPY_THRESHOLD_LEN 256

This threshold may not be optimal for all CPU architectures and/or DMA =
engines.

Could you please provide a test application to compare the performance =
of DMA copy with CPU rte_memcpy?

The performance metric should be simple: How many cycles does the CPU =
spend copying various packet sizes using each the two methods.

You could provide test_dmadev_perf.c in addition to the existing =
test_dmadev.c.
You can probably copy a some of the concepts and code from =
test_memcpy_perf.c.
Alternatively, you might be able to add DMA copy to test_memcpy_perf.c.

I'm sorry to push this on you - it should have been done as part of =
DMAdev development already.

-Morten