From mboxrd@z Thu Jan  1 00:00:00 1970
From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Subject: Re: [PATCH 0/3] [RFC] vhost: micro vhost optimization
Date: Tue, 10 May 2016 15:08:45 -0700
Message-ID: <20160510220845.GW5641@yliu-dev.sh.intel.com>
References: <1462236378-7604-1-git-send-email-yuanhan.liu@linux.intel.com>
 <CAGSMBPM3NCaw+Q1U2zkcAJBkv2DZP=z_GPLodfB=9eur7hrcag@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable
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 mga03.intel.com (mga03.intel.com [134.134.136.65])
 by dpdk.org (Postfix) with ESMTP id 33B73C32C
 for <dev@dpdk.org>; Wed, 11 May 2016 00:04:01 +0200 (CEST)
Content-Disposition: inline
In-Reply-To: <CAGSMBPM3NCaw+Q1U2zkcAJBkv2DZP=z_GPLodfB=9eur7hrcag@mail.gmail.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 Tue, May 10, 2016 at 02:49:43PM -0700, Rich Lane wrote:
> I see a significant performance improvement with these patches, around =
5% at 64
> bytes.

Thanks for testing.

>=20
> The one patch that didn't give any performance boost for me was "vhost:=
 arrange
> virtio_net fields for better cache sharing".

Yeah, same here from my test. I mean, in theory, it should give us a
tiny boost, it doesn't in real life though. And since it (should) do
no harm, I would still include this patch in this set. Maybe I should
have noted at first that no real perf gain from the 3rd patch.

	--yliu

>=20
> Tested-by: Rich Lane <rich.lane@bigswitch.com>
>=20
> On Mon, May 2, 2016 at 5:46 PM, Yuanhan Liu <yuanhan.liu@linux.intel.co=
m>
> wrote:
>=20
>     Here is a small patch set does the micro optimization, which brings=
 about
>     10% performance boost in my 64B packet testing, with the following =
topo:
>=20
>     =A0 =A0 pkt generator <----> NIC <-----> Virtio NIC
>=20
>     Patch 1 pre updates the used ring and update them in batch. It shou=
ld be
>     feasible from my understanding: there will be no issue, guest drive=
r will
>     not start processing them as far as we haven't updated the "used->i=
dx"
>     yet. I could miss something though.
>=20
>     Patch 2 saves one check for small packets (that can be hold in one =
desc
>     buf and mbuf).
>=20
>     Patch 3 moves several frequently used fields into one cache line, f=
or
>     better cache sharing.
>=20
>     Note that this patch set is based on my latest vhost ABI refactorin=
g
>     patchset.
>=20
>=20
>     ---
>     Yuanhan Liu (3):
>     =A0 vhost: pre update used ring for Tx and Rx
>     =A0 vhost: optimize dequeue for small packets
>     =A0 vhost: arrange virtio_net fields for better cache sharing
>=20
>     =A0lib/librte_vhost/vhost-net.h=A0 |=A0 =A08 +--
>     =A0lib/librte_vhost/vhost_rxtx.c | 110
>     ++++++++++++++++++++++++------------------
>     =A02 files changed, 68 insertions(+), 50 deletions(-)
>   =20
>     --
>     1.9.0
>=20
>=20
>=20