From mboxrd@z Thu Jan  1 00:00:00 1970
From: "Hu, Jiayu" <jiayu.hu@intel.com>
Subject: Re: [PATCH v2 2/2] gro: support VxLAN GRO
Date: Thu, 14 Dec 2017 04:37:09 +0000
Message-ID: <ED946F0BEFE0A141B63BABBD629A2A9B3881E4FE@shsmsx102.ccr.corp.intel.com>
References: <1511579860-37020-1-git-send-email-jiayu.hu@intel.com>
 <1513219779-100115-1-git-send-email-jiayu.hu@intel.com>
 <1513219779-100115-3-git-send-email-jiayu.hu@intel.com>
 <20171213190239.5154c571@xeon-e3>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
Cc: "dev@dpdk.org" <dev@dpdk.org>, "Ananyev, Konstantin"
 <konstantin.ananyev@intel.com>, "Tan, Jianfeng" <jianfeng.tan@intel.com>,
 "Chen, Junjie J" <junjie.j.chen@intel.com>, "Mcnamara, John"
 <john.mcnamara@intel.com>, "matvejchikov@gmail.com" <matvejchikov@gmail.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Return-path: <dev-bounces@dpdk.org>
Received: from mga06.intel.com (mga06.intel.com [134.134.136.31])
 by dpdk.org (Postfix) with ESMTP id 435A12030
 for <dev@dpdk.org>; Thu, 14 Dec 2017 05:37:13 +0100 (CET)
In-Reply-To: <20171213190239.5154c571@xeon-e3>
Content-Language: en-US
List-Id: DPDK patches and discussions <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>

Hi Stephen,

> -----Original Message-----
> From: Stephen Hemminger [mailto:stephen@networkplumber.org]
> Sent: Thursday, December 14, 2017 11:03 AM
> To: Hu, Jiayu <jiayu.hu@intel.com>
> Cc: dev@dpdk.org; Ananyev, Konstantin <konstantin.ananyev@intel.com>;
> Tan, Jianfeng <jianfeng.tan@intel.com>; Chen, Junjie J
> <junjie.j.chen@intel.com>; Mcnamara, John <john.mcnamara@intel.com>;
> matvejchikov@gmail.com
> Subject: Re: [PATCH v2 2/2] gro: support VxLAN GRO
>=20
> On Thu, 14 Dec 2017 10:49:39 +0800
> Jiayu Hu <jiayu.hu@intel.com> wrote:
>=20
> > +	/* Don't merge packets whose outer DF bits are different. */
> > +	if (item->outer_is_atomic ^ outer_is_atomic)
>=20
> unlikely() here?

Agree. Add it in the next version.

>=20
> > +		return 0;
> > +
> > +	l2_offset =3D pkt->outer_l2_len + pkt->outer_l3_len;
> > +	cmp =3D check_seq_option(&item->inner_item, tcp_hdr, sent_seq,
> ip_id,
> > +			tcp_hl, tcp_dl, l2_offset, is_atomic);
> > +	if ((cmp =3D=3D 1) && (outer_is_atomic || (outer_ip_id =3D=3D
> > +					item->outer_ip_id +
> > +					item->inner_item.nb_merged)))
>=20
> More readable if you break the line at the ||

Exactly, I will change it in the next version.

>=20
> > +		/* Append the packet. */
> > +		return 1;
> > +	else if ((cmp =3D=3D -1) && (outer_is_atomic || (outer_ip_id + 1 =3D=
=3D
> > +					item->outer_ip_id)))
>=20
> else unecessary after return. Similar line break for readabilty.

Correctly, I will change it.

>=20
> > +		/* Prepend the packet. */
> > +		return -1;
> > +	else
> > +		return 0;
> > +}
> > +
>=20
> maybe?
> 	if (cmp =3D=3D 1) {
> 		if (outer_is_atomic ||
> 		    outer_ip_id =3D=3D item->outer_ip_id + item-
> >inner_item.nb_merged)
> 			return 1;
> 	} else if (cmp =3D=3D -1) {
> 		if (uter_is_atomic || outer_ip_id + 1 =3D=3D item->outer_ip_id)
> 			return -1;
> 	}
> 	return 0;
>=20

The reason to replace "if ((cmp =3D=3D 1) && (outer_is_atomic ...))" with t=
wo if statements is
for readability?

But will two if statements make codes less efficient?

Thanks,
Jiayu