From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <netdev-owner@vger.kernel.org>
Received: from mga03.intel.com ([134.134.136.65]:21607 "EHLO mga03.intel.com"
        rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
        id S1751889AbeCWXhN (ORCPT <rfc822;netdev@vger.kernel.org>);
        Fri, 23 Mar 2018 19:37:13 -0400
Subject: Re: [RFC v3 net-next 13/18] net/sched: Introduce the TBS Qdisc
To: Thomas Gleixner <tglx@linutronix.de>
Cc: netdev@vger.kernel.org, jhs@mojatatu.com, xiyou.wangcong@gmail.com,
        jiri@resnulli.us, vinicius.gomes@intel.com,
        richardcochran@gmail.com, anna-maria@linutronix.de,
        henrik@austad.us, john.stultz@linaro.org, levi.pearson@harman.com,
        edumazet@google.com, willemb@google.com, mlichvar@redhat.com
References: <20180307011230.24001-1-jesus.sanchez-palencia@intel.com>
 <20180307011230.24001-14-jesus.sanchez-palencia@intel.com>
 <alpine.DEB.2.21.1803211407520.3754@nanos.tec.linutronix.de>
 <7c3f5a9f-cc16-8483-cb77-b5548d46cd5b@intel.com>
 <alpine.DEB.2.21.1803222227060.1489@nanos.tec.linutronix.de>
 <4a61fd66-445d-1273-b63b-0b8989a217b8@intel.com>
 <alpine.DEB.2.21.1803230948210.4625@nanos.tec.linutronix.de>
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Message-ID: <eaddd974-abdf-0a96-40a9-936cfcd64d3e@intel.com>
Date: Fri, 23 Mar 2018 16:34:18 -0700
MIME-Version: 1.0
In-Reply-To: <alpine.DEB.2.21.1803230948210.4625@nanos.tec.linutronix.de>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

Hi Thomas,


On 03/23/2018 01:49 AM, Thomas Gleixner wrote:
> On Thu, 22 Mar 2018, Jesus Sanchez-Palencia wrote:
>> On 03/22/2018 03:11 PM, Thomas Gleixner wrote:
>> So, are you just opposing to the case where sorting off + offload off is used?
>> (i.e. the scheduled FIFO case)
> 
> FIFO does not make any sense if your packets have a fixed transmission
> time. I yet have to see a reasonable explanation why FIFO in the context of
> time ordered would be a good thing.


On context of tbs, the scheduled FIFO was developed just so consistency was kept
between all 4 variants, basically (sw best-effort or hw offload vs sorting
enabled or sorting disabled).

I don't have any strong argument in favor of this mode at the moment, so I will
just remove it on a next version - unless someone else brings up a valid use
case for it, of course.

Thanks for the feedback,
Jesus