From mboxrd@z Thu Jan  1 00:00:00 1970
From: David Miller <davem@davemloft.net>
Subject: Re: [PATCH net-next v2] net: sched: red: don't reset the backlog
 on every stat dump
Date: Wed, 17 Jan 2018 14:29:53 -0500 (EST)
Message-ID: <20180117.142953.453437428037852638.davem@davemloft.net>
References: <20180115040126.14190-1-jakub.kicinski@netronome.com>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: jiri@resnulli.us, nogahf@mellanox.com, netdev@vger.kernel.org,
        oss-drivers@netronome.com, xiyou.wangcong@gmail.com,
        edumazet@google.com, yuvalm@mellanox.com
To: jakub.kicinski@netronome.com
Return-path: <netdev-owner@vger.kernel.org>
Received: from shards.monkeyblade.net ([184.105.139.130]:34254 "EHLO
        shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S932253AbeAQT3z (ORCPT
        <rfc822;netdev@vger.kernel.org>); Wed, 17 Jan 2018 14:29:55 -0500
In-Reply-To: <20180115040126.14190-1-jakub.kicinski@netronome.com>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Sun, 14 Jan 2018 20:01:26 -0800

> Commit 0dfb33a0d7e2 ("sch_red: report backlog information") copied
> child's backlog into RED's backlog.  Back then RED did not maintain
> its own backlog counts.  This has changed after commit 2ccccf5fb43f
> ("net_sched: update hierarchical backlog too") and commit d7f4f332f082
> ("sch_red: update backlog as well").  Copying is no longer necessary.
> 
> Tested:
> 
> $ tc -s qdisc show dev veth0
> qdisc red 1: root refcnt 2 limit 400000b min 30000b max 30000b ecn
>  Sent 20942 bytes 221 pkt (dropped 0, overlimits 0 requeues 0)
>  backlog 1260b 14p requeues 14
>   marked 0 early 0 pdrop 0 other 0
> qdisc tbf 2: parent 1: rate 1Kbit burst 15000b lat 3585.0s
>  Sent 20942 bytes 221 pkt (dropped 0, overlimits 138 requeues 0)
>  backlog 1260b 14p requeues 14
> 
> Recently RED offload was added.  We need to make sure drivers don't
> depend on resetting the stats.  This means backlog should be treated
> like any other statistic:
> 
>   total_stat = new_hw_stat - prev_hw_stat;
> 
> Adjust mlxsw.
> 
> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> ---
> v2:
>  - reuse the mlxsw infra added for prio;
>  - align the way qstats are passed with prio.

Applied, thanks Jakub.