From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nishanth Devarajan Subject: Re: [PATCH v2 net-next] net/sched: add skbprio scheduler Date: Tue, 26 Jun 2018 06:04:09 +0530 Message-ID: <20180626003408.GA4645@gmail.com> References: <20180623204745.GA4337@gmail.com> <8076dc76-9f93-bebd-8376-28b8b4aa756b@mojatatu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Cong Wang , Jiri Pirko , David Miller , netdev@vger.kernel.org, doucette@bu.edu, michel@digirati.com.br, Alexander Duyck To: Jamal Hadi Salim Return-path: Received: from mail-ot0-f194.google.com ([74.125.82.194]:43522 "EHLO mail-ot0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934212AbeFZAen (ORCPT ); Mon, 25 Jun 2018 20:34:43 -0400 Received: by mail-ot0-f194.google.com with SMTP id i19-v6so17124674otk.10 for ; Mon, 25 Jun 2018 17:34:43 -0700 (PDT) Content-Disposition: inline In-Reply-To: <8076dc76-9f93-bebd-8376-28b8b4aa756b@mojatatu.com> Sender: netdev-owner@vger.kernel.org List-ID: On Sun, Jun 24, 2018 at 11:43:07AM -0400, Jamal Hadi Salim wrote: > On 23/06/18 04:47 PM, Nishanth Devarajan wrote: > [..] > > >+ /* Drop the packet at the tail of the lowest priority qdisc. */ > >+ lp_qdisc = &q->qdiscs[lp]; > >+ to_drop = __skb_dequeue_tail(lp_qdisc); > >+ BUG_ON(!to_drop); > >+ qdisc_qstats_backlog_dec(sch, to_drop); > >+ qdisc_drop(to_drop, sch, to_free); > >+ > > Maybe also increase overlimit stat here? It will keep track > of low prio things dropped because you were congested. > Such a stat helps when debugging or collecting analytics. > > Per Alex's comment, how about: > > ----------- > Skbprio (SKB Priority Queue) is a queueing discipline that > prioritizes packets according to their skb->priority field. > Under congestion, already-enqueued lower priority packets > will be dropped to make space available for higher priority > packets. Skbprio was conceived as a solution for > denial-of-service defenses that need to route packets with > different priorities as a means to overcome DoS attacks > as described in paper xxxx... > > > cheers, > jamal Sounds good, will make some changes in v3. Thanks, Nishanth