netdev - Re: [PATCH v2 net-next] net/sched: add skbprio scheduler

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Tue, 26 Jun 2018 06:04:09 +0530
From:   Nishanth Devarajan <ndev2021@...il.com>
To:     Jamal Hadi Salim <jhs@...atatu.com>
Cc:     Cong Wang <xiyou.wangcong@...il.com>,
        Jiri Pirko <jiri@...nulli.us>,
        David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
        doucette@...edu, michel@...irati.com.br,
        Alexander Duyck <alexander.duyck@...il.com>
Subject: Re: [PATCH v2 net-next] net/sched: add skbprio scheduler

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