netdev - Re: [PATCH net-next] sched: add dualpi2 scheduler module

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>] [day] [month] [year] [list]

Date:   Mon, 11 Mar 2019 09:08:15 -0700
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Olga Albisser <olga@...isser.org>
Cc:     Olga Albisser <olgabnd@...il.com>, netdev@...r.kernel.org,
        Koen De Schepper <koen.de_schepper@...ia-bell-labs.com>,
        Oliver Tilmans <olivier.tilmans@...ia-bell-labs.com>,
        Bob Briscoe <research@...briscoe.net>,
        Henrik Steen <henrist@...rist.net>
Subject: Re: [PATCH net-next] sched: add dualpi2 scheduler module



On 03/11/2019 09:00 AM, Olga Albisser wrote:
> Hi Eric,
> 
> I thought the window opened roughly a week ago, and would be open for another week (since it's 2 weeks in total), have I misunderstood?

Yes, you have misunderstood.

When Linus opens his window, it is the time for maintainers to push their stuff to Linus,
and time for us to fix all the bugs.

At this moment, we are fixing the bugs that current merge window (for upcoming linux-5.1) is adding.

Please take a look at Documentation/networking/netdev-FAQ.rst around line 54.

Also we prefer not top-posting in netdev mailing list.



> 
> Regards,
> Olga
> 
> On Mon, Mar 11, 2019 at 4:41 PM Eric Dumazet <eric.dumazet@...il.com <mailto:eric.dumazet@...il.com>> wrote:
> 
>     FYI, net-next tree is currently closed.
> 
>     On 03/11/2019 08:14 AM, Olga Albisser wrote:
>     > DUALPI2 provides extremely low latency & loss to traffic that uses a
>     > scalable congestion controller (e.g. L4S, DCTCP) without degrading the
>     > performance of 'classic' traffic (e.g. Reno, Cubic etc.). It is intended
>     > to be the reference implementation of the IETF's DualQ Coupled AQM.
> 
> 
>     > +
>     > +static int dualpi2_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
>     > +                              struct sk_buff **to_free)
>     > +{
>     > +     struct dualpi2_sched_data *q = qdisc_priv(sch);
>     > +     u32 ecn = get_ecn_field(skb);
>     > +     int err;
>     > +
>     > +     /* set to the time the HTQ packet is in the Q */
>     > +     __net_timestamp(skb);
>     > +
> 
>     You can not do that in a qdisc ( blindly overwriting skb->tstamp )
> 
>     EDT model was adopted in TCP in linux-4.20
> 
>     You will need to use part of skb->cb instead.
> 
>     BTW, prefer CLOCK_MONOTONIC, this can avoid all sort of surprises...
>