netdev - Re: Bug report: CoDel patch

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]

Message-ID: <CAN0zt4M7G-kUb21YJkBwXawwEio91jaMOELHO+Vkv7Yv2YD0Nw@mail.gmail.com>
Date: Fri, 23 Jan 2026 10:12:48 +0100
From: Karel Řeřicha <karel@....cz>
To: Jamal Hadi Salim <jhs@...atatu.com>
Cc: Paolo Abeni <pabeni@...hat.com>, xiyou.wangcong@...il.com, 
	Jiri Pirko <jiri@...nulli.us>, "netdev@...r.kernel.org" <netdev@...r.kernel.org>, 
	Victor Nogueira <victor@...atatu.com>
Subject: Re: Bug report: CoDel patch

Hi Jamal,

no simple script so far. Bug appears on servers with tens of thousands
HFSC classes and FQ_CoDel qdiscs with around 10Gbit of traffic,
multiqueue interfaces and CPU core affinities. So it would not be
trivial to prepare a simple test script.

Two days ago I tested 6.18.6. Original kernel went into deadlock in
about 20 seconds after I redirected mirrored traffic from the
production server to the test server. When I reverted commit
342debc12183b51773b3345ba267e9263bdfaaef the test server is stable for
34 hours now.

If it is required to have a test script for independent confirmation I
can try to prepare one, but it will take some time and I will have to
move the test setup from mirroring production traffic to some kind of
TRex Packet generator or so.

Karel

st 21. 1. 2026 v 13:53 odesílatel Jamal Hadi Salim <jhs@...atatu.com> napsal:
>
> On Wed, Jan 21, 2026 at 6:27 AM Paolo Abeni <pabeni@...hat.com> wrote:
> >
> > On 1/21/26 12:12 PM, Karel Řeřicha wrote:
> > > please see
> > >
> > > https://bugzilla.netfilter.org/show_bug.cgi?id=1825
> > >
> > > Apologies for contacting you directly, but it has been a week and
> > > nobody noticed it. Maybe the wrong place to report?
> >
> > Indeed the netfilter bugzilla instance is not the best place to report
> > sched issue. Adding the netdev ML and more people.
> >
>
> Hi Karel,
>
> Please post this on the netdev mailing list in the future.
> The proper commit is 342debc12183b51773b3345ba267e9263bdfaaef
> Do you have a simple script to reproduce this issue?
>
> cheers,
> jamal
> > /P
> >