[<prev] [next>] [day] [month] [year] [list]
Message-ID: <CAA93jw4KdC72309Y++-vanu4m_L6bwxY2k9EQSGbwJKgPYvEFg@mail.gmail.com>
Date: Mon, 4 Jun 2018 14:32:42 -0700
From: Dave Taht <dave.taht@...il.com>
To: David Miller <davem@...emloft.net>
Cc: Toke Høiland-Jørgensen <toke@...e.dk>,
Linux Kernel Network Developers <netdev@...r.kernel.org>,
Cake List <cake@...ts.bufferbloat.net>,
George Amanakis <gamanakis@...il.com>,
Pete Heist <peteheist@...il.com>,
Yuchung Cheng <ycheng@...gle.com>,
Neal Cardwell <ncardwell@...gle.com>,
Netfilter Development Mailinglist
<netfilter-devel@...r.kernel.org>
Subject: issues with shaping cake to 60 gbits or in unlimited mode at 100gbps
I would like to point a finger at the mlx5 code rather than cake itself,
I am wondering if there is anyone out there with a different 100gps
capable device and setup that could give the sch_cake code a go?
we've been unable to duplicate the lockup we're seeing with the veth devices,
for example.
On Fri, Jun 1, 2018 at 11:17 AM, David Miller <davem@...emloft.net> wrote:
> From: Toke Høiland-Jørgensen <toke@...e.dk>
> Date: Fri, 01 Jun 2018 19:42:12 +0200
>
>> Toke Høiland-Jørgensen <toke@...e.dk> writes:
>>
>>> This patch series adds the CAKE qdisc, and has been split up to ease
>>> review.
>>>
>>> I have attempted to split out each configurable feature into its own patch.
>>> The first commit adds the base shaper and packet scheduler, while
>>> subsequent commits add the optional features. The full userspace API and
>>> most data structures are included in this commit, but options not
>>> understood in the base version will be ignored.
>>
>> Hmm, there seems to be a lockup issue being triggered when running CAKE
>> at high speeds (>40 Gbps in my tests). Please drop this series for now,
>> we'll return for 4.19 with a revised version.
>
> Ok.
>
> Thanks for continuing to push this work along.
--
Dave Täht
CEO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-669-226-2619
Powered by blists - more mailing lists