[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAM_iQpX=CzjO+AeivaRUfvHruMQEmkXCuMt8S0Web3kNpmKAiQ@mail.gmail.com>
Date: Sat, 24 Sep 2016 16:50:56 -0700
From: Cong Wang <xiyou.wangcong@...il.com>
To: Shmulik Ladkani <shmulik.ladkani@...ellosystems.com>
Cc: "David S. Miller" <davem@...emloft.net>,
Jamal Hadi Salim <jhs@...atatu.com>,
Eric Dumazet <edumazet@...gle.com>,
Linux Kernel Network Developers <netdev@...r.kernel.org>,
Shmulik Ladkani <shmulik.ladkani@...il.com>
Subject: Re: [PATCH net-next 4/4] net/sched: act_mirred: Implement ingress actions
On Thu, Sep 22, 2016 at 6:21 AM, Shmulik Ladkani
<shmulik.ladkani@...ellosystems.com> wrote:
> From: Shmulik Ladkani <shmulik.ladkani@...il.com>
>
> Up until now, 'action mirred' supported only egress actions (either
> TCA_EGRESS_REDIR or TCA_EGRESS_MIRROR).
>
> This patch implements the corresponding ingress actions
> TCA_INGRESS_REDIR and TCA_INGRESS_MIRROR.
>
> This allows attaching filters whose target is to hand matching skbs into
> the rx processing of a specified device.
I like this idea, this idea actually came to my mind when we
tried to redirect packets from eth0 to veth device in containers.
I remember I already brought this up to Jamal before (either personally
or publicly), but I forgot why I stopped.
This would reduce some latency for our Mesos containers, we
would just skip one veth TX in our scenario.
Powered by blists - more mailing lists