netdev - Re: [PATCH bpf-next 0/7] bpf: Propagate cn to TCP

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

Date:   Sat, 23 Mar 2019 22:48:18 -0700
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     Alexei Starovoitov <alexei.starovoitov@...il.com>,
        Eric Dumazet <eric.dumazet@...il.com>
Cc:     brakmo <brakmo@...com>, netdev <netdev@...r.kernel.org>,
        Martin Lau <kafai@...com>, Alexei Starovoitov <ast@...com>,
        Daniel Borkmann <daniel@...earbox.net>,
        Kernel Team <Kernel-team@...com>
Subject: Re: [PATCH bpf-next 0/7] bpf: Propagate cn to TCP

On 03/23/2019 08:41 AM, Alexei Starovoitov wrote:
> On Sat, Mar 23, 2019 at 02:12:39AM -0700, Eric Dumazet wrote:

>> Please think about offloading the pacing/throttling in the NIC,
>> there is no way we will report back to tcp stack instant notificatiions.
> 
> I don't think 'offload to google proprietary nic' is a suggestion
> that folks can practically follow.
> Very few NICs can offload pacing to hw and there are plenty of limitations.
> This patch set represents a pure sw solution that works and scales to millions of flows.

offloading is not a unique feature to "Google nic", this is ridiculous.

By offloading I meant : Any hop that might not be controlled by linux stack.

Think about VM, and think about pacers that can be on various existing NIC,
like Mellanox ones. For them, it is trivial to implement L4S style capabilities.

Beauty of ECN is that is relies on standard TCP feedback, not on some immediate
reaction from one one intermediate hop, sending another signal back to the sender.

HTTP 3 is planned to use QUIC (over UDP), we do not want to add TCP-only features in
IP fast path.

Lets have experimental results first, please ?