netdev - Re: [PATCH v2 net-next 0/2] mptcp: adjust tcp rcvspace on rx

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: <20200527.112931.1797611080625540455.davem@davemloft.net>
Date:   Wed, 27 May 2020 11:29:31 -0700 (PDT)
From:   David Miller <davem@...emloft.net>
To:     fw@...len.de
Cc:     netdev@...r.kernel.org, matthieu.baerts@...sares.net,
        mathew.j.martineau@...ux.intel.com, pabeni@...hat.com
Subject: Re: [PATCH v2 net-next 0/2] mptcp: adjust tcp rcvspace on rx

From: Florian Westphal <fw@...len.de>
Date: Wed, 27 May 2020 13:55:45 +0200

> David Miller <davem@...emloft.net> wrote:
>> From: Florian Westphal <fw@...len.de>
>> Date: Mon, 25 May 2020 20:15:06 +0200
>> 
>> > These two patches improve mptcp throughput by making sure tcp grows
>> > the receive buffer when we move skbs from subflow socket to the
>> > mptcp socket.
>> > 
>> > The second patch moves mptcp receive buffer increase to the recvmsg
>> > path, i.e. we only change its size when userspace processes/consumes
>> > the data.  This is done by using the largest rcvbuf size of the active
>> > subflows.
>> 
>> What's the follow-up wrt. Christoph's feedback on patch #2?
> 
> Please drop these patches, I have no idea (yet?) how to address it.

Ok, thank you.