netdev - Re: TCP throughput drops sharply around MTU of 180 bytes

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, 14 Nov 2009 17:24:56 +0800
From:	Ang Way Chuang <wcang79@...il.com>
To:	Eric Dumazet <eric.dumazet@...il.com>, netdev@...r.kernel.org
Subject: Re: TCP throughput drops sharply around MTU of 180 bytes

I assume that ip route .... advmss achieves that effect? I tried it,
but it doesn't work.


On Sat, Nov 14, 2009 at 5:12 PM, Eric Dumazet <eric.dumazet@...il.com> wrote:
> Eric Dumazet a écrit :
>>
>> Oh well, this reminds me TCP_MAXSEG doesnt work as expected...
>
> Oops, this problem I had few years ago was fixed last year in 2.6.27, sorry ...
>
> commit f5fff5dc8a7a3f395b0525c02ba92c95d42b7390
> Author: Tom Quetchenbach <virtualphtn@...il.com>
> Date:   Sun Sep 21 00:21:51 2008 -0700
>
>    tcp: advertise MSS requested by user
>
>    I'm trying to use the TCP_MAXSEG option to setsockopt() to set the MSS
>    for both sides of a bidirectional connection.
>
>    man tcp says: "If this option is set before connection establishment, it
>    also changes the MSS value announced to the other end in the initial
>    packet."
>
>    However, the kernel only uses the MTU/route cache to set the advertised
>    MSS. That means if I set the MSS to, say, 500 before calling connect(),
>    I will send at most 500-byte packets, but I will still receive 1500-byte
>    packets in reply.
>
>    This is a bug, either in the kernel or the documentation.
>
>    This patch (applies to latest net-2.6) reduces the advertised value to
>    that requested by the user as long as setsockopt() is called before
>    connect() or accept(). This seems like the behavior that one would
>    expect as well as that which is documented.
>
>    I've tried to make sure that things that depend on the advertised MSS
>    are set correctly.
>
>    Signed-off-by: Tom Quetchenbach <virtualphtn@...il.com>
>    Signed-off-by: David S. Miller <davem@...emloft.net>
>
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html