[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1465909802.7945.183.camel@edumazet-glaptop3.roam.corp.google.com>
Date: Tue, 14 Jun 2016 06:10:02 -0700
From: Eric Dumazet <eric.dumazet@...il.com>
To: "Eggert, Lars" <lars@...app.com>
Cc: Pavel Emelyanov <xemul@...tuozzo.com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"criu@...nvz.org" <criu@...nvz.org>,
Andrey Vagin <avagin@...tuozzo.com>,
"Honda, Michio" <michio@...app.com>
Subject: Re: [CRIU] TCP_REPAIR MSS issue
On Tue, 2016-06-14 at 06:03 -0700, Eric Dumazet wrote:
> On Tue, 2016-06-14 at 11:40 +0000, Eggert, Lars wrote:
> > On 2016-06-14, at 13:28, Pavel Emelyanov <xemul@...tuozzo.com> wrote:
> > > Andrey (in Cc) has played with TCP_REPAIR recently, I guess he can know something.
> >
> > Thanks for CC'ing him. We looked a little bit more into this:
> >
> > When TCP_REPAIR is on, tcp_connect() directly calls tcp_finish_connect() before returning, passing NULL for skb, which causes sk_rx_dst_set() to be bypassed. Later, when TCP_REPAIR is being turned off, do_tcp_setsockopt() just does tcp_send_window_probe(), but apparently all the "dst" stuff is being bypassed then also, so the mss remains at TCP_MSS_DEFAULT.
> >
> > Lars
>
> What gives :
>
> sysctl net/ipv4/ip_no_pmtu_disc net/ipv4/tcp_mtu_probing
>
Also, is it a regression ? Was this working better with an older linux
version ?
Powered by blists - more mailing lists