[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CADVnQy=s-u1MKSwBv-E87rHCoyCSnN8ywXi2TYQc15RXffWFpw@mail.gmail.com>
Date: Sat, 8 Feb 2025 17:47:35 -0600
From: Neal Cardwell <ncardwell@...gle.com>
To: Jason Xing <kerneljasonxing@...il.com>
Cc: Eric Dumazet <edumazet@...gle.com>, "David S . Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>, netdev@...r.kernel.org,
Kuniyuki Iwashima <kuniyu@...zon.com>, Jason Xing <kernelxing@...cent.com>,
Simon Horman <horms@...nel.org>, eric.dumazet@...il.com
Subject: Re: [PATCH net-next 4/5] tcp: add the ability to control max RTO
On Fri, Feb 7, 2025 at 11:37 PM Jason Xing <kerneljasonxing@...il.com> wrote:
>
> On Fri, Feb 7, 2025 at 11:31 PM Eric Dumazet <edumazet@...gle.com> wrote:
> >
> > Currently, TCP stack uses a constant (120 seconds)
> > to limit the RTO value exponential growth.
> >
> > Some applications want to set a lower value.
> >
> > Add TCP_RTO_MAX_MS socket option to set a value (in ms)
> > between 1 and 120 seconds.
> >
> > It is discouraged to change the socket rto max on a live
> > socket, as it might lead to unexpected disconnects.
> >
> > Following patch is adding a netns sysctl to control the
> > default value at socket creation time.
>
> I assume a bpf extension could be considered as a follow up patch on
> top of the series?
>
> >
> > Signed-off-by: Eric Dumazet <edumazet@...gle.com>
>
> Reviewed-by: Jason Xing <kerneljasonxing@...il.com>
Reviewed-by: Neal Cardwell <ncardwell@...gle.com>
Thanks, Eric!
neal
Powered by blists - more mailing lists