[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4908A7BC.1060905@hp.com>
Date: Wed, 29 Oct 2008 11:13:16 -0700
From: Rick Jones <rick.jones2@...com>
To: David Miller <davem@...emloft.net>
CC: shemminger@...tta.com, ilpo.jarvinen@...sinki.fi,
doug.leith@...m.ie, netdev@...r.kernel.org
Subject: Re: FYI - TCP/IP thin stream latency
David Miller wrote:
> From: Stephen Hemminger <shemminger@...tta.com>
> Date: Fri, 24 Oct 2008 07:59:38 -0700
>
>
>>I was reading "Removing Exponential Backoff from TCP" by Mondal and
>>Kusmznovic at Northwesetern in ACM CCR. The paper tries to show that
>>nothing breaks by getting rid of backoff. Interestingly, FreeBSD
>>already doesn't do backoff until after 5th retry.
>
>
> Cell phone network folks want this (or something like it) too.
Wouldn't one get that by being able to tune TCP_RTO_MAX on some sort of
basis (per dest perhaps)?
rick jones
--
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
Powered by blists - more mailing lists