TCP optimization

[Diego Woitasen]

On Tue, Jan 31, 2012 at 3:51 PM, reiner otto <augustus_meyer at yahoo.de> wrote:
> Sounds like some existing principles of squid to me:
> Persistent connections to (parent) proxy with idle-timeout, or keep-alive.
> You might try to combine WAN-proxy and squid to get something similar, you
> think about.
>
> Actually, I have a long distance connection between a server in Western
> Europe, and another server in the "Wild East".
> Basiclly I had similar problem; more or less reliably solved using 2 squids.
>
> Theoretically, the config could look like this:
> local_client-WAN-proxy-squid---------------------squid-WAN-proxy-server
>
> Using some type of keep-alive traffic, when no real data to be transferred,
> should keep the long distance connections established.
>
> However, using squid it might be difficult to do, what you want, in case
> traffic is balanced in both directions.
>
> ________________________________
> Von: Diego Woitasen <diego at woitasen.com.ar>
> An: wanproxy at lists.wanproxy.org
> Gesendet: 20:11 Dienstag, 31.Januar 2012
> Betreff: TCP optimization
>
> Hi,
> In one of the customers where I'm going to implement Wanproxy we are
> discussing about developing on-disk storage and tcp optimization.
> On-disk storage was already discussed on this list, now I was to start
> a discussion about TCP optimization.
>
> Wanproxy optimizes the amount of data transferred right now, but one
> of the biggest problems of some WAN connections is the latency
> (Satellite specially). I was thinking about a method to improve TCP
> using pools of connections.  Right now the Wanproxy client connects to
> the Wanproxy server when it receives a TCP connection. I think that we
> could improve the performance having a pool of idle TCP connections.
> When a connection is established to the Wanproxy client, it finds a
> free connection and use it. Then the connection could be closed and a
> new one could be established to keep always the same numbers idle
> ones. Or may be we could not close it and to be reused.
>
> In the past I worked in a consultancy job where I developed a proof of
> concept of the described above and there results were great.
>
> What do you think?
>
> Regards,
> Diego
>
> --
> Diego Woitasen
> _______________________________________________
> wanproxy mailing list
> wanproxy at lists.wanproxy.org
> http://lists.wanproxy.org/listinfo.cgi/wanproxy-wanproxy.org
>
>

That's different. Persistence it just an attempt to optimize the HTTP
protocol avoid some connections but it's not a true TCP optimization.

-- 
Diego Woitasen