|
Hi!
> Dynamic scheduling for a clustering solution like LVS is essentially TCP
> hijacking -- which when weighed with the effort in implementing such a
> technique -- to me doesn't seem practical *at all*. (short connections,
> connection tracking to the *extreme*, etc...)
So, for example the client wants to download a 30MB file. You mean
"dynamic scheduling" would be to download, say, 10MB form one server.
Then you recognize that the server is very loaded, stop the transfer
and load the rest from the other server?
This can hardly be done, I think. And IF you do it, it doesn't
make much sense, because most traffic will be little pics, text,
so only small objects, not worth the overhead.
> I couldn't quite convince the guy of this, but anyway, I'm off to dinner.
Bon appetit!
Thomas
|
