|
Hi,
On Wednesday 07 May 2003 04:24 pm, Chris wrote:
> To digress slightly,
>
> How about this for a scenario,
>
> LVS director and a fair number of real servers, say at least 4
>
> Each real server runs a very complex database driven system, where request
> fulfilment time varies considerably depending on the complexity of the
> request. A simple weighted / or least connection would not distribute
> evenly as a single request may take up to a minute.
lvs-kiss (http://lvs-kiss.sf.net/) does this. It polls the status of the
server, say every 10 or 20 seconds and reconfigures the director.
> Each real server has a debug page within the site which returns the servers
> status and a loading level.
We have not yet used this for databases, but we have used it with great
success for mail-servers. The debug page returned contains the number of
emails currently in the spool.
This makes it possible to build clusters containing computers of diffrent
speeds, as long as you are able to produce som sort of number which indicates
load.
> The director queries each real server and uses the returned loading level
> as that servers weighting value for a WLC balancing algorithm.
We mostly use WRR, as a number of connections not always implicates load.
> <..>
>
> Has anyone done this?
We've been using it for almost a year, now.
--
There are only 10 different kinds of people in the world,
those who understand binary, and those who don't.
|
