Running NW 6.5.6

Is there any way of finding out what is causing high disk requests on a
server? It's not constant, but periodically it will climb to between 100 and
200. This will cause response time to increase to unsatisfactory levels with
my users for hours at a time. I don't suspect there is anything
fundamentally wrong with the server other than that it has too much on it, I
just need to be able to point a finger at a particular user doing a
particular task.

On top of being the primary file server, it is also the DNS/DHCP server, the
110-user GroupWise server (except WebAccess) with 25 IMAP users and houses a
very large database app that averages 30 concurrent users.

Looking to virtualize and separate GW and the database app onto separate
servers, but there is no money for that right now.