What do you mean precisely by “disk based paging”? And what was different then from today? memory paging has always been on disk in practice, and this is true even today (just, this is much faster since SSDs came into the equation). This is orthogonal to cache issues.
My point is that it was often preferable to use strides (incx, etc) rather than duplicating the data.
Sorry, but I really don’t get what you mean here…