Lynn's most recent response is unsatisfactory, in substance evasive. Let us for the sake of the argument stipulate, though this is not usually the case, that some "non-mainframe server" can perform some single I/O operation faster than some mainframe.
It turns out that this stipulation does not much help Lynn's argument. Mainframes handle aggregate I/O workloads, comprised of many single I/O operations, faster and with much less CP involvement than any "non-mainframe server". CPU involvement is much lower, and many I/O operations are handled concurrently. The channels, which for some reason Lynn seems to want to disparage, do most of the work. Mark Post's point nevertheless remains crucial. Every case is indeed different. There are single applications that, particularly when they are considered in isolation, are easy enough to accomplish on a "non-mainframe" server. It is when many such applications are aggregated together that the mainframe comes into its own as an alternative, a highly attractive one, to server farms. John Gilmore, Ashland, MA 01721 - USA ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
